Update aml-pipelines-use-databricks-as-compute-target.ipynb

Update samples from Release-111 as a part of SDK 1.34.0 release

.vscode/settings.json

@@ -0,0 +1 @@
+{}

CODE_OF_CONDUCT.md

@@ -0,0 +1,9 @@
+# Microsoft Open Source Code of Conduct
+
+This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
+
+Resources:
+
+- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
+- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
+- Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns

NBSETUP.md

@@ -28,7 +28,7 @@ git clone https://github.com/Azure/MachineLearningNotebooks.git
 pip install azureml-sdk[notebooks,tensorboard]
 
 # install model explainability component
-pip install azureml-sdk[explain]
+pip install azureml-sdk[interpret]
 
 # install automated ml components
 pip install azureml-sdk[automl]
@@ -86,7 +86,7 @@ If you need additional Azure ML SDK components, you can either modify the Docker
 pip install azureml-sdk[automl]
 
 # install the core SDK and model explainability component
-pip install azureml-sdk[explain]
+pip install azureml-sdk[interpret]
 
 # install the core SDK and experimental components
 pip install azureml-sdk[contrib]

README.md

@@ -1,76 +1,43 @@
-# Azure Machine Learning service example notebooks
+# Azure Machine Learning Python SDK notebooks
 
-This repository contains example notebooks demonstrating the [Azure Machine Learning](https://azure.microsoft.com/en-us/services/machine-learning-service/) Python SDK which allows you to build, train, deploy and manage machine learning solutions using Azure.  The AML SDK allows you the choice of using local or cloud compute resources, while managing and maintaining the complete data science workflow from the cloud.
+> a community-driven repository of examples using mlflow for tracking can be found at https://github.com/Azure/azureml-examples
 
-![Azure ML Workflow](https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/master/articles/machine-learning/service/media/concept-azure-machine-learning-architecture/workflow.png)
+Welcome to the Azure Machine Learning Python SDK notebooks repository!
 
+## Getting started
 
-## Quick installation
-```sh
-pip install azureml-sdk
-```
-Read more detailed instructions on [how to set up your environment](./NBSETUP.md) using Azure Notebook service, your own Jupyter notebook server, or Docker.
+These notebooks are recommended for use in an Azure Machine Learning [Compute Instance](https://docs.microsoft.com/azure/machine-learning/concept-compute-instance), where you can run them without any additional set up.
 
-## How to navigate and use the example notebooks?
-If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, you should always run the [Configuration](./configuration.ipynb) notebook first when setting up a notebook library on a new machine or in a new environment. It configures your notebook library to connect to an Azure Machine Learning workspace, and sets up your workspace and compute to be used by many of the other examples. 
-This [index](.index.md) should assist in navigating the Azure Machine Learning notebook samples and encourage efficient retrieval of topics and content. 
+However, the notebooks can be run in any development environment with the correct `azureml` packages installed.
 
-If you want to...
-
- * ...try out and explore Azure ML, start with image classification tutorials: [Part 1 (Training)](./tutorials/img-classification-part1-training.ipynb) and [Part 2 (Deployment)](./tutorials/img-classification-part2-deploy.ipynb).
- * ...learn about experimentation and tracking run history, first [train within Notebook](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), then try [training on remote VM](./how-to-use-azureml/training/train-on-remote-vm/train-on-remote-vm.ipynb) and [using logging APIs](./how-to-use-azureml/training/logging-api/logging-api.ipynb).
- * ...train deep learning models at scale, first learn about [Machine Learning Compute](./how-to-use-azureml/training/train-on-amlcompute/train-on-amlcompute.ipynb), and then try [distributed hyperparameter tuning](./how-to-use-azureml/training-with-deep-learning/train-hyperparameter-tune-deploy-with-pytorch/train-hyperparameter-tune-deploy-with-pytorch.ipynb) and [distributed training](./how-to-use-azureml/training-with-deep-learning/distributed-pytorch-with-horovod/distributed-pytorch-with-horovod.ipynb).
- * ...deploy models as a realtime scoring service, first learn the basics by [training within Notebook and deploying to Azure Container Instance](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), then learn how to [register and manage models, and create Docker images](./how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb), and [production deploy models on Azure Kubernetes Cluster](./how-to-use-azureml/deployment/production-deploy-to-aks/production-deploy-to-aks.ipynb).
- * ...deploy models as a batch scoring service, first [train a model within Notebook](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), learn how to [register and manage models](./how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb), then [create Machine Learning Compute for scoring compute](./how-to-use-azureml/training/train-on-amlcompute/train-on-amlcompute.ipynb), and [use Machine Learning Pipelines to deploy your model](https://aka.ms/pl-batch-scoring).
- * ...monitor your deployed models, learn about using [App Insights](./how-to-use-azureml/deployment/enable-app-insights-in-production-service/enable-app-insights-in-production-service.ipynb).
-
-## Tutorials
-
-The [Tutorials](./tutorials) folder contains notebooks for the tutorials described in the [Azure Machine Learning documentation](https://aka.ms/aml-docs).
-  
-## How to use Azure ML
-
-The [How to use Azure ML](./how-to-use-azureml) folder contains specific examples demonstrating the features of the Azure Machine Learning SDK
-
-- [Training](./how-to-use-azureml/training) - Examples of how to build models using Azure ML's logging and execution capabilities on local and remote compute targets
-- [Training with Deep Learning](./how-to-use-azureml/training-with-deep-learning) - Examples demonstrating how to build deep learning models using estimators and parameter sweeps
-- [Manage Azure ML Service](./how-to-use-azureml/manage-azureml-service) - Examples how to perform tasks, such as authenticate against Azure ML service in different ways.
-- [Automated Machine Learning](./how-to-use-azureml/automated-machine-learning) - Examples using Automated Machine Learning to automatically generate optimal machine learning pipelines and models
-- [Machine Learning Pipelines](./how-to-use-azureml/machine-learning-pipelines) - Examples showing how to create and use reusable pipelines for training and batch scoring
-- [Deployment](./how-to-use-azureml/deployment) - Examples showing how to deploy and manage machine learning models and solutions
-- [Azure Databricks](./how-to-use-azureml/azure-databricks) - Examples showing how to use Azure ML with Azure Databricks
-- [Monitor Models](./how-to-use-azureml/monitor-models) - Examples showing how to enable model monitoring services such as DataDrift
-
----
-## Documentation
-
- * Quickstarts, end-to-end tutorials, and how-tos on the [official documentation site for Azure Machine Learning service](https://docs.microsoft.com/en-us/azure/machine-learning/service/).
- * [Python SDK reference](https://docs.microsoft.com/en-us/python/api/overview/azure/ml/intro?view=azure-ml-py)
- * Azure ML Data Prep SDK [overview](https://aka.ms/data-prep-sdk), [Python SDK reference](https://aka.ms/aml-data-prep-apiref), and [tutorials and how-tos](https://aka.ms/aml-data-prep-notebooks).
-
----
-
-
-## Community Repository 
-Visit this [community repository](https://github.com/microsoft/MLOps/tree/master/examples) to find useful end-to-end sample notebooks. Also, please follow these [contribution guidelines](https://github.com/microsoft/MLOps/blob/master/contributing.md) when contributing to this repository.   
-
-## Projects using Azure Machine Learning
-
-Visit following repos to see projects contributed by Azure ML users:
- - [AMLSamples](https://github.com/Azure/AMLSamples) Number of end-to-end examples, including face recognition, predictive maintenance, customer churn and sentiment analysis.
- - [Learn about Natural Language Processing best practices using Azure Machine Learning service](https://github.com/microsoft/nlp)
- - [Pre-Train BERT models using Azure Machine Learning service](https://github.com/Microsoft/AzureML-BERT)
- - [Fashion MNIST with Azure ML SDK](https://github.com/amynic/azureml-sdk-fashion)
- - [UMass Amherst Student Samples](https://github.com/katiehouse3/microsoft-azure-ml-notebooks) - A number of end-to-end machine learning notebooks, including machine translation, image classification, and customer churn, created by students in the 696DS course at UMass Amherst.
- 
-## Data/Telemetry 
-This repository collects usage data and sends it to Mircosoft to help improve our products and services. Read Microsoft's [privacy statement to learn more](https://privacy.microsoft.com/en-US/privacystatement)
-
-To opt out of tracking, please go to the raw markdown or .ipynb files and remove the following line of code:
+Install the `azureml.core` Python package:
 
 ```sh
-    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/README.png)"
+pip install azureml-core
 ```
-This URL will be slightly different depending on the file. 
 
- ![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/README.png)
+Install additional packages as needed:
+
+```sh
+pip install azureml-mlflow
+pip install azureml-dataset-runtime
+pip install azureml-automl-runtime
+pip install azureml-pipeline
+pip install azureml-pipeline-steps
+...
+```
+
+We recommend starting with one of the [quickstarts](tutorials/compute-instance-quickstarts).
+
+## Contributing
+
+This repository is a push-only mirror. Pull requests are ignored.
+
+## Code of Conduct
+
+This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/). Please see the [code of conduct](CODE_OF_CONDUCT.md) for details.
+
+## Reference
+
+- [Documentation](https://docs.microsoft.com/azure/machine-learning)
+

configuration.ipynb

@@ -103,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.72.1 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -254,6 +254,8 @@
         "\n",
         "Many of the sample notebooks use Azure ML managed compute (AmlCompute) to train models using a dynamically scalable pool of compute. In this section you will create default compute clusters for use by the other notebooks and any other operations you choose.\n",
         "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\n",
         "To create a cluster, you need to specify a compute configuration that specifies the type of machine to be used and the scalability behaviors.  Then you choose a name for the cluster that is unique within the workspace that can be used to address the cluster later.\n",
         "\n",
         "The cluster parameters are:\n",

contrib/fairness/fairlearn-azureml-mitigation.ipynb

@@ -0,0 +1,621 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/contrib/fairness/fairlearn-azureml-mitigation.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Unfairness Mitigation with Fairlearn and Azure Machine Learning\n",
+        "**This notebook shows how to upload results from Fairlearn's GridSearch mitigation algorithm into a dashboard in Azure Machine Learning Studio**\n",
+        "\n",
+        "## Table of Contents\n",
+        "\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Loading the Data](#LoadingData)\n",
+        "1. [Training an Unmitigated Model](#UnmitigatedModel)\n",
+        "1. [Mitigation with GridSearch](#Mitigation)\n",
+        "1. [Uploading a Fairness Dashboard to Azure](#AzureUpload)\n",
+        "    1. Registering models\n",
+        "    1. Computing Fairness Metrics\n",
+        "    1. Uploading to Azure\n",
+        "1. [Conclusion](#Conclusion)\n",
+        "\n",
+        "<a id=\"Introduction\"></a>\n",
+        "## Introduction\n",
+        "This notebook shows how to use [Fairlearn (an open source fairness assessment and unfairness mitigation package)](http://fairlearn.org) and Azure Machine Learning Studio for a binary classification problem. This example uses the well-known adult census dataset. For the purposes of this notebook, we shall treat this as a loan decision problem. We will pretend that the label indicates whether or not each individual repaid a loan in the past. We will use the data to train a predictor to predict whether previously unseen individuals will repay a loan or not. The assumption is that the model predictions are used to decide whether an individual should be offered a loan. Its purpose is purely illustrative of a workflow including a fairness dashboard - in particular, we do **not** include a full discussion of the detailed issues which arise when considering fairness in machine learning. For such discussions, please [refer to the Fairlearn website](http://fairlearn.org/).\n",
+        "\n",
+        "We will apply the [grid search algorithm](https://fairlearn.org/v0.4.6/api_reference/fairlearn.reductions.html#fairlearn.reductions.GridSearch) from the Fairlearn package using a specific notion of fairness called Demographic Parity. This produces a set of models, and we will view these in a dashboard both locally and in the Azure Machine Learning Studio.\n",
+        "\n",
+        "### Setup\n",
+        "\n",
+        "To use this notebook, an Azure Machine Learning workspace is required.\n",
+        "Please see the [configuration notebook](../../configuration.ipynb) for information about creating one, if required.\n",
+        "This notebook also requires the following packages:\n",
+        "* `azureml-contrib-fairness`\n",
+        "* `fairlearn>=0.6.2` (pre-v0.5.0 will work with minor modifications)\n",
+        "* `joblib`\n",
+        "* `liac-arff`\n",
+        "* `raiwidgets~=0.7.0`\n",
+        "\n",
+        "Fairlearn relies on features introduced in v0.22.1 of `scikit-learn`. If you have an older version already installed, please uncomment and run the following cell:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# !pip install --upgrade scikit-learn>=0.22.1"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Finally, please ensure that when you downloaded this notebook, you also downloaded the `fairness_nb_utils.py` file from the same location, and placed it in the same directory as this notebook."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"LoadingData\"></a>\n",
+        "## Loading the Data\n",
+        "We use the well-known `adult` census dataset, which we will fetch from the OpenML website. We start with a fairly unremarkable set of imports:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from fairlearn.reductions import GridSearch, DemographicParity, ErrorRate\n",
+        "from raiwidgets import FairnessDashboard\n",
+        "\n",
+        "from sklearn.compose import ColumnTransformer\n",
+        "from sklearn.impute import SimpleImputer\n",
+        "from sklearn.linear_model import LogisticRegression\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
+        "from sklearn.compose import make_column_selector as selector\n",
+        "from sklearn.pipeline import Pipeline\n",
+        "\n",
+        "import pandas as pd"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We can now load and inspect the data:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from fairness_nb_utils import fetch_census_dataset\n",
+        "\n",
+        "data = fetch_census_dataset()\n",
+        "    \n",
+        "# Extract the items we want\n",
+        "X_raw = data.data\n",
+        "y = (data.target == '>50K') * 1\n",
+        "\n",
+        "X_raw[\"race\"].value_counts().to_dict()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We are going to treat the sex and race of each individual as protected attributes, and in this particular case we are going to remove these attributes from the main data (this is not always the best option - see the [Fairlearn website](http://fairlearn.github.io/) for further discussion). Protected attributes are often denoted by 'A' in the literature, and we follow that convention here:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "A = X_raw[['sex','race']]\n",
+        "X_raw = X_raw.drop(labels=['sex', 'race'], axis = 1)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We now preprocess our data. To avoid the problem of data leakage, we split our data into training and test sets before performing any other transformations. Subsequent transformations (such as scalings) will be fit to the training data set, and then applied to the test dataset."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "(X_train, X_test, y_train, y_test, A_train, A_test) = train_test_split(\n",
+        "    X_raw, y, A, test_size=0.3, random_state=12345, stratify=y\n",
+        ")\n",
+        "\n",
+        "# Ensure indices are aligned between X, y and A,\n",
+        "# after all the slicing and splitting of DataFrames\n",
+        "# and Series\n",
+        "\n",
+        "X_train = X_train.reset_index(drop=True)\n",
+        "X_test = X_test.reset_index(drop=True)\n",
+        "y_train = y_train.reset_index(drop=True)\n",
+        "y_test = y_test.reset_index(drop=True)\n",
+        "A_train = A_train.reset_index(drop=True)\n",
+        "A_test = A_test.reset_index(drop=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We have two types of column in the dataset - categorical columns which will need to be one-hot encoded, and numeric ones which will need to be rescaled. We also need to take care of missing values. We use a simple approach here, but please bear in mind that this is another way that bias could be introduced (especially if one subgroup tends to have more missing values).\n",
+        "\n",
+        "For this preprocessing, we make use of `Pipeline` objects from `sklearn`:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "numeric_transformer = Pipeline(\n",
+        "    steps=[\n",
+        "        (\"impute\", SimpleImputer()),\n",
+        "        (\"scaler\", StandardScaler()),\n",
+        "    ]\n",
+        ")\n",
+        "\n",
+        "categorical_transformer = Pipeline(\n",
+        "    [\n",
+        "        (\"impute\", SimpleImputer(strategy=\"most_frequent\")),\n",
+        "        (\"ohe\", OneHotEncoder(handle_unknown=\"ignore\", sparse=False)),\n",
+        "    ]\n",
+        ")\n",
+        "\n",
+        "preprocessor = ColumnTransformer(\n",
+        "    transformers=[\n",
+        "        (\"num\", numeric_transformer, selector(dtype_exclude=\"category\")),\n",
+        "        (\"cat\", categorical_transformer, selector(dtype_include=\"category\")),\n",
+        "    ]\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now, the preprocessing pipeline is defined, we can run it on our training data, and apply the generated transform to our test data:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_train = preprocessor.fit_transform(X_train)\n",
+        "X_test = preprocessor.transform(X_test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"UnmitigatedModel\"></a>\n",
+        "## Training an Unmitigated Model\n",
+        "\n",
+        "So we have a point of comparison, we first train a model (specifically, logistic regression from scikit-learn) on the raw data, without applying any mitigation algorithm:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "unmitigated_predictor = LogisticRegression(solver='liblinear', fit_intercept=True)\n",
+        "\n",
+        "unmitigated_predictor.fit(X_train, y_train)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We can view this model in the fairness dashboard, and see the disparities which appear:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "FairnessDashboard(sensitive_features=A_test,\n",
+        "                  y_true=y_test,\n",
+        "                  y_pred={\"unmitigated\": unmitigated_predictor.predict(X_test)})"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Looking at the disparity in accuracy when we select 'Sex' as the sensitive feature, we see that males have an error rate about three times greater than the females. More interesting is the disparity in opportunitiy - males are offered loans at three times the rate of females.\n",
+        "\n",
+        "Despite the fact that we removed the feature from the training data, our predictor still discriminates based on sex. This demonstrates that simply ignoring a protected attribute when fitting a predictor rarely eliminates unfairness. There will generally be enough other features correlated with the removed attribute to lead to disparate impact."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"Mitigation\"></a>\n",
+        "## Mitigation with GridSearch\n",
+        "\n",
+        "The `GridSearch` class in `Fairlearn` implements a simplified version of the exponentiated gradient reduction of [Agarwal et al. 2018](https://arxiv.org/abs/1803.02453). The user supplies a standard ML estimator, which is treated as a blackbox - for this simple example, we shall use the logistic regression estimator from scikit-learn. `GridSearch` works by generating a sequence of relabellings and reweightings, and trains a predictor for each.\n",
+        "\n",
+        "For this example, we specify demographic parity (on the protected attribute of sex) as the fairness metric. Demographic parity requires that individuals are offered the opportunity (a loan in this example) independent of membership in the protected class (i.e., females and males should be offered loans at the same rate). *We are using this metric for the sake of simplicity* in this example; the appropriate fairness metric can only be selected after *careful examination of the broader context* in which the model is to be used."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "sweep = GridSearch(LogisticRegression(solver='liblinear', fit_intercept=True),\n",
+        "                   constraints=DemographicParity(),\n",
+        "                   grid_size=71)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "With our estimator created, we can fit it to the data. After `fit()` completes, we extract the full set of predictors from the `GridSearch` object.\n",
+        "\n",
+        "The following cell trains a many copies of the underlying estimator, and may take a minute or two to run:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "sweep.fit(X_train, y_train,\n",
+        "          sensitive_features=A_train.sex)\n",
+        "\n",
+        "# For Fairlearn pre-v0.5.0, need sweep._predictors\n",
+        "predictors = sweep.predictors_"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We could load these predictors into the Fairness dashboard now. However, the plot would be somewhat confusing due to their number. In this case, we are going to remove the predictors which are dominated in the error-disparity space by others from the sweep (note that the disparity will only be calculated for the protected attribute; other potentially protected attributes will *not* be mitigated). In general, one might not want to do this, since there may be other considerations beyond the strict optimisation of error and disparity (of the given protected attribute)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "errors, disparities = [], []\n",
+        "for predictor in predictors:\n",
+        "    error = ErrorRate()\n",
+        "    error.load_data(X_train, pd.Series(y_train), sensitive_features=A_train.sex)\n",
+        "    disparity = DemographicParity()\n",
+        "    disparity.load_data(X_train, pd.Series(y_train), sensitive_features=A_train.sex)\n",
+        "    \n",
+        "    errors.append(error.gamma(predictor.predict)[0])\n",
+        "    disparities.append(disparity.gamma(predictor.predict).max())\n",
+        "    \n",
+        "all_results = pd.DataFrame( {\"predictor\": predictors, \"error\": errors, \"disparity\": disparities})\n",
+        "\n",
+        "dominant_models_dict = dict()\n",
+        "base_name_format = \"census_gs_model_{0}\"\n",
+        "row_id = 0\n",
+        "for row in all_results.itertuples():\n",
+        "    model_name = base_name_format.format(row_id)\n",
+        "    errors_for_lower_or_eq_disparity = all_results[\"error\"][all_results[\"disparity\"]<=row.disparity]\n",
+        "    if row.error <= errors_for_lower_or_eq_disparity.min():\n",
+        "        dominant_models_dict[model_name] = row.predictor\n",
+        "    row_id = row_id + 1"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We can construct predictions for the dominant models (we include the unmitigated predictor as well, for comparison):"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "predictions_dominant = {\"census_unmitigated\": unmitigated_predictor.predict(X_test)}\n",
+        "models_dominant = {\"census_unmitigated\": unmitigated_predictor}\n",
+        "for name, predictor in dominant_models_dict.items():\n",
+        "    value = predictor.predict(X_test)\n",
+        "    predictions_dominant[name] = value\n",
+        "    models_dominant[name] = predictor"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "These predictions may then be viewed in the fairness dashboard. We include the race column from the dataset, as an alternative basis for assessing the models. However, since we have not based our mitigation on it, the variation in the models with respect to race can be large."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "FairnessDashboard(sensitive_features=A_test, \n",
+        "                  y_true=y_test.tolist(),\n",
+        "                  y_pred=predictions_dominant)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "When using sex as the sensitive feature and accuracy as the metric, we see a Pareto front forming - the set of predictors which represent optimal tradeoffs between accuracy and disparity in predictions. In the ideal case, we would have a predictor at (1,0) - perfectly accurate and without any unfairness under demographic parity (with respect to the protected attribute \"sex\"). The Pareto front represents the closest we can come to this ideal based on our data and choice of estimator. Note the range of the axes - the disparity axis covers more values than the accuracy, so we can reduce disparity substantially for a small loss in accuracy. Finally, we also see that the unmitigated model is towards the top right of the plot, with high accuracy, but worst disparity.\n",
+        "\n",
+        "By clicking on individual models on the plot, we can inspect their metrics for disparity and accuracy in greater detail. In a real example, we would then pick the model which represented the best trade-off between accuracy and disparity given the relevant business constraints."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"AzureUpload\"></a>\n",
+        "## Uploading a Fairness Dashboard to Azure\n",
+        "\n",
+        "Uploading a fairness dashboard to Azure is a two stage process. The `FairnessDashboard` invoked in the previous section relies on the underlying Python kernel to compute metrics on demand. This is obviously not available when the fairness dashboard is rendered in AzureML Studio. By default, the dashboard in Azure Machine Learning Studio also requires the models to be registered. The required stages are therefore:\n",
+        "1. Register the dominant models\n",
+        "1. Precompute all the required metrics\n",
+        "1. Upload to Azure\n",
+        "\n",
+        "Before that, we need to connect to Azure Machine Learning Studio:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace, Experiment, Model\n",
+        "\n",
+        "ws = Workspace.from_config()\n",
+        "ws.get_details()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"RegisterModels\"></a>\n",
+        "### Registering Models\n",
+        "\n",
+        "The fairness dashboard is designed to integrate with registered models, so we need to do this for the models we want in the Studio portal. The assumption is that the names of the models specified in the dashboard dictionary correspond to the `id`s (i.e. `<name>:<version>` pairs) of registered models in the workspace. We register each of the models in the `models_dominant` dictionary into the workspace. For this, we have to save each model to a file, and then register that file:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import joblib\n",
+        "import os\n",
+        "\n",
+        "os.makedirs('models', exist_ok=True)\n",
+        "def register_model(name, model):\n",
+        "    print(\"Registering \", name)\n",
+        "    model_path = \"models/{0}.pkl\".format(name)\n",
+        "    joblib.dump(value=model, filename=model_path)\n",
+        "    registered_model = Model.register(model_path=model_path,\n",
+        "                                      model_name=name,\n",
+        "                                      workspace=ws)\n",
+        "    print(\"Registered \", registered_model.id)\n",
+        "    return registered_model.id\n",
+        "\n",
+        "model_name_id_mapping = dict()\n",
+        "for name, model in models_dominant.items():\n",
+        "    m_id = register_model(name, model)\n",
+        "    model_name_id_mapping[name] = m_id"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now, produce new predictions dictionaries, with the updated names:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "predictions_dominant_ids = dict()\n",
+        "for name, y_pred in predictions_dominant.items():\n",
+        "    predictions_dominant_ids[model_name_id_mapping[name]] = y_pred"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"PrecomputeMetrics\"></a>\n",
+        "### Precomputing Metrics\n",
+        "\n",
+        "We create a _dashboard dictionary_ using Fairlearn's `metrics` package. The `_create_group_metric_set` method has arguments similar to the Dashboard constructor, except that the sensitive features are passed as a dictionary (to ensure that names are available), and we must specify the type of prediction. Note that we use the `predictions_dominant_ids` dictionary we just created:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "sf = { 'sex': A_test.sex, 'race': A_test.race }\n",
+        "\n",
+        "from fairlearn.metrics._group_metric_set import _create_group_metric_set\n",
+        "\n",
+        "\n",
+        "dash_dict = _create_group_metric_set(y_true=y_test,\n",
+        "                                     predictions=predictions_dominant_ids,\n",
+        "                                     sensitive_features=sf,\n",
+        "                                     prediction_type='binary_classification')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"DashboardUpload\"></a>\n",
+        "### Uploading the Dashboard\n",
+        "\n",
+        "Now, we import our `contrib` package which contains the routine to perform the upload:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.contrib.fairness import upload_dashboard_dictionary, download_dashboard_by_upload_id"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now we can create an Experiment, then a Run, and upload our dashboard to it:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "exp = Experiment(ws, \"Test_Fairlearn_GridSearch_Census_Demo\")\n",
+        "print(exp)\n",
+        "\n",
+        "run = exp.start_logging()\n",
+        "try:\n",
+        "    dashboard_title = \"Dominant Models from GridSearch\"\n",
+        "    upload_id = upload_dashboard_dictionary(run,\n",
+        "                                            dash_dict,\n",
+        "                                            dashboard_name=dashboard_title)\n",
+        "    print(\"\\nUploaded to id: {0}\\n\".format(upload_id))\n",
+        "\n",
+        "    downloaded_dict = download_dashboard_by_upload_id(run, upload_id)\n",
+        "finally:\n",
+        "    run.complete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The dashboard can be viewed in the Run Details page.\n",
+        "\n",
+        "Finally, we can verify that the dashboard dictionary which we downloaded matches our upload:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(dash_dict == downloaded_dict)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"Conclusion\"></a>\n",
+        "## Conclusion\n",
+        "\n",
+        "In this notebook we have demonstrated how to use the `GridSearch` algorithm from Fairlearn to generate a collection of models, and then present them in the fairness dashboard in Azure Machine Learning Studio. Please remember that this notebook has not attempted to discuss the many considerations which should be part of any approach to unfairness mitigation. The [Fairlearn website](http://fairlearn.org/) provides that discussion"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "riedgar"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.10"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

contrib/fairness/fairlearn-azureml-mitigation.yml

@@ -0,0 +1,9 @@
+name: fairlearn-azureml-mitigation
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-contrib-fairness
+  - fairlearn>=0.6.2
+  - joblib
+  - liac-arff
+  - raiwidgets~=0.7.0

contrib/fairness/fairness_nb_utils.py

@@ -0,0 +1,111 @@
+# ---------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# ---------------------------------------------------------
+
+"""Utilities for azureml-contrib-fairness notebooks."""
+
+import arff
+from collections import OrderedDict
+from contextlib import closing
+import gzip
+import pandas as pd
+from sklearn.datasets import fetch_openml
+from sklearn.utils import Bunch
+import time
+
+
+def fetch_openml_with_retries(data_id, max_retries=4, retry_delay=60):
+    """Fetch a given dataset from OpenML with retries as specified."""
+    for i in range(max_retries):
+        try:
+            print("Download attempt {0} of {1}".format(i + 1, max_retries))
+            data = fetch_openml(data_id=data_id, as_frame=True)
+            break
+        except Exception as e:  # noqa: B902
+            print("Download attempt failed with exception:")
+            print(e)
+            if i + 1 != max_retries:
+                print("Will retry after {0} seconds".format(retry_delay))
+                time.sleep(retry_delay)
+                retry_delay = retry_delay * 2
+    else:
+        raise RuntimeError("Unable to download dataset from OpenML")
+
+    return data
+
+
+_categorical_columns = [
+    'workclass',
+    'education',
+    'marital-status',
+    'occupation',
+    'relationship',
+    'race',
+    'sex',
+    'native-country'
+]
+
+
+def fetch_census_dataset():
+    """Fetch the Adult Census Dataset.
+
+    This uses a particular URL for the Adult Census dataset. The code
+    is a simplified version of fetch_openml() in sklearn.
+
+    The data are copied from:
+    https://openml.org/data/v1/download/1595261.gz
+    (as of 2021-03-31)
+    """
+    try:
+        from urllib import urlretrieve
+    except ImportError:
+        from urllib.request import urlretrieve
+
+    filename = "1595261.gz"
+    data_url = "https://rainotebookscdn.blob.core.windows.net/datasets/"
+
+    remaining_attempts = 5
+    sleep_duration = 10
+    while remaining_attempts > 0:
+        try:
+            urlretrieve(data_url + filename, filename)
+
+            http_stream = gzip.GzipFile(filename=filename, mode='rb')
+
+            with closing(http_stream):
+                def _stream_generator(response):
+                    for line in response:
+                        yield line.decode('utf-8')
+
+                stream = _stream_generator(http_stream)
+                data = arff.load(stream)
+        except Exception as exc:  # noqa: B902
+            remaining_attempts -= 1
+            print("Error downloading dataset from {} ({} attempt(s) remaining)"
+                  .format(data_url, remaining_attempts))
+            print(exc)
+            time.sleep(sleep_duration)
+            sleep_duration *= 2
+            continue
+        else:
+            # dataset successfully downloaded
+            break
+    else:
+        raise Exception("Could not retrieve dataset from {}.".format(data_url))
+
+    attributes = OrderedDict(data['attributes'])
+    arff_columns = list(attributes)
+
+    raw_df = pd.DataFrame(data=data['data'], columns=arff_columns)
+
+    target_column_name = 'class'
+    target = raw_df.pop(target_column_name)
+    for col_name in _categorical_columns:
+        dtype = pd.api.types.CategoricalDtype(attributes[col_name])
+        raw_df[col_name] = raw_df[col_name].astype(dtype, copy=False)
+
+    result = Bunch()
+    result.data = raw_df
+    result.target = target
+
+    return result

contrib/fairness/upload-fairness-dashboard.ipynb

@@ -0,0 +1,545 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/contrib/fairness/upload-fairness-dashboard.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Upload a Fairness Dashboard to Azure Machine Learning Studio\n",
+        "**This notebook shows how to generate and upload a fairness assessment dashboard from Fairlearn to AzureML Studio**\n",
+        "\n",
+        "## Table of Contents\n",
+        "\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Loading the Data](#LoadingData)\n",
+        "1. [Processing the Data](#ProcessingData)\n",
+        "1. [Training Models](#TrainingModels)\n",
+        "1. [Logging in to AzureML](#LoginAzureML)\n",
+        "1. [Registering the Models](#RegisterModels)\n",
+        "1. [Using the Fairness Dashboard](#LocalDashboard)\n",
+        "1. [Uploading a Fairness Dashboard to Azure](#AzureUpload)\n",
+        "    1. Computing Fairness Metrics\n",
+        "    1. Uploading to Azure\n",
+        "1. [Conclusion](#Conclusion)\n",
+        "    \n",
+        "\n",
+        "<a id=\"Introduction\"></a>\n",
+        "## Introduction\n",
+        "\n",
+        "In this notebook, we walk through a simple example of using the `azureml-contrib-fairness` package to upload a collection of fairness statistics for a fairness dashboard. It is an example of integrating the [open source Fairlearn package](https://www.github.com/fairlearn/fairlearn) with Azure Machine Learning. This is not an example of fairness analysis or mitigation - this notebook simply shows how to get a fairness dashboard into the Azure Machine Learning portal. We will load the data and train a couple of simple models. We will then use Fairlearn to generate data for a Fairness dashboard, which we can upload to Azure Machine Learning portal and view there.\n",
+        "\n",
+        "### Setup\n",
+        "\n",
+        "To use this notebook, an Azure Machine Learning workspace is required.\n",
+        "Please see the [configuration notebook](../../configuration.ipynb) for information about creating one, if required.\n",
+        "This notebook also requires the following packages:\n",
+        "* `azureml-contrib-fairness`\n",
+        "* `fairlearn>=0.6.2` (also works for pre-v0.5.0 with slight modifications)\n",
+        "* `joblib`\n",
+        "* `liac-arff`\n",
+        "* `raiwidgets~=0.7.0`\n",
+        "\n",
+        "Fairlearn relies on features introduced in v0.22.1 of `scikit-learn`. If you have an older version already installed, please uncomment and run the following cell:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# !pip install --upgrade scikit-learn>=0.22.1"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Finally, please ensure that when you downloaded this notebook, you also downloaded the `fairness_nb_utils.py` file from the same location, and placed it in the same directory as this notebook."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"LoadingData\"></a>\n",
+        "## Loading the Data\n",
+        "We use the well-known `adult` census dataset, which we fetch from the OpenML website. We start with a fairly unremarkable set of imports:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn import svm\n",
+        "from sklearn.compose import ColumnTransformer\n",
+        "from sklearn.impute import SimpleImputer\n",
+        "from sklearn.linear_model import LogisticRegression\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
+        "from sklearn.compose import make_column_selector as selector\n",
+        "from sklearn.pipeline import Pipeline"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now we can load the data:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from fairness_nb_utils import fetch_census_dataset\n",
+        "\n",
+        "data = fetch_census_dataset()\n",
+        "    \n",
+        "# Extract the items we want\n",
+        "X_raw = data.data\n",
+        "y = (data.target == '>50K') * 1"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We can take a look at some of the data. For example, the next cells shows the counts of the different races identified in the dataset:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(X_raw[\"race\"].value_counts().to_dict())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"ProcessingData\"></a>\n",
+        "## Processing the Data\n",
+        "\n",
+        "With the data loaded, we process it for our needs. First, we extract the sensitive features of interest into `A` (conventionally used in the literature) and leave the rest of the feature data in `X_raw`:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "A = X_raw[['sex','race']]\n",
+        "X_raw = X_raw.drop(labels=['sex', 'race'],axis = 1)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We now preprocess our data. To avoid the problem of data leakage, we split our data into training and test sets before performing any other transformations. Subsequent transformations (such as scalings) will be fit to the training data set, and then applied to the test dataset."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "(X_train, X_test, y_train, y_test, A_train, A_test) = train_test_split(\n",
+        "    X_raw, y, A, test_size=0.3, random_state=12345, stratify=y\n",
+        ")\n",
+        "\n",
+        "# Ensure indices are aligned between X, y and A,\n",
+        "# after all the slicing and splitting of DataFrames\n",
+        "# and Series\n",
+        "\n",
+        "X_train = X_train.reset_index(drop=True)\n",
+        "X_test = X_test.reset_index(drop=True)\n",
+        "y_train = y_train.reset_index(drop=True)\n",
+        "y_test = y_test.reset_index(drop=True)\n",
+        "A_train = A_train.reset_index(drop=True)\n",
+        "A_test = A_test.reset_index(drop=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We have two types of column in the dataset - categorical columns which will need to be one-hot encoded, and numeric ones which will need to be rescaled. We also need to take care of missing values. We use a simple approach here, but please bear in mind that this is another way that bias could be introduced (especially if one subgroup tends to have more missing values).\n",
+        "\n",
+        "For this preprocessing, we make use of `Pipeline` objects from `sklearn`:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "numeric_transformer = Pipeline(\n",
+        "    steps=[\n",
+        "        (\"impute\", SimpleImputer()),\n",
+        "        (\"scaler\", StandardScaler()),\n",
+        "    ]\n",
+        ")\n",
+        "\n",
+        "categorical_transformer = Pipeline(\n",
+        "    [\n",
+        "        (\"impute\", SimpleImputer(strategy=\"most_frequent\")),\n",
+        "        (\"ohe\", OneHotEncoder(handle_unknown=\"ignore\", sparse=False)),\n",
+        "    ]\n",
+        ")\n",
+        "\n",
+        "preprocessor = ColumnTransformer(\n",
+        "    transformers=[\n",
+        "        (\"num\", numeric_transformer, selector(dtype_exclude=\"category\")),\n",
+        "        (\"cat\", categorical_transformer, selector(dtype_include=\"category\")),\n",
+        "    ]\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now, the preprocessing pipeline is defined, we can run it on our training data, and apply the generated transform to our test data:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_train = preprocessor.fit_transform(X_train)\n",
+        "X_test = preprocessor.transform(X_test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"TrainingModels\"></a>\n",
+        "## Training Models\n",
+        "\n",
+        "We now train a couple of different models on our data. The `adult` census dataset is a classification problem - the goal is to predict whether a particular individual exceeds an income threshold. For the purpose of generating a dashboard to upload, it is sufficient to train two basic classifiers. First, a logistic regression classifier:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lr_predictor = LogisticRegression(solver='liblinear', fit_intercept=True)\n",
+        "\n",
+        "lr_predictor.fit(X_train, y_train)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "And for comparison, a support vector classifier:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "svm_predictor = svm.SVC()\n",
+        "\n",
+        "svm_predictor.fit(X_train, y_train)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"LoginAzureML\"></a>\n",
+        "## Logging in to AzureML\n",
+        "\n",
+        "With our two classifiers trained, we can log into our AzureML workspace:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Workspace, Experiment, Model\n",
+        "\n",
+        "ws = Workspace.from_config()\n",
+        "ws.get_details()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"RegisterModels\"></a>\n",
+        "## Registering the Models\n",
+        "\n",
+        "Next, we register our models. By default, the subroutine which uploads the models checks that the names provided correspond to registered models in the workspace. We define a utility routine to do the registering:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import joblib\n",
+        "import os\n",
+        "\n",
+        "os.makedirs('models', exist_ok=True)\n",
+        "def register_model(name, model):\n",
+        "    print(\"Registering \", name)\n",
+        "    model_path = \"models/{0}.pkl\".format(name)\n",
+        "    joblib.dump(value=model, filename=model_path)\n",
+        "    registered_model = Model.register(model_path=model_path,\n",
+        "                                      model_name=name,\n",
+        "                                      workspace=ws)\n",
+        "    print(\"Registered \", registered_model.id)\n",
+        "    return registered_model.id"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now, we register the models. For convenience in subsequent method calls, we store the results in a dictionary, which maps the `id` of the registered model (a string in `name:version` format) to the predictor itself:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model_dict = {}\n",
+        "\n",
+        "lr_reg_id = register_model(\"fairness_linear_regression\", lr_predictor)\n",
+        "model_dict[lr_reg_id] = lr_predictor\n",
+        "svm_reg_id = register_model(\"fairness_svm\", svm_predictor)\n",
+        "model_dict[svm_reg_id] = svm_predictor"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"LocalDashboard\"></a>\n",
+        "## Using the Fairlearn Dashboard\n",
+        "\n",
+        "We can now examine the fairness of the two models we have training, both as a function of race and (binary) sex. Before uploading the dashboard to the AzureML portal, we will first instantiate a local instance of the Fairlearn dashboard.\n",
+        "\n",
+        "Regardless of the viewing location, the dashboard is based on three things - the true values, the model predictions and the sensitive feature values. The dashboard can use predictions from multiple models and multiple sensitive features if desired (as we are doing here).\n",
+        "\n",
+        "Our first step is to generate a dictionary mapping the `id` of the registered model to the corresponding array of predictions:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ys_pred = {}\n",
+        "for n, p in model_dict.items():\n",
+        "    ys_pred[n] = p.predict(X_test)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We can examine these predictions in a locally invoked Fairlearn dashboard. This can be compared to the dashboard uploaded to the portal (in the next section):"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from raiwidgets import FairnessDashboard\n",
+        "\n",
+        "FairnessDashboard(sensitive_features=A_test, \n",
+        "                  y_true=y_test.tolist(),\n",
+        "                  y_pred=ys_pred)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"AzureUpload\"></a>\n",
+        "## Uploading a Fairness Dashboard to Azure\n",
+        "\n",
+        "Uploading a fairness dashboard to Azure is a two stage process. The `FairnessDashboard` invoked in the previous section relies on the underlying Python kernel to compute metrics on demand. This is obviously not available when the fairness dashboard is rendered in AzureML Studio. The required stages are therefore:\n",
+        "1. Precompute all the required metrics\n",
+        "1. Upload to Azure\n",
+        "\n",
+        "\n",
+        "### Computing Fairness Metrics\n",
+        "We use Fairlearn to create a dictionary which contains all the data required to display a dashboard. This includes both the raw data (true values, predicted values and sensitive features), and also the fairness metrics. The API is similar to that used to invoke the Dashboard locally. However, there are a few minor changes to the API, and the type of problem being examined (binary classification, regression etc.) needs to be specified explicitly:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "sf = { 'Race': A_test.race, 'Sex': A_test.sex }\n",
+        "\n",
+        "from fairlearn.metrics._group_metric_set import _create_group_metric_set\n",
+        "\n",
+        "dash_dict = _create_group_metric_set(y_true=y_test,\n",
+        "                                     predictions=ys_pred,\n",
+        "                                     sensitive_features=sf,\n",
+        "                                     prediction_type='binary_classification')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The `_create_group_metric_set()` method is currently underscored since its exact design is not yet final in Fairlearn."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Uploading to Azure\n",
+        "\n",
+        "We can now import the `azureml.contrib.fairness` package itself. We will round-trip the data, so there are two required subroutines:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.contrib.fairness import upload_dashboard_dictionary, download_dashboard_by_upload_id"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Finally, we can upload the generated dictionary to AzureML. The upload method requires a run, so we first create an experiment and a run. The uploaded dashboard can be seen on the corresponding Run Details page in AzureML Studio. For completeness, we also download the dashboard dictionary which we uploaded."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "exp = Experiment(ws, \"notebook-01\")\n",
+        "print(exp)\n",
+        "\n",
+        "run = exp.start_logging()\n",
+        "try:\n",
+        "    dashboard_title = \"Sample notebook upload\"\n",
+        "    upload_id = upload_dashboard_dictionary(run,\n",
+        "                                            dash_dict,\n",
+        "                                            dashboard_name=dashboard_title)\n",
+        "    print(\"\\nUploaded to id: {0}\\n\".format(upload_id))\n",
+        "\n",
+        "    downloaded_dict = download_dashboard_by_upload_id(run, upload_id)\n",
+        "finally:\n",
+        "    run.complete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Finally, we can verify that the dashboard dictionary which we downloaded matches our upload:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(dash_dict == downloaded_dict)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<a id=\"Conclusion\"></a>\n",
+        "## Conclusion\n",
+        "\n",
+        "In this notebook we have demonstrated how to generate and upload a fairness dashboard to AzureML Studio. We have not discussed how to analyse the results and apply mitigations. Those topics will be covered elsewhere."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "riedgar"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.10"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 4
+}

contrib/fairness/upload-fairness-dashboard.yml

@@ -0,0 +1,9 @@
+name: upload-fairness-dashboard
+dependencies:
+- pip:
+  - azureml-sdk
+  - azureml-contrib-fairness
+  - fairlearn>=0.6.2
+  - joblib
+  - liac-arff
+  - raiwidgets~=0.7.0

contrib/gbdt/lightgbm/binary0.test

@@ -1,500 +0,0 @@
-1	0.644	0.247	-0.447	0.862	0.374	0.854	-1.126	-0.790	2.173	1.015	-0.201	1.400	0.000	1.575	1.807	1.607	0.000	1.585	-0.190	-0.744	3.102	0.958	1.061	0.980	0.875	0.581	0.905	0.796
-0	0.385	1.800	1.037	1.044	0.349	1.502	-0.966	1.734	0.000	0.966	-1.960	-0.249	0.000	1.501	0.465	-0.354	2.548	0.834	-0.440	0.638	3.102	0.695	0.909	0.981	0.803	0.813	1.149	1.116
-0	1.214	-0.166	0.004	0.505	1.434	0.628	-1.174	-1.230	1.087	0.579	-1.047	-0.118	0.000	0.835	0.340	1.234	2.548	0.711	-1.383	1.355	0.000	0.848	0.911	1.043	0.931	1.058	0.744	0.696
-1	0.420	1.111	0.137	1.516	-1.657	0.854	0.623	1.605	1.087	1.511	-1.297	0.251	0.000	0.872	-0.368	-0.721	0.000	0.543	0.731	1.424	3.102	1.597	1.282	1.105	0.730	0.148	1.231	1.234
-0	0.897	-1.703	-1.306	1.022	-0.729	0.836	0.859	-0.333	2.173	1.336	-0.965	0.972	2.215	0.671	1.021	-1.439	0.000	0.493	-2.019	-0.289	0.000	0.805	0.930	0.984	1.430	2.198	1.934	1.684
-0	0.756	1.126	-0.945	2.355	-0.555	0.889	0.800	1.440	0.000	0.585	0.271	0.631	2.215	0.722	1.744	1.051	0.000	0.618	0.924	0.698	1.551	0.976	0.864	0.988	0.803	0.234	0.822	0.911
-0	1.141	-0.741	0.953	1.478	-0.524	1.197	-0.871	1.689	2.173	0.875	1.321	-0.518	1.107	0.540	0.037	-0.987	0.000	0.879	1.187	0.245	0.000	0.888	0.701	1.747	1.358	2.479	1.491	1.223
-1	0.606	-0.936	-0.384	1.257	-1.162	2.719	-0.600	0.100	2.173	3.303	-0.284	1.561	1.107	0.689	1.786	-0.326	0.000	0.780	-0.532	1.216	0.000	0.936	2.022	0.985	1.574	4.323	2.263	1.742
-1	0.603	0.429	-0.279	1.448	1.301	1.008	2.423	-1.295	0.000	0.452	1.305	0.533	0.000	1.076	1.011	1.256	2.548	2.021	1.260	-0.343	0.000	0.890	0.969	1.281	0.763	0.652	0.827	0.785
-0	1.171	-0.962	0.521	0.841	-0.315	1.196	-0.744	-0.882	2.173	0.726	-1.305	1.377	1.107	0.643	-1.790	-1.264	0.000	1.257	0.222	0.817	0.000	0.862	0.911	0.987	0.846	1.293	0.899	0.756
-1	1.392	-0.358	0.235	1.494	-0.461	0.895	-0.848	1.549	2.173	0.841	-0.384	0.666	1.107	1.199	2.509	-0.891	0.000	1.109	-0.364	-0.945	0.000	0.693	2.135	1.170	1.362	0.959	2.056	1.842
-1	1.024	1.076	-0.886	0.851	1.530	0.673	-0.449	0.187	1.087	0.628	-0.895	1.176	2.215	0.696	-0.232	-0.875	0.000	0.411	1.501	0.048	0.000	0.842	0.919	1.063	1.193	0.777	0.964	0.807
-1	0.890	-0.760	1.182	1.369	0.751	0.696	-0.959	-0.710	1.087	0.775	-0.130	-1.409	2.215	0.701	-0.110	-0.739	0.000	0.508	-0.451	0.390	0.000	0.762	0.738	0.998	1.126	0.788	0.940	0.790
-1	0.460	0.537	0.636	1.442	-0.269	0.585	0.323	-1.731	2.173	0.503	1.034	-0.927	0.000	0.928	-1.024	1.006	2.548	0.513	-0.618	-1.336	0.000	0.802	0.831	0.992	1.019	0.925	1.056	0.833
-1	0.364	1.648	0.560	1.720	0.829	1.110	0.811	-0.588	0.000	0.408	1.045	1.054	2.215	0.319	-1.138	1.545	0.000	0.423	1.025	-1.265	3.102	1.656	0.928	1.003	0.544	0.327	0.670	0.746
-1	0.525	-0.096	1.206	0.948	-1.103	1.519	-0.582	0.606	2.173	1.274	-0.572	-0.934	0.000	0.855	-1.028	-1.222	0.000	0.578	-1.000	-1.725	3.102	0.896	0.878	0.981	0.498	0.909	0.772	0.668
-0	0.536	-0.821	-1.029	0.703	1.113	0.363	-0.711	0.022	1.087	0.325	1.503	1.249	2.215	0.673	1.041	-0.401	0.000	0.480	2.127	1.681	0.000	0.767	1.034	0.990	0.671	0.836	0.669	0.663
-1	1.789	-0.583	1.641	0.897	0.799	0.515	-0.100	-1.483	0.000	1.101	0.031	-0.326	2.215	1.195	0.001	0.126	2.548	0.768	-0.148	0.601	0.000	0.916	0.921	1.207	1.069	0.483	0.934	0.795
-1	1.332	-0.571	0.986	0.580	1.508	0.582	0.634	-0.746	1.087	1.084	-0.964	-0.489	0.000	0.785	0.274	0.343	2.548	0.779	0.721	1.489	0.000	1.733	1.145	0.990	1.270	0.715	0.897	0.915
-0	1.123	0.629	-1.708	0.597	-0.882	0.752	0.195	1.522	2.173	1.671	1.515	-0.003	0.000	0.778	0.514	0.139	1.274	0.801	1.260	1.600	0.000	1.495	0.976	0.988	0.676	0.921	1.010	0.943
-0	1.816	-0.515	0.171	0.980	-0.454	0.870	0.202	-1.399	2.173	1.130	1.066	-1.593	0.000	0.844	0.735	1.275	2.548	1.125	-1.133	0.348	0.000	0.837	0.693	0.988	1.112	0.784	1.009	0.974
-1	0.364	0.694	0.445	1.862	0.159	0.963	-1.356	1.260	1.087	0.887	-0.540	-1.533	2.215	0.658	-2.544	-1.236	0.000	0.516	-0.807	0.039	0.000	0.891	1.004	0.991	1.092	0.976	1.000	0.953
-1	0.790	-1.175	0.475	1.846	0.094	0.999	-1.090	0.257	0.000	1.422	0.854	1.112	2.215	1.302	1.004	-1.702	1.274	2.557	-0.787	-1.048	0.000	0.890	1.429	0.993	2.807	0.840	2.248	1.821
-1	0.765	-0.500	-0.603	1.843	-0.560	1.068	0.007	0.746	2.173	1.154	-0.017	1.329	0.000	1.165	1.791	-1.585	0.000	1.116	0.441	-0.886	0.000	0.774	0.982	0.989	1.102	0.633	1.178	1.021
-1	1.407	1.293	-1.418	0.502	-1.527	2.005	-2.122	0.622	0.000	1.699	1.508	-0.649	2.215	1.665	0.748	-0.755	0.000	2.555	0.811	1.423	1.551	7.531	5.520	0.985	1.115	1.881	4.487	3.379
-1	0.772	-0.186	-1.372	0.823	-0.140	0.781	0.763	0.046	2.173	1.128	0.516	1.380	0.000	0.797	-0.640	-0.134	2.548	2.019	-0.972	-1.670	0.000	2.022	1.466	0.989	0.856	0.808	1.230	0.991
-1	0.546	-0.954	0.715	1.335	-1.689	0.783	-0.443	-1.735	2.173	1.081	0.185	-0.435	0.000	1.433	-0.662	-0.389	0.000	0.969	0.924	1.099	0.000	0.910	0.879	0.988	0.683	0.753	0.878	0.865
-1	0.596	0.276	-1.054	1.358	1.355	1.444	1.813	-0.208	0.000	1.175	-0.949	-1.573	0.000	0.855	-1.228	-0.925	2.548	1.837	-0.400	0.913	0.000	0.637	0.901	1.028	0.553	0.790	0.679	0.677
-0	0.458	2.292	1.530	0.291	1.283	0.749	-0.930	-0.198	0.000	0.300	-1.560	0.990	0.000	0.811	-0.176	0.995	2.548	1.085	-0.178	-1.213	3.102	0.891	0.648	0.999	0.732	0.655	0.619	0.620
-0	0.638	-0.575	-1.048	0.125	0.178	0.846	-0.753	-0.339	1.087	0.799	-0.727	1.182	0.000	0.888	0.283	0.717	0.000	1.051	-1.046	-1.557	3.102	0.889	0.871	0.989	0.884	0.923	0.836	0.779
-1	0.434	-1.119	-0.313	2.427	0.461	0.497	0.261	-1.177	2.173	0.618	-0.737	-0.688	0.000	1.150	-1.237	-1.652	2.548	0.757	-0.054	1.700	0.000	0.809	0.741	0.982	1.450	0.936	1.086	0.910
-1	0.431	-1.144	-1.030	0.778	-0.655	0.490	0.047	-1.546	0.000	1.583	-0.014	0.891	2.215	0.516	0.956	0.567	2.548	0.935	-1.123	-0.082	0.000	0.707	0.995	0.995	0.700	0.602	0.770	0.685
-1	1.894	0.222	1.224	1.578	1.715	0.966	2.890	-0.013	0.000	0.922	-0.703	-0.844	0.000	0.691	2.056	1.039	0.000	0.900	-0.733	-1.240	3.102	1.292	1.992	1.026	0.881	0.684	1.759	1.755
-0	0.985	-0.316	0.141	1.067	-0.946	0.819	-1.177	1.307	2.173	1.080	-0.429	0.557	1.107	1.726	1.435	-1.075	0.000	1.100	1.547	-0.647	0.000	0.873	1.696	1.179	1.146	1.015	1.538	1.270
-0	0.998	-0.187	-0.236	0.882	0.755	0.468	0.950	-0.439	2.173	0.579	-0.550	-0.624	0.000	1.847	1.196	1.384	1.274	0.846	1.273	-1.072	0.000	1.194	0.797	1.013	1.319	1.174	0.963	0.898
-0	0.515	0.246	-0.593	1.082	1.591	0.912	-0.623	-0.957	2.173	0.858	0.418	0.844	0.000	0.948	2.519	1.599	0.000	1.158	1.385	-0.095	3.102	0.973	1.033	0.988	0.998	1.716	1.054	0.901
-0	0.919	-1.001	1.506	1.389	0.653	0.507	-0.616	-0.689	2.173	0.808	0.536	-0.467	2.215	0.496	2.187	-0.859	0.000	0.822	0.807	1.163	0.000	0.876	0.861	1.088	0.947	0.614	0.911	1.087
-0	0.794	0.051	1.477	1.504	-1.695	0.716	0.315	0.264	1.087	0.879	-0.135	-1.094	2.215	1.433	-0.741	0.201	0.000	1.566	0.534	-0.989	0.000	0.627	0.882	0.974	0.807	1.130	0.929	0.925
-1	0.455	-0.946	-1.175	1.453	-0.580	0.763	-0.856	0.840	0.000	0.829	1.223	1.174	2.215	0.714	0.638	-0.466	0.000	1.182	0.223	-1.333	0.000	0.977	0.938	0.986	0.713	0.714	0.796	0.843
-1	0.662	-0.296	-1.287	1.212	-0.707	0.641	1.457	0.222	0.000	0.600	0.525	-1.700	2.215	0.784	-0.835	-0.961	2.548	0.865	1.131	1.162	0.000	0.854	0.877	0.978	0.740	0.734	0.888	0.811
-0	0.390	0.698	-1.629	1.888	0.298	0.990	1.614	-1.572	0.000	1.666	0.170	0.719	2.215	1.590	1.064	-0.886	1.274	0.952	0.305	-1.216	0.000	1.048	0.897	1.173	0.891	1.936	1.273	1.102
-0	1.014	0.117	1.384	0.686	-1.047	0.609	-1.245	-0.850	0.000	1.076	-1.158	0.814	1.107	1.598	-0.389	-0.111	0.000	0.907	1.688	-1.673	0.000	1.333	0.866	0.989	0.975	0.442	0.797	0.788
-0	1.530	-1.408	-0.207	0.440	-1.357	0.902	-0.647	1.325	1.087	1.320	-0.819	0.246	1.107	0.503	1.407	-1.683	0.000	1.189	-0.972	-0.925	0.000	0.386	1.273	0.988	0.829	1.335	1.173	1.149
-1	1.689	-0.590	0.915	2.076	1.202	0.644	-0.478	-0.238	0.000	0.809	-1.660	-1.184	0.000	1.227	-0.224	-0.808	2.548	1.655	1.047	-0.623	0.000	0.621	1.192	0.988	1.309	0.866	0.924	1.012
-0	1.102	0.402	-1.622	1.262	1.022	0.576	0.271	-0.269	0.000	0.591	0.495	-1.278	0.000	1.271	0.209	0.575	2.548	0.941	0.964	-0.685	3.102	0.989	0.963	1.124	0.857	0.858	0.716	0.718
-0	2.491	0.825	0.581	1.593	0.205	0.782	-0.815	1.499	0.000	1.179	-0.999	-1.509	0.000	0.926	0.920	-0.522	2.548	2.068	-1.021	-1.050	3.102	0.874	0.943	0.980	0.945	1.525	1.570	1.652
-0	0.666	0.254	1.601	1.303	-0.250	1.236	-1.929	0.793	0.000	1.074	0.447	-0.871	0.000	0.991	1.059	-0.342	0.000	1.703	-0.393	-1.419	3.102	0.921	0.945	1.285	0.931	0.462	0.770	0.729
-0	0.937	-1.126	1.424	1.395	1.743	0.760	0.428	-0.238	2.173	0.846	0.494	1.320	2.215	0.872	-1.826	-0.507	0.000	0.612	1.860	1.403	0.000	3.402	2.109	0.985	1.298	1.165	1.404	1.240
-1	0.881	-1.086	-0.870	0.513	0.266	2.049	-1.870	1.160	0.000	2.259	-0.428	-0.935	2.215	1.321	-0.655	-0.449	2.548	1.350	-1.766	-0.108	0.000	0.911	1.852	0.987	1.167	0.820	1.903	1.443
-0	0.410	0.835	-0.819	1.257	1.112	0.871	-1.737	-0.401	0.000	0.927	0.158	1.253	0.000	1.183	0.405	-1.570	0.000	0.807	-0.704	-0.438	3.102	0.932	0.962	0.987	0.653	0.315	0.616	0.648
-1	0.634	0.196	-1.679	1.379	-0.967	2.260	-0.273	1.114	0.000	1.458	1.070	-0.278	1.107	1.195	0.110	-0.688	2.548	0.907	0.298	-1.359	0.000	0.949	1.129	0.984	0.675	0.877	0.938	0.824
-1	0.632	-1.254	1.201	0.496	-0.106	0.235	2.731	-0.955	0.000	0.615	-0.805	0.600	0.000	0.633	-0.934	1.641	0.000	1.407	-0.483	-0.962	1.551	0.778	0.797	0.989	0.578	0.722	0.576	0.539
-0	0.714	1.122	1.566	2.399	-1.431	1.665	0.299	0.323	0.000	1.489	1.087	-0.861	2.215	1.174	0.140	1.083	2.548	0.404	-0.968	1.105	0.000	0.867	0.969	0.981	1.039	1.552	1.157	1.173
-1	0.477	-0.321	-0.471	1.966	1.034	2.282	1.359	-0.874	0.000	1.672	-0.258	1.109	0.000	1.537	0.604	0.231	2.548	1.534	-0.640	0.827	0.000	0.746	1.337	1.311	0.653	0.721	0.795	0.742
-1	1.351	0.460	0.031	1.194	-1.185	0.670	-1.157	-1.637	2.173	0.599	-0.823	0.680	0.000	0.478	0.373	1.716	0.000	0.809	-0.919	0.010	1.551	0.859	0.839	1.564	0.994	0.777	0.971	0.826
-1	0.520	-1.442	-0.348	0.840	1.654	1.273	-0.760	1.317	0.000	0.861	2.579	-0.791	0.000	1.779	0.257	-0.703	0.000	2.154	1.928	0.457	0.000	1.629	3.194	0.992	0.730	1.107	2.447	2.747
-0	0.700	-0.308	0.920	0.438	-0.879	0.516	1.409	1.101	0.000	0.960	0.701	-0.049	2.215	1.442	-0.416	-1.439	2.548	0.628	1.009	-0.364	0.000	0.848	0.817	0.987	0.759	1.421	0.937	0.920
-1	0.720	1.061	-0.546	0.798	-1.521	1.066	0.173	0.271	1.087	1.453	0.114	1.336	1.107	0.702	0.616	-0.367	0.000	0.543	-0.386	-1.301	0.000	0.653	0.948	0.989	1.031	1.500	0.965	0.790
-1	0.735	-0.416	0.588	1.308	-0.382	1.042	0.344	1.609	0.000	0.926	0.163	-0.520	1.107	1.050	-0.427	1.159	2.548	0.834	0.613	0.948	0.000	0.848	1.189	1.042	0.844	1.099	0.829	0.843
-1	0.777	-0.396	1.540	1.608	0.638	0.955	0.040	0.918	2.173	1.315	1.116	-0.823	0.000	0.781	-0.762	0.564	2.548	0.945	-0.573	1.379	0.000	0.679	0.706	1.124	0.608	0.593	0.515	0.493
-1	0.934	0.319	-0.257	0.970	-0.980	0.726	0.774	0.731	0.000	0.896	0.038	-1.465	1.107	0.773	-0.055	-0.831	2.548	1.439	-0.229	0.698	0.000	0.964	1.031	0.995	0.845	0.480	0.810	0.762
-0	0.461	0.771	0.019	2.055	-1.288	1.043	0.147	0.261	2.173	0.833	-0.156	1.425	0.000	0.832	0.805	-0.491	2.548	0.589	1.252	1.414	0.000	0.850	0.906	1.245	1.364	0.850	0.908	0.863
-1	0.858	-0.116	-0.937	0.966	1.167	0.825	-0.108	1.111	1.087	0.733	1.163	-0.634	0.000	0.894	0.771	0.020	0.000	0.846	-1.124	-1.195	3.102	0.724	1.194	1.195	0.813	0.969	0.985	0.856
-0	0.720	-0.335	-0.307	1.445	0.540	1.108	-0.034	-1.691	1.087	0.883	-1.356	-0.678	2.215	0.440	1.093	0.253	0.000	0.389	-1.582	-1.097	0.000	1.113	1.034	0.988	1.256	1.572	1.062	0.904
-1	0.750	-0.811	-0.542	0.985	0.408	0.471	0.477	0.355	0.000	1.347	-0.875	-1.556	2.215	0.564	1.082	-0.724	0.000	0.793	-0.958	-0.020	3.102	0.836	0.825	0.986	1.066	0.924	0.927	0.883
-0	0.392	-0.468	-0.216	0.680	1.565	1.086	-0.765	-0.581	1.087	1.264	-1.035	1.189	2.215	0.986	-0.338	0.747	0.000	0.884	-1.328	-0.965	0.000	1.228	0.988	0.982	1.135	1.741	1.108	0.956
-1	0.434	-1.269	0.643	0.713	0.608	0.597	0.832	1.627	0.000	0.708	-0.422	0.079	2.215	1.533	-0.823	-1.127	2.548	0.408	-1.357	-0.828	0.000	1.331	1.087	0.999	1.075	1.015	0.875	0.809
-0	0.828	-1.803	0.342	0.847	-0.162	1.585	-1.128	-0.272	2.173	1.974	0.039	-1.717	0.000	0.900	0.764	-1.741	0.000	1.349	-0.079	1.035	3.102	0.984	0.815	0.985	0.780	1.661	1.403	1.184
-1	1.089	-0.350	-0.747	1.472	0.792	1.087	-0.069	-1.192	0.000	0.512	-0.841	-1.284	0.000	2.162	-0.821	0.545	2.548	1.360	2.243	-0.183	0.000	0.977	0.628	1.725	1.168	0.635	0.823	0.822
-1	0.444	0.451	-1.332	1.176	-0.247	0.898	0.194	0.007	0.000	1.958	0.576	-1.618	2.215	0.584	1.203	0.268	0.000	0.939	1.033	1.264	3.102	0.829	0.886	0.985	1.265	0.751	1.032	0.948
-0	0.629	0.114	1.177	0.917	-1.204	0.845	0.828	-0.088	0.000	0.962	-1.302	0.823	2.215	0.732	0.358	-1.334	2.548	0.538	0.582	1.561	0.000	1.028	0.834	0.988	0.904	1.205	1.039	0.885
-1	1.754	-1.259	-0.573	0.959	-1.483	0.358	0.448	-1.452	0.000	0.711	0.313	0.499	2.215	1.482	-0.390	1.474	2.548	1.879	-1.540	0.668	0.000	0.843	0.825	1.313	1.315	0.939	1.048	0.871
-1	0.549	0.706	-1.437	0.894	0.891	0.680	-0.762	-1.568	0.000	0.981	0.499	-0.425	2.215	1.332	0.678	0.485	1.274	0.803	0.022	-0.893	0.000	0.793	1.043	0.987	0.761	0.899	0.915	0.794
-0	0.475	0.542	-0.987	1.569	0.069	0.551	1.543	-1.488	0.000	0.608	0.301	1.734	2.215	0.277	0.499	-0.522	0.000	1.375	1.212	0.696	3.102	0.652	0.756	0.987	0.828	0.830	0.715	0.679
-1	0.723	0.049	-1.153	1.300	0.083	0.723	-0.749	0.630	0.000	1.126	0.412	-0.384	0.000	1.272	1.256	1.358	2.548	3.108	0.777	-1.486	3.102	0.733	1.096	1.206	1.269	0.899	1.015	0.903
-1	1.062	0.296	0.725	0.285	-0.531	0.819	1.277	-0.667	0.000	0.687	0.829	-0.092	0.000	1.158	0.447	1.047	2.548	1.444	-0.186	-1.491	3.102	0.863	1.171	0.986	0.769	0.828	0.919	0.840
-0	0.572	-0.349	1.396	2.023	0.795	0.577	0.457	-0.533	0.000	1.351	0.701	-1.091	0.000	0.724	-1.012	-0.182	2.548	0.923	-0.012	0.789	3.102	0.936	1.025	0.985	1.002	0.600	0.828	0.909
-1	0.563	0.387	0.412	0.553	1.050	0.723	-0.992	-0.447	0.000	0.748	0.948	0.546	2.215	1.761	-0.559	-1.183	0.000	1.114	-0.251	1.192	3.102	0.936	0.912	0.976	0.578	0.722	0.829	0.892
-1	1.632	1.577	-0.697	0.708	-1.263	0.863	0.012	1.197	2.173	0.498	0.990	-0.806	0.000	0.627	2.387	-1.283	0.000	0.607	1.290	-0.174	3.102	0.916	1.328	0.986	0.557	0.971	0.935	0.836
-1	0.562	-0.360	0.399	0.803	-1.334	1.443	-0.116	1.628	2.173	0.750	0.987	0.135	1.107	0.795	0.298	-0.556	0.000	1.150	-0.113	-0.093	0.000	0.493	1.332	0.985	1.001	1.750	1.013	0.886
-1	0.987	0.706	-0.492	0.861	0.607	0.593	0.088	-0.184	0.000	0.802	0.894	1.608	2.215	0.782	-0.471	1.500	2.548	0.521	0.772	-0.960	0.000	0.658	0.893	1.068	0.877	0.664	0.709	0.661
-1	1.052	0.883	-0.581	1.566	0.860	0.931	1.515	-0.873	0.000	0.493	0.145	-0.672	0.000	1.133	0.935	1.581	2.548	1.630	0.695	0.923	3.102	1.105	1.087	1.713	0.948	0.590	0.872	0.883
-1	2.130	-0.516	-0.291	0.776	-1.230	0.689	-0.257	0.800	2.173	0.730	-0.274	-1.437	0.000	0.615	0.241	1.083	0.000	0.834	0.757	1.613	3.102	0.836	0.806	1.333	1.061	0.730	0.889	0.783
-1	0.742	0.797	1.628	0.311	-0.418	0.620	0.685	-1.457	0.000	0.683	1.774	-1.082	0.000	1.700	1.104	0.225	2.548	0.382	-2.184	-1.307	0.000	0.945	1.228	0.984	0.864	0.931	0.988	0.838
-0	0.311	-1.249	-0.927	1.272	-1.262	0.642	-1.228	-0.136	0.000	1.220	-0.804	-1.558	2.215	0.950	-0.828	0.495	1.274	2.149	-1.672	0.634	0.000	1.346	0.887	0.981	0.856	1.101	1.001	1.106
-0	0.660	-1.834	-0.667	0.601	1.236	0.932	-0.933	-0.135	2.173	1.373	-0.122	1.429	0.000	0.654	-0.034	-0.847	2.548	0.711	0.911	0.703	0.000	1.144	0.942	0.984	0.822	0.739	0.992	0.895
-0	3.609	-0.590	0.851	0.615	0.455	1.280	0.003	-0.866	1.087	1.334	0.708	-1.131	0.000	0.669	0.480	0.092	0.000	0.975	0.983	-1.429	3.102	1.301	1.089	0.987	1.476	0.934	1.469	1.352
-1	0.905	-0.403	1.567	2.651	0.953	1.194	-0.241	-0.567	1.087	0.308	-0.384	-0.007	0.000	0.608	-0.175	-1.163	2.548	0.379	0.941	1.662	0.000	0.580	0.721	1.126	0.895	0.544	1.097	0.836
-1	0.983	0.255	1.093	0.905	-0.874	0.863	0.060	-0.368	0.000	0.824	-0.747	-0.633	0.000	0.614	0.961	1.052	0.000	0.792	-0.260	1.632	3.102	0.874	0.883	1.280	0.663	0.406	0.592	0.645
-1	1.160	-1.027	0.274	0.460	0.322	2.085	-1.623	-0.840	0.000	1.634	-1.046	1.182	2.215	0.492	-0.367	1.174	0.000	0.824	-0.998	1.617	0.000	0.943	0.884	1.001	1.209	1.313	1.034	0.866
-0	0.299	0.028	-1.372	1.930	-0.661	0.840	-0.979	0.664	1.087	0.535	-2.041	1.434	0.000	1.087	-1.797	0.344	0.000	0.485	-0.560	-1.105	3.102	0.951	0.890	0.980	0.483	0.684	0.730	0.706
-0	0.293	1.737	-1.418	2.074	0.794	0.679	1.024	-1.457	0.000	1.034	1.094	-0.168	1.107	0.506	1.680	-0.661	0.000	0.523	-0.042	-1.274	3.102	0.820	0.944	0.987	0.842	0.694	0.761	0.750
-0	0.457	-0.393	1.560	0.738	-0.007	0.475	-0.230	0.246	0.000	0.776	-1.264	-0.606	2.215	0.865	-0.731	-1.576	2.548	1.153	0.343	1.436	0.000	1.060	0.883	0.988	0.972	0.703	0.758	0.720
-0	0.935	-0.582	0.240	2.401	0.818	1.231	-0.618	-1.289	0.000	0.799	0.544	-0.228	2.215	0.525	-1.494	-0.969	0.000	0.609	-1.123	1.168	3.102	0.871	0.767	1.035	1.154	0.919	0.868	1.006
-1	0.902	-0.745	-1.215	1.174	-0.501	1.215	0.167	1.162	0.000	0.896	1.217	-0.976	0.000	0.585	-0.429	1.036	0.000	1.431	-0.416	0.151	3.102	0.524	0.952	0.990	0.707	0.271	0.592	0.826
-1	0.653	0.337	-0.320	1.118	-0.934	1.050	0.745	0.529	1.087	1.075	1.742	-1.538	0.000	0.585	1.090	0.973	0.000	1.091	-0.187	1.160	1.551	1.006	1.108	0.978	1.121	0.838	0.947	0.908
-0	1.157	1.401	0.340	0.395	-1.218	0.945	1.928	-0.876	0.000	1.384	0.320	1.002	1.107	1.900	1.177	-0.462	2.548	1.122	1.316	1.720	0.000	1.167	1.096	0.989	0.937	1.879	1.307	1.041
-0	0.960	0.355	-0.152	0.872	-0.338	0.391	0.348	0.956	1.087	0.469	2.664	1.409	0.000	0.756	-1.561	1.500	0.000	0.525	1.436	1.728	3.102	1.032	0.946	0.996	0.929	0.470	0.698	0.898
-1	1.038	0.274	0.825	1.198	0.963	1.078	-0.496	-1.014	2.173	0.739	-0.727	-0.151	2.215	1.035	-0.799	0.398	0.000	1.333	-0.872	-1.498	0.000	0.849	1.033	0.985	0.886	0.936	0.975	0.823
-0	0.490	0.277	0.318	1.303	0.694	1.333	-1.620	-0.563	0.000	1.459	-1.326	1.140	0.000	0.779	-0.673	-1.324	2.548	0.860	-1.247	0.043	0.000	0.857	0.932	0.992	0.792	0.278	0.841	1.498
-0	1.648	-0.688	-1.386	2.790	0.995	1.087	1.359	-0.687	0.000	1.050	-0.223	-0.261	2.215	0.613	-0.889	1.335	0.000	1.204	0.827	0.309	3.102	0.464	0.973	2.493	1.737	0.827	1.319	1.062
-0	1.510	-0.662	1.668	0.860	0.280	0.705	0.974	-1.647	1.087	0.662	-0.393	-0.225	0.000	0.610	-0.996	0.532	2.548	0.464	1.305	0.102	0.000	0.859	1.057	1.498	0.799	1.260	0.946	0.863
-1	0.850	-1.185	-0.117	0.943	-0.449	1.142	0.875	-0.030	0.000	2.223	-0.461	1.627	2.215	0.767	-1.761	-1.692	0.000	1.012	-0.727	0.639	3.102	3.649	2.062	0.985	1.478	1.087	1.659	1.358
-0	0.933	1.259	0.130	0.326	-0.890	0.306	1.136	1.142	0.000	0.964	0.705	-1.373	2.215	0.546	-0.196	-0.001	0.000	0.578	-1.169	1.004	3.102	0.830	0.836	0.988	0.837	1.031	0.749	0.655
-0	0.471	0.697	1.570	1.109	0.201	1.248	0.348	-1.448	0.000	2.103	0.773	0.686	2.215	1.451	-0.087	-0.453	2.548	1.197	-0.045	-1.026	0.000	0.793	1.094	0.987	0.851	1.804	1.378	1.089
-1	2.446	-0.701	-1.568	0.059	0.822	1.401	-0.600	-0.044	2.173	0.324	-0.001	1.344	2.215	0.913	-0.818	1.049	0.000	0.442	-1.088	-0.005	0.000	0.611	1.062	0.979	0.562	0.988	0.998	0.806
-0	0.619	2.029	0.933	0.528	-0.903	0.974	0.760	-0.311	2.173	0.825	0.658	-1.466	1.107	0.894	1.594	0.370	0.000	0.882	-0.258	1.661	0.000	1.498	1.088	0.987	0.867	1.139	0.900	0.779
-1	0.674	-0.131	-0.362	0.518	-1.574	0.876	0.442	0.145	1.087	0.497	-1.526	-1.704	0.000	0.680	2.514	-1.374	0.000	0.792	-0.479	0.773	1.551	0.573	1.198	0.984	0.800	0.667	0.987	0.832
-1	1.447	1.145	-0.937	0.307	-1.458	0.478	1.264	0.816	1.087	0.558	1.015	-0.101	2.215	0.937	-0.190	1.177	0.000	0.699	0.954	-1.512	0.000	0.877	0.838	0.990	0.873	0.566	0.646	0.713
-1	0.976	0.308	-0.844	0.436	0.610	1.253	0.149	-1.585	2.173	1.415	0.568	0.096	2.215	0.953	-0.855	0.441	0.000	0.867	-0.650	1.643	0.000	0.890	1.234	0.988	0.796	2.002	1.179	0.977
-0	0.697	0.401	-0.718	0.920	0.735	0.958	-0.172	0.168	2.173	0.872	-0.097	-1.335	0.000	0.513	-1.192	-1.710	1.274	0.426	-1.637	1.368	0.000	0.997	1.227	1.072	0.800	1.013	0.786	0.749
-1	1.305	-2.157	1.740	0.661	-0.912	0.705	-0.516	0.759	2.173	0.989	-0.716	-0.300	2.215	0.627	-1.052	-1.736	0.000	0.467	-2.467	0.568	0.000	0.807	0.964	0.988	1.427	1.012	1.165	0.926
-0	1.847	1.663	-0.618	0.280	1.258	1.462	-0.054	1.371	0.000	0.900	0.309	-0.544	0.000	0.331	-2.149	-0.341	0.000	1.091	-0.833	0.710	3.102	1.496	0.931	0.989	1.549	0.115	1.140	1.150
-0	0.410	-0.323	1.069	2.160	0.010	0.892	0.942	-1.640	2.173	0.946	0.938	1.314	0.000	1.213	-1.099	-0.794	2.548	0.650	0.053	0.056	0.000	1.041	0.916	1.063	0.985	1.910	1.246	1.107
-1	0.576	1.092	-0.088	0.777	-1.579	0.757	0.271	0.109	0.000	0.819	0.827	-1.554	2.215	1.313	2.341	-1.568	0.000	2.827	0.239	-0.338	0.000	0.876	0.759	0.986	0.692	0.457	0.796	0.791
-1	0.537	0.925	-1.406	0.306	-0.050	0.906	1.051	0.037	0.000	1.469	-0.177	-1.320	2.215	1.872	0.723	1.158	0.000	1.313	0.227	-0.501	3.102	0.953	0.727	0.978	0.755	0.892	0.932	0.781
-0	0.716	-0.065	-0.484	1.313	-1.563	0.596	-0.242	0.678	2.173	0.426	-1.909	0.616	0.000	0.885	-0.406	-1.343	2.548	0.501	-1.327	-0.340	0.000	0.470	0.728	1.109	0.919	0.881	0.665	0.692
-1	0.624	-0.389	0.128	1.636	-1.110	1.025	0.573	-0.843	2.173	0.646	-0.697	1.064	0.000	0.632	-1.442	0.961	0.000	0.863	-0.106	1.717	0.000	0.825	0.917	1.257	0.983	0.713	0.890	0.824
-0	0.484	2.101	1.714	1.131	-0.823	0.750	0.583	-1.304	1.087	0.894	0.421	0.559	2.215	0.921	-0.063	0.282	0.000	0.463	-0.474	-1.387	0.000	0.742	0.886	0.995	0.993	1.201	0.806	0.754
-0	0.570	0.339	-1.478	0.528	0.439	0.978	1.479	-1.411	2.173	0.763	1.541	-0.734	0.000	1.375	0.840	0.903	0.000	0.965	1.599	0.364	0.000	0.887	1.061	0.992	1.322	1.453	1.013	0.969
-0	0.940	1.303	1.636	0.851	-1.732	0.803	-0.030	-0.177	0.000	0.480	-0.125	-0.954	0.000	0.944	0.709	0.296	2.548	1.342	-0.418	1.197	3.102	0.853	0.989	0.979	0.873	0.858	0.719	0.786
-1	0.599	0.544	-0.238	0.816	1.043	0.857	0.660	1.128	2.173	0.864	-0.624	-0.843	0.000	1.159	0.367	0.174	0.000	1.520	-0.543	-1.508	0.000	0.842	0.828	0.984	0.759	0.895	0.918	0.791
-1	1.651	1.897	-0.914	0.423	0.315	0.453	0.619	-1.607	2.173	0.532	-0.424	0.209	1.107	0.369	2.479	0.034	0.000	0.701	0.217	0.984	0.000	0.976	0.951	1.035	0.879	0.825	0.915	0.798
-1	0.926	-0.574	-0.763	0.285	1.094	0.672	2.314	1.545	0.000	1.124	0.415	0.809	0.000	1.387	0.270	-0.949	2.548	1.547	-0.631	-0.200	3.102	0.719	0.920	0.986	0.889	0.933	0.797	0.777
-0	0.677	1.698	-0.890	0.641	-0.449	0.607	1.754	1.720	0.000	0.776	0.372	0.782	2.215	0.511	1.491	-0.480	0.000	0.547	-0.341	0.853	3.102	0.919	1.026	0.997	0.696	0.242	0.694	0.687
-0	1.266	0.602	0.958	0.487	1.256	0.709	0.843	-1.196	0.000	0.893	1.303	-0.594	1.107	1.090	1.320	0.354	0.000	0.797	1.846	1.139	0.000	0.780	0.896	0.986	0.661	0.709	0.790	0.806
-1	0.628	-0.616	-0.329	0.764	-1.150	0.477	-0.715	1.187	2.173	1.250	0.607	1.026	2.215	0.983	-0.023	-0.583	0.000	0.377	1.344	-1.015	0.000	0.744	0.954	0.987	0.837	0.841	0.795	0.694
-1	1.035	-0.828	-1.358	1.870	-1.060	1.075	0.130	0.448	2.173	0.660	0.697	0.641	0.000	0.425	1.006	-1.035	0.000	0.751	1.055	1.364	3.102	0.826	0.822	0.988	0.967	0.901	1.077	0.906
-1	0.830	0.265	-0.150	0.660	1.105	0.592	-0.557	0.908	2.173	0.670	-1.419	-0.671	0.000	1.323	-0.409	1.644	2.548	0.850	-0.033	-0.615	0.000	0.760	0.967	0.984	0.895	0.681	0.747	0.770
-1	1.395	1.100	1.167	1.088	0.218	0.400	-0.132	0.024	2.173	0.743	0.530	-1.361	2.215	0.341	-0.691	-0.238	0.000	0.396	-1.426	-0.933	0.000	0.363	0.472	1.287	0.922	0.810	0.792	0.656
-1	1.070	1.875	-1.298	1.215	-0.106	0.767	0.795	0.514	1.087	0.401	2.780	1.276	0.000	0.686	1.127	1.721	2.548	0.391	-0.259	-1.167	0.000	1.278	1.113	1.389	0.852	0.824	0.838	0.785
-0	1.114	-0.071	1.719	0.399	-1.383	0.849	0.254	0.481	0.000	0.958	-0.579	0.742	0.000	1.190	-0.140	-0.862	2.548	0.479	1.390	0.856	0.000	0.952	0.988	0.985	0.764	0.419	0.835	0.827
-0	0.714	0.376	-0.568	1.578	-1.165	0.648	0.141	0.639	2.173	0.472	0.569	1.449	1.107	0.783	1.483	0.361	0.000	0.540	-0.790	0.032	0.000	0.883	0.811	0.982	0.775	0.572	0.760	0.745
-0	0.401	-1.731	0.765	0.974	1.648	0.652	-1.024	0.191	0.000	0.544	-0.366	-1.246	2.215	0.627	0.140	1.008	2.548	0.810	0.409	0.429	0.000	0.950	0.934	0.977	0.621	0.580	0.677	0.650
-1	0.391	1.679	-1.298	0.605	-0.832	0.549	1.338	0.522	2.173	1.244	0.884	1.070	0.000	1.002	0.846	-1.345	2.548	0.783	-2.464	-0.237	0.000	4.515	2.854	0.981	0.877	0.939	1.942	1.489
-1	0.513	-0.220	-0.444	1.699	0.479	1.109	0.181	-0.999	2.173	0.883	-0.335	-1.716	2.215	1.075	-0.380	1.352	0.000	0.857	0.048	0.147	0.000	0.937	0.758	0.986	1.206	0.958	0.949	0.876
-0	1.367	-0.388	0.798	1.158	1.078	0.811	-1.024	-1.628	0.000	1.504	0.097	-0.999	2.215	1.652	-0.860	0.054	2.548	0.573	-0.142	-1.401	0.000	0.869	0.833	1.006	1.412	1.641	1.214	1.041
-1	1.545	-0.533	-1.517	1.177	1.289	2.331	-0.370	-0.073	0.000	1.295	-0.358	-0.891	2.215	0.476	0.756	0.985	0.000	1.945	-0.016	-1.651	3.102	1.962	1.692	1.073	0.656	0.941	1.312	1.242
-0	0.858	0.978	-1.258	0.286	0.161	0.729	1.230	1.087	2.173	0.561	2.670	-0.109	0.000	0.407	2.346	0.938	0.000	1.078	0.729	-0.658	3.102	0.597	0.921	0.982	0.579	0.954	0.733	0.769
-1	1.454	-1.384	0.870	0.067	0.394	1.033	-0.673	0.318	0.000	1.166	-0.763	-1.533	2.215	2.848	-0.045	-0.856	2.548	0.697	-0.140	1.134	0.000	0.931	1.293	0.977	1.541	1.326	1.201	1.078
-1	0.559	-0.913	0.486	1.104	-0.321	1.073	-0.348	1.345	0.000	0.901	-0.827	-0.842	0.000	0.739	0.047	-0.415	2.548	0.433	-1.132	1.268	0.000	0.797	0.695	0.985	0.868	0.346	0.674	0.623
-1	1.333	0.780	-0.964	0.916	1.202	1.822	-0.071	0.742	2.173	1.486	-0.399	-0.824	0.000	0.740	0.568	-0.134	0.000	0.971	-0.070	-1.589	3.102	1.278	0.929	1.421	1.608	1.214	1.215	1.137
-1	2.417	0.631	-0.317	0.323	0.581	0.841	1.524	-1.738	0.000	0.543	1.176	-0.325	0.000	0.827	0.700	0.866	0.000	0.834	-0.262	-1.702	3.102	0.932	0.820	0.988	0.646	0.287	0.595	0.589
-0	0.955	-1.242	0.938	1.104	0.474	0.798	-0.743	1.535	0.000	1.356	-1.357	-1.080	2.215	1.320	-1.396	-0.132	2.548	0.728	-0.529	-0.633	0.000	0.832	0.841	0.988	0.923	1.077	0.988	0.816
-1	1.305	-1.918	0.391	1.161	0.063	0.724	2.593	1.481	0.000	0.592	-1.207	-0.329	0.000	0.886	-0.836	-1.168	2.548	1.067	-1.481	-1.440	0.000	0.916	0.688	0.991	0.969	0.550	0.665	0.638
-0	1.201	0.071	-1.123	2.242	-1.533	0.702	-0.256	0.688	0.000	0.967	0.491	1.040	2.215	1.271	-0.558	0.095	0.000	1.504	0.676	-0.383	3.102	0.917	1.006	0.985	1.017	1.057	0.928	1.057
-0	0.994	-1.607	1.596	0.774	-1.391	0.625	-0.134	-0.862	2.173	0.746	-0.765	-0.316	2.215	1.131	-0.320	0.869	0.000	0.607	0.826	0.301	0.000	0.798	0.967	0.999	0.880	0.581	0.712	0.774
-1	0.482	-0.467	0.729	1.419	1.458	0.824	0.376	-0.242	0.000	1.368	0.023	1.459	2.215	0.826	0.669	-1.079	2.548	0.936	2.215	-0.309	0.000	1.883	1.216	0.997	1.065	0.946	1.224	1.526
-1	0.383	1.588	1.611	0.748	1.194	0.866	-0.279	-0.636	0.000	0.707	0.536	0.801	2.215	1.647	-1.155	0.367	0.000	1.292	0.303	-1.681	3.102	2.016	1.581	0.986	0.584	0.684	1.107	0.958
-0	0.629	0.203	0.736	0.671	-0.271	1.350	-0.486	0.761	2.173	0.496	-0.805	-1.718	0.000	2.393	0.044	-1.046	1.274	0.651	-0.116	-0.541	0.000	0.697	1.006	0.987	1.069	2.317	1.152	0.902
-0	0.905	-0.564	-0.570	0.263	1.096	1.219	-1.397	-1.414	1.087	1.164	-0.533	-0.208	0.000	1.459	1.965	0.784	0.000	2.220	-1.421	0.452	0.000	0.918	1.360	0.993	0.904	0.389	2.118	1.707
-1	1.676	1.804	1.171	0.529	1.175	1.664	0.354	-0.530	0.000	1.004	0.691	-1.280	2.215	0.838	0.373	0.626	2.548	1.094	1.774	0.501	0.000	0.806	1.100	0.991	0.769	0.976	0.807	0.740
-1	1.364	-1.936	0.020	1.327	0.428	1.021	-1.665	-0.907	2.173	0.818	-2.701	1.303	0.000	0.716	-0.590	-1.629	2.548	0.895	-2.280	-1.602	0.000	1.211	0.849	0.989	1.320	0.864	1.065	0.949
-0	0.629	-0.626	0.609	1.828	1.280	0.644	-0.856	-0.873	2.173	0.555	1.066	-0.640	0.000	0.477	-1.364	-1.021	2.548	1.017	0.036	0.380	0.000	0.947	0.941	0.994	1.128	0.241	0.793	0.815
-1	1.152	-0.843	0.926	1.802	0.800	2.493	-1.449	-1.127	0.000	1.737	0.833	0.488	0.000	1.026	0.929	-0.990	2.548	1.408	0.689	1.142	3.102	1.171	0.956	0.993	2.009	0.867	1.499	1.474
-0	2.204	0.081	0.008	1.021	-0.679	2.676	0.090	1.163	0.000	2.210	-1.686	-1.195	0.000	1.805	0.891	-0.148	2.548	0.450	-0.502	-1.295	3.102	6.959	3.492	1.205	0.908	0.845	2.690	2.183
-1	0.957	0.954	1.702	0.043	-0.503	1.113	0.033	-0.308	0.000	0.757	-0.363	-1.129	2.215	1.635	0.068	1.048	1.274	0.415	-2.098	0.061	0.000	1.010	0.979	0.992	0.704	1.125	0.761	0.715
-0	1.222	0.418	1.059	1.303	1.442	0.282	-1.499	-1.286	0.000	1.567	0.016	-0.164	2.215	0.451	2.229	-1.229	0.000	0.660	-0.513	-0.296	3.102	2.284	1.340	0.985	1.531	0.314	1.032	1.094
-1	0.603	1.675	-0.973	0.703	-1.709	1.023	0.652	1.296	2.173	1.078	0.363	-0.263	0.000	0.734	-0.457	-0.745	1.274	0.561	1.434	-0.042	0.000	0.888	0.771	0.984	0.847	1.234	0.874	0.777
-0	0.897	0.949	-0.848	1.115	-0.085	0.522	-1.267	-1.418	0.000	0.684	-0.599	1.474	0.000	1.176	0.922	0.641	2.548	0.470	0.103	0.148	3.102	0.775	0.697	0.984	0.839	0.358	0.847	1.008
-1	0.987	1.013	-1.504	0.468	-0.259	1.160	0.476	-0.971	2.173	1.266	0.919	0.780	0.000	0.634	1.695	0.233	0.000	0.487	-0.082	0.719	3.102	0.921	0.641	0.991	0.730	0.828	0.952	0.807
-1	0.847	1.581	-1.397	1.629	1.529	1.053	0.816	-0.344	2.173	0.895	0.779	0.332	0.000	0.750	1.311	0.419	2.548	1.604	0.844	1.367	0.000	1.265	0.798	0.989	1.328	0.783	0.930	0.879
-1	0.805	1.416	-1.327	0.397	0.589	0.488	0.982	0.843	0.000	0.664	-0.999	0.129	0.000	0.624	0.613	-0.558	0.000	1.431	-0.667	-1.561	3.102	0.959	1.103	0.989	0.590	0.632	0.926	0.798
-0	1.220	-0.313	-0.489	1.759	0.201	1.698	-0.220	0.241	2.173	1.294	1.390	-1.682	0.000	1.447	-1.623	-1.296	0.000	1.710	0.872	-1.356	3.102	1.198	0.981	1.184	0.859	2.165	1.807	1.661
-0	0.772	-0.611	-0.549	0.465	-1.528	1.103	-0.140	0.001	2.173	0.854	-0.406	1.655	0.000	0.733	-1.250	1.072	0.000	0.883	0.627	-1.132	3.102	0.856	0.927	0.987	1.094	1.013	0.938	0.870
-1	1.910	0.771	0.828	0.231	1.267	1.398	1.455	-0.295	2.173	0.837	-2.564	0.770	0.000	0.540	2.189	1.287	0.000	1.345	1.311	-1.151	0.000	0.861	0.869	0.984	1.359	1.562	1.105	0.963
-1	0.295	0.832	1.399	1.222	-0.517	2.480	0.013	1.591	0.000	2.289	0.436	0.287	2.215	1.995	-0.367	-0.409	1.274	0.375	1.367	-1.716	0.000	1.356	2.171	0.990	1.467	1.664	1.855	1.705
-1	1.228	0.339	-0.575	0.417	1.474	0.480	-1.416	-1.498	2.173	0.614	-0.933	-0.961	0.000	1.189	1.690	1.003	0.000	1.690	-1.065	0.106	3.102	0.963	1.147	0.987	1.086	0.948	0.930	0.866
-0	2.877	-1.014	1.440	0.782	0.483	1.134	-0.735	-0.196	2.173	1.123	0.084	-0.596	0.000	1.796	-0.356	1.044	2.548	1.406	1.582	-0.991	0.000	0.939	1.178	1.576	0.996	1.629	1.216	1.280
-1	2.178	0.259	1.107	0.256	1.222	0.979	-0.440	-0.538	1.087	0.496	-0.760	-0.049	0.000	1.471	1.683	-1.486	0.000	0.646	0.695	-1.577	3.102	1.093	1.070	0.984	0.608	0.889	0.962	0.866
-1	0.604	0.592	1.295	0.964	0.348	1.178	-0.016	0.832	2.173	1.626	-0.420	-0.760	0.000	0.748	0.461	-0.906	0.000	0.728	0.309	-1.269	1.551	0.852	0.604	0.989	0.678	0.949	1.021	0.878
-0	0.428	-1.352	-0.912	1.713	0.797	1.894	-1.452	0.191	2.173	2.378	2.113	-1.190	0.000	0.860	2.174	0.949	0.000	1.693	0.759	1.426	3.102	0.885	1.527	1.186	1.090	3.294	4.492	3.676
-0	0.473	0.485	0.154	1.433	-1.504	0.766	1.257	-1.302	2.173	0.414	0.119	0.238	0.000	0.805	0.242	-0.691	2.548	0.734	0.749	0.753	0.000	0.430	0.893	1.137	0.686	0.724	0.618	0.608
-1	0.763	-0.601	0.876	0.182	-1.678	0.818	0.599	0.481	2.173	0.658	-0.737	-0.553	0.000	0.857	-1.138	-1.435	0.000	1.540	-1.466	-0.447	0.000	0.870	0.566	0.989	0.728	0.658	0.821	0.726
-0	0.619	-0.273	-0.143	0.992	-1.267	0.566	0.876	-1.396	2.173	0.515	0.892	0.618	0.000	0.434	-0.902	0.862	2.548	0.490	-0.539	0.549	0.000	0.568	0.794	0.984	0.667	0.867	0.597	0.578
-0	0.793	0.970	0.324	0.570	0.816	0.761	-0.550	1.519	2.173	1.150	0.496	-0.447	0.000	0.925	0.724	1.008	1.274	1.135	-0.275	-0.843	0.000	0.829	1.068	0.978	1.603	0.892	1.041	1.059
-1	0.480	0.364	-0.067	1.906	-1.582	1.397	1.159	0.140	0.000	0.639	0.398	-1.102	0.000	1.597	-0.668	1.607	2.548	1.306	-0.797	0.288	3.102	0.856	1.259	1.297	1.022	1.032	1.049	0.939
-0	0.514	1.304	1.490	1.741	-0.220	0.648	0.155	0.535	0.000	0.562	-1.016	0.837	0.000	0.863	-0.780	-0.815	2.548	1.688	-0.130	-1.545	3.102	0.887	0.980	1.309	1.269	0.654	1.044	1.035
-0	1.225	0.333	0.656	0.893	0.859	1.037	-0.876	1.603	1.087	1.769	0.272	-0.227	2.215	1.000	0.579	-1.690	0.000	1.385	0.471	-0.860	0.000	0.884	1.207	0.995	1.097	2.336	1.282	1.145
-0	2.044	-1.472	-0.294	0.392	0.369	0.927	0.718	1.492	1.087	1.619	-0.736	0.047	2.215	1.884	-0.101	-1.540	0.000	0.548	-0.441	1.117	0.000	0.798	0.877	0.981	0.750	2.272	1.469	1.276
-0	1.037	-0.276	0.735	3.526	1.156	2.498	0.401	-0.590	1.087	0.714	-1.203	1.393	2.215	0.681	0.629	1.534	0.000	0.719	-0.355	-0.706	0.000	0.831	0.857	0.988	2.864	2.633	1.988	1.466
-1	0.651	-1.218	-0.791	0.770	-1.449	0.610	-0.535	0.960	2.173	0.380	-1.072	-0.031	2.215	0.415	2.123	-1.100	0.000	0.776	0.217	0.420	0.000	0.986	1.008	1.001	0.853	0.588	0.799	0.776
-0	1.586	-0.409	0.085	3.258	0.405	1.647	-0.674	-1.519	0.000	0.640	-1.027	-1.681	0.000	1.452	-0.444	-0.957	2.548	0.927	-0.017	1.215	3.102	0.519	0.866	0.992	0.881	0.847	1.018	1.278
-0	0.712	0.092	-0.466	0.688	1.236	0.921	-1.217	-1.022	2.173	2.236	-1.167	0.868	2.215	0.851	-1.892	-0.753	0.000	0.475	-1.216	-0.383	0.000	0.668	0.758	0.988	1.180	2.093	1.157	0.934
-0	0.419	0.471	0.974	2.805	0.235	1.473	-0.198	1.255	1.087	0.931	1.083	-0.712	0.000	1.569	1.358	-1.179	2.548	2.506	0.199	-0.842	0.000	0.929	0.991	0.992	1.732	2.367	1.549	1.430
-1	0.667	1.003	1.504	0.368	1.061	0.885	-0.318	-0.353	0.000	1.438	-1.939	0.710	0.000	1.851	0.277	-1.460	2.548	1.403	0.517	-0.157	0.000	0.883	1.019	1.000	0.790	0.859	0.938	0.841
-1	1.877	-0.492	0.372	0.441	0.955	1.034	-1.220	-0.846	1.087	0.952	-0.320	1.125	0.000	0.542	0.308	-1.261	2.548	1.018	-1.415	-1.547	0.000	1.280	0.932	0.991	1.273	0.878	0.921	0.906
-0	1.052	0.901	1.176	1.280	1.517	0.562	-1.150	-0.079	2.173	1.228	-0.308	-0.354	0.000	0.790	-1.492	-0.963	0.000	0.942	-0.672	-1.588	3.102	1.116	0.902	0.988	1.993	0.765	1.375	1.325
-1	0.518	-0.254	1.642	0.865	0.725	0.980	0.734	0.023	0.000	1.448	0.780	-1.736	2.215	0.955	0.513	-0.519	0.000	0.365	-0.444	-0.243	3.102	0.833	0.555	0.984	0.827	0.795	0.890	0.786
-0	0.870	0.815	-0.506	0.663	-0.518	0.935	0.289	-1.675	2.173	1.188	0.005	0.635	0.000	0.580	0.066	-1.455	2.548	0.580	-0.634	-0.199	0.000	0.852	0.788	0.979	1.283	0.208	0.856	0.950
-0	0.628	1.382	0.135	0.683	0.571	1.097	0.564	-0.950	2.173	0.617	-0.326	0.371	0.000	1.093	0.918	1.667	2.548	0.460	1.221	0.708	0.000	0.743	0.861	0.975	1.067	1.007	0.843	0.762
-0	4.357	0.816	-1.609	1.845	-1.288	3.292	0.726	0.324	2.173	1.528	0.583	-0.801	2.215	0.605	0.572	1.406	0.000	0.794	-0.791	0.122	0.000	0.967	1.132	1.124	3.602	2.811	2.460	1.861
-0	0.677	-1.265	1.559	0.866	-0.618	0.823	0.260	0.185	0.000	1.133	0.337	1.589	2.215	0.563	-0.830	0.510	0.000	0.777	0.117	-0.941	3.102	0.839	0.763	0.986	1.182	0.649	0.796	0.851
-0	2.466	-1.838	-1.648	1.717	1.533	1.676	-1.553	-0.109	2.173	0.670	-0.666	0.284	0.000	0.334	-2.480	0.316	0.000	0.366	-0.804	-1.298	3.102	0.875	0.894	0.997	0.548	0.770	1.302	1.079
-1	1.403	0.129	-1.307	0.688	0.306	0.579	0.753	0.814	1.087	0.474	0.694	-1.400	0.000	0.520	1.995	0.185	0.000	0.929	-0.504	1.270	3.102	0.972	0.998	1.353	0.948	0.650	0.688	0.724
-1	0.351	1.188	-0.360	0.254	-0.346	1.129	0.545	1.691	0.000	0.652	-0.039	-0.258	2.215	1.089	0.655	0.472	2.548	0.554	-0.493	1.366	0.000	0.808	1.045	0.992	0.570	0.649	0.809	0.744
-0	1.875	-0.013	-0.128	0.236	1.163	0.902	0.426	0.590	2.173	1.251	-1.210	-0.616	0.000	1.035	1.534	0.912	0.000	1.944	1.789	-1.691	0.000	0.974	1.113	0.990	0.925	1.120	0.956	0.912
-0	0.298	0.750	-0.507	1.555	1.463	0.804	1.200	-0.665	0.000	0.439	-0.829	-0.252	1.107	0.770	-1.090	0.947	2.548	1.165	-0.166	-0.763	0.000	1.140	0.997	0.988	1.330	0.555	1.005	1.012
-0	0.647	0.342	0.245	4.340	-0.157	2.229	0.068	1.170	2.173	2.133	-0.201	-1.441	0.000	1.467	0.697	-0.532	1.274	1.457	0.583	-1.640	0.000	0.875	1.417	0.976	2.512	2.390	1.794	1.665
-1	1.731	-0.803	-1.013	1.492	-0.020	1.646	-0.541	1.121	2.173	0.459	-1.251	-1.495	2.215	0.605	-1.711	-0.232	0.000	0.658	0.634	-0.068	0.000	1.214	0.886	1.738	1.833	1.024	1.192	1.034
-0	0.515	1.416	-1.089	1.697	1.426	1.414	0.941	0.027	0.000	1.480	0.133	-1.595	2.215	1.110	0.752	0.760	2.548	1.062	0.697	-0.492	0.000	0.851	0.955	0.994	1.105	1.255	1.175	1.095
-0	1.261	0.858	1.465	0.757	0.305	2.310	0.679	1.080	2.173	1.544	2.518	-0.464	0.000	2.326	0.270	-0.841	0.000	2.163	0.839	-0.500	3.102	0.715	0.825	1.170	0.980	2.371	1.527	1.221
-1	1.445	1.509	1.471	0.414	-1.285	0.767	0.864	-0.677	2.173	0.524	1.388	0.171	0.000	0.826	0.190	0.121	2.548	0.572	1.691	-1.603	0.000	0.870	0.935	0.994	0.968	0.735	0.783	0.777
-1	0.919	-0.264	-1.245	0.681	-1.722	1.022	1.010	0.097	2.173	0.685	0.403	-1.351	0.000	1.357	-0.429	1.262	1.274	0.687	1.021	-0.563	0.000	0.953	0.796	0.991	0.873	1.749	1.056	0.917
-1	0.293	-2.258	-1.427	1.191	1.202	0.394	-2.030	1.438	0.000	0.723	0.596	-0.024	2.215	0.525	-1.678	-0.290	0.000	0.788	-0.824	-1.029	3.102	0.821	0.626	0.976	1.080	0.810	0.842	0.771
-0	3.286	0.386	1.688	1.619	-1.620	1.392	-0.009	0.280	0.000	1.179	-0.776	-0.110	2.215	1.256	0.248	-1.114	2.548	0.777	0.825	-0.156	0.000	1.026	1.065	0.964	0.909	1.249	1.384	1.395
-1	1.075	0.603	0.561	0.656	-0.685	0.985	0.175	0.979	2.173	1.154	0.584	-0.886	0.000	1.084	-0.354	-1.004	2.548	0.865	1.224	1.269	0.000	1.346	1.073	1.048	0.873	1.310	1.003	0.865
-1	1.098	-0.091	1.466	1.558	0.915	0.649	1.314	-1.182	2.173	0.791	0.073	0.351	0.000	0.517	0.940	1.195	0.000	1.150	1.187	-0.692	3.102	0.866	0.822	0.980	1.311	0.394	1.119	0.890
-1	0.481	-1.042	0.148	1.135	-1.249	1.202	-0.344	0.308	1.087	0.779	-1.431	1.581	0.000	0.860	-0.860	-1.125	0.000	0.785	0.303	1.199	3.102	0.878	0.853	0.988	1.072	0.827	0.936	0.815
-0	1.348	0.497	0.318	0.806	0.976	1.393	-0.152	0.632	2.173	2.130	0.515	-1.054	0.000	0.908	0.062	-0.780	0.000	1.185	0.687	1.668	1.551	0.720	0.898	0.985	0.683	1.292	1.320	1.131
-0	2.677	-0.420	-1.685	1.828	1.433	2.040	-0.718	-0.039	0.000	0.400	-0.873	0.472	0.000	0.444	0.340	-0.830	2.548	0.431	0.768	-1.417	3.102	0.869	0.917	0.996	0.707	0.193	0.728	1.154
-1	1.300	0.586	-0.122	1.306	0.609	0.727	-0.556	-1.652	2.173	0.636	0.720	1.393	2.215	0.328	1.280	-0.390	0.000	0.386	0.752	-0.905	0.000	0.202	0.751	1.106	0.864	0.799	0.928	0.717
-0	0.637	-0.176	1.737	1.322	-0.414	0.702	-0.964	-0.680	0.000	1.054	-0.461	0.889	2.215	0.861	-0.267	0.225	0.000	1.910	-1.888	1.027	0.000	0.919	0.899	1.186	0.993	1.109	0.862	0.775
-1	0.723	-0.104	1.572	0.428	-0.840	0.655	0.544	1.401	2.173	1.522	-0.154	-0.452	2.215	0.996	0.190	0.273	0.000	1.906	-0.176	0.966	0.000	0.945	0.894	0.990	0.981	1.555	0.988	0.893
-0	2.016	-0.570	1.612	0.798	0.441	0.334	0.191	-0.909	0.000	0.939	0.146	0.021	2.215	0.553	-0.444	1.156	2.548	0.781	-1.545	-0.520	0.000	0.922	0.956	1.528	0.722	0.699	0.778	0.901
-0	1.352	-0.707	1.284	0.665	0.580	0.694	-1.040	-0.899	2.173	0.692	-2.048	0.029	0.000	0.545	-2.042	1.259	0.000	0.661	-0.808	-1.251	3.102	0.845	0.991	0.979	0.662	0.225	0.685	0.769
-1	1.057	-1.561	-0.411	0.952	-0.681	1.236	-1.107	1.045	2.173	1.288	-2.521	-0.521	0.000	1.361	-1.239	1.546	0.000	0.373	-1.540	0.028	0.000	0.794	0.782	0.987	0.889	0.832	0.972	0.828
-0	1.118	-0.017	-1.227	1.077	1.256	0.714	0.624	-0.811	0.000	0.800	0.704	0.387	1.107	0.604	0.234	0.986	0.000	1.306	-0.456	0.094	3.102	0.828	0.984	1.195	0.987	0.672	0.774	0.748
-1	0.602	2.201	0.212	0.119	0.182	0.474	2.130	1.270	0.000	0.370	2.088	-0.573	0.000	0.780	-0.725	-1.033	0.000	1.642	0.598	0.303	3.102	0.886	0.988	0.985	0.644	0.756	0.651	0.599
-0	1.677	-0.844	1.581	0.585	0.887	1.012	-2.315	0.752	0.000	1.077	0.748	-0.195	0.000	0.718	0.832	-1.337	1.274	1.181	-0.557	-1.006	3.102	1.018	1.247	0.988	0.908	0.651	1.311	1.120
-1	1.695	0.259	1.224	1.344	1.067	0.718	-1.752	-0.215	0.000	0.473	0.991	-0.993	0.000	0.891	1.285	-1.500	2.548	0.908	-0.131	0.288	0.000	0.945	0.824	0.979	1.009	0.951	0.934	0.833
-0	0.793	0.628	0.432	1.707	0.302	0.919	1.045	-0.784	0.000	1.472	0.175	-1.284	2.215	1.569	0.155	0.971	2.548	0.435	0.735	1.625	0.000	0.801	0.907	0.992	0.831	1.446	1.082	1.051
-1	0.537	-0.664	-0.244	1.104	1.272	1.154	0.394	1.633	0.000	1.527	0.963	0.559	2.215	1.744	0.650	-0.912	0.000	1.097	0.730	-0.368	3.102	1.953	1.319	1.045	1.309	0.869	1.196	1.126
-1	0.585	-1.469	1.005	0.749	-1.060	1.224	-0.717	-0.323	2.173	1.012	-0.201	1.268	0.000	0.359	-0.567	0.476	0.000	1.117	-1.124	1.557	3.102	0.636	1.281	0.986	0.616	1.289	0.890	0.881
-1	0.354	-1.517	0.667	2.534	-1.298	1.020	-0.375	1.254	0.000	1.119	-0.060	-1.538	2.215	1.059	-0.395	-0.140	0.000	2.609	0.199	-0.778	1.551	0.957	0.975	1.286	1.666	1.003	1.224	1.135
-1	0.691	-1.619	-1.380	0.361	1.727	1.493	-1.093	-0.289	0.000	1.447	-0.640	1.341	0.000	1.453	-0.617	-1.456	1.274	1.061	-1.481	-0.091	0.000	0.744	0.649	0.987	0.596	0.727	0.856	0.797
-0	1.336	1.293	-1.359	0.357	0.067	1.110	-0.058	-0.515	0.000	0.976	1.498	1.207	0.000	1.133	0.437	1.053	2.548	0.543	1.374	0.171	0.000	0.764	0.761	0.984	0.827	0.553	0.607	0.612
-0	0.417	-1.111	1.661	2.209	-0.683	1.931	-0.642	0.959	1.087	1.514	-2.032	-0.686	0.000	1.521	-0.539	1.344	0.000	0.978	-0.866	0.363	1.551	2.813	1.850	1.140	1.854	0.799	1.600	1.556
-0	1.058	0.390	-0.591	0.134	1.149	0.346	-1.550	0.186	0.000	1.108	-0.999	0.843	1.107	1.124	0.415	-1.514	0.000	1.067	-0.426	-1.000	3.102	1.744	1.050	0.985	1.006	1.010	0.883	0.789
-1	1.655	0.253	1.216	0.270	1.703	0.500	-0.006	-1.418	2.173	0.690	-0.350	0.170	2.215	1.045	-0.924	-0.774	0.000	0.996	-0.745	-0.123	0.000	0.839	0.820	0.993	0.921	0.869	0.725	0.708
-0	1.603	-0.850	0.564	0.829	0.093	1.270	-1.113	-1.155	2.173	0.853	-1.021	1.248	2.215	0.617	-1.270	1.733	0.000	0.935	-0.092	0.136	0.000	1.011	1.074	0.977	0.823	1.269	1.054	0.878
-0	1.568	-0.792	1.005	0.545	0.896	0.895	-1.698	-0.988	0.000	0.608	-1.634	1.705	0.000	0.826	0.208	0.618	1.274	2.063	-1.743	-0.520	0.000	0.939	0.986	0.990	0.600	0.435	1.033	1.087
-0	0.489	-1.335	-1.102	1.738	1.028	0.628	-0.992	-0.627	0.000	0.652	-0.064	-0.215	0.000	1.072	0.173	-1.251	2.548	1.042	0.057	0.841	3.102	0.823	0.895	1.200	1.164	0.770	0.837	0.846
-1	1.876	0.870	1.234	0.556	-1.262	1.764	0.855	-0.467	2.173	1.079	1.351	0.852	0.000	0.773	0.383	0.874	0.000	1.292	0.829	-1.228	3.102	0.707	0.969	1.102	1.601	1.017	1.112	1.028
-0	1.033	0.407	-0.374	0.705	-1.254	0.690	-0.231	1.502	2.173	0.433	-2.009	-0.057	0.000	0.861	1.151	0.334	0.000	0.960	-0.839	1.299	3.102	2.411	1.480	0.982	0.995	0.377	1.012	0.994
-0	1.092	0.653	-0.801	0.463	0.426	0.529	-1.055	0.040	0.000	0.663	0.999	1.255	1.107	0.749	-1.106	1.185	2.548	0.841	-0.745	-1.029	0.000	0.841	0.743	0.988	0.750	1.028	0.831	0.868
-1	0.799	-0.285	-0.011	0.531	1.392	1.063	0.854	0.494	2.173	1.187	-1.065	-0.851	0.000	0.429	-0.296	1.072	0.000	0.942	-1.985	1.172	0.000	0.873	0.693	0.992	0.819	0.689	1.131	0.913
-0	0.503	1.973	-0.377	1.515	-1.514	0.708	1.081	-0.313	2.173	1.110	-0.417	0.839	0.000	0.712	-1.153	1.165	0.000	0.675	-0.303	-0.930	1.551	0.709	0.761	1.032	0.986	0.698	0.963	1.291
-0	0.690	-0.574	-1.608	1.182	1.118	0.557	-2.243	0.144	0.000	0.969	0.216	-1.383	1.107	1.054	0.888	-0.709	2.548	0.566	1.663	-0.550	0.000	0.752	1.528	0.987	1.408	0.740	1.290	1.123
-1	0.890	1.501	0.786	0.779	-0.615	1.126	0.716	1.541	2.173	0.887	0.728	-0.673	2.215	1.216	0.332	-0.020	0.000	0.965	1.828	0.101	0.000	0.827	0.715	1.099	1.088	1.339	0.924	0.878
-0	0.566	0.883	0.655	1.600	0.034	1.155	2.028	-1.499	0.000	0.723	-0.871	0.763	0.000	1.286	-0.696	-0.676	2.548	1.134	-0.113	1.207	3.102	4.366	2.493	0.984	0.960	0.962	1.843	1.511
-0	1.146	1.086	-0.911	0.838	1.298	0.821	0.127	-0.145	0.000	1.352	0.474	-1.580	2.215	1.619	-0.081	0.675	2.548	1.382	-0.748	0.127	0.000	0.958	0.976	1.239	0.876	1.481	1.116	1.076
-0	1.739	-0.326	-1.661	0.420	-1.705	1.193	-0.031	-1.212	2.173	1.783	-0.442	0.522	0.000	1.064	-0.692	0.027	0.000	1.314	0.359	-0.037	3.102	0.968	0.897	0.986	0.907	1.196	1.175	1.112
-1	0.669	0.194	-0.703	0.657	-0.260	0.899	-2.511	0.311	0.000	1.482	0.773	0.974	2.215	3.459	0.037	-1.299	1.274	2.113	0.067	1.516	0.000	0.740	0.871	0.979	1.361	2.330	1.322	1.046
-1	1.355	-1.033	-1.173	0.552	-0.048	0.899	-0.482	-1.287	2.173	1.422	-1.227	0.390	1.107	1.937	-0.028	0.914	0.000	0.849	-0.230	-1.734	0.000	0.986	1.224	1.017	1.051	1.788	1.150	1.009
-1	0.511	-0.202	1.029	0.780	1.154	0.816	0.532	-0.731	0.000	0.757	0.517	0.749	2.215	1.302	0.289	-1.188	0.000	0.584	1.211	-0.350	0.000	0.876	0.943	0.995	0.963	0.256	0.808	0.891
-1	1.109	0.572	1.484	0.753	1.543	1.711	-0.145	-0.746	1.087	1.759	0.631	0.845	2.215	0.945	0.542	0.003	0.000	0.378	-1.150	-0.044	0.000	0.764	1.042	0.992	1.045	2.736	1.441	1.140
-0	0.712	-0.025	0.553	0.928	-0.711	1.304	0.045	-0.300	0.000	0.477	0.720	0.969	0.000	1.727	-0.474	1.328	1.274	1.282	2.222	1.684	0.000	0.819	0.765	1.023	0.961	0.657	0.799	0.744
-1	1.131	-0.302	1.079	0.901	0.236	0.904	-0.249	1.694	2.173	1.507	-0.702	-1.128	0.000	0.774	0.565	0.284	2.548	1.802	1.446	-0.192	0.000	3.720	2.108	0.986	0.930	1.101	1.484	1.238
-0	1.392	1.253	0.118	0.864	-1.358	0.922	-0.447	-1.243	1.087	1.969	1.031	0.774	2.215	1.333	-0.359	-0.681	0.000	1.099	-0.257	1.473	0.000	1.246	0.909	1.475	1.234	2.531	1.449	1.306
-0	1.374	2.291	-0.479	1.339	-0.243	0.687	2.345	1.310	0.000	0.467	1.081	0.772	0.000	0.656	1.155	-1.636	2.548	0.592	0.536	-1.269	3.102	0.981	0.821	1.010	0.877	0.217	0.638	0.758
-1	0.401	-1.516	0.909	2.738	0.519	0.887	0.566	-1.202	0.000	0.909	-0.176	1.682	0.000	2.149	-0.878	-0.514	2.548	0.929	-0.563	-1.555	3.102	1.228	0.803	0.980	1.382	0.884	1.025	1.172
-1	0.430	-1.589	1.417	2.158	1.226	1.180	-0.829	-0.781	2.173	0.798	1.400	-0.111	0.000	0.939	-0.878	1.076	2.548	0.576	1.335	-0.826	0.000	0.861	0.970	0.982	1.489	1.308	1.015	0.992
-1	1.943	-0.391	-0.840	0.621	-1.613	2.026	1.734	1.025	0.000	0.930	0.573	-0.912	0.000	1.326	0.847	-0.220	1.274	1.181	0.079	0.709	3.102	1.164	1.007	0.987	1.094	0.821	0.857	0.786
-1	0.499	0.436	0.887	0.859	1.509	0.733	-0.559	1.111	1.087	1.011	-0.796	0.279	2.215	1.472	-0.510	-0.982	0.000	1.952	0.379	-0.733	0.000	1.076	1.358	0.991	0.589	0.879	1.068	0.922
-0	0.998	-0.407	-1.711	0.139	0.652	0.810	-0.331	-0.721	0.000	0.471	-0.533	0.442	0.000	0.531	-1.405	0.120	2.548	0.707	0.098	-1.176	1.551	1.145	0.809	0.988	0.529	0.612	0.562	0.609
-1	1.482	0.872	0.638	1.288	0.362	0.856	0.900	-0.511	1.087	1.072	1.061	-1.432	2.215	1.770	-2.292	-1.547	0.000	1.131	1.374	0.783	0.000	6.316	4.381	1.002	1.317	1.048	2.903	2.351
-1	2.084	-0.422	1.289	1.125	0.735	1.104	-0.518	-0.326	2.173	0.413	-0.719	-0.699	0.000	0.857	0.108	-1.631	0.000	0.527	0.641	-1.362	3.102	0.791	0.952	1.016	0.776	0.856	0.987	0.836
-0	0.464	0.674	0.025	0.430	-1.703	0.982	-1.311	-0.808	2.173	1.875	1.060	0.821	2.215	0.954	-0.480	-1.677	0.000	0.567	0.702	-0.939	0.000	0.781	1.076	0.989	1.256	3.632	1.652	1.252
-1	0.457	-1.944	-1.010	1.409	0.931	1.098	-0.742	-0.415	0.000	1.537	-0.834	0.945	2.215	1.752	-0.287	-1.269	2.548	0.692	-1.537	-0.223	0.000	0.801	1.192	1.094	1.006	1.659	1.175	1.122
-0	3.260	-0.943	1.737	0.920	1.309	0.946	-0.139	-0.271	2.173	0.994	-0.952	-0.311	0.000	0.563	-0.136	-0.881	0.000	1.236	-0.507	0.906	1.551	0.747	0.869	0.985	1.769	1.034	1.179	1.042
-0	0.615	-0.778	0.246	1.861	1.619	0.560	-0.943	-0.204	2.173	0.550	-0.759	-1.342	2.215	0.578	0.076	-0.973	0.000	0.939	0.035	0.680	0.000	0.810	0.747	1.401	0.772	0.702	0.719	0.662
-1	2.370	-0.064	-0.237	1.737	0.154	2.319	-1.838	-1.673	0.000	1.053	-1.305	-0.075	0.000	0.925	0.149	0.318	1.274	0.851	-0.922	0.981	3.102	0.919	0.940	0.989	0.612	0.598	1.219	1.626
-1	1.486	0.311	-1.262	1.354	-0.847	0.886	-0.158	1.213	2.173	1.160	-0.218	0.239	0.000	1.166	0.494	0.278	2.548	0.575	1.454	-1.701	0.000	0.429	1.129	0.983	1.111	1.049	1.006	0.920
-1	1.294	1.587	-0.864	0.487	-0.312	0.828	1.051	-0.031	1.087	2.443	1.216	1.609	2.215	1.167	0.813	0.921	0.000	1.751	-0.415	0.119	0.000	1.015	1.091	0.974	1.357	2.093	1.178	1.059
-1	0.984	0.465	-1.661	0.379	-0.554	0.977	0.237	0.365	0.000	0.510	0.143	1.101	0.000	1.099	-0.662	-1.593	2.548	1.104	-0.197	-0.648	3.102	0.925	0.922	0.986	0.642	0.667	0.806	0.722
-1	0.930	-0.009	0.047	0.667	1.367	1.065	-0.231	0.815	0.000	1.199	-1.114	-0.877	2.215	0.940	0.824	-1.583	0.000	1.052	-0.407	-0.076	1.551	1.843	1.257	1.013	1.047	0.751	1.158	0.941
-0	0.767	-0.011	-0.637	0.341	-1.437	1.438	-0.425	-0.450	2.173	1.073	-0.718	1.341	2.215	0.633	-1.394	0.486	0.000	0.603	-1.945	-1.626	0.000	0.703	0.790	0.984	1.111	1.848	1.129	1.072
-1	1.779	0.017	0.432	0.402	1.022	0.959	1.480	1.595	2.173	1.252	1.365	0.006	0.000	1.188	-0.174	-1.107	0.000	1.181	0.518	-0.258	0.000	1.057	0.910	0.991	1.616	0.779	1.158	1.053
-0	0.881	0.630	1.029	1.990	0.508	1.102	0.742	-1.298	2.173	1.565	1.085	0.686	2.215	2.691	1.391	-0.904	0.000	0.499	1.388	-1.199	0.000	0.347	0.861	0.997	0.881	1.920	1.233	1.310
-0	1.754	-0.266	0.389	0.347	-0.030	0.462	-1.408	-0.957	2.173	0.515	-2.341	-1.700	0.000	0.588	-0.797	1.355	2.548	0.608	0.329	-1.389	0.000	1.406	0.909	0.988	0.760	0.593	0.768	0.847
-0	1.087	0.311	-1.447	0.173	0.567	0.854	0.362	0.584	0.000	1.416	-0.716	-1.211	2.215	0.648	-0.358	-0.692	1.274	0.867	-0.513	0.206	0.000	0.803	0.813	0.984	1.110	0.491	0.921	0.873
-0	0.279	1.114	-1.190	3.004	-0.738	1.233	0.896	1.092	2.173	0.454	-0.374	0.117	2.215	0.357	0.119	1.270	0.000	0.458	1.343	0.316	0.000	0.495	0.540	0.988	1.715	1.139	1.618	1.183
-1	1.773	-0.694	-1.518	2.306	-1.200	3.104	0.749	0.362	0.000	1.871	0.230	-1.686	2.215	0.805	-0.179	-0.871	1.274	0.910	0.607	-0.246	0.000	1.338	1.598	0.984	1.050	0.919	1.678	1.807
-0	0.553	0.683	0.827	0.973	-0.706	1.488	0.149	1.140	2.173	1.788	0.447	-0.478	0.000	0.596	1.043	1.607	0.000	0.373	-0.868	-1.308	1.551	1.607	1.026	0.998	1.134	0.808	1.142	0.936
-1	0.397	1.101	-1.139	1.688	0.146	0.972	0.541	1.518	0.000	1.549	-0.873	-1.012	0.000	2.282	-0.151	0.314	2.548	1.174	0.033	-1.368	0.000	0.937	0.776	1.039	1.143	0.959	0.986	1.013
-1	0.840	1.906	-0.959	0.869	0.576	0.642	0.554	-1.351	0.000	0.756	0.923	-0.823	2.215	1.251	1.130	0.545	2.548	1.513	0.410	1.073	0.000	1.231	0.985	1.163	0.812	0.987	0.816	0.822
-1	0.477	1.665	0.814	0.763	-0.382	0.828	-0.008	0.280	2.173	1.213	-0.001	1.560	0.000	1.136	0.311	-1.289	0.000	0.797	1.091	-0.616	3.102	1.026	0.964	0.992	0.772	0.869	0.916	0.803
-0	2.655	0.020	0.273	1.464	0.482	1.709	-0.107	-1.456	2.173	0.825	0.141	-0.386	0.000	1.342	-0.592	1.635	1.274	0.859	-0.175	-0.874	0.000	0.829	0.946	1.003	2.179	0.836	1.505	1.176
-0	0.771	-1.992	-0.720	0.732	-1.464	0.869	-1.290	0.388	2.173	0.926	-1.072	-1.489	2.215	0.640	-1.232	0.840	0.000	0.528	-2.440	-0.446	0.000	0.811	0.868	0.993	0.995	1.317	0.809	0.714
-0	1.357	1.302	0.076	0.283	-1.060	0.783	1.559	-0.994	0.000	0.947	1.212	1.617	0.000	1.127	0.311	0.442	2.548	0.582	-0.052	1.186	1.551	1.330	0.995	0.985	0.846	0.404	0.858	0.815
-0	0.442	-0.381	-0.424	1.244	0.591	0.731	0.605	-0.713	2.173	0.629	2.762	1.040	0.000	0.476	2.693	-0.617	0.000	0.399	0.442	1.486	3.102	0.839	0.755	0.988	0.869	0.524	0.877	0.918
-0	0.884	0.422	0.055	0.818	0.624	0.950	-0.763	1.624	0.000	0.818	-0.609	-1.166	0.000	1.057	-0.528	1.070	2.548	1.691	-0.124	-0.335	3.102	1.104	0.933	0.985	0.913	1.000	0.863	1.056
-0	1.276	0.156	1.714	1.053	-1.189	0.672	-0.464	-0.030	2.173	0.469	-2.483	0.442	0.000	0.564	2.580	-0.253	0.000	0.444	-0.628	1.080	1.551	5.832	2.983	0.985	1.162	0.494	1.809	1.513
-0	1.106	-0.556	0.406	0.573	-1.400	0.769	-0.518	1.457	2.173	0.743	-0.352	-0.010	0.000	1.469	-0.550	-0.930	2.548	0.540	1.236	-0.571	0.000	0.962	0.970	1.101	0.805	1.107	0.873	0.773
-0	0.539	-0.964	-0.464	1.371	-1.606	0.667	-0.160	0.655	0.000	0.952	0.352	-0.740	2.215	0.952	0.007	1.123	0.000	1.061	-0.505	1.389	3.102	1.063	0.991	1.019	0.633	0.967	0.732	0.799
-1	0.533	-0.989	-1.608	0.462	-1.723	1.204	-0.598	-0.098	2.173	1.343	-0.460	1.632	2.215	0.577	0.221	-0.492	0.000	0.628	-0.073	0.472	0.000	0.518	0.880	0.988	1.179	1.874	1.041	0.813
-1	1.024	1.075	-0.795	0.286	-1.436	1.365	0.857	-0.309	2.173	0.804	1.532	1.435	0.000	1.511	0.722	1.494	0.000	1.778	0.903	0.753	1.551	0.686	0.810	0.999	0.900	1.360	1.133	0.978
-1	2.085	-0.269	-1.423	0.789	1.298	0.281	1.652	0.187	0.000	0.658	-0.760	-0.042	2.215	0.663	0.024	0.120	0.000	0.552	-0.299	-0.428	3.102	0.713	0.811	1.130	0.705	0.218	0.675	0.743
-1	0.980	-0.443	0.813	0.785	-1.253	0.719	0.448	-1.458	0.000	1.087	0.595	0.635	1.107	1.428	0.029	-0.995	0.000	1.083	1.562	-0.092	0.000	0.834	0.891	1.165	0.967	0.661	0.880	0.817
-1	0.903	-0.733	-0.980	0.634	-0.639	0.780	0.266	-0.287	2.173	1.264	-0.936	1.004	0.000	1.002	-0.056	-1.344	2.548	1.183	-0.098	1.169	0.000	0.733	1.002	0.985	0.711	0.916	0.966	0.875
-0	0.734	-0.304	-1.175	2.851	1.674	0.904	-0.634	0.412	2.173	1.363	-1.050	-0.282	0.000	1.476	-1.603	0.103	0.000	2.231	-0.718	1.708	3.102	0.813	0.896	1.088	0.686	1.392	1.033	1.078
-1	1.680	0.591	-0.243	0.111	-0.478	0.326	-0.079	-1.555	2.173	0.711	0.714	0.922	2.215	0.355	0.858	1.682	0.000	0.727	1.620	1.360	0.000	0.334	0.526	1.001	0.862	0.633	0.660	0.619
-1	1.163	0.225	-0.202	0.501	-0.979	1.609	-0.938	1.424	0.000	1.224	-0.118	-1.274	0.000	2.034	1.241	-0.254	0.000	1.765	0.536	0.237	3.102	0.894	0.838	0.988	0.693	0.579	0.762	0.726
-0	1.223	1.232	1.471	0.489	1.728	0.703	-0.111	0.411	0.000	1.367	1.014	-1.294	1.107	1.524	-0.414	-0.164	2.548	1.292	0.833	0.316	0.000	0.861	0.752	0.994	0.836	1.814	1.089	0.950
-0	0.816	1.637	-1.557	1.036	-0.342	0.913	1.333	0.949	2.173	0.812	0.756	-0.628	2.215	1.333	0.470	1.495	0.000	1.204	-2.222	-1.675	0.000	1.013	0.924	1.133	0.758	1.304	0.855	0.860
-0	0.851	-0.564	-0.691	0.692	1.345	1.219	1.014	0.318	0.000	1.422	-0.262	-1.635	2.215	0.531	1.802	0.008	0.000	0.508	0.515	-1.267	3.102	0.821	0.787	1.026	0.783	0.432	1.149	1.034
-0	0.800	-0.599	0.204	0.552	-0.484	0.974	0.413	0.961	2.173	1.269	-0.984	-1.039	2.215	0.380	-1.213	1.371	0.000	0.551	0.332	-0.659	0.000	0.694	0.852	0.984	1.057	2.037	1.096	0.846
-0	0.744	-0.071	-0.255	0.638	0.512	1.125	0.407	0.844	2.173	0.860	-0.481	-0.677	0.000	1.102	0.181	-1.194	0.000	1.011	-1.081	-1.713	3.102	0.854	0.862	0.982	1.111	1.372	1.042	0.920
-1	0.400	1.049	-0.625	0.880	-0.407	1.040	2.150	-1.359	0.000	0.747	-0.144	0.847	2.215	0.560	-1.829	0.698	0.000	1.663	-0.668	0.267	0.000	0.845	0.964	0.996	0.820	0.789	0.668	0.668
-0	1.659	-0.705	-1.057	1.803	-1.436	1.008	0.693	0.005	0.000	0.895	-0.007	0.681	1.107	1.085	0.125	1.476	2.548	1.214	1.068	0.486	0.000	0.867	0.919	0.986	1.069	0.692	1.026	1.313
-0	0.829	-0.153	0.861	0.615	-0.548	0.589	1.077	-0.041	2.173	1.056	0.763	-1.737	0.000	0.639	0.970	0.725	0.000	0.955	1.227	-0.799	3.102	1.020	1.024	0.985	0.750	0.525	0.685	0.671
-1	0.920	-0.806	-0.840	1.048	0.278	0.973	-0.077	-1.364	2.173	1.029	0.309	0.133	0.000	1.444	1.484	1.618	1.274	1.419	-0.482	0.417	0.000	0.831	1.430	1.151	1.829	1.560	1.343	1.224
-1	0.686	0.249	-0.905	0.343	-1.731	0.724	-2.823	-0.901	0.000	0.982	0.303	1.312	1.107	1.016	0.245	0.610	0.000	1.303	-0.557	-0.360	3.102	1.384	1.030	0.984	0.862	1.144	0.866	0.779
-0	1.603	0.444	0.508	0.586	0.401	0.610	0.467	-1.735	2.173	0.914	0.626	-1.019	0.000	0.812	0.422	-0.408	2.548	0.902	1.679	1.490	0.000	1.265	0.929	0.990	1.004	0.816	0.753	0.851
-1	0.623	0.780	-0.203	0.056	0.015	0.899	0.793	1.326	1.087	0.803	1.478	-1.499	2.215	1.561	1.492	-0.120	0.000	0.904	0.795	0.137	0.000	0.548	1.009	0.850	0.924	0.838	0.914	0.860
-0	1.654	-2.032	-1.160	0.859	-1.583	0.689	-1.965	0.891	0.000	0.646	-1.014	-0.288	2.215	0.630	-0.815	0.402	0.000	0.638	0.316	0.655	3.102	0.845	0.879	0.993	1.067	0.625	1.041	0.958
-1	0.828	-1.269	-1.203	0.744	-0.213	0.626	-1.017	-0.404	0.000	1.281	-0.931	1.733	2.215	0.699	-0.351	1.287	0.000	1.251	-1.171	0.197	0.000	0.976	1.186	0.987	0.646	0.655	0.733	0.671
-1	0.677	0.111	1.090	1.580	1.591	1.560	0.654	-0.341	2.173	0.794	-0.266	0.702	0.000	0.823	0.651	-1.239	2.548	0.730	1.467	-1.530	0.000	1.492	1.023	0.983	1.909	1.022	1.265	1.127
-1	0.736	0.882	-1.060	0.589	0.168	1.663	0.781	1.022	2.173	2.025	1.648	-1.292	0.000	1.240	0.924	-0.421	1.274	1.354	0.065	0.501	0.000	0.316	0.925	0.988	0.664	1.736	0.992	0.807
-1	1.040	-0.822	1.638	0.974	-0.674	0.393	0.830	0.011	2.173	0.770	-0.140	-0.402	0.000	0.294	-0.133	0.030	0.000	1.220	0.807	0.638	0.000	0.826	1.063	1.216	1.026	0.705	0.934	0.823
-1	0.711	0.602	0.048	1.145	0.966	0.934	0.263	-1.589	2.173	0.971	-0.496	-0.421	1.107	0.628	-0.865	0.845	0.000	0.661	-0.008	-0.565	0.000	0.893	0.705	0.988	0.998	1.339	0.908	0.872
-1	0.953	-1.651	-0.167	0.885	1.053	1.013	-1.239	0.133	0.000	1.884	-1.122	1.222	2.215	1.906	-0.860	-1.184	1.274	1.413	-0.668	-1.647	0.000	1.873	1.510	1.133	1.050	1.678	1.246	1.061
-1	0.986	-0.892	-1.380	0.917	1.134	0.950	-1.162	-0.469	0.000	0.569	-1.393	0.215	0.000	0.320	2.667	1.712	0.000	1.570	-0.375	1.457	3.102	0.925	1.128	1.011	0.598	0.824	0.913	0.833
-1	1.067	0.099	1.154	0.527	-0.789	1.085	0.623	-1.602	2.173	1.511	-0.230	0.022	2.215	0.269	-0.377	0.883	0.000	0.571	-0.540	-0.512	0.000	0.414	0.803	1.022	0.959	2.053	1.041	0.780
-0	0.825	-2.118	0.217	1.453	-0.493	0.819	0.313	-0.942	0.000	2.098	-0.725	1.096	2.215	0.484	1.336	1.458	0.000	0.482	0.100	1.163	0.000	0.913	0.536	0.990	1.679	0.957	1.095	1.143
-1	1.507	0.054	1.120	0.698	-1.340	0.912	0.384	0.015	1.087	0.720	0.247	-0.820	0.000	0.286	0.154	1.578	2.548	0.629	1.582	-0.576	0.000	0.828	0.893	1.136	0.514	0.632	0.699	0.709
-1	0.610	1.180	-0.993	0.816	0.301	0.932	0.758	1.539	0.000	0.726	-0.830	0.248	2.215	0.883	0.857	-1.305	0.000	1.338	1.009	-0.252	3.102	0.901	1.074	0.987	0.875	1.159	1.035	0.858
-1	1.247	-1.360	1.502	1.525	-1.332	0.618	1.063	0.755	0.000	0.582	-0.155	0.473	2.215	1.214	-0.422	-0.551	2.548	0.838	-1.171	-1.166	0.000	2.051	1.215	1.062	1.091	0.725	0.896	1.091
-0	0.373	-0.600	1.291	2.573	0.207	0.765	-0.209	1.667	0.000	0.668	0.724	-1.499	0.000	1.045	-0.338	-0.754	2.548	0.558	-0.469	0.029	3.102	0.868	0.939	1.124	0.519	0.383	0.636	0.838
-0	0.791	0.336	-0.307	0.494	1.213	1.158	0.336	1.081	2.173	0.918	1.289	-0.449	0.000	0.735	-0.521	-0.969	0.000	1.052	0.499	-1.188	3.102	0.699	1.013	0.987	0.622	1.050	0.712	0.661
-0	1.321	0.856	0.464	0.202	0.901	1.144	0.120	-1.651	0.000	0.803	0.577	-0.509	2.215	0.695	-0.114	0.423	2.548	0.621	1.852	-0.420	0.000	0.697	0.964	0.983	0.527	0.659	0.719	0.729
-0	0.563	2.081	0.913	0.982	-0.533	0.549	-0.481	-1.730	0.000	0.962	0.921	0.569	2.215	0.731	1.184	-0.679	1.274	0.918	0.931	-1.432	0.000	1.008	0.919	0.993	0.895	0.819	0.810	0.878
-1	1.148	0.345	0.953	0.921	0.617	0.991	1.103	-0.484	0.000	0.970	1.978	1.525	0.000	1.150	0.689	-0.757	2.548	0.517	0.995	1.245	0.000	1.093	1.140	0.998	1.006	0.756	0.864	0.838
-1	1.400	0.128	-1.695	1.169	1.070	1.094	-0.345	-0.249	0.000	1.224	0.364	-0.036	2.215	1.178	0.530	-1.544	0.000	1.334	0.933	1.604	0.000	0.560	1.267	1.073	0.716	0.780	0.832	0.792
-0	0.330	-2.133	1.403	0.628	0.379	1.686	-0.995	0.030	1.087	2.071	0.127	-0.457	0.000	4.662	-0.855	1.477	0.000	2.072	-0.917	-1.416	3.102	5.403	3.074	0.977	0.936	1.910	2.325	1.702
-0	0.989	0.473	0.968	1.970	1.368	0.844	0.574	-0.290	2.173	0.866	-0.345	-1.019	0.000	1.130	0.605	-0.752	0.000	0.956	-0.888	0.870	3.102	0.885	0.886	0.982	1.157	1.201	1.100	1.068
-1	0.773	0.418	0.753	1.388	1.070	1.104	-0.378	-0.758	0.000	1.027	0.397	-0.496	2.215	1.234	0.027	1.084	2.548	0.936	0.209	1.677	0.000	1.355	1.020	0.983	0.550	1.206	0.916	0.931
-0	0.319	2.015	1.534	0.570	-1.134	0.632	0.124	0.757	0.000	0.477	0.598	-1.109	1.107	0.449	0.438	-0.755	2.548	0.574	-0.659	0.691	0.000	0.440	0.749	0.985	0.517	0.158	0.505	0.522
-0	1.215	1.453	-1.386	1.276	1.298	0.643	0.570	-0.196	2.173	0.588	2.104	0.498	0.000	0.617	-0.296	-0.801	2.548	0.452	0.110	0.313	0.000	0.815	0.953	1.141	1.166	0.547	0.892	0.807
-1	1.257	-1.869	-0.060	0.265	0.653	1.527	-0.346	1.163	2.173	0.758	-2.119	-0.604	0.000	1.473	-1.133	-1.290	2.548	0.477	-0.428	-0.066	0.000	0.818	0.841	0.984	1.446	1.729	1.211	1.054
-1	1.449	0.464	1.585	1.418	-1.488	1.540	0.942	0.087	0.000	0.898	0.402	-0.631	2.215	0.753	0.039	-1.729	0.000	0.859	0.849	-1.054	0.000	0.791	0.677	0.995	0.687	0.527	0.703	0.606
-1	1.084	-1.997	0.900	1.333	1.024	0.872	-0.864	-1.500	2.173	1.072	-0.813	-0.421	2.215	0.924	0.478	0.304	0.000	0.992	-0.398	-1.022	0.000	0.741	1.085	0.980	1.221	1.176	1.032	0.961
-0	1.712	1.129	0.125	1.120	-1.402	1.749	0.951	-1.575	2.173	1.711	0.445	0.578	0.000	1.114	0.234	-1.011	0.000	1.577	-0.088	0.086	3.102	2.108	1.312	1.882	1.597	2.009	1.441	1.308
-0	0.530	0.248	1.622	1.450	-1.012	1.221	-1.154	-0.763	2.173	1.698	-0.586	0.733	0.000	0.889	1.042	1.038	1.274	0.657	0.008	0.701	0.000	0.430	1.005	0.983	0.930	2.264	1.357	1.146
-1	0.921	1.735	0.883	0.699	-1.614	0.821	1.463	0.319	1.087	1.099	0.814	-1.600	2.215	1.375	0.702	-0.691	0.000	0.869	1.326	-0.790	0.000	0.980	0.900	0.988	0.832	1.452	0.816	0.709
-0	2.485	-0.823	-0.297	0.886	-1.404	0.989	0.835	1.615	2.173	0.382	0.588	-0.224	0.000	1.029	-0.456	1.546	2.548	0.613	-0.359	-0.789	0.000	0.768	0.977	1.726	2.007	0.913	1.338	1.180
-1	0.657	-0.069	-0.078	1.107	1.549	0.804	1.335	-1.630	2.173	1.271	0.481	0.153	1.107	1.028	0.144	-0.762	0.000	1.098	0.132	1.570	0.000	0.830	0.979	1.175	1.069	1.624	1.000	0.868
-1	2.032	0.329	-1.003	0.493	-0.136	1.159	-0.224	0.750	1.087	0.396	0.546	0.587	0.000	0.620	1.805	0.982	0.000	1.236	0.744	-1.621	0.000	0.930	1.200	0.988	0.482	0.771	0.887	0.779
-0	0.524	-1.319	0.634	0.471	1.221	0.599	-0.588	-0.461	0.000	1.230	-1.504	-1.517	1.107	1.436	-0.035	0.104	2.548	0.629	1.997	-1.282	0.000	2.084	1.450	0.984	1.084	1.827	1.547	1.213
-1	0.871	0.618	-1.544	0.718	0.186	1.041	-1.180	0.434	2.173	1.133	1.558	-1.301	0.000	0.452	-0.595	0.522	0.000	0.665	0.567	0.130	3.102	1.872	1.114	1.095	1.398	0.979	1.472	1.168
-1	3.308	1.037	-0.634	0.690	-0.619	1.975	0.949	1.280	0.000	0.826	0.546	-0.139	2.215	0.635	-0.045	0.427	0.000	1.224	0.112	1.339	3.102	1.756	1.050	0.992	0.738	0.903	0.968	1.238
-0	0.588	2.104	-0.872	1.136	1.743	0.842	0.638	0.015	0.000	0.481	0.928	1.000	2.215	0.595	0.125	1.429	0.000	0.951	-1.140	-0.511	3.102	1.031	1.057	0.979	0.673	1.064	1.001	0.891
-0	0.289	0.823	0.013	0.615	-1.601	0.177	2.403	-0.015	0.000	0.258	1.151	1.036	2.215	0.694	0.553	-1.326	2.548	0.411	0.366	0.106	0.000	0.482	0.562	0.989	0.670	0.404	0.516	0.561
-1	0.294	-0.660	-1.162	1.752	0.384	0.860	0.513	1.119	0.000	2.416	0.107	-1.342	0.000	1.398	0.361	-0.350	2.548	1.126	-0.902	0.040	1.551	0.650	1.125	0.988	0.531	0.843	0.912	0.911
-0	0.599	-0.616	1.526	1.381	0.507	0.955	-0.646	-0.085	2.173	0.775	-0.533	1.116	2.215	0.789	-0.136	-1.176	0.000	2.449	1.435	-1.433	0.000	1.692	1.699	1.000	0.869	1.119	1.508	1.303
-1	1.100	-1.174	-1.114	1.601	-1.576	1.056	-1.343	0.547	2.173	0.555	0.367	0.592	2.215	0.580	-1.862	-0.914	0.000	0.904	0.508	-0.444	0.000	1.439	1.105	0.986	1.408	1.104	1.190	1.094
-1	2.237	-0.701	1.470	0.719	-0.199	0.745	-0.132	-0.737	1.087	0.976	-0.227	0.093	2.215	0.699	0.057	1.133	0.000	0.661	0.573	-0.679	0.000	0.785	0.772	1.752	1.235	0.856	0.990	0.825
-1	0.455	-0.880	-1.482	1.260	-0.178	1.499	0.158	1.022	0.000	1.867	-0.435	-0.675	2.215	1.234	0.783	1.586	0.000	0.641	-0.454	-0.409	3.102	1.002	0.964	0.986	0.761	0.240	1.190	0.995
-1	1.158	-0.778	-0.159	0.823	1.641	1.341	-0.830	-1.169	2.173	0.840	-1.554	0.934	0.000	0.693	0.488	-1.218	2.548	1.042	1.395	0.276	0.000	0.946	0.785	1.350	1.079	0.893	1.267	1.151
-1	0.902	-0.078	-0.055	0.872	-0.012	0.843	1.276	1.739	2.173	0.838	1.492	0.918	0.000	0.626	0.904	-0.648	2.548	0.412	-2.027	-0.883	0.000	2.838	1.664	0.988	1.803	0.768	1.244	1.280
-1	0.649	-1.028	-1.521	1.097	0.774	1.216	-0.383	-0.318	2.173	1.643	-0.285	-1.705	0.000	0.911	-0.091	0.341	0.000	0.592	0.537	0.732	3.102	0.911	0.856	1.027	1.160	0.874	0.986	0.893
-1	1.192	1.846	-0.781	1.326	-0.747	1.550	1.177	1.366	0.000	1.196	0.151	0.387	2.215	0.527	2.261	-0.190	0.000	0.390	1.474	0.381	0.000	0.986	1.025	1.004	1.392	0.761	0.965	1.043
-0	0.438	-0.358	-1.549	0.836	0.436	0.818	0.276	-0.708	2.173	0.707	0.826	0.392	0.000	1.050	1.741	-1.066	0.000	1.276	-1.583	0.842	0.000	1.475	1.273	0.986	0.853	1.593	1.255	1.226
-1	1.083	0.142	1.701	0.605	-0.253	1.237	0.791	1.183	2.173	0.842	2.850	-0.082	0.000	0.724	-0.464	-0.694	0.000	1.499	0.456	-0.226	3.102	0.601	0.799	1.102	0.995	1.389	1.013	0.851
-0	0.828	1.897	-0.615	0.572	-0.545	0.572	0.461	0.464	2.173	0.393	0.356	1.069	2.215	1.840	0.088	1.500	0.000	0.407	-0.663	-0.787	0.000	0.950	0.965	0.979	0.733	0.363	0.618	0.733
-0	0.735	1.438	1.197	1.123	-0.214	0.641	0.949	0.858	0.000	1.162	0.524	-0.896	2.215	0.992	0.454	-1.475	2.548	0.902	1.079	0.019	0.000	0.822	0.917	1.203	1.032	0.569	0.780	0.764
-0	0.437	-2.102	0.044	1.779	-1.042	1.231	-0.181	-0.515	1.087	2.666	0.863	1.466	2.215	1.370	0.345	-1.371	0.000	0.906	0.363	1.611	0.000	1.140	1.362	1.013	3.931	3.004	2.724	2.028
-1	0.881	1.814	-0.987	0.384	0.800	2.384	1.422	0.640	0.000	1.528	0.292	-0.962	1.107	2.126	-0.371	-1.401	2.548	0.700	0.109	0.203	0.000	0.450	0.813	0.985	0.956	1.013	0.993	0.774
-1	0.630	0.408	0.152	0.194	0.316	0.710	-0.824	-0.358	2.173	0.741	0.535	-0.851	2.215	0.933	0.406	1.148	0.000	0.523	-0.479	-0.625	0.000	0.873	0.960	0.988	0.830	0.921	0.711	0.661
-1	0.870	-0.448	-1.134	0.616	0.135	0.600	0.649	-0.622	2.173	0.768	0.709	-0.123	0.000	1.308	0.500	1.468	0.000	1.973	-0.286	1.462	3.102	0.909	0.944	0.990	0.835	1.250	0.798	0.776
-0	1.290	0.552	1.330	0.615	-1.353	0.661	0.240	-0.393	0.000	0.531	0.053	-1.588	0.000	0.675	0.839	-0.345	1.274	1.597	0.020	0.536	3.102	1.114	0.964	0.987	0.783	0.675	0.662	0.675
-1	0.943	0.936	1.068	1.373	0.671	2.170	-2.011	-1.032	0.000	0.640	0.361	-0.806	0.000	2.239	-0.083	0.590	2.548	1.224	0.646	-1.723	0.000	0.879	0.834	0.981	1.436	0.568	0.916	0.931
-1	0.431	1.686	-1.053	0.388	1.739	0.457	-0.471	-0.743	2.173	0.786	1.432	-0.547	2.215	0.537	-0.413	1.256	0.000	0.413	2.311	-0.408	0.000	1.355	1.017	0.982	0.689	1.014	0.821	0.715
-0	1.620	-0.055	-0.862	1.341	-1.571	0.634	-0.906	0.935	2.173	0.501	-2.198	-0.525	0.000	0.778	-0.708	-0.060	0.000	0.988	-0.621	0.489	3.102	0.870	0.956	1.216	0.992	0.336	0.871	0.889
-1	0.549	0.304	-1.443	1.309	-0.312	1.116	0.644	1.519	2.173	1.078	-0.303	-0.736	0.000	1.261	0.387	0.628	2.548	0.945	-0.190	0.090	0.000	0.893	1.043	1.000	1.124	1.077	1.026	0.886
-0	0.412	-0.618	-1.486	1.133	-0.665	0.646	0.436	1.520	0.000	0.993	0.976	0.106	2.215	0.832	0.091	0.164	2.548	0.672	-0.650	1.256	0.000	0.695	1.131	0.991	1.017	0.455	1.226	1.087
-0	1.183	-0.084	1.644	1.389	0.967	0.843	0.938	-0.670	0.000	0.480	0.256	0.123	2.215	0.437	1.644	0.491	0.000	0.501	-0.416	0.101	3.102	1.060	0.804	1.017	0.775	0.173	0.535	0.760
-0	1.629	-1.486	-0.683	2.786	-0.492	1.347	-2.638	1.453	0.000	1.857	0.208	0.873	0.000	0.519	-1.265	-1.602	1.274	0.903	-1.102	-0.329	1.551	6.892	3.522	0.998	0.570	0.477	2.039	2.006
-1	2.045	-0.671	-1.235	0.490	-0.952	0.525	-1.252	1.289	0.000	1.088	-0.993	0.648	2.215	0.975	-0.109	-0.254	2.548	0.556	-1.095	-0.194	0.000	0.803	0.861	0.980	1.282	0.945	0.925	0.811
-0	0.448	-0.058	-0.974	0.945	-1.633	1.181	-1.139	0.266	2.173	1.118	-0.761	1.502	1.107	1.706	0.585	-0.680	0.000	0.487	-1.951	0.945	0.000	2.347	1.754	0.993	1.161	1.549	1.414	1.176
-0	0.551	0.519	0.448	2.183	1.293	1.220	0.628	-0.627	2.173	1.019	-0.002	-0.652	0.000	1.843	-0.386	1.042	2.548	0.400	-1.102	-1.014	0.000	0.648	0.792	1.049	0.888	2.132	1.262	1.096
-0	1.624	0.488	1.403	0.760	0.559	0.812	0.777	-1.244	2.173	0.613	0.589	-0.030	2.215	0.692	1.058	0.683	0.000	1.054	1.165	-0.765	0.000	0.915	0.875	1.059	0.821	0.927	0.792	0.721
-1	0.774	0.444	1.257	0.515	-0.689	0.515	1.448	-1.271	0.000	0.793	0.118	0.811	1.107	0.679	0.326	-0.426	0.000	1.066	-0.865	-0.049	3.102	0.960	1.046	0.986	0.716	0.772	0.855	0.732
-1	2.093	-1.240	1.615	0.918	-1.202	1.412	-0.541	0.640	1.087	2.019	0.872	-0.639	0.000	0.672	-0.936	0.972	0.000	0.896	0.235	0.212	0.000	0.810	0.700	1.090	0.797	0.862	1.049	0.874
-1	0.908	1.069	0.283	0.400	1.293	0.609	1.452	-1.136	0.000	0.623	0.417	-0.098	2.215	1.023	0.775	1.054	1.274	0.706	2.346	-1.305	0.000	0.744	1.006	0.991	0.606	0.753	0.796	0.753
-0	0.403	-1.328	-0.065	0.901	1.052	0.708	-0.354	-0.718	2.173	0.892	0.633	1.684	2.215	0.999	-1.205	0.941	0.000	0.930	1.072	-0.809	0.000	2.105	1.430	0.989	0.838	1.147	1.042	0.883
-0	1.447	0.453	0.118	1.731	0.650	0.771	0.446	-1.564	0.000	0.973	-2.014	0.354	0.000	1.949	-0.643	-1.531	1.274	1.106	-0.334	-1.163	0.000	0.795	0.821	1.013	1.699	0.918	1.118	1.018
-1	1.794	0.123	-0.454	0.057	1.489	0.966	-1.190	1.090	1.087	0.539	-0.535	1.035	0.000	1.096	-1.069	-1.236	2.548	0.659	-1.196	-0.283	0.000	0.803	0.756	0.985	1.343	1.109	0.993	0.806
-0	1.484	-2.047	0.813	0.591	-0.295	0.923	0.312	-1.164	2.173	0.654	-0.316	0.752	2.215	0.599	1.966	-1.128	0.000	0.626	-0.304	-1.431	0.000	1.112	0.910	1.090	0.986	1.189	1.350	1.472
-0	0.417	-2.016	0.849	1.817	0.040	1.201	-1.676	-1.394	0.000	0.792	0.537	0.641	2.215	0.794	-1.222	0.187	0.000	0.825	-0.217	1.334	3.102	1.470	0.931	0.987	1.203	0.525	0.833	0.827
-1	0.603	1.009	0.033	0.486	1.225	0.884	-0.617	-1.058	0.000	0.500	-1.407	-0.567	0.000	1.476	-0.876	0.605	2.548	0.970	0.560	1.092	3.102	0.853	1.153	0.988	0.846	0.920	0.944	0.835
-1	1.381	-0.326	0.552	0.417	-0.027	1.030	-0.835	-1.287	2.173	0.941	-0.421	1.519	2.215	0.615	-1.650	0.377	0.000	0.606	0.644	0.650	0.000	1.146	0.970	0.990	1.191	0.884	0.897	0.826
-1	0.632	1.200	-0.703	0.438	-1.700	0.779	-0.731	0.958	1.087	0.605	0.393	-1.376	0.000	0.670	-0.827	-1.315	2.548	0.626	-0.501	0.417	0.000	0.904	0.903	0.998	0.673	0.803	0.722	0.640
-1	1.561	-0.569	1.580	0.329	0.237	1.059	0.731	0.415	2.173	0.454	0.016	-0.828	0.000	0.587	0.008	-0.291	1.274	0.597	1.119	1.191	0.000	0.815	0.908	0.988	0.733	0.690	0.892	0.764
-1	2.102	0.087	0.449	1.164	-0.390	1.085	-0.408	-1.116	2.173	0.578	0.197	-0.137	0.000	1.202	0.917	1.523	0.000	0.959	-0.832	1.404	3.102	1.380	1.109	1.486	1.496	0.886	1.066	1.025
-1	1.698	-0.489	-0.552	0.976	-1.009	1.620	-0.721	0.648	1.087	1.481	-1.860	-1.354	0.000	1.142	-1.140	1.401	2.548	1.000	-1.274	-0.158	0.000	1.430	1.130	0.987	1.629	1.154	1.303	1.223
-1	1.111	-0.249	-1.457	0.421	0.939	0.646	-2.076	0.362	0.000	1.315	0.796	-1.436	2.215	0.780	0.130	0.055	0.000	1.662	-0.834	0.461	0.000	0.920	0.948	0.990	1.046	0.905	1.493	1.169
-1	0.945	0.390	-1.159	1.675	0.437	0.356	0.261	0.543	1.087	0.574	0.838	1.599	2.215	0.496	-1.220	-0.022	0.000	0.558	-2.454	1.440	0.000	0.763	0.983	1.728	1.000	0.578	0.922	1.003
-1	2.076	0.014	-1.314	0.854	-0.306	3.446	1.341	0.598	0.000	2.086	0.227	-0.747	2.215	1.564	-0.216	1.649	2.548	0.965	-0.857	-1.062	0.000	0.477	0.734	1.456	1.003	1.660	1.001	0.908
-1	1.992	0.192	-0.103	0.108	-1.599	0.938	0.595	-1.360	2.173	0.869	-1.012	1.432	0.000	1.302	0.850	0.436	2.548	0.487	1.051	-1.027	0.000	0.502	0.829	0.983	1.110	1.394	0.904	0.836
-0	0.460	1.625	1.485	1.331	1.242	0.675	-0.329	-1.039	1.087	0.671	-1.028	-0.514	0.000	1.265	-0.788	0.415	1.274	0.570	-0.683	-1.738	0.000	0.725	0.758	1.004	1.024	1.156	0.944	0.833
-0	0.871	0.839	-1.536	0.428	1.198	0.875	-1.256	-0.466	1.087	0.684	-0.768	0.150	0.000	0.556	-1.793	0.389	0.000	0.942	-1.126	1.339	1.551	0.624	0.734	0.986	1.357	0.960	1.474	1.294
-1	0.951	1.651	0.576	1.273	1.495	0.834	0.048	-0.578	2.173	0.386	-0.056	-1.448	0.000	0.597	-0.196	0.162	2.548	0.524	1.649	1.625	0.000	0.737	0.901	1.124	1.014	0.556	1.039	0.845
-1	1.049	-0.223	0.685	0.256	-1.191	2.506	0.238	-0.359	0.000	1.510	-0.904	1.158	1.107	2.733	-0.902	1.679	2.548	0.407	-0.474	-1.572	0.000	1.513	2.472	0.982	1.238	0.978	1.985	1.510
-0	0.455	-0.028	0.265	1.286	1.373	0.459	0.331	-0.922	0.000	0.343	0.634	0.430	0.000	0.279	-0.084	-0.272	0.000	0.475	0.926	-0.123	3.102	0.803	0.495	0.987	0.587	0.211	0.417	0.445
-1	2.074	0.388	0.878	1.110	1.557	1.077	-0.226	-0.295	2.173	0.865	-0.319	-1.116	2.215	0.707	-0.835	0.722	0.000	0.632	-0.608	-0.728	0.000	0.715	0.802	1.207	1.190	0.960	1.143	0.926
-1	1.390	0.265	1.196	0.919	-1.371	1.858	0.506	0.786	0.000	1.280	-1.367	-0.720	2.215	1.483	-0.441	-0.675	2.548	1.076	0.294	-0.539	0.000	1.126	0.830	1.155	1.551	0.702	1.103	0.933
-1	1.014	-0.079	1.597	1.038	-0.281	1.135	-0.722	-0.177	2.173	0.544	-1.475	-1.501	0.000	1.257	-1.315	1.212	0.000	0.496	-0.060	1.180	1.551	0.815	0.611	1.411	1.110	0.792	0.846	0.853
-0	0.335	1.267	-1.154	2.011	-0.574	0.753	0.618	1.411	0.000	0.474	0.748	0.681	2.215	0.608	-0.446	-0.354	2.548	0.399	1.295	-0.581	0.000	0.911	0.882	0.975	0.832	0.598	0.580	0.678
-1	0.729	-0.189	1.182	0.293	1.310	0.412	0.459	-0.632	0.000	0.869	-1.128	-0.625	2.215	1.173	-0.893	0.478	2.548	0.584	-2.394	-1.727	0.000	2.016	1.272	0.995	1.034	0.905	0.966	1.038
-1	1.225	-1.215	-0.088	0.881	-0.237	0.600	-0.976	1.462	2.173	0.876	0.506	1.583	2.215	0.718	1.228	-0.031	0.000	0.653	-1.292	1.216	0.000	0.838	1.108	0.981	1.805	0.890	1.251	1.197
-1	2.685	-0.444	0.847	0.253	0.183	0.641	-1.541	-0.873	2.173	0.417	2.874	-0.551	0.000	0.706	-1.431	0.764	0.000	1.390	-0.596	-1.397	0.000	0.894	0.829	0.993	0.789	0.654	0.883	0.746
-0	0.638	-0.481	0.683	1.457	-1.024	0.707	-1.338	1.498	0.000	0.980	0.518	0.289	2.215	0.964	-0.531	-0.423	0.000	0.694	-0.654	-1.314	3.102	0.807	1.283	1.335	0.658	0.907	0.797	0.772
-1	1.789	-0.765	-0.732	0.421	-0.020	1.142	-1.353	1.439	2.173	0.725	-1.518	-1.261	0.000	0.812	-2.597	-0.463	0.000	1.203	-0.120	1.001	0.000	0.978	0.673	0.985	1.303	1.400	1.078	0.983
-1	0.784	-1.431	1.724	0.848	0.559	0.615	-1.643	-1.456	0.000	1.339	-0.513	0.040	2.215	0.394	-2.483	1.304	0.000	0.987	0.889	-0.339	0.000	0.732	0.713	0.987	0.973	0.705	0.875	0.759
-1	0.911	1.098	-1.289	0.421	0.823	1.218	-0.503	0.431	0.000	0.775	0.432	-1.680	0.000	0.855	-0.226	-0.460	2.548	0.646	-0.947	-1.243	1.551	2.201	1.349	0.985	0.730	0.451	0.877	0.825
-1	0.959	0.372	-0.269	1.255	0.702	1.151	0.097	0.805	2.173	0.993	1.011	0.767	2.215	1.096	0.185	0.381	0.000	1.001	-0.205	0.059	0.000	0.979	0.997	1.168	0.796	0.771	0.839	0.776
-0	0.283	-1.864	-1.663	0.219	1.624	0.955	-1.213	0.932	2.173	0.889	0.395	-0.268	0.000	0.597	-1.083	-0.921	2.548	0.584	1.325	-1.072	0.000	0.856	0.927	0.996	0.937	0.936	1.095	0.892
-0	2.017	-0.488	-0.466	1.029	-0.870	3.157	0.059	-0.343	2.173	3.881	0.872	1.502	1.107	3.631	1.720	0.963	0.000	0.633	-1.264	-1.734	0.000	4.572	3.339	1.005	1.407	5.590	3.614	3.110
-1	1.088	0.414	-0.841	0.485	0.605	0.860	1.110	-0.568	0.000	1.152	-0.325	1.203	2.215	0.324	1.652	-0.104	0.000	0.510	1.095	-1.728	0.000	0.880	0.722	0.989	0.977	0.711	0.888	0.762
-0	0.409	-1.717	0.712	0.809	-1.301	0.701	-1.529	-1.411	0.000	1.191	-0.582	0.438	2.215	1.147	0.813	-0.571	2.548	1.039	0.543	0.892	0.000	0.636	0.810	0.986	0.861	1.411	0.907	0.756
-1	1.094	1.577	-0.988	0.497	-0.149	0.891	-2.459	1.034	0.000	0.646	0.792	-1.022	0.000	1.573	0.254	-0.053	2.548	1.428	0.190	-1.641	3.102	4.322	2.687	0.985	0.881	1.135	1.907	1.831
-1	0.613	1.993	-0.280	0.544	0.931	0.909	1.526	1.559	0.000	0.840	1.473	-0.483	2.215	0.856	0.352	0.408	2.548	1.058	1.733	-1.396	0.000	0.801	1.066	0.984	0.639	0.841	0.871	0.748
-0	0.958	-1.202	0.600	0.434	0.170	0.783	-0.214	1.319	0.000	0.835	-0.454	-0.615	2.215	0.658	-1.858	-0.891	0.000	0.640	0.172	-1.204	3.102	1.790	1.086	0.997	0.804	0.403	0.793	0.756
-1	1.998	-0.238	0.972	0.058	0.266	0.759	1.576	-0.357	2.173	1.004	-0.349	-0.747	2.215	0.962	0.490	-0.453	0.000	1.592	0.661	-1.405	0.000	0.874	1.086	0.990	1.436	1.527	1.177	0.993
-1	0.796	-0.171	-0.818	0.574	-1.625	1.201	-0.737	1.451	2.173	0.651	0.404	-0.452	0.000	1.150	-0.652	-0.120	0.000	1.008	-0.093	0.531	3.102	0.884	0.706	0.979	1.193	0.937	0.943	0.881
-1	0.773	1.023	0.527	1.537	-0.201	2.967	-0.574	-1.534	2.173	2.346	-0.307	0.394	2.215	1.393	0.135	-0.027	0.000	3.015	0.187	0.516	0.000	0.819	1.260	0.982	2.552	3.862	2.179	1.786
-0	1.823	1.008	-1.489	0.234	-0.962	0.591	0.461	0.996	2.173	0.568	-1.297	-0.410	0.000	0.887	2.157	1.194	0.000	2.079	0.369	-0.085	3.102	0.770	0.945	0.995	1.179	0.971	0.925	0.983
-0	0.780	0.640	0.490	0.680	-1.301	0.715	-0.137	0.152	2.173	0.616	-0.831	1.668	0.000	1.958	0.528	-0.982	2.548	0.966	-1.551	0.462	0.000	1.034	1.079	1.008	0.827	1.369	1.152	0.983
-1	0.543	0.801	1.543	1.134	-0.772	0.954	-0.849	0.410	1.087	0.851	-1.988	1.686	0.000	0.799	-0.912	-1.156	0.000	0.479	0.097	1.334	0.000	0.923	0.597	0.989	1.231	0.759	0.975	0.867
-0	1.241	-0.014	0.129	1.158	0.670	0.445	-0.732	1.739	2.173	0.918	0.659	-1.340	2.215	0.557	2.410	-1.404	0.000	0.966	-1.545	-1.120	0.000	0.874	0.918	0.987	1.001	0.798	0.904	0.937
-0	1.751	-0.266	-1.575	0.489	1.292	1.112	1.533	0.137	2.173	1.204	-0.414	-0.928	0.000	0.879	1.237	-0.415	2.548	1.479	1.469	0.913	0.000	2.884	1.747	0.989	1.742	0.600	1.363	1.293
-1	1.505	1.208	-1.476	0.995	-0.836	2.800	-1.600	0.111	0.000	2.157	1.241	1.110	2.215	1.076	2.619	-0.913	0.000	1.678	2.204	-1.575	0.000	0.849	1.224	0.990	1.412	0.976	1.271	1.105
-0	0.816	0.611	0.779	1.694	0.278	0.575	-0.787	1.592	2.173	1.148	1.076	-0.831	2.215	0.421	1.316	0.632	0.000	0.589	0.452	-1.466	0.000	0.779	0.909	0.990	1.146	1.639	1.236	0.949
-1	0.551	-0.808	0.330	1.188	-0.294	0.447	-0.035	-0.993	0.000	0.432	-0.276	-0.481	2.215	1.959	-0.288	1.195	2.548	0.638	0.583	1.107	0.000	0.832	0.924	0.993	0.723	0.976	0.968	0.895
-0	1.316	-0.093	0.995	0.860	-0.621	0.593	-0.560	-1.599	2.173	0.524	-0.318	-0.240	2.215	0.566	0.759	-0.368	0.000	0.483	-2.030	-1.104	0.000	1.468	1.041	1.464	0.811	0.778	0.690	0.722
-1	1.528	0.067	-0.855	0.959	-1.464	1.143	-0.082	1.023	0.000	0.702	-0.763	-0.244	0.000	0.935	-0.881	0.206	2.548	0.614	-0.831	1.657	3.102	1.680	1.105	0.983	1.078	0.559	0.801	0.809
-0	0.558	-0.833	-0.598	1.436	-1.724	1.316	-0.661	1.593	2.173	1.148	-0.503	-0.132	1.107	1.584	-0.125	0.380	0.000	1.110	-1.216	-0.181	0.000	1.258	0.860	1.053	0.790	1.814	1.159	1.007
-1	0.819	0.879	1.221	0.598	-1.450	0.754	0.417	-0.369	2.173	0.477	1.199	0.274	0.000	1.073	0.368	0.273	2.548	1.599	2.047	1.690	0.000	0.933	0.984	0.983	0.788	0.613	0.728	0.717
-0	0.981	-1.007	0.489	0.923	1.261	0.436	-0.698	-0.506	2.173	0.764	-1.105	-1.241	2.215	0.577	-2.573	-0.036	0.000	0.565	-1.628	1.610	0.000	0.688	0.801	0.991	0.871	0.554	0.691	0.656
-0	2.888	0.568	-1.416	1.461	-1.157	1.756	-0.900	0.522	0.000	0.657	0.409	1.076	2.215	1.419	0.672	-0.019	0.000	1.436	-0.184	-0.980	3.102	0.946	0.919	0.995	1.069	0.890	0.834	0.856
-1	0.522	1.805	-0.963	1.136	0.418	0.727	-0.195	-1.695	2.173	0.309	2.559	-0.178	0.000	0.521	1.794	0.919	0.000	0.788	0.174	-0.406	3.102	0.555	0.729	1.011	1.385	0.753	0.927	0.832
-1	0.793	-0.162	-1.643	0.634	0.337	0.898	-0.633	1.689	0.000	0.806	-0.826	-0.356	2.215	0.890	-0.142	-1.268	0.000	1.293	0.574	0.725	0.000	0.833	1.077	0.988	0.721	0.679	0.867	0.753
-0	1.298	1.098	0.280	0.371	-0.373	0.855	-0.306	-1.186	0.000	0.977	-0.421	1.003	0.000	0.978	0.956	-1.249	2.548	0.735	0.577	-0.037	3.102	0.974	1.002	0.992	0.549	0.587	0.725	0.954
-1	0.751	-0.520	-1.653	0.168	-0.419	0.878	-1.023	-1.364	2.173	1.310	-0.667	0.863	0.000	1.196	-0.827	0.358	0.000	1.154	-0.165	-0.360	1.551	0.871	0.950	0.983	0.907	0.955	0.959	0.874
-0	1.730	0.666	-1.432	0.446	1.302	0.921	-0.203	0.621	0.000	1.171	-0.365	-0.611	1.107	0.585	0.807	1.150	0.000	0.415	-0.843	1.311	0.000	0.968	0.786	0.986	1.059	0.371	0.790	0.848
-1	0.596	-1.486	0.690	1.045	-1.344	0.928	0.867	0.820	2.173	0.610	0.999	-1.329	2.215	0.883	-0.001	-0.106	0.000	1.145	2.184	-0.808	0.000	2.019	1.256	1.056	1.751	1.037	1.298	1.518
-1	0.656	-1.993	-0.519	1.643	-0.143	0.815	0.256	1.220	1.087	0.399	-1.184	-1.458	0.000	0.738	1.361	-1.443	0.000	0.842	0.033	0.293	0.000	0.910	0.891	0.993	0.668	0.562	0.958	0.787
-1	1.127	-0.542	0.645	0.318	-1.496	0.661	-0.640	0.369	2.173	0.992	0.358	1.702	0.000	1.004	0.316	-1.109	0.000	1.616	-0.936	-0.707	1.551	0.875	1.191	0.985	0.651	0.940	0.969	0.834
-0	0.916	-1.423	-1.490	1.248	-0.538	0.625	-0.535	-0.174	0.000	0.769	-0.389	1.608	2.215	0.667	-1.138	-1.738	1.274	0.877	-0.019	0.482	0.000	0.696	0.917	1.121	0.678	0.347	0.647	0.722
-1	2.756	-0.637	-1.715	1.331	1.124	0.913	-0.296	-0.491	0.000	0.983	-0.831	0.000	2.215	1.180	-0.428	0.742	0.000	1.113	0.005	-1.157	1.551	1.681	1.096	1.462	0.976	0.917	1.009	1.040
-0	0.755	1.754	0.701	2.111	0.256	1.243	0.057	-1.502	2.173	0.565	-0.034	-1.078	1.107	0.529	1.696	-1.090	0.000	0.665	0.292	0.107	0.000	0.870	0.780	0.990	2.775	0.465	1.876	1.758
-1	0.593	-0.762	1.743	0.908	0.442	0.773	-1.357	-0.768	2.173	0.432	1.421	1.236	0.000	0.579	0.291	-0.403	0.000	0.966	-0.309	1.016	3.102	0.893	0.743	0.989	0.857	1.030	0.943	0.854
-1	0.891	-1.151	-1.269	0.504	-0.622	0.893	-0.549	0.700	0.000	0.828	-0.825	0.154	2.215	1.083	0.632	-1.141	0.000	1.059	-0.557	1.526	3.102	2.117	1.281	0.987	0.819	0.802	0.917	0.828
-1	2.358	-0.248	0.080	0.747	-0.975	1.019	1.374	1.363	0.000	0.935	0.127	-1.707	2.215	0.312	-0.827	0.017	0.000	0.737	1.059	-0.327	0.000	0.716	0.828	1.495	0.953	0.704	0.880	0.745
-0	0.660	-0.017	-1.138	0.453	1.002	0.645	0.518	0.703	2.173	0.751	0.705	-0.592	2.215	0.744	-0.909	-1.596	0.000	0.410	-1.135	0.481	0.000	0.592	0.922	0.989	0.897	0.948	0.777	0.701
-1	0.718	0.518	0.225	1.710	-0.022	1.888	-0.424	1.092	0.000	4.134	0.185	-1.366	0.000	1.415	1.293	0.242	2.548	2.351	0.264	-0.057	3.102	0.830	1.630	0.976	1.215	0.890	1.422	1.215
-1	1.160	0.203	0.941	0.594	0.212	0.636	-0.556	0.679	2.173	1.089	-0.481	-1.008	1.107	1.245	-0.056	-1.357	0.000	0.587	1.007	0.056	0.000	1.106	0.901	0.987	0.786	1.224	0.914	0.837
-1	0.697	0.542	0.619	0.985	1.481	0.745	0.415	1.644	2.173	0.903	0.495	-0.958	2.215	1.165	1.195	0.346	0.000	1.067	-0.881	-0.264	0.000	0.830	1.025	0.987	0.690	0.863	0.894	0.867
-0	1.430	0.190	-0.700	0.246	0.518	1.302	0.660	-0.247	2.173	1.185	-0.539	1.504	0.000	1.976	-0.401	1.079	0.000	0.855	-0.958	-1.110	3.102	0.886	0.953	0.993	0.889	1.400	1.376	1.119
-1	1.122	-0.795	0.202	0.397	-1.553	0.597	-1.459	-0.734	2.173	0.522	1.044	1.027	2.215	0.783	-1.243	1.701	0.000	0.371	1.737	0.199	0.000	1.719	1.176	0.988	0.723	1.583	1.063	0.914
-0	1.153	0.526	1.236	0.266	0.001	1.139	-1.236	-0.585	2.173	1.337	-0.215	-1.356	2.215	1.780	1.129	0.902	0.000	1.608	-0.391	-0.161	0.000	1.441	1.633	0.990	1.838	1.516	1.635	1.373
-1	0.760	1.012	0.758	0.937	0.051	0.941	0.687	-1.247	2.173	1.288	-0.743	0.822	0.000	1.552	1.782	-1.533	0.000	0.767	1.349	0.168	0.000	0.716	0.862	0.988	0.595	0.359	0.697	0.623
-1	1.756	-1.469	1.395	1.345	-1.595	0.817	0.017	-0.741	2.173	0.483	-0.008	0.293	0.000	1.768	-0.663	0.438	1.274	1.202	-1.387	-0.222	0.000	1.022	1.058	0.992	1.407	1.427	1.356	1.133
-0	0.397	0.582	-0.758	1.260	-1.735	0.889	-0.515	1.139	2.173	0.973	1.616	0.460	0.000	1.308	1.001	-0.709	2.548	0.858	0.995	-0.231	0.000	0.749	0.888	0.979	1.487	1.804	1.208	1.079
-0	0.515	-0.984	0.425	1.114	-0.439	1.999	0.818	1.561	0.000	1.407	0.009	-0.380	0.000	1.332	0.230	0.397	0.000	1.356	-0.616	-1.057	3.102	0.978	1.017	0.990	1.118	0.862	0.835	0.919
-1	1.368	-0.921	-0.866	0.842	-0.598	0.456	-1.176	1.219	1.087	0.419	-1.974	-0.819	0.000	0.791	-1.640	0.881	0.000	1.295	-0.782	0.442	3.102	0.945	0.761	0.974	0.915	0.535	0.733	0.651
-0	2.276	0.134	0.399	2.525	0.376	1.111	-1.078	-1.571	0.000	0.657	2.215	-0.900	0.000	1.183	-0.662	-0.508	2.548	1.436	-0.517	0.960	3.102	0.569	0.931	0.993	1.170	0.967	0.879	1.207
-0	0.849	0.907	0.124	0.652	1.585	0.715	0.355	-1.200	0.000	0.599	-0.892	1.301	0.000	1.106	1.151	0.582	0.000	1.895	-0.279	-0.568	3.102	0.881	0.945	0.998	0.559	0.649	0.638	0.660
-1	2.105	0.248	-0.797	0.530	0.206	1.957	-2.175	0.797	0.000	1.193	0.637	-1.646	2.215	0.881	1.111	-1.046	0.000	0.872	-0.185	1.085	1.551	0.986	1.343	1.151	1.069	0.714	2.063	1.951
-1	1.838	1.060	1.637	1.017	1.370	0.913	0.461	-0.609	1.087	0.766	-0.461	0.303	2.215	0.724	-0.061	0.886	0.000	0.941	1.123	-0.745	0.000	0.858	0.847	0.979	1.313	1.083	1.094	0.910
-0	0.364	1.274	1.066	1.570	-0.394	0.485	0.012	-1.716	0.000	0.317	-1.233	0.534	2.215	0.548	-2.165	0.762	0.000	0.729	0.169	-0.318	3.102	0.892	0.944	1.013	0.594	0.461	0.688	0.715
-1	0.503	1.343	-0.031	1.134	-1.204	0.590	-0.309	0.174	2.173	0.408	2.372	-0.628	0.000	1.850	0.400	1.147	2.548	0.664	-0.458	-0.885	0.000	1.445	1.283	0.989	1.280	1.118	1.127	1.026
-0	1.873	0.258	0.103	2.491	0.530	1.678	0.644	-1.738	2.173	1.432	0.848	-1.340	0.000	0.621	1.323	-1.316	0.000	0.628	0.789	-0.206	1.551	0.426	0.802	1.125	0.688	1.079	1.338	1.239
-1	0.826	-0.732	1.587	0.582	-1.236	0.495	0.757	-0.741	2.173	0.940	1.474	0.354	2.215	0.474	1.055	-1.657	0.000	0.415	1.758	0.841	0.000	0.451	0.578	0.984	0.757	0.922	0.860	0.696
-0	0.935	-1.614	-0.597	0.299	1.223	0.707	-0.853	-1.026	0.000	0.751	0.007	-1.691	0.000	1.062	-0.125	0.976	2.548	0.877	1.275	0.646	0.000	0.962	1.074	0.980	0.608	0.726	0.741	0.662
-1	0.643	0.542	-1.285	0.474	-0.366	0.667	-0.446	1.195	2.173	1.076	0.145	-0.126	0.000	0.970	-0.661	0.394	1.274	1.218	-0.184	-1.722	0.000	1.331	1.019	0.985	1.192	0.677	0.973	0.910
-0	0.713	0.164	1.080	1.427	-0.460	0.960	-0.152	-0.940	2.173	1.427	-0.901	1.036	1.107	0.440	-1.269	-0.194	0.000	0.452	1.932	-0.532	0.000	1.542	1.210	1.374	1.319	1.818	1.220	1.050
-0	0.876	-0.463	-1.224	2.458	-1.689	1.007	-0.752	0.398	0.000	2.456	-1.285	-0.152	1.107	1.641	1.838	1.717	0.000	0.458	0.194	0.488	3.102	4.848	2.463	0.986	1.981	0.974	2.642	2.258
-1	0.384	-0.275	0.387	1.403	-0.994	0.620	-1.529	1.685	0.000	1.091	-1.644	1.078	0.000	0.781	-1.311	0.326	2.548	1.228	-0.728	-0.633	1.551	0.920	0.854	0.987	0.646	0.609	0.740	0.884
-0	0.318	-1.818	-1.008	0.977	1.268	0.457	2.451	-1.522	0.000	0.881	1.351	0.461	2.215	0.929	0.239	-0.380	2.548	0.382	-0.613	1.330	0.000	1.563	1.193	0.994	0.829	0.874	0.901	1.026
-1	0.612	-1.120	1.098	0.402	-0.480	0.818	0.188	1.511	0.000	0.800	-0.253	0.977	0.000	1.175	0.271	-1.289	1.274	2.531	0.226	-0.409	3.102	0.889	0.947	0.979	1.486	0.940	1.152	1.119
-1	0.587	-0.737	-0.228	0.970	1.119	0.823	0.184	1.594	0.000	1.104	0.301	-0.818	2.215	0.819	0.712	-0.560	0.000	2.240	-0.419	0.340	3.102	1.445	1.103	0.988	0.715	1.363	1.019	0.926
-0	1.030	-0.694	-1.638	0.893	-1.074	1.160	-0.766	0.485	0.000	1.632	-0.698	-1.142	2.215	1.050	-1.092	0.952	0.000	1.475	0.286	0.125	3.102	0.914	1.075	0.982	0.732	1.493	1.219	1.079
-1	2.142	0.617	1.517	0.387	-0.862	0.345	1.203	-1.014	2.173	0.609	1.092	0.275	0.000	1.331	0.582	-0.183	2.548	0.557	1.540	-1.642	0.000	0.801	0.737	1.060	0.715	0.626	0.749	0.674
-0	1.076	0.240	-0.246	0.871	-1.241	0.496	0.282	0.746	2.173	1.095	-0.648	1.100	2.215	0.446	-1.756	0.764	0.000	0.434	0.788	-0.991	0.000	1.079	0.868	1.047	0.818	0.634	0.795	0.733
-0	1.400	0.901	-1.617	0.625	-0.163	0.661	-0.411	-1.616	2.173	0.685	0.524	0.425	0.000	0.881	-0.766	0.312	0.000	0.979	0.255	-0.667	3.102	0.898	1.105	1.253	0.730	0.716	0.738	0.795
-0	3.302	1.132	1.051	0.658	0.768	1.308	0.251	-0.374	1.087	1.673	0.015	-0.898	0.000	0.688	-0.535	1.363	1.274	0.871	1.325	-1.583	0.000	1.646	1.249	0.995	1.919	1.288	1.330	1.329
-0	1.757	0.202	0.750	0.767	-0.362	0.932	-1.033	-1.366	0.000	1.529	-1.012	-0.771	0.000	1.161	-0.287	0.059	0.000	2.185	1.147	1.099	3.102	0.795	0.529	1.354	1.144	1.491	1.319	1.161
-0	1.290	0.905	-1.711	1.017	-0.695	1.008	-1.038	0.693	2.173	1.202	-0.595	0.187	0.000	1.011	0.139	-1.607	0.000	0.789	-0.613	-1.041	3.102	1.304	0.895	1.259	1.866	0.955	1.211	1.200
-1	1.125	-0.004	1.694	0.373	0.329	0.978	0.640	-0.391	0.000	1.122	-0.376	1.521	2.215	0.432	2.413	-1.259	0.000	0.969	0.730	0.512	3.102	0.716	0.773	0.991	0.624	0.977	0.981	0.875
-0	1.081	0.861	1.252	1.621	1.474	1.293	0.600	0.630	0.000	1.991	-0.090	-0.675	2.215	0.861	1.105	-0.201	0.000	1.135	2.489	-1.659	0.000	1.089	0.657	0.991	2.179	0.412	1.334	1.071
-1	0.652	-0.294	1.241	1.034	0.490	1.033	0.551	-0.963	2.173	0.661	1.031	-1.654	2.215	1.376	-0.018	0.843	0.000	0.943	-0.329	-0.269	0.000	1.085	1.067	0.991	1.504	0.773	1.135	0.993
-1	1.408	-1.028	-1.018	0.252	-0.242	0.465	-0.364	-0.200	0.000	1.466	0.669	0.739	1.107	1.031	0.415	-1.468	2.548	0.457	-1.091	-1.722	0.000	0.771	0.811	0.979	1.459	1.204	1.041	0.866
-1	0.781	-1.143	-0.659	0.961	1.266	1.183	-0.686	0.119	2.173	1.126	-0.064	1.447	0.000	0.730	1.430	-1.535	0.000	1.601	0.513	1.658	0.000	0.871	1.345	1.184	1.058	0.620	1.107	0.978
-1	1.300	-0.616	1.032	0.751	-0.731	0.961	-0.716	1.592	0.000	2.079	-1.063	-0.271	2.215	0.475	0.518	1.695	1.274	0.395	-2.204	0.349	0.000	1.350	0.983	1.369	1.265	1.428	1.135	0.982
-1	0.833	0.809	1.657	1.637	1.019	0.705	1.077	-0.968	2.173	1.261	0.114	-0.298	1.107	1.032	0.017	0.236	0.000	0.640	-0.026	-1.598	0.000	0.894	0.982	0.981	1.250	1.054	1.018	0.853
-1	1.686	-1.090	-0.301	0.890	0.557	1.304	-0.284	-1.393	2.173	0.388	2.118	0.513	0.000	0.514	-0.015	0.891	0.000	0.460	0.547	0.627	3.102	0.942	0.524	1.186	1.528	0.889	1.015	1.122
-1	0.551	0.911	0.879	0.379	-0.796	1.154	-0.808	-0.966	0.000	1.168	-0.513	0.355	2.215	0.646	-1.309	0.773	0.000	0.544	-0.283	1.301	3.102	0.847	0.705	0.990	0.772	0.546	0.790	0.719
-1	1.597	0.793	-1.119	0.691	-1.455	0.370	0.337	1.354	0.000	0.646	-1.005	0.732	2.215	1.019	0.040	0.209	0.000	0.545	0.958	0.239	3.102	0.962	0.793	0.994	0.719	0.745	0.812	0.739
-0	1.033	-1.193	-0.452	0.247	0.970	0.503	-1.424	1.362	0.000	1.062	-0.416	-1.156	2.215	0.935	-0.023	0.555	2.548	0.410	-1.766	0.379	0.000	0.590	0.953	0.991	0.717	1.081	0.763	0.690
-1	0.859	-1.004	1.521	0.781	-0.993	0.677	0.643	-0.338	2.173	0.486	0.409	1.283	0.000	0.679	0.110	0.285	0.000	0.715	-0.735	-0.157	1.551	0.702	0.773	0.984	0.627	0.633	0.694	0.643
-0	0.612	-1.127	1.074	1.225	-0.426	0.927	-2.141	-0.473	0.000	1.290	-0.927	-1.085	2.215	1.183	1.981	-1.687	0.000	2.176	0.406	-1.581	0.000	0.945	0.651	1.170	0.895	1.604	1.179	1.142
-1	0.535	0.321	-1.095	0.281	-0.960	0.876	-0.709	-0.076	0.000	1.563	-0.666	1.536	2.215	0.773	-0.321	0.435	0.000	0.682	-0.801	-0.952	3.102	0.711	0.667	0.985	0.888	0.741	0.872	0.758
-1	0.745	1.586	1.578	0.863	-1.423	0.530	1.714	1.085	0.000	1.174	0.679	1.015	0.000	1.158	0.609	-1.186	2.548	1.851	0.832	-0.248	3.102	0.910	1.164	0.983	0.947	0.858	0.928	0.823
-0	0.677	-1.014	-1.648	1.455	1.461	0.596	-2.358	0.517	0.000	0.800	0.849	-0.743	2.215	1.024	-0.282	-1.004	0.000	1.846	-0.977	0.378	3.102	2.210	1.423	0.982	1.074	1.623	1.417	1.258
-1	0.815	-1.263	0.057	1.018	-0.208	0.339	-0.347	-1.646	2.173	1.223	0.600	-1.658	2.215	1.435	0.042	0.926	0.000	0.777	1.698	-0.698	0.000	1.022	1.058	1.000	0.784	0.477	0.886	0.836
-0	3.512	-1.094	-0.220	0.338	-0.328	1.962	-1.099	1.544	1.087	1.461	-1.305	-0.922	2.215	1.219	-1.289	0.400	0.000	0.731	0.155	1.249	0.000	1.173	1.366	0.993	2.259	2.000	1.626	1.349
-0	0.904	1.248	0.325	0.317	-1.624	0.685	-0.538	1.665	2.173	0.685	-2.145	-1.106	0.000	0.632	-1.460	1.017	0.000	1.085	-0.182	0.162	3.102	0.885	0.801	0.989	0.930	0.904	1.012	0.961

contrib/gbdt/lightgbm/binary1.test

@@ -1,500 +0,0 @@
-1	0.644	0.247	-0.447	0.862	0.374	0.854	-1.126	-0.790	2.173	1.015	-0.201	1.400	0.000	1.575	1.807	1.607	0.000	1.585	-0.190	-0.744	3.102	0.958	1.061	0.980	0.875	0.581	0.905	0.796
-0	0.385	1.800	1.037	1.044	0.349	1.502	-0.966	1.734	0.000	0.966	-1.960	-0.249	0.000	1.501	0.465	-0.354	2.548	0.834	-0.440	0.638	3.102	0.695	0.909	0.981	0.803	0.813	1.149	1.116
-0	1.214	-0.166	0.004	0.505	1.434	0.628	-1.174	-1.230	1.087	0.579	-1.047	-0.118	0.000	0.835	0.340	1.234	2.548	0.711	-1.383	1.355	0.000	0.848	0.911	1.043	0.931	1.058	0.744	0.696
-1	0.420	1.111	0.137	1.516	-1.657	0.854	0.623	1.605	1.087	1.511	-1.297	0.251	0.000	0.872	-0.368	-0.721	0.000	0.543	0.731	1.424	3.102	1.597	1.282	1.105	0.730	0.148	1.231	1.234
-0	0.897	-1.703	-1.306	1.022	-0.729	0.836	0.859	-0.333	2.173	1.336	-0.965	0.972	2.215	0.671	1.021	-1.439	0.000	0.493	-2.019	-0.289	0.000	0.805	0.930	0.984	1.430	2.198	1.934	1.684
-0	0.756	1.126	-0.945	2.355	-0.555	0.889	0.800	1.440	0.000	0.585	0.271	0.631	2.215	0.722	1.744	1.051	0.000	0.618	0.924	0.698	1.551	0.976	0.864	0.988	0.803	0.234	0.822	0.911
-0	1.141	-0.741	0.953	1.478	-0.524	1.197	-0.871	1.689	2.173	0.875	1.321	-0.518	1.107	0.540	0.037	-0.987	0.000	0.879	1.187	0.245	0.000	0.888	0.701	1.747	1.358	2.479	1.491	1.223
-1	0.606	-0.936	-0.384	1.257	-1.162	2.719	-0.600	0.100	2.173	3.303	-0.284	1.561	1.107	0.689	1.786	-0.326	0.000	0.780	-0.532	1.216	0.000	0.936	2.022	0.985	1.574	4.323	2.263	1.742
-1	0.603	0.429	-0.279	1.448	1.301	1.008	2.423	-1.295	0.000	0.452	1.305	0.533	0.000	1.076	1.011	1.256	2.548	2.021	1.260	-0.343	0.000	0.890	0.969	1.281	0.763	0.652	0.827	0.785
-0	1.171	-0.962	0.521	0.841	-0.315	1.196	-0.744	-0.882	2.173	0.726	-1.305	1.377	1.107	0.643	-1.790	-1.264	0.000	1.257	0.222	0.817	0.000	0.862	0.911	0.987	0.846	1.293	0.899	0.756
-1	1.392	-0.358	0.235	1.494	-0.461	0.895	-0.848	1.549	2.173	0.841	-0.384	0.666	1.107	1.199	2.509	-0.891	0.000	1.109	-0.364	-0.945	0.000	0.693	2.135	1.170	1.362	0.959	2.056	1.842
-1	1.024	1.076	-0.886	0.851	1.530	0.673	-0.449	0.187	1.087	0.628	-0.895	1.176	2.215	0.696	-0.232	-0.875	0.000	0.411	1.501	0.048	0.000	0.842	0.919	1.063	1.193	0.777	0.964	0.807
-1	0.890	-0.760	1.182	1.369	0.751	0.696	-0.959	-0.710	1.087	0.775	-0.130	-1.409	2.215	0.701	-0.110	-0.739	0.000	0.508	-0.451	0.390	0.000	0.762	0.738	0.998	1.126	0.788	0.940	0.790
-1	0.460	0.537	0.636	1.442	-0.269	0.585	0.323	-1.731	2.173	0.503	1.034	-0.927	0.000	0.928	-1.024	1.006	2.548	0.513	-0.618	-1.336	0.000	0.802	0.831	0.992	1.019	0.925	1.056	0.833
-1	0.364	1.648	0.560	1.720	0.829	1.110	0.811	-0.588	0.000	0.408	1.045	1.054	2.215	0.319	-1.138	1.545	0.000	0.423	1.025	-1.265	3.102	1.656	0.928	1.003	0.544	0.327	0.670	0.746
-1	0.525	-0.096	1.206	0.948	-1.103	1.519	-0.582	0.606	2.173	1.274	-0.572	-0.934	0.000	0.855	-1.028	-1.222	0.000	0.578	-1.000	-1.725	3.102	0.896	0.878	0.981	0.498	0.909	0.772	0.668
-0	0.536	-0.821	-1.029	0.703	1.113	0.363	-0.711	0.022	1.087	0.325	1.503	1.249	2.215	0.673	1.041	-0.401	0.000	0.480	2.127	1.681	0.000	0.767	1.034	0.990	0.671	0.836	0.669	0.663
-1	1.789	-0.583	1.641	0.897	0.799	0.515	-0.100	-1.483	0.000	1.101	0.031	-0.326	2.215	1.195	0.001	0.126	2.548	0.768	-0.148	0.601	0.000	0.916	0.921	1.207	1.069	0.483	0.934	0.795
-1	1.332	-0.571	0.986	0.580	1.508	0.582	0.634	-0.746	1.087	1.084	-0.964	-0.489	0.000	0.785	0.274	0.343	2.548	0.779	0.721	1.489	0.000	1.733	1.145	0.990	1.270	0.715	0.897	0.915
-0	1.123	0.629	-1.708	0.597	-0.882	0.752	0.195	1.522	2.173	1.671	1.515	-0.003	0.000	0.778	0.514	0.139	1.274	0.801	1.260	1.600	0.000	1.495	0.976	0.988	0.676	0.921	1.010	0.943
-0	1.816	-0.515	0.171	0.980	-0.454	0.870	0.202	-1.399	2.173	1.130	1.066	-1.593	0.000	0.844	0.735	1.275	2.548	1.125	-1.133	0.348	0.000	0.837	0.693	0.988	1.112	0.784	1.009	0.974
-1	0.364	0.694	0.445	1.862	0.159	0.963	-1.356	1.260	1.087	0.887	-0.540	-1.533	2.215	0.658	-2.544	-1.236	0.000	0.516	-0.807	0.039	0.000	0.891	1.004	0.991	1.092	0.976	1.000	0.953
-1	0.790	-1.175	0.475	1.846	0.094	0.999	-1.090	0.257	0.000	1.422	0.854	1.112	2.215	1.302	1.004	-1.702	1.274	2.557	-0.787	-1.048	0.000	0.890	1.429	0.993	2.807	0.840	2.248	1.821
-1	0.765	-0.500	-0.603	1.843	-0.560	1.068	0.007	0.746	2.173	1.154	-0.017	1.329	0.000	1.165	1.791	-1.585	0.000	1.116	0.441	-0.886	0.000	0.774	0.982	0.989	1.102	0.633	1.178	1.021
-1	1.407	1.293	-1.418	0.502	-1.527	2.005	-2.122	0.622	0.000	1.699	1.508	-0.649	2.215	1.665	0.748	-0.755	0.000	2.555	0.811	1.423	1.551	7.531	5.520	0.985	1.115	1.881	4.487	3.379
-1	0.772	-0.186	-1.372	0.823	-0.140	0.781	0.763	0.046	2.173	1.128	0.516	1.380	0.000	0.797	-0.640	-0.134	2.548	2.019	-0.972	-1.670	0.000	2.022	1.466	0.989	0.856	0.808	1.230	0.991
-1	0.546	-0.954	0.715	1.335	-1.689	0.783	-0.443	-1.735	2.173	1.081	0.185	-0.435	0.000	1.433	-0.662	-0.389	0.000	0.969	0.924	1.099	0.000	0.910	0.879	0.988	0.683	0.753	0.878	0.865
-1	0.596	0.276	-1.054	1.358	1.355	1.444	1.813	-0.208	0.000	1.175	-0.949	-1.573	0.000	0.855	-1.228	-0.925	2.548	1.837	-0.400	0.913	0.000	0.637	0.901	1.028	0.553	0.790	0.679	0.677
-0	0.458	2.292	1.530	0.291	1.283	0.749	-0.930	-0.198	0.000	0.300	-1.560	0.990	0.000	0.811	-0.176	0.995	2.548	1.085	-0.178	-1.213	3.102	0.891	0.648	0.999	0.732	0.655	0.619	0.620
-0	0.638	-0.575	-1.048	0.125	0.178	0.846	-0.753	-0.339	1.087	0.799	-0.727	1.182	0.000	0.888	0.283	0.717	0.000	1.051	-1.046	-1.557	3.102	0.889	0.871	0.989	0.884	0.923	0.836	0.779
-1	0.434	-1.119	-0.313	2.427	0.461	0.497	0.261	-1.177	2.173	0.618	-0.737	-0.688	0.000	1.150	-1.237	-1.652	2.548	0.757	-0.054	1.700	0.000	0.809	0.741	0.982	1.450	0.936	1.086	0.910
-1	0.431	-1.144	-1.030	0.778	-0.655	0.490	0.047	-1.546	0.000	1.583	-0.014	0.891	2.215	0.516	0.956	0.567	2.548	0.935	-1.123	-0.082	0.000	0.707	0.995	0.995	0.700	0.602	0.770	0.685
-1	1.894	0.222	1.224	1.578	1.715	0.966	2.890	-0.013	0.000	0.922	-0.703	-0.844	0.000	0.691	2.056	1.039	0.000	0.900	-0.733	-1.240	3.102	1.292	1.992	1.026	0.881	0.684	1.759	1.755
-0	0.985	-0.316	0.141	1.067	-0.946	0.819	-1.177	1.307	2.173	1.080	-0.429	0.557	1.107	1.726	1.435	-1.075	0.000	1.100	1.547	-0.647	0.000	0.873	1.696	1.179	1.146	1.015	1.538	1.270
-0	0.998	-0.187	-0.236	0.882	0.755	0.468	0.950	-0.439	2.173	0.579	-0.550	-0.624	0.000	1.847	1.196	1.384	1.274	0.846	1.273	-1.072	0.000	1.194	0.797	1.013	1.319	1.174	0.963	0.898
-0	0.515	0.246	-0.593	1.082	1.591	0.912	-0.623	-0.957	2.173	0.858	0.418	0.844	0.000	0.948	2.519	1.599	0.000	1.158	1.385	-0.095	3.102	0.973	1.033	0.988	0.998	1.716	1.054	0.901
-0	0.919	-1.001	1.506	1.389	0.653	0.507	-0.616	-0.689	2.173	0.808	0.536	-0.467	2.215	0.496	2.187	-0.859	0.000	0.822	0.807	1.163	0.000	0.876	0.861	1.088	0.947	0.614	0.911	1.087
-0	0.794	0.051	1.477	1.504	-1.695	0.716	0.315	0.264	1.087	0.879	-0.135	-1.094	2.215	1.433	-0.741	0.201	0.000	1.566	0.534	-0.989	0.000	0.627	0.882	0.974	0.807	1.130	0.929	0.925
-1	0.455	-0.946	-1.175	1.453	-0.580	0.763	-0.856	0.840	0.000	0.829	1.223	1.174	2.215	0.714	0.638	-0.466	0.000	1.182	0.223	-1.333	0.000	0.977	0.938	0.986	0.713	0.714	0.796	0.843
-1	0.662	-0.296	-1.287	1.212	-0.707	0.641	1.457	0.222	0.000	0.600	0.525	-1.700	2.215	0.784	-0.835	-0.961	2.548	0.865	1.131	1.162	0.000	0.854	0.877	0.978	0.740	0.734	0.888	0.811
-0	0.390	0.698	-1.629	1.888	0.298	0.990	1.614	-1.572	0.000	1.666	0.170	0.719	2.215	1.590	1.064	-0.886	1.274	0.952	0.305	-1.216	0.000	1.048	0.897	1.173	0.891	1.936	1.273	1.102
-0	1.014	0.117	1.384	0.686	-1.047	0.609	-1.245	-0.850	0.000	1.076	-1.158	0.814	1.107	1.598	-0.389	-0.111	0.000	0.907	1.688	-1.673	0.000	1.333	0.866	0.989	0.975	0.442	0.797	0.788
-0	1.530	-1.408	-0.207	0.440	-1.357	0.902	-0.647	1.325	1.087	1.320	-0.819	0.246	1.107	0.503	1.407	-1.683	0.000	1.189	-0.972	-0.925	0.000	0.386	1.273	0.988	0.829	1.335	1.173	1.149
-1	1.689	-0.590	0.915	2.076	1.202	0.644	-0.478	-0.238	0.000	0.809	-1.660	-1.184	0.000	1.227	-0.224	-0.808	2.548	1.655	1.047	-0.623	0.000	0.621	1.192	0.988	1.309	0.866	0.924	1.012
-0	1.102	0.402	-1.622	1.262	1.022	0.576	0.271	-0.269	0.000	0.591	0.495	-1.278	0.000	1.271	0.209	0.575	2.548	0.941	0.964	-0.685	3.102	0.989	0.963	1.124	0.857	0.858	0.716	0.718
-0	2.491	0.825	0.581	1.593	0.205	0.782	-0.815	1.499	0.000	1.179	-0.999	-1.509	0.000	0.926	0.920	-0.522	2.548	2.068	-1.021	-1.050	3.102	0.874	0.943	0.980	0.945	1.525	1.570	1.652
-0	0.666	0.254	1.601	1.303	-0.250	1.236	-1.929	0.793	0.000	1.074	0.447	-0.871	0.000	0.991	1.059	-0.342	0.000	1.703	-0.393	-1.419	3.102	0.921	0.945	1.285	0.931	0.462	0.770	0.729
-0	0.937	-1.126	1.424	1.395	1.743	0.760	0.428	-0.238	2.173	0.846	0.494	1.320	2.215	0.872	-1.826	-0.507	0.000	0.612	1.860	1.403	0.000	3.402	2.109	0.985	1.298	1.165	1.404	1.240
-1	0.881	-1.086	-0.870	0.513	0.266	2.049	-1.870	1.160	0.000	2.259	-0.428	-0.935	2.215	1.321	-0.655	-0.449	2.548	1.350	-1.766	-0.108	0.000	0.911	1.852	0.987	1.167	0.820	1.903	1.443
-0	0.410	0.835	-0.819	1.257	1.112	0.871	-1.737	-0.401	0.000	0.927	0.158	1.253	0.000	1.183	0.405	-1.570	0.000	0.807	-0.704	-0.438	3.102	0.932	0.962	0.987	0.653	0.315	0.616	0.648
-1	0.634	0.196	-1.679	1.379	-0.967	2.260	-0.273	1.114	0.000	1.458	1.070	-0.278	1.107	1.195	0.110	-0.688	2.548	0.907	0.298	-1.359	0.000	0.949	1.129	0.984	0.675	0.877	0.938	0.824
-1	0.632	-1.254	1.201	0.496	-0.106	0.235	2.731	-0.955	0.000	0.615	-0.805	0.600	0.000	0.633	-0.934	1.641	0.000	1.407	-0.483	-0.962	1.551	0.778	0.797	0.989	0.578	0.722	0.576	0.539
-0	0.714	1.122	1.566	2.399	-1.431	1.665	0.299	0.323	0.000	1.489	1.087	-0.861	2.215	1.174	0.140	1.083	2.548	0.404	-0.968	1.105	0.000	0.867	0.969	0.981	1.039	1.552	1.157	1.173
-1	0.477	-0.321	-0.471	1.966	1.034	2.282	1.359	-0.874	0.000	1.672	-0.258	1.109	0.000	1.537	0.604	0.231	2.548	1.534	-0.640	0.827	0.000	0.746	1.337	1.311	0.653	0.721	0.795	0.742
-1	1.351	0.460	0.031	1.194	-1.185	0.670	-1.157	-1.637	2.173	0.599	-0.823	0.680	0.000	0.478	0.373	1.716	0.000	0.809	-0.919	0.010	1.551	0.859	0.839	1.564	0.994	0.777	0.971	0.826
-1	0.520	-1.442	-0.348	0.840	1.654	1.273	-0.760	1.317	0.000	0.861	2.579	-0.791	0.000	1.779	0.257	-0.703	0.000	2.154	1.928	0.457	0.000	1.629	3.194	0.992	0.730	1.107	2.447	2.747
-0	0.700	-0.308	0.920	0.438	-0.879	0.516	1.409	1.101	0.000	0.960	0.701	-0.049	2.215	1.442	-0.416	-1.439	2.548	0.628	1.009	-0.364	0.000	0.848	0.817	0.987	0.759	1.421	0.937	0.920
-1	0.720	1.061	-0.546	0.798	-1.521	1.066	0.173	0.271	1.087	1.453	0.114	1.336	1.107	0.702	0.616	-0.367	0.000	0.543	-0.386	-1.301	0.000	0.653	0.948	0.989	1.031	1.500	0.965	0.790
-1	0.735	-0.416	0.588	1.308	-0.382	1.042	0.344	1.609	0.000	0.926	0.163	-0.520	1.107	1.050	-0.427	1.159	2.548	0.834	0.613	0.948	0.000	0.848	1.189	1.042	0.844	1.099	0.829	0.843
-1	0.777	-0.396	1.540	1.608	0.638	0.955	0.040	0.918	2.173	1.315	1.116	-0.823	0.000	0.781	-0.762	0.564	2.548	0.945	-0.573	1.379	0.000	0.679	0.706	1.124	0.608	0.593	0.515	0.493
-1	0.934	0.319	-0.257	0.970	-0.980	0.726	0.774	0.731	0.000	0.896	0.038	-1.465	1.107	0.773	-0.055	-0.831	2.548	1.439	-0.229	0.698	0.000	0.964	1.031	0.995	0.845	0.480	0.810	0.762
-0	0.461	0.771	0.019	2.055	-1.288	1.043	0.147	0.261	2.173	0.833	-0.156	1.425	0.000	0.832	0.805	-0.491	2.548	0.589	1.252	1.414	0.000	0.850	0.906	1.245	1.364	0.850	0.908	0.863
-1	0.858	-0.116	-0.937	0.966	1.167	0.825	-0.108	1.111	1.087	0.733	1.163	-0.634	0.000	0.894	0.771	0.020	0.000	0.846	-1.124	-1.195	3.102	0.724	1.194	1.195	0.813	0.969	0.985	0.856
-0	0.720	-0.335	-0.307	1.445	0.540	1.108	-0.034	-1.691	1.087	0.883	-1.356	-0.678	2.215	0.440	1.093	0.253	0.000	0.389	-1.582	-1.097	0.000	1.113	1.034	0.988	1.256	1.572	1.062	0.904
-1	0.750	-0.811	-0.542	0.985	0.408	0.471	0.477	0.355	0.000	1.347	-0.875	-1.556	2.215	0.564	1.082	-0.724	0.000	0.793	-0.958	-0.020	3.102	0.836	0.825	0.986	1.066	0.924	0.927	0.883
-0	0.392	-0.468	-0.216	0.680	1.565	1.086	-0.765	-0.581	1.087	1.264	-1.035	1.189	2.215	0.986	-0.338	0.747	0.000	0.884	-1.328	-0.965	0.000	1.228	0.988	0.982	1.135	1.741	1.108	0.956
-1	0.434	-1.269	0.643	0.713	0.608	0.597	0.832	1.627	0.000	0.708	-0.422	0.079	2.215	1.533	-0.823	-1.127	2.548	0.408	-1.357	-0.828	0.000	1.331	1.087	0.999	1.075	1.015	0.875	0.809
-0	0.828	-1.803	0.342	0.847	-0.162	1.585	-1.128	-0.272	2.173	1.974	0.039	-1.717	0.000	0.900	0.764	-1.741	0.000	1.349	-0.079	1.035	3.102	0.984	0.815	0.985	0.780	1.661	1.403	1.184
-1	1.089	-0.350	-0.747	1.472	0.792	1.087	-0.069	-1.192	0.000	0.512	-0.841	-1.284	0.000	2.162	-0.821	0.545	2.548	1.360	2.243	-0.183	0.000	0.977	0.628	1.725	1.168	0.635	0.823	0.822
-1	0.444	0.451	-1.332	1.176	-0.247	0.898	0.194	0.007	0.000	1.958	0.576	-1.618	2.215	0.584	1.203	0.268	0.000	0.939	1.033	1.264	3.102	0.829	0.886	0.985	1.265	0.751	1.032	0.948
-0	0.629	0.114	1.177	0.917	-1.204	0.845	0.828	-0.088	0.000	0.962	-1.302	0.823	2.215	0.732	0.358	-1.334	2.548	0.538	0.582	1.561	0.000	1.028	0.834	0.988	0.904	1.205	1.039	0.885
-1	1.754	-1.259	-0.573	0.959	-1.483	0.358	0.448	-1.452	0.000	0.711	0.313	0.499	2.215	1.482	-0.390	1.474	2.548	1.879	-1.540	0.668	0.000	0.843	0.825	1.313	1.315	0.939	1.048	0.871
-1	0.549	0.706	-1.437	0.894	0.891	0.680	-0.762	-1.568	0.000	0.981	0.499	-0.425	2.215	1.332	0.678	0.485	1.274	0.803	0.022	-0.893	0.000	0.793	1.043	0.987	0.761	0.899	0.915	0.794
-0	0.475	0.542	-0.987	1.569	0.069	0.551	1.543	-1.488	0.000	0.608	0.301	1.734	2.215	0.277	0.499	-0.522	0.000	1.375	1.212	0.696	3.102	0.652	0.756	0.987	0.828	0.830	0.715	0.679
-1	0.723	0.049	-1.153	1.300	0.083	0.723	-0.749	0.630	0.000	1.126	0.412	-0.384	0.000	1.272	1.256	1.358	2.548	3.108	0.777	-1.486	3.102	0.733	1.096	1.206	1.269	0.899	1.015	0.903
-1	1.062	0.296	0.725	0.285	-0.531	0.819	1.277	-0.667	0.000	0.687	0.829	-0.092	0.000	1.158	0.447	1.047	2.548	1.444	-0.186	-1.491	3.102	0.863	1.171	0.986	0.769	0.828	0.919	0.840
-0	0.572	-0.349	1.396	2.023	0.795	0.577	0.457	-0.533	0.000	1.351	0.701	-1.091	0.000	0.724	-1.012	-0.182	2.548	0.923	-0.012	0.789	3.102	0.936	1.025	0.985	1.002	0.600	0.828	0.909
-1	0.563	0.387	0.412	0.553	1.050	0.723	-0.992	-0.447	0.000	0.748	0.948	0.546	2.215	1.761	-0.559	-1.183	0.000	1.114	-0.251	1.192	3.102	0.936	0.912	0.976	0.578	0.722	0.829	0.892
-1	1.632	1.577	-0.697	0.708	-1.263	0.863	0.012	1.197	2.173	0.498	0.990	-0.806	0.000	0.627	2.387	-1.283	0.000	0.607	1.290	-0.174	3.102	0.916	1.328	0.986	0.557	0.971	0.935	0.836
-1	0.562	-0.360	0.399	0.803	-1.334	1.443	-0.116	1.628	2.173	0.750	0.987	0.135	1.107	0.795	0.298	-0.556	0.000	1.150	-0.113	-0.093	0.000	0.493	1.332	0.985	1.001	1.750	1.013	0.886
-1	0.987	0.706	-0.492	0.861	0.607	0.593	0.088	-0.184	0.000	0.802	0.894	1.608	2.215	0.782	-0.471	1.500	2.548	0.521	0.772	-0.960	0.000	0.658	0.893	1.068	0.877	0.664	0.709	0.661
-1	1.052	0.883	-0.581	1.566	0.860	0.931	1.515	-0.873	0.000	0.493	0.145	-0.672	0.000	1.133	0.935	1.581	2.548	1.630	0.695	0.923	3.102	1.105	1.087	1.713	0.948	0.590	0.872	0.883
-1	2.130	-0.516	-0.291	0.776	-1.230	0.689	-0.257	0.800	2.173	0.730	-0.274	-1.437	0.000	0.615	0.241	1.083	0.000	0.834	0.757	1.613	3.102	0.836	0.806	1.333	1.061	0.730	0.889	0.783
-1	0.742	0.797	1.628	0.311	-0.418	0.620	0.685	-1.457	0.000	0.683	1.774	-1.082	0.000	1.700	1.104	0.225	2.548	0.382	-2.184	-1.307	0.000	0.945	1.228	0.984	0.864	0.931	0.988	0.838
-0	0.311	-1.249	-0.927	1.272	-1.262	0.642	-1.228	-0.136	0.000	1.220	-0.804	-1.558	2.215	0.950	-0.828	0.495	1.274	2.149	-1.672	0.634	0.000	1.346	0.887	0.981	0.856	1.101	1.001	1.106
-0	0.660	-1.834	-0.667	0.601	1.236	0.932	-0.933	-0.135	2.173	1.373	-0.122	1.429	0.000	0.654	-0.034	-0.847	2.548	0.711	0.911	0.703	0.000	1.144	0.942	0.984	0.822	0.739	0.992	0.895
-0	3.609	-0.590	0.851	0.615	0.455	1.280	0.003	-0.866	1.087	1.334	0.708	-1.131	0.000	0.669	0.480	0.092	0.000	0.975	0.983	-1.429	3.102	1.301	1.089	0.987	1.476	0.934	1.469	1.352
-1	0.905	-0.403	1.567	2.651	0.953	1.194	-0.241	-0.567	1.087	0.308	-0.384	-0.007	0.000	0.608	-0.175	-1.163	2.548	0.379	0.941	1.662	0.000	0.580	0.721	1.126	0.895	0.544	1.097	0.836
-1	0.983	0.255	1.093	0.905	-0.874	0.863	0.060	-0.368	0.000	0.824	-0.747	-0.633	0.000	0.614	0.961	1.052	0.000	0.792	-0.260	1.632	3.102	0.874	0.883	1.280	0.663	0.406	0.592	0.645
-1	1.160	-1.027	0.274	0.460	0.322	2.085	-1.623	-0.840	0.000	1.634	-1.046	1.182	2.215	0.492	-0.367	1.174	0.000	0.824	-0.998	1.617	0.000	0.943	0.884	1.001	1.209	1.313	1.034	0.866
-0	0.299	0.028	-1.372	1.930	-0.661	0.840	-0.979	0.664	1.087	0.535	-2.041	1.434	0.000	1.087	-1.797	0.344	0.000	0.485	-0.560	-1.105	3.102	0.951	0.890	0.980	0.483	0.684	0.730	0.706
-0	0.293	1.737	-1.418	2.074	0.794	0.679	1.024	-1.457	0.000	1.034	1.094	-0.168	1.107	0.506	1.680	-0.661	0.000	0.523	-0.042	-1.274	3.102	0.820	0.944	0.987	0.842	0.694	0.761	0.750
-0	0.457	-0.393	1.560	0.738	-0.007	0.475	-0.230	0.246	0.000	0.776	-1.264	-0.606	2.215	0.865	-0.731	-1.576	2.548	1.153	0.343	1.436	0.000	1.060	0.883	0.988	0.972	0.703	0.758	0.720
-0	0.935	-0.582	0.240	2.401	0.818	1.231	-0.618	-1.289	0.000	0.799	0.544	-0.228	2.215	0.525	-1.494	-0.969	0.000	0.609	-1.123	1.168	3.102	0.871	0.767	1.035	1.154	0.919	0.868	1.006
-1	0.902	-0.745	-1.215	1.174	-0.501	1.215	0.167	1.162	0.000	0.896	1.217	-0.976	0.000	0.585	-0.429	1.036	0.000	1.431	-0.416	0.151	3.102	0.524	0.952	0.990	0.707	0.271	0.592	0.826
-1	0.653	0.337	-0.320	1.118	-0.934	1.050	0.745	0.529	1.087	1.075	1.742	-1.538	0.000	0.585	1.090	0.973	0.000	1.091	-0.187	1.160	1.551	1.006	1.108	0.978	1.121	0.838	0.947	0.908
-0	1.157	1.401	0.340	0.395	-1.218	0.945	1.928	-0.876	0.000	1.384	0.320	1.002	1.107	1.900	1.177	-0.462	2.548	1.122	1.316	1.720	0.000	1.167	1.096	0.989	0.937	1.879	1.307	1.041
-0	0.960	0.355	-0.152	0.872	-0.338	0.391	0.348	0.956	1.087	0.469	2.664	1.409	0.000	0.756	-1.561	1.500	0.000	0.525	1.436	1.728	3.102	1.032	0.946	0.996	0.929	0.470	0.698	0.898
-1	1.038	0.274	0.825	1.198	0.963	1.078	-0.496	-1.014	2.173	0.739	-0.727	-0.151	2.215	1.035	-0.799	0.398	0.000	1.333	-0.872	-1.498	0.000	0.849	1.033	0.985	0.886	0.936	0.975	0.823
-0	0.490	0.277	0.318	1.303	0.694	1.333	-1.620	-0.563	0.000	1.459	-1.326	1.140	0.000	0.779	-0.673	-1.324	2.548	0.860	-1.247	0.043	0.000	0.857	0.932	0.992	0.792	0.278	0.841	1.498
-0	1.648	-0.688	-1.386	2.790	0.995	1.087	1.359	-0.687	0.000	1.050	-0.223	-0.261	2.215	0.613	-0.889	1.335	0.000	1.204	0.827	0.309	3.102	0.464	0.973	2.493	1.737	0.827	1.319	1.062
-0	1.510	-0.662	1.668	0.860	0.280	0.705	0.974	-1.647	1.087	0.662	-0.393	-0.225	0.000	0.610	-0.996	0.532	2.548	0.464	1.305	0.102	0.000	0.859	1.057	1.498	0.799	1.260	0.946	0.863
-1	0.850	-1.185	-0.117	0.943	-0.449	1.142	0.875	-0.030	0.000	2.223	-0.461	1.627	2.215	0.767	-1.761	-1.692	0.000	1.012	-0.727	0.639	3.102	3.649	2.062	0.985	1.478	1.087	1.659	1.358
-0	0.933	1.259	0.130	0.326	-0.890	0.306	1.136	1.142	0.000	0.964	0.705	-1.373	2.215	0.546	-0.196	-0.001	0.000	0.578	-1.169	1.004	3.102	0.830	0.836	0.988	0.837	1.031	0.749	0.655
-0	0.471	0.697	1.570	1.109	0.201	1.248	0.348	-1.448	0.000	2.103	0.773	0.686	2.215	1.451	-0.087	-0.453	2.548	1.197	-0.045	-1.026	0.000	0.793	1.094	0.987	0.851	1.804	1.378	1.089
-1	2.446	-0.701	-1.568	0.059	0.822	1.401	-0.600	-0.044	2.173	0.324	-0.001	1.344	2.215	0.913	-0.818	1.049	0.000	0.442	-1.088	-0.005	0.000	0.611	1.062	0.979	0.562	0.988	0.998	0.806
-0	0.619	2.029	0.933	0.528	-0.903	0.974	0.760	-0.311	2.173	0.825	0.658	-1.466	1.107	0.894	1.594	0.370	0.000	0.882	-0.258	1.661	0.000	1.498	1.088	0.987	0.867	1.139	0.900	0.779
-1	0.674	-0.131	-0.362	0.518	-1.574	0.876	0.442	0.145	1.087	0.497	-1.526	-1.704	0.000	0.680	2.514	-1.374	0.000	0.792	-0.479	0.773	1.551	0.573	1.198	0.984	0.800	0.667	0.987	0.832
-1	1.447	1.145	-0.937	0.307	-1.458	0.478	1.264	0.816	1.087	0.558	1.015	-0.101	2.215	0.937	-0.190	1.177	0.000	0.699	0.954	-1.512	0.000	0.877	0.838	0.990	0.873	0.566	0.646	0.713
-1	0.976	0.308	-0.844	0.436	0.610	1.253	0.149	-1.585	2.173	1.415	0.568	0.096	2.215	0.953	-0.855	0.441	0.000	0.867	-0.650	1.643	0.000	0.890	1.234	0.988	0.796	2.002	1.179	0.977
-0	0.697	0.401	-0.718	0.920	0.735	0.958	-0.172	0.168	2.173	0.872	-0.097	-1.335	0.000	0.513	-1.192	-1.710	1.274	0.426	-1.637	1.368	0.000	0.997	1.227	1.072	0.800	1.013	0.786	0.749
-1	1.305	-2.157	1.740	0.661	-0.912	0.705	-0.516	0.759	2.173	0.989	-0.716	-0.300	2.215	0.627	-1.052	-1.736	0.000	0.467	-2.467	0.568	0.000	0.807	0.964	0.988	1.427	1.012	1.165	0.926
-0	1.847	1.663	-0.618	0.280	1.258	1.462	-0.054	1.371	0.000	0.900	0.309	-0.544	0.000	0.331	-2.149	-0.341	0.000	1.091	-0.833	0.710	3.102	1.496	0.931	0.989	1.549	0.115	1.140	1.150
-0	0.410	-0.323	1.069	2.160	0.010	0.892	0.942	-1.640	2.173	0.946	0.938	1.314	0.000	1.213	-1.099	-0.794	2.548	0.650	0.053	0.056	0.000	1.041	0.916	1.063	0.985	1.910	1.246	1.107
-1	0.576	1.092	-0.088	0.777	-1.579	0.757	0.271	0.109	0.000	0.819	0.827	-1.554	2.215	1.313	2.341	-1.568	0.000	2.827	0.239	-0.338	0.000	0.876	0.759	0.986	0.692	0.457	0.796	0.791
-1	0.537	0.925	-1.406	0.306	-0.050	0.906	1.051	0.037	0.000	1.469	-0.177	-1.320	2.215	1.872	0.723	1.158	0.000	1.313	0.227	-0.501	3.102	0.953	0.727	0.978	0.755	0.892	0.932	0.781
-0	0.716	-0.065	-0.484	1.313	-1.563	0.596	-0.242	0.678	2.173	0.426	-1.909	0.616	0.000	0.885	-0.406	-1.343	2.548	0.501	-1.327	-0.340	0.000	0.470	0.728	1.109	0.919	0.881	0.665	0.692
-1	0.624	-0.389	0.128	1.636	-1.110	1.025	0.573	-0.843	2.173	0.646	-0.697	1.064	0.000	0.632	-1.442	0.961	0.000	0.863	-0.106	1.717	0.000	0.825	0.917	1.257	0.983	0.713	0.890	0.824
-0	0.484	2.101	1.714	1.131	-0.823	0.750	0.583	-1.304	1.087	0.894	0.421	0.559	2.215	0.921	-0.063	0.282	0.000	0.463	-0.474	-1.387	0.000	0.742	0.886	0.995	0.993	1.201	0.806	0.754
-0	0.570	0.339	-1.478	0.528	0.439	0.978	1.479	-1.411	2.173	0.763	1.541	-0.734	0.000	1.375	0.840	0.903	0.000	0.965	1.599	0.364	0.000	0.887	1.061	0.992	1.322	1.453	1.013	0.969
-0	0.940	1.303	1.636	0.851	-1.732	0.803	-0.030	-0.177	0.000	0.480	-0.125	-0.954	0.000	0.944	0.709	0.296	2.548	1.342	-0.418	1.197	3.102	0.853	0.989	0.979	0.873	0.858	0.719	0.786
-1	0.599	0.544	-0.238	0.816	1.043	0.857	0.660	1.128	2.173	0.864	-0.624	-0.843	0.000	1.159	0.367	0.174	0.000	1.520	-0.543	-1.508	0.000	0.842	0.828	0.984	0.759	0.895	0.918	0.791
-1	1.651	1.897	-0.914	0.423	0.315	0.453	0.619	-1.607	2.173	0.532	-0.424	0.209	1.107	0.369	2.479	0.034	0.000	0.701	0.217	0.984	0.000	0.976	0.951	1.035	0.879	0.825	0.915	0.798
-1	0.926	-0.574	-0.763	0.285	1.094	0.672	2.314	1.545	0.000	1.124	0.415	0.809	0.000	1.387	0.270	-0.949	2.548	1.547	-0.631	-0.200	3.102	0.719	0.920	0.986	0.889	0.933	0.797	0.777
-0	0.677	1.698	-0.890	0.641	-0.449	0.607	1.754	1.720	0.000	0.776	0.372	0.782	2.215	0.511	1.491	-0.480	0.000	0.547	-0.341	0.853	3.102	0.919	1.026	0.997	0.696	0.242	0.694	0.687
-0	1.266	0.602	0.958	0.487	1.256	0.709	0.843	-1.196	0.000	0.893	1.303	-0.594	1.107	1.090	1.320	0.354	0.000	0.797	1.846	1.139	0.000	0.780	0.896	0.986	0.661	0.709	0.790	0.806
-1	0.628	-0.616	-0.329	0.764	-1.150	0.477	-0.715	1.187	2.173	1.250	0.607	1.026	2.215	0.983	-0.023	-0.583	0.000	0.377	1.344	-1.015	0.000	0.744	0.954	0.987	0.837	0.841	0.795	0.694
-1	1.035	-0.828	-1.358	1.870	-1.060	1.075	0.130	0.448	2.173	0.660	0.697	0.641	0.000	0.425	1.006	-1.035	0.000	0.751	1.055	1.364	3.102	0.826	0.822	0.988	0.967	0.901	1.077	0.906
-1	0.830	0.265	-0.150	0.660	1.105	0.592	-0.557	0.908	2.173	0.670	-1.419	-0.671	0.000	1.323	-0.409	1.644	2.548	0.850	-0.033	-0.615	0.000	0.760	0.967	0.984	0.895	0.681	0.747	0.770
-1	1.395	1.100	1.167	1.088	0.218	0.400	-0.132	0.024	2.173	0.743	0.530	-1.361	2.215	0.341	-0.691	-0.238	0.000	0.396	-1.426	-0.933	0.000	0.363	0.472	1.287	0.922	0.810	0.792	0.656
-1	1.070	1.875	-1.298	1.215	-0.106	0.767	0.795	0.514	1.087	0.401	2.780	1.276	0.000	0.686	1.127	1.721	2.548	0.391	-0.259	-1.167	0.000	1.278	1.113	1.389	0.852	0.824	0.838	0.785
-0	1.114	-0.071	1.719	0.399	-1.383	0.849	0.254	0.481	0.000	0.958	-0.579	0.742	0.000	1.190	-0.140	-0.862	2.548	0.479	1.390	0.856	0.000	0.952	0.988	0.985	0.764	0.419	0.835	0.827
-0	0.714	0.376	-0.568	1.578	-1.165	0.648	0.141	0.639	2.173	0.472	0.569	1.449	1.107	0.783	1.483	0.361	0.000	0.540	-0.790	0.032	0.000	0.883	0.811	0.982	0.775	0.572	0.760	0.745
-0	0.401	-1.731	0.765	0.974	1.648	0.652	-1.024	0.191	0.000	0.544	-0.366	-1.246	2.215	0.627	0.140	1.008	2.548	0.810	0.409	0.429	0.000	0.950	0.934	0.977	0.621	0.580	0.677	0.650
-1	0.391	1.679	-1.298	0.605	-0.832	0.549	1.338	0.522	2.173	1.244	0.884	1.070	0.000	1.002	0.846	-1.345	2.548	0.783	-2.464	-0.237	0.000	4.515	2.854	0.981	0.877	0.939	1.942	1.489
-1	0.513	-0.220	-0.444	1.699	0.479	1.109	0.181	-0.999	2.173	0.883	-0.335	-1.716	2.215	1.075	-0.380	1.352	0.000	0.857	0.048	0.147	0.000	0.937	0.758	0.986	1.206	0.958	0.949	0.876
-0	1.367	-0.388	0.798	1.158	1.078	0.811	-1.024	-1.628	0.000	1.504	0.097	-0.999	2.215	1.652	-0.860	0.054	2.548	0.573	-0.142	-1.401	0.000	0.869	0.833	1.006	1.412	1.641	1.214	1.041
-1	1.545	-0.533	-1.517	1.177	1.289	2.331	-0.370	-0.073	0.000	1.295	-0.358	-0.891	2.215	0.476	0.756	0.985	0.000	1.945	-0.016	-1.651	3.102	1.962	1.692	1.073	0.656	0.941	1.312	1.242
-0	0.858	0.978	-1.258	0.286	0.161	0.729	1.230	1.087	2.173	0.561	2.670	-0.109	0.000	0.407	2.346	0.938	0.000	1.078	0.729	-0.658	3.102	0.597	0.921	0.982	0.579	0.954	0.733	0.769
-1	1.454	-1.384	0.870	0.067	0.394	1.033	-0.673	0.318	0.000	1.166	-0.763	-1.533	2.215	2.848	-0.045	-0.856	2.548	0.697	-0.140	1.134	0.000	0.931	1.293	0.977	1.541	1.326	1.201	1.078
-1	0.559	-0.913	0.486	1.104	-0.321	1.073	-0.348	1.345	0.000	0.901	-0.827	-0.842	0.000	0.739	0.047	-0.415	2.548	0.433	-1.132	1.268	0.000	0.797	0.695	0.985	0.868	0.346	0.674	0.623
-1	1.333	0.780	-0.964	0.916	1.202	1.822	-0.071	0.742	2.173	1.486	-0.399	-0.824	0.000	0.740	0.568	-0.134	0.000	0.971	-0.070	-1.589	3.102	1.278	0.929	1.421	1.608	1.214	1.215	1.137
-1	2.417	0.631	-0.317	0.323	0.581	0.841	1.524	-1.738	0.000	0.543	1.176	-0.325	0.000	0.827	0.700	0.866	0.000	0.834	-0.262	-1.702	3.102	0.932	0.820	0.988	0.646	0.287	0.595	0.589
-0	0.955	-1.242	0.938	1.104	0.474	0.798	-0.743	1.535	0.000	1.356	-1.357	-1.080	2.215	1.320	-1.396	-0.132	2.548	0.728	-0.529	-0.633	0.000	0.832	0.841	0.988	0.923	1.077	0.988	0.816
-1	1.305	-1.918	0.391	1.161	0.063	0.724	2.593	1.481	0.000	0.592	-1.207	-0.329	0.000	0.886	-0.836	-1.168	2.548	1.067	-1.481	-1.440	0.000	0.916	0.688	0.991	0.969	0.550	0.665	0.638
-0	1.201	0.071	-1.123	2.242	-1.533	0.702	-0.256	0.688	0.000	0.967	0.491	1.040	2.215	1.271	-0.558	0.095	0.000	1.504	0.676	-0.383	3.102	0.917	1.006	0.985	1.017	1.057	0.928	1.057
-0	0.994	-1.607	1.596	0.774	-1.391	0.625	-0.134	-0.862	2.173	0.746	-0.765	-0.316	2.215	1.131	-0.320	0.869	0.000	0.607	0.826	0.301	0.000	0.798	0.967	0.999	0.880	0.581	0.712	0.774
-1	0.482	-0.467	0.729	1.419	1.458	0.824	0.376	-0.242	0.000	1.368	0.023	1.459	2.215	0.826	0.669	-1.079	2.548	0.936	2.215	-0.309	0.000	1.883	1.216	0.997	1.065	0.946	1.224	1.526
-1	0.383	1.588	1.611	0.748	1.194	0.866	-0.279	-0.636	0.000	0.707	0.536	0.801	2.215	1.647	-1.155	0.367	0.000	1.292	0.303	-1.681	3.102	2.016	1.581	0.986	0.584	0.684	1.107	0.958
-0	0.629	0.203	0.736	0.671	-0.271	1.350	-0.486	0.761	2.173	0.496	-0.805	-1.718	0.000	2.393	0.044	-1.046	1.274	0.651	-0.116	-0.541	0.000	0.697	1.006	0.987	1.069	2.317	1.152	0.902
-0	0.905	-0.564	-0.570	0.263	1.096	1.219	-1.397	-1.414	1.087	1.164	-0.533	-0.208	0.000	1.459	1.965	0.784	0.000	2.220	-1.421	0.452	0.000	0.918	1.360	0.993	0.904	0.389	2.118	1.707
-1	1.676	1.804	1.171	0.529	1.175	1.664	0.354	-0.530	0.000	1.004	0.691	-1.280	2.215	0.838	0.373	0.626	2.548	1.094	1.774	0.501	0.000	0.806	1.100	0.991	0.769	0.976	0.807	0.740
-1	1.364	-1.936	0.020	1.327	0.428	1.021	-1.665	-0.907	2.173	0.818	-2.701	1.303	0.000	0.716	-0.590	-1.629	2.548	0.895	-2.280	-1.602	0.000	1.211	0.849	0.989	1.320	0.864	1.065	0.949
-0	0.629	-0.626	0.609	1.828	1.280	0.644	-0.856	-0.873	2.173	0.555	1.066	-0.640	0.000	0.477	-1.364	-1.021	2.548	1.017	0.036	0.380	0.000	0.947	0.941	0.994	1.128	0.241	0.793	0.815
-1	1.152	-0.843	0.926	1.802	0.800	2.493	-1.449	-1.127	0.000	1.737	0.833	0.488	0.000	1.026	0.929	-0.990	2.548	1.408	0.689	1.142	3.102	1.171	0.956	0.993	2.009	0.867	1.499	1.474
-0	2.204	0.081	0.008	1.021	-0.679	2.676	0.090	1.163	0.000	2.210	-1.686	-1.195	0.000	1.805	0.891	-0.148	2.548	0.450	-0.502	-1.295	3.102	6.959	3.492	1.205	0.908	0.845	2.690	2.183
-1	0.957	0.954	1.702	0.043	-0.503	1.113	0.033	-0.308	0.000	0.757	-0.363	-1.129	2.215	1.635	0.068	1.048	1.274	0.415	-2.098	0.061	0.000	1.010	0.979	0.992	0.704	1.125	0.761	0.715
-0	1.222	0.418	1.059	1.303	1.442	0.282	-1.499	-1.286	0.000	1.567	0.016	-0.164	2.215	0.451	2.229	-1.229	0.000	0.660	-0.513	-0.296	3.102	2.284	1.340	0.985	1.531	0.314	1.032	1.094
-1	0.603	1.675	-0.973	0.703	-1.709	1.023	0.652	1.296	2.173	1.078	0.363	-0.263	0.000	0.734	-0.457	-0.745	1.274	0.561	1.434	-0.042	0.000	0.888	0.771	0.984	0.847	1.234	0.874	0.777
-0	0.897	0.949	-0.848	1.115	-0.085	0.522	-1.267	-1.418	0.000	0.684	-0.599	1.474	0.000	1.176	0.922	0.641	2.548	0.470	0.103	0.148	3.102	0.775	0.697	0.984	0.839	0.358	0.847	1.008
-1	0.987	1.013	-1.504	0.468	-0.259	1.160	0.476	-0.971	2.173	1.266	0.919	0.780	0.000	0.634	1.695	0.233	0.000	0.487	-0.082	0.719	3.102	0.921	0.641	0.991	0.730	0.828	0.952	0.807
-1	0.847	1.581	-1.397	1.629	1.529	1.053	0.816	-0.344	2.173	0.895	0.779	0.332	0.000	0.750	1.311	0.419	2.548	1.604	0.844	1.367	0.000	1.265	0.798	0.989	1.328	0.783	0.930	0.879
-1	0.805	1.416	-1.327	0.397	0.589	0.488	0.982	0.843	0.000	0.664	-0.999	0.129	0.000	0.624	0.613	-0.558	0.000	1.431	-0.667	-1.561	3.102	0.959	1.103	0.989	0.590	0.632	0.926	0.798
-0	1.220	-0.313	-0.489	1.759	0.201	1.698	-0.220	0.241	2.173	1.294	1.390	-1.682	0.000	1.447	-1.623	-1.296	0.000	1.710	0.872	-1.356	3.102	1.198	0.981	1.184	0.859	2.165	1.807	1.661
-0	0.772	-0.611	-0.549	0.465	-1.528	1.103	-0.140	0.001	2.173	0.854	-0.406	1.655	0.000	0.733	-1.250	1.072	0.000	0.883	0.627	-1.132	3.102	0.856	0.927	0.987	1.094	1.013	0.938	0.870
-1	1.910	0.771	0.828	0.231	1.267	1.398	1.455	-0.295	2.173	0.837	-2.564	0.770	0.000	0.540	2.189	1.287	0.000	1.345	1.311	-1.151	0.000	0.861	0.869	0.984	1.359	1.562	1.105	0.963
-1	0.295	0.832	1.399	1.222	-0.517	2.480	0.013	1.591	0.000	2.289	0.436	0.287	2.215	1.995	-0.367	-0.409	1.274	0.375	1.367	-1.716	0.000	1.356	2.171	0.990	1.467	1.664	1.855	1.705
-1	1.228	0.339	-0.575	0.417	1.474	0.480	-1.416	-1.498	2.173	0.614	-0.933	-0.961	0.000	1.189	1.690	1.003	0.000	1.690	-1.065	0.106	3.102	0.963	1.147	0.987	1.086	0.948	0.930	0.866
-0	2.877	-1.014	1.440	0.782	0.483	1.134	-0.735	-0.196	2.173	1.123	0.084	-0.596	0.000	1.796	-0.356	1.044	2.548	1.406	1.582	-0.991	0.000	0.939	1.178	1.576	0.996	1.629	1.216	1.280
-1	2.178	0.259	1.107	0.256	1.222	0.979	-0.440	-0.538	1.087	0.496	-0.760	-0.049	0.000	1.471	1.683	-1.486	0.000	0.646	0.695	-1.577	3.102	1.093	1.070	0.984	0.608	0.889	0.962	0.866
-1	0.604	0.592	1.295	0.964	0.348	1.178	-0.016	0.832	2.173	1.626	-0.420	-0.760	0.000	0.748	0.461	-0.906	0.000	0.728	0.309	-1.269	1.551	0.852	0.604	0.989	0.678	0.949	1.021	0.878
-0	0.428	-1.352	-0.912	1.713	0.797	1.894	-1.452	0.191	2.173	2.378	2.113	-1.190	0.000	0.860	2.174	0.949	0.000	1.693	0.759	1.426	3.102	0.885	1.527	1.186	1.090	3.294	4.492	3.676
-0	0.473	0.485	0.154	1.433	-1.504	0.766	1.257	-1.302	2.173	0.414	0.119	0.238	0.000	0.805	0.242	-0.691	2.548	0.734	0.749	0.753	0.000	0.430	0.893	1.137	0.686	0.724	0.618	0.608
-1	0.763	-0.601	0.876	0.182	-1.678	0.818	0.599	0.481	2.173	0.658	-0.737	-0.553	0.000	0.857	-1.138	-1.435	0.000	1.540	-1.466	-0.447	0.000	0.870	0.566	0.989	0.728	0.658	0.821	0.726
-0	0.619	-0.273	-0.143	0.992	-1.267	0.566	0.876	-1.396	2.173	0.515	0.892	0.618	0.000	0.434	-0.902	0.862	2.548	0.490	-0.539	0.549	0.000	0.568	0.794	0.984	0.667	0.867	0.597	0.578
-0	0.793	0.970	0.324	0.570	0.816	0.761	-0.550	1.519	2.173	1.150	0.496	-0.447	0.000	0.925	0.724	1.008	1.274	1.135	-0.275	-0.843	0.000	0.829	1.068	0.978	1.603	0.892	1.041	1.059
-1	0.480	0.364	-0.067	1.906	-1.582	1.397	1.159	0.140	0.000	0.639	0.398	-1.102	0.000	1.597	-0.668	1.607	2.548	1.306	-0.797	0.288	3.102	0.856	1.259	1.297	1.022	1.032	1.049	0.939
-0	0.514	1.304	1.490	1.741	-0.220	0.648	0.155	0.535	0.000	0.562	-1.016	0.837	0.000	0.863	-0.780	-0.815	2.548	1.688	-0.130	-1.545	3.102	0.887	0.980	1.309	1.269	0.654	1.044	1.035
-0	1.225	0.333	0.656	0.893	0.859	1.037	-0.876	1.603	1.087	1.769	0.272	-0.227	2.215	1.000	0.579	-1.690	0.000	1.385	0.471	-0.860	0.000	0.884	1.207	0.995	1.097	2.336	1.282	1.145
-0	2.044	-1.472	-0.294	0.392	0.369	0.927	0.718	1.492	1.087	1.619	-0.736	0.047	2.215	1.884	-0.101	-1.540	0.000	0.548	-0.441	1.117	0.000	0.798	0.877	0.981	0.750	2.272	1.469	1.276
-0	1.037	-0.276	0.735	3.526	1.156	2.498	0.401	-0.590	1.087	0.714	-1.203	1.393	2.215	0.681	0.629	1.534	0.000	0.719	-0.355	-0.706	0.000	0.831	0.857	0.988	2.864	2.633	1.988	1.466
-1	0.651	-1.218	-0.791	0.770	-1.449	0.610	-0.535	0.960	2.173	0.380	-1.072	-0.031	2.215	0.415	2.123	-1.100	0.000	0.776	0.217	0.420	0.000	0.986	1.008	1.001	0.853	0.588	0.799	0.776
-0	1.586	-0.409	0.085	3.258	0.405	1.647	-0.674	-1.519	0.000	0.640	-1.027	-1.681	0.000	1.452	-0.444	-0.957	2.548	0.927	-0.017	1.215	3.102	0.519	0.866	0.992	0.881	0.847	1.018	1.278
-0	0.712	0.092	-0.466	0.688	1.236	0.921	-1.217	-1.022	2.173	2.236	-1.167	0.868	2.215	0.851	-1.892	-0.753	0.000	0.475	-1.216	-0.383	0.000	0.668	0.758	0.988	1.180	2.093	1.157	0.934
-0	0.419	0.471	0.974	2.805	0.235	1.473	-0.198	1.255	1.087	0.931	1.083	-0.712	0.000	1.569	1.358	-1.179	2.548	2.506	0.199	-0.842	0.000	0.929	0.991	0.992	1.732	2.367	1.549	1.430
-1	0.667	1.003	1.504	0.368	1.061	0.885	-0.318	-0.353	0.000	1.438	-1.939	0.710	0.000	1.851	0.277	-1.460	2.548	1.403	0.517	-0.157	0.000	0.883	1.019	1.000	0.790	0.859	0.938	0.841
-1	1.877	-0.492	0.372	0.441	0.955	1.034	-1.220	-0.846	1.087	0.952	-0.320	1.125	0.000	0.542	0.308	-1.261	2.548	1.018	-1.415	-1.547	0.000	1.280	0.932	0.991	1.273	0.878	0.921	0.906
-0	1.052	0.901	1.176	1.280	1.517	0.562	-1.150	-0.079	2.173	1.228	-0.308	-0.354	0.000	0.790	-1.492	-0.963	0.000	0.942	-0.672	-1.588	3.102	1.116	0.902	0.988	1.993	0.765	1.375	1.325
-1	0.518	-0.254	1.642	0.865	0.725	0.980	0.734	0.023	0.000	1.448	0.780	-1.736	2.215	0.955	0.513	-0.519	0.000	0.365	-0.444	-0.243	3.102	0.833	0.555	0.984	0.827	0.795	0.890	0.786
-0	0.870	0.815	-0.506	0.663	-0.518	0.935	0.289	-1.675	2.173	1.188	0.005	0.635	0.000	0.580	0.066	-1.455	2.548	0.580	-0.634	-0.199	0.000	0.852	0.788	0.979	1.283	0.208	0.856	0.950
-0	0.628	1.382	0.135	0.683	0.571	1.097	0.564	-0.950	2.173	0.617	-0.326	0.371	0.000	1.093	0.918	1.667	2.548	0.460	1.221	0.708	0.000	0.743	0.861	0.975	1.067	1.007	0.843	0.762
-0	4.357	0.816	-1.609	1.845	-1.288	3.292	0.726	0.324	2.173	1.528	0.583	-0.801	2.215	0.605	0.572	1.406	0.000	0.794	-0.791	0.122	0.000	0.967	1.132	1.124	3.602	2.811	2.460	1.861
-0	0.677	-1.265	1.559	0.866	-0.618	0.823	0.260	0.185	0.000	1.133	0.337	1.589	2.215	0.563	-0.830	0.510	0.000	0.777	0.117	-0.941	3.102	0.839	0.763	0.986	1.182	0.649	0.796	0.851
-0	2.466	-1.838	-1.648	1.717	1.533	1.676	-1.553	-0.109	2.173	0.670	-0.666	0.284	0.000	0.334	-2.480	0.316	0.000	0.366	-0.804	-1.298	3.102	0.875	0.894	0.997	0.548	0.770	1.302	1.079
-1	1.403	0.129	-1.307	0.688	0.306	0.579	0.753	0.814	1.087	0.474	0.694	-1.400	0.000	0.520	1.995	0.185	0.000	0.929	-0.504	1.270	3.102	0.972	0.998	1.353	0.948	0.650	0.688	0.724
-1	0.351	1.188	-0.360	0.254	-0.346	1.129	0.545	1.691	0.000	0.652	-0.039	-0.258	2.215	1.089	0.655	0.472	2.548	0.554	-0.493	1.366	0.000	0.808	1.045	0.992	0.570	0.649	0.809	0.744
-0	1.875	-0.013	-0.128	0.236	1.163	0.902	0.426	0.590	2.173	1.251	-1.210	-0.616	0.000	1.035	1.534	0.912	0.000	1.944	1.789	-1.691	0.000	0.974	1.113	0.990	0.925	1.120	0.956	0.912
-0	0.298	0.750	-0.507	1.555	1.463	0.804	1.200	-0.665	0.000	0.439	-0.829	-0.252	1.107	0.770	-1.090	0.947	2.548	1.165	-0.166	-0.763	0.000	1.140	0.997	0.988	1.330	0.555	1.005	1.012
-0	0.647	0.342	0.245	4.340	-0.157	2.229	0.068	1.170	2.173	2.133	-0.201	-1.441	0.000	1.467	0.697	-0.532	1.274	1.457	0.583	-1.640	0.000	0.875	1.417	0.976	2.512	2.390	1.794	1.665
-1	1.731	-0.803	-1.013	1.492	-0.020	1.646	-0.541	1.121	2.173	0.459	-1.251	-1.495	2.215	0.605	-1.711	-0.232	0.000	0.658	0.634	-0.068	0.000	1.214	0.886	1.738	1.833	1.024	1.192	1.034
-0	0.515	1.416	-1.089	1.697	1.426	1.414	0.941	0.027	0.000	1.480	0.133	-1.595	2.215	1.110	0.752	0.760	2.548	1.062	0.697	-0.492	0.000	0.851	0.955	0.994	1.105	1.255	1.175	1.095
-0	1.261	0.858	1.465	0.757	0.305	2.310	0.679	1.080	2.173	1.544	2.518	-0.464	0.000	2.326	0.270	-0.841	0.000	2.163	0.839	-0.500	3.102	0.715	0.825	1.170	0.980	2.371	1.527	1.221
-1	1.445	1.509	1.471	0.414	-1.285	0.767	0.864	-0.677	2.173	0.524	1.388	0.171	0.000	0.826	0.190	0.121	2.548	0.572	1.691	-1.603	0.000	0.870	0.935	0.994	0.968	0.735	0.783	0.777
-1	0.919	-0.264	-1.245	0.681	-1.722	1.022	1.010	0.097	2.173	0.685	0.403	-1.351	0.000	1.357	-0.429	1.262	1.274	0.687	1.021	-0.563	0.000	0.953	0.796	0.991	0.873	1.749	1.056	0.917
-1	0.293	-2.258	-1.427	1.191	1.202	0.394	-2.030	1.438	0.000	0.723	0.596	-0.024	2.215	0.525	-1.678	-0.290	0.000	0.788	-0.824	-1.029	3.102	0.821	0.626	0.976	1.080	0.810	0.842	0.771
-0	3.286	0.386	1.688	1.619	-1.620	1.392	-0.009	0.280	0.000	1.179	-0.776	-0.110	2.215	1.256	0.248	-1.114	2.548	0.777	0.825	-0.156	0.000	1.026	1.065	0.964	0.909	1.249	1.384	1.395
-1	1.075	0.603	0.561	0.656	-0.685	0.985	0.175	0.979	2.173	1.154	0.584	-0.886	0.000	1.084	-0.354	-1.004	2.548	0.865	1.224	1.269	0.000	1.346	1.073	1.048	0.873	1.310	1.003	0.865
-1	1.098	-0.091	1.466	1.558	0.915	0.649	1.314	-1.182	2.173	0.791	0.073	0.351	0.000	0.517	0.940	1.195	0.000	1.150	1.187	-0.692	3.102	0.866	0.822	0.980	1.311	0.394	1.119	0.890
-1	0.481	-1.042	0.148	1.135	-1.249	1.202	-0.344	0.308	1.087	0.779	-1.431	1.581	0.000	0.860	-0.860	-1.125	0.000	0.785	0.303	1.199	3.102	0.878	0.853	0.988	1.072	0.827	0.936	0.815
-0	1.348	0.497	0.318	0.806	0.976	1.393	-0.152	0.632	2.173	2.130	0.515	-1.054	0.000	0.908	0.062	-0.780	0.000	1.185	0.687	1.668	1.551	0.720	0.898	0.985	0.683	1.292	1.320	1.131
-0	2.677	-0.420	-1.685	1.828	1.433	2.040	-0.718	-0.039	0.000	0.400	-0.873	0.472	0.000	0.444	0.340	-0.830	2.548	0.431	0.768	-1.417	3.102	0.869	0.917	0.996	0.707	0.193	0.728	1.154
-1	1.300	0.586	-0.122	1.306	0.609	0.727	-0.556	-1.652	2.173	0.636	0.720	1.393	2.215	0.328	1.280	-0.390	0.000	0.386	0.752	-0.905	0.000	0.202	0.751	1.106	0.864	0.799	0.928	0.717
-0	0.637	-0.176	1.737	1.322	-0.414	0.702	-0.964	-0.680	0.000	1.054	-0.461	0.889	2.215	0.861	-0.267	0.225	0.000	1.910	-1.888	1.027	0.000	0.919	0.899	1.186	0.993	1.109	0.862	0.775
-1	0.723	-0.104	1.572	0.428	-0.840	0.655	0.544	1.401	2.173	1.522	-0.154	-0.452	2.215	0.996	0.190	0.273	0.000	1.906	-0.176	0.966	0.000	0.945	0.894	0.990	0.981	1.555	0.988	0.893
-0	2.016	-0.570	1.612	0.798	0.441	0.334	0.191	-0.909	0.000	0.939	0.146	0.021	2.215	0.553	-0.444	1.156	2.548	0.781	-1.545	-0.520	0.000	0.922	0.956	1.528	0.722	0.699	0.778	0.901
-0	1.352	-0.707	1.284	0.665	0.580	0.694	-1.040	-0.899	2.173	0.692	-2.048	0.029	0.000	0.545	-2.042	1.259	0.000	0.661	-0.808	-1.251	3.102	0.845	0.991	0.979	0.662	0.225	0.685	0.769
-1	1.057	-1.561	-0.411	0.952	-0.681	1.236	-1.107	1.045	2.173	1.288	-2.521	-0.521	0.000	1.361	-1.239	1.546	0.000	0.373	-1.540	0.028	0.000	0.794	0.782	0.987	0.889	0.832	0.972	0.828
-0	1.118	-0.017	-1.227	1.077	1.256	0.714	0.624	-0.811	0.000	0.800	0.704	0.387	1.107	0.604	0.234	0.986	0.000	1.306	-0.456	0.094	3.102	0.828	0.984	1.195	0.987	0.672	0.774	0.748
-1	0.602	2.201	0.212	0.119	0.182	0.474	2.130	1.270	0.000	0.370	2.088	-0.573	0.000	0.780	-0.725	-1.033	0.000	1.642	0.598	0.303	3.102	0.886	0.988	0.985	0.644	0.756	0.651	0.599
-0	1.677	-0.844	1.581	0.585	0.887	1.012	-2.315	0.752	0.000	1.077	0.748	-0.195	0.000	0.718	0.832	-1.337	1.274	1.181	-0.557	-1.006	3.102	1.018	1.247	0.988	0.908	0.651	1.311	1.120
-1	1.695	0.259	1.224	1.344	1.067	0.718	-1.752	-0.215	0.000	0.473	0.991	-0.993	0.000	0.891	1.285	-1.500	2.548	0.908	-0.131	0.288	0.000	0.945	0.824	0.979	1.009	0.951	0.934	0.833
-0	0.793	0.628	0.432	1.707	0.302	0.919	1.045	-0.784	0.000	1.472	0.175	-1.284	2.215	1.569	0.155	0.971	2.548	0.435	0.735	1.625	0.000	0.801	0.907	0.992	0.831	1.446	1.082	1.051
-1	0.537	-0.664	-0.244	1.104	1.272	1.154	0.394	1.633	0.000	1.527	0.963	0.559	2.215	1.744	0.650	-0.912	0.000	1.097	0.730	-0.368	3.102	1.953	1.319	1.045	1.309	0.869	1.196	1.126
-1	0.585	-1.469	1.005	0.749	-1.060	1.224	-0.717	-0.323	2.173	1.012	-0.201	1.268	0.000	0.359	-0.567	0.476	0.000	1.117	-1.124	1.557	3.102	0.636	1.281	0.986	0.616	1.289	0.890	0.881
-1	0.354	-1.517	0.667	2.534	-1.298	1.020	-0.375	1.254	0.000	1.119	-0.060	-1.538	2.215	1.059	-0.395	-0.140	0.000	2.609	0.199	-0.778	1.551	0.957	0.975	1.286	1.666	1.003	1.224	1.135
-1	0.691	-1.619	-1.380	0.361	1.727	1.493	-1.093	-0.289	0.000	1.447	-0.640	1.341	0.000	1.453	-0.617	-1.456	1.274	1.061	-1.481	-0.091	0.000	0.744	0.649	0.987	0.596	0.727	0.856	0.797
-0	1.336	1.293	-1.359	0.357	0.067	1.110	-0.058	-0.515	0.000	0.976	1.498	1.207	0.000	1.133	0.437	1.053	2.548	0.543	1.374	0.171	0.000	0.764	0.761	0.984	0.827	0.553	0.607	0.612
-0	0.417	-1.111	1.661	2.209	-0.683	1.931	-0.642	0.959	1.087	1.514	-2.032	-0.686	0.000	1.521	-0.539	1.344	0.000	0.978	-0.866	0.363	1.551	2.813	1.850	1.140	1.854	0.799	1.600	1.556
-0	1.058	0.390	-0.591	0.134	1.149	0.346	-1.550	0.186	0.000	1.108	-0.999	0.843	1.107	1.124	0.415	-1.514	0.000	1.067	-0.426	-1.000	3.102	1.744	1.050	0.985	1.006	1.010	0.883	0.789
-1	1.655	0.253	1.216	0.270	1.703	0.500	-0.006	-1.418	2.173	0.690	-0.350	0.170	2.215	1.045	-0.924	-0.774	0.000	0.996	-0.745	-0.123	0.000	0.839	0.820	0.993	0.921	0.869	0.725	0.708
-0	1.603	-0.850	0.564	0.829	0.093	1.270	-1.113	-1.155	2.173	0.853	-1.021	1.248	2.215	0.617	-1.270	1.733	0.000	0.935	-0.092	0.136	0.000	1.011	1.074	0.977	0.823	1.269	1.054	0.878
-0	1.568	-0.792	1.005	0.545	0.896	0.895	-1.698	-0.988	0.000	0.608	-1.634	1.705	0.000	0.826	0.208	0.618	1.274	2.063	-1.743	-0.520	0.000	0.939	0.986	0.990	0.600	0.435	1.033	1.087
-0	0.489	-1.335	-1.102	1.738	1.028	0.628	-0.992	-0.627	0.000	0.652	-0.064	-0.215	0.000	1.072	0.173	-1.251	2.548	1.042	0.057	0.841	3.102	0.823	0.895	1.200	1.164	0.770	0.837	0.846
-1	1.876	0.870	1.234	0.556	-1.262	1.764	0.855	-0.467	2.173	1.079	1.351	0.852	0.000	0.773	0.383	0.874	0.000	1.292	0.829	-1.228	3.102	0.707	0.969	1.102	1.601	1.017	1.112	1.028
-0	1.033	0.407	-0.374	0.705	-1.254	0.690	-0.231	1.502	2.173	0.433	-2.009	-0.057	0.000	0.861	1.151	0.334	0.000	0.960	-0.839	1.299	3.102	2.411	1.480	0.982	0.995	0.377	1.012	0.994
-0	1.092	0.653	-0.801	0.463	0.426	0.529	-1.055	0.040	0.000	0.663	0.999	1.255	1.107	0.749	-1.106	1.185	2.548	0.841	-0.745	-1.029	0.000	0.841	0.743	0.988	0.750	1.028	0.831	0.868
-1	0.799	-0.285	-0.011	0.531	1.392	1.063	0.854	0.494	2.173	1.187	-1.065	-0.851	0.000	0.429	-0.296	1.072	0.000	0.942	-1.985	1.172	0.000	0.873	0.693	0.992	0.819	0.689	1.131	0.913
-0	0.503	1.973	-0.377	1.515	-1.514	0.708	1.081	-0.313	2.173	1.110	-0.417	0.839	0.000	0.712	-1.153	1.165	0.000	0.675	-0.303	-0.930	1.551	0.709	0.761	1.032	0.986	0.698	0.963	1.291
-0	0.690	-0.574	-1.608	1.182	1.118	0.557	-2.243	0.144	0.000	0.969	0.216	-1.383	1.107	1.054	0.888	-0.709	2.548	0.566	1.663	-0.550	0.000	0.752	1.528	0.987	1.408	0.740	1.290	1.123
-1	0.890	1.501	0.786	0.779	-0.615	1.126	0.716	1.541	2.173	0.887	0.728	-0.673	2.215	1.216	0.332	-0.020	0.000	0.965	1.828	0.101	0.000	0.827	0.715	1.099	1.088	1.339	0.924	0.878
-0	0.566	0.883	0.655	1.600	0.034	1.155	2.028	-1.499	0.000	0.723	-0.871	0.763	0.000	1.286	-0.696	-0.676	2.548	1.134	-0.113	1.207	3.102	4.366	2.493	0.984	0.960	0.962	1.843	1.511
-0	1.146	1.086	-0.911	0.838	1.298	0.821	0.127	-0.145	0.000	1.352	0.474	-1.580	2.215	1.619	-0.081	0.675	2.548	1.382	-0.748	0.127	0.000	0.958	0.976	1.239	0.876	1.481	1.116	1.076
-0	1.739	-0.326	-1.661	0.420	-1.705	1.193	-0.031	-1.212	2.173	1.783	-0.442	0.522	0.000	1.064	-0.692	0.027	0.000	1.314	0.359	-0.037	3.102	0.968	0.897	0.986	0.907	1.196	1.175	1.112
-1	0.669	0.194	-0.703	0.657	-0.260	0.899	-2.511	0.311	0.000	1.482	0.773	0.974	2.215	3.459	0.037	-1.299	1.274	2.113	0.067	1.516	0.000	0.740	0.871	0.979	1.361	2.330	1.322	1.046
-1	1.355	-1.033	-1.173	0.552	-0.048	0.899	-0.482	-1.287	2.173	1.422	-1.227	0.390	1.107	1.937	-0.028	0.914	0.000	0.849	-0.230	-1.734	0.000	0.986	1.224	1.017	1.051	1.788	1.150	1.009
-1	0.511	-0.202	1.029	0.780	1.154	0.816	0.532	-0.731	0.000	0.757	0.517	0.749	2.215	1.302	0.289	-1.188	0.000	0.584	1.211	-0.350	0.000	0.876	0.943	0.995	0.963	0.256	0.808	0.891
-1	1.109	0.572	1.484	0.753	1.543	1.711	-0.145	-0.746	1.087	1.759	0.631	0.845	2.215	0.945	0.542	0.003	0.000	0.378	-1.150	-0.044	0.000	0.764	1.042	0.992	1.045	2.736	1.441	1.140
-0	0.712	-0.025	0.553	0.928	-0.711	1.304	0.045	-0.300	0.000	0.477	0.720	0.969	0.000	1.727	-0.474	1.328	1.274	1.282	2.222	1.684	0.000	0.819	0.765	1.023	0.961	0.657	0.799	0.744
-1	1.131	-0.302	1.079	0.901	0.236	0.904	-0.249	1.694	2.173	1.507	-0.702	-1.128	0.000	0.774	0.565	0.284	2.548	1.802	1.446	-0.192	0.000	3.720	2.108	0.986	0.930	1.101	1.484	1.238
-0	1.392	1.253	0.118	0.864	-1.358	0.922	-0.447	-1.243	1.087	1.969	1.031	0.774	2.215	1.333	-0.359	-0.681	0.000	1.099	-0.257	1.473	0.000	1.246	0.909	1.475	1.234	2.531	1.449	1.306
-0	1.374	2.291	-0.479	1.339	-0.243	0.687	2.345	1.310	0.000	0.467	1.081	0.772	0.000	0.656	1.155	-1.636	2.548	0.592	0.536	-1.269	3.102	0.981	0.821	1.010	0.877	0.217	0.638	0.758
-1	0.401	-1.516	0.909	2.738	0.519	0.887	0.566	-1.202	0.000	0.909	-0.176	1.682	0.000	2.149	-0.878	-0.514	2.548	0.929	-0.563	-1.555	3.102	1.228	0.803	0.980	1.382	0.884	1.025	1.172
-1	0.430	-1.589	1.417	2.158	1.226	1.180	-0.829	-0.781	2.173	0.798	1.400	-0.111	0.000	0.939	-0.878	1.076	2.548	0.576	1.335	-0.826	0.000	0.861	0.970	0.982	1.489	1.308	1.015	0.992
-1	1.943	-0.391	-0.840	0.621	-1.613	2.026	1.734	1.025	0.000	0.930	0.573	-0.912	0.000	1.326	0.847	-0.220	1.274	1.181	0.079	0.709	3.102	1.164	1.007	0.987	1.094	0.821	0.857	0.786
-1	0.499	0.436	0.887	0.859	1.509	0.733	-0.559	1.111	1.087	1.011	-0.796	0.279	2.215	1.472	-0.510	-0.982	0.000	1.952	0.379	-0.733	0.000	1.076	1.358	0.991	0.589	0.879	1.068	0.922
-0	0.998	-0.407	-1.711	0.139	0.652	0.810	-0.331	-0.721	0.000	0.471	-0.533	0.442	0.000	0.531	-1.405	0.120	2.548	0.707	0.098	-1.176	1.551	1.145	0.809	0.988	0.529	0.612	0.562	0.609
-1	1.482	0.872	0.638	1.288	0.362	0.856	0.900	-0.511	1.087	1.072	1.061	-1.432	2.215	1.770	-2.292	-1.547	0.000	1.131	1.374	0.783	0.000	6.316	4.381	1.002	1.317	1.048	2.903	2.351
-1	2.084	-0.422	1.289	1.125	0.735	1.104	-0.518	-0.326	2.173	0.413	-0.719	-0.699	0.000	0.857	0.108	-1.631	0.000	0.527	0.641	-1.362	3.102	0.791	0.952	1.016	0.776	0.856	0.987	0.836
-0	0.464	0.674	0.025	0.430	-1.703	0.982	-1.311	-0.808	2.173	1.875	1.060	0.821	2.215	0.954	-0.480	-1.677	0.000	0.567	0.702	-0.939	0.000	0.781	1.076	0.989	1.256	3.632	1.652	1.252
-1	0.457	-1.944	-1.010	1.409	0.931	1.098	-0.742	-0.415	0.000	1.537	-0.834	0.945	2.215	1.752	-0.287	-1.269	2.548	0.692	-1.537	-0.223	0.000	0.801	1.192	1.094	1.006	1.659	1.175	1.122
-0	3.260	-0.943	1.737	0.920	1.309	0.946	-0.139	-0.271	2.173	0.994	-0.952	-0.311	0.000	0.563	-0.136	-0.881	0.000	1.236	-0.507	0.906	1.551	0.747	0.869	0.985	1.769	1.034	1.179	1.042
-0	0.615	-0.778	0.246	1.861	1.619	0.560	-0.943	-0.204	2.173	0.550	-0.759	-1.342	2.215	0.578	0.076	-0.973	0.000	0.939	0.035	0.680	0.000	0.810	0.747	1.401	0.772	0.702	0.719	0.662
-1	2.370	-0.064	-0.237	1.737	0.154	2.319	-1.838	-1.673	0.000	1.053	-1.305	-0.075	0.000	0.925	0.149	0.318	1.274	0.851	-0.922	0.981	3.102	0.919	0.940	0.989	0.612	0.598	1.219	1.626
-1	1.486	0.311	-1.262	1.354	-0.847	0.886	-0.158	1.213	2.173	1.160	-0.218	0.239	0.000	1.166	0.494	0.278	2.548	0.575	1.454	-1.701	0.000	0.429	1.129	0.983	1.111	1.049	1.006	0.920
-1	1.294	1.587	-0.864	0.487	-0.312	0.828	1.051	-0.031	1.087	2.443	1.216	1.609	2.215	1.167	0.813	0.921	0.000	1.751	-0.415	0.119	0.000	1.015	1.091	0.974	1.357	2.093	1.178	1.059
-1	0.984	0.465	-1.661	0.379	-0.554	0.977	0.237	0.365	0.000	0.510	0.143	1.101	0.000	1.099	-0.662	-1.593	2.548	1.104	-0.197	-0.648	3.102	0.925	0.922	0.986	0.642	0.667	0.806	0.722
-1	0.930	-0.009	0.047	0.667	1.367	1.065	-0.231	0.815	0.000	1.199	-1.114	-0.877	2.215	0.940	0.824	-1.583	0.000	1.052	-0.407	-0.076	1.551	1.843	1.257	1.013	1.047	0.751	1.158	0.941
-0	0.767	-0.011	-0.637	0.341	-1.437	1.438	-0.425	-0.450	2.173	1.073	-0.718	1.341	2.215	0.633	-1.394	0.486	0.000	0.603	-1.945	-1.626	0.000	0.703	0.790	0.984	1.111	1.848	1.129	1.072
-1	1.779	0.017	0.432	0.402	1.022	0.959	1.480	1.595	2.173	1.252	1.365	0.006	0.000	1.188	-0.174	-1.107	0.000	1.181	0.518	-0.258	0.000	1.057	0.910	0.991	1.616	0.779	1.158	1.053
-0	0.881	0.630	1.029	1.990	0.508	1.102	0.742	-1.298	2.173	1.565	1.085	0.686	2.215	2.691	1.391	-0.904	0.000	0.499	1.388	-1.199	0.000	0.347	0.861	0.997	0.881	1.920	1.233	1.310
-0	1.754	-0.266	0.389	0.347	-0.030	0.462	-1.408	-0.957	2.173	0.515	-2.341	-1.700	0.000	0.588	-0.797	1.355	2.548	0.608	0.329	-1.389	0.000	1.406	0.909	0.988	0.760	0.593	0.768	0.847
-0	1.087	0.311	-1.447	0.173	0.567	0.854	0.362	0.584	0.000	1.416	-0.716	-1.211	2.215	0.648	-0.358	-0.692	1.274	0.867	-0.513	0.206	0.000	0.803	0.813	0.984	1.110	0.491	0.921	0.873
-0	0.279	1.114	-1.190	3.004	-0.738	1.233	0.896	1.092	2.173	0.454	-0.374	0.117	2.215	0.357	0.119	1.270	0.000	0.458	1.343	0.316	0.000	0.495	0.540	0.988	1.715	1.139	1.618	1.183
-1	1.773	-0.694	-1.518	2.306	-1.200	3.104	0.749	0.362	0.000	1.871	0.230	-1.686	2.215	0.805	-0.179	-0.871	1.274	0.910	0.607	-0.246	0.000	1.338	1.598	0.984	1.050	0.919	1.678	1.807
-0	0.553	0.683	0.827	0.973	-0.706	1.488	0.149	1.140	2.173	1.788	0.447	-0.478	0.000	0.596	1.043	1.607	0.000	0.373	-0.868	-1.308	1.551	1.607	1.026	0.998	1.134	0.808	1.142	0.936
-1	0.397	1.101	-1.139	1.688	0.146	0.972	0.541	1.518	0.000	1.549	-0.873	-1.012	0.000	2.282	-0.151	0.314	2.548	1.174	0.033	-1.368	0.000	0.937	0.776	1.039	1.143	0.959	0.986	1.013
-1	0.840	1.906	-0.959	0.869	0.576	0.642	0.554	-1.351	0.000	0.756	0.923	-0.823	2.215	1.251	1.130	0.545	2.548	1.513	0.410	1.073	0.000	1.231	0.985	1.163	0.812	0.987	0.816	0.822
-1	0.477	1.665	0.814	0.763	-0.382	0.828	-0.008	0.280	2.173	1.213	-0.001	1.560	0.000	1.136	0.311	-1.289	0.000	0.797	1.091	-0.616	3.102	1.026	0.964	0.992	0.772	0.869	0.916	0.803
-0	2.655	0.020	0.273	1.464	0.482	1.709	-0.107	-1.456	2.173	0.825	0.141	-0.386	0.000	1.342	-0.592	1.635	1.274	0.859	-0.175	-0.874	0.000	0.829	0.946	1.003	2.179	0.836	1.505	1.176
-0	0.771	-1.992	-0.720	0.732	-1.464	0.869	-1.290	0.388	2.173	0.926	-1.072	-1.489	2.215	0.640	-1.232	0.840	0.000	0.528	-2.440	-0.446	0.000	0.811	0.868	0.993	0.995	1.317	0.809	0.714
-0	1.357	1.302	0.076	0.283	-1.060	0.783	1.559	-0.994	0.000	0.947	1.212	1.617	0.000	1.127	0.311	0.442	2.548	0.582	-0.052	1.186	1.551	1.330	0.995	0.985	0.846	0.404	0.858	0.815
-0	0.442	-0.381	-0.424	1.244	0.591	0.731	0.605	-0.713	2.173	0.629	2.762	1.040	0.000	0.476	2.693	-0.617	0.000	0.399	0.442	1.486	3.102	0.839	0.755	0.988	0.869	0.524	0.877	0.918
-0	0.884	0.422	0.055	0.818	0.624	0.950	-0.763	1.624	0.000	0.818	-0.609	-1.166	0.000	1.057	-0.528	1.070	2.548	1.691	-0.124	-0.335	3.102	1.104	0.933	0.985	0.913	1.000	0.863	1.056
-0	1.276	0.156	1.714	1.053	-1.189	0.672	-0.464	-0.030	2.173	0.469	-2.483	0.442	0.000	0.564	2.580	-0.253	0.000	0.444	-0.628	1.080	1.551	5.832	2.983	0.985	1.162	0.494	1.809	1.513
-0	1.106	-0.556	0.406	0.573	-1.400	0.769	-0.518	1.457	2.173	0.743	-0.352	-0.010	0.000	1.469	-0.550	-0.930	2.548	0.540	1.236	-0.571	0.000	0.962	0.970	1.101	0.805	1.107	0.873	0.773
-0	0.539	-0.964	-0.464	1.371	-1.606	0.667	-0.160	0.655	0.000	0.952	0.352	-0.740	2.215	0.952	0.007	1.123	0.000	1.061	-0.505	1.389	3.102	1.063	0.991	1.019	0.633	0.967	0.732	0.799
-1	0.533	-0.989	-1.608	0.462	-1.723	1.204	-0.598	-0.098	2.173	1.343	-0.460	1.632	2.215	0.577	0.221	-0.492	0.000	0.628	-0.073	0.472	0.000	0.518	0.880	0.988	1.179	1.874	1.041	0.813
-1	1.024	1.075	-0.795	0.286	-1.436	1.365	0.857	-0.309	2.173	0.804	1.532	1.435	0.000	1.511	0.722	1.494	0.000	1.778	0.903	0.753	1.551	0.686	0.810	0.999	0.900	1.360	1.133	0.978
-1	2.085	-0.269	-1.423	0.789	1.298	0.281	1.652	0.187	0.000	0.658	-0.760	-0.042	2.215	0.663	0.024	0.120	0.000	0.552	-0.299	-0.428	3.102	0.713	0.811	1.130	0.705	0.218	0.675	0.743
-1	0.980	-0.443	0.813	0.785	-1.253	0.719	0.448	-1.458	0.000	1.087	0.595	0.635	1.107	1.428	0.029	-0.995	0.000	1.083	1.562	-0.092	0.000	0.834	0.891	1.165	0.967	0.661	0.880	0.817
-1	0.903	-0.733	-0.980	0.634	-0.639	0.780	0.266	-0.287	2.173	1.264	-0.936	1.004	0.000	1.002	-0.056	-1.344	2.548	1.183	-0.098	1.169	0.000	0.733	1.002	0.985	0.711	0.916	0.966	0.875
-0	0.734	-0.304	-1.175	2.851	1.674	0.904	-0.634	0.412	2.173	1.363	-1.050	-0.282	0.000	1.476	-1.603	0.103	0.000	2.231	-0.718	1.708	3.102	0.813	0.896	1.088	0.686	1.392	1.033	1.078
-1	1.680	0.591	-0.243	0.111	-0.478	0.326	-0.079	-1.555	2.173	0.711	0.714	0.922	2.215	0.355	0.858	1.682	0.000	0.727	1.620	1.360	0.000	0.334	0.526	1.001	0.862	0.633	0.660	0.619
-1	1.163	0.225	-0.202	0.501	-0.979	1.609	-0.938	1.424	0.000	1.224	-0.118	-1.274	0.000	2.034	1.241	-0.254	0.000	1.765	0.536	0.237	3.102	0.894	0.838	0.988	0.693	0.579	0.762	0.726
-0	1.223	1.232	1.471	0.489	1.728	0.703	-0.111	0.411	0.000	1.367	1.014	-1.294	1.107	1.524	-0.414	-0.164	2.548	1.292	0.833	0.316	0.000	0.861	0.752	0.994	0.836	1.814	1.089	0.950
-0	0.816	1.637	-1.557	1.036	-0.342	0.913	1.333	0.949	2.173	0.812	0.756	-0.628	2.215	1.333	0.470	1.495	0.000	1.204	-2.222	-1.675	0.000	1.013	0.924	1.133	0.758	1.304	0.855	0.860
-0	0.851	-0.564	-0.691	0.692	1.345	1.219	1.014	0.318	0.000	1.422	-0.262	-1.635	2.215	0.531	1.802	0.008	0.000	0.508	0.515	-1.267	3.102	0.821	0.787	1.026	0.783	0.432	1.149	1.034
-0	0.800	-0.599	0.204	0.552	-0.484	0.974	0.413	0.961	2.173	1.269	-0.984	-1.039	2.215	0.380	-1.213	1.371	0.000	0.551	0.332	-0.659	0.000	0.694	0.852	0.984	1.057	2.037	1.096	0.846
-0	0.744	-0.071	-0.255	0.638	0.512	1.125	0.407	0.844	2.173	0.860	-0.481	-0.677	0.000	1.102	0.181	-1.194	0.000	1.011	-1.081	-1.713	3.102	0.854	0.862	0.982	1.111	1.372	1.042	0.920
-1	0.400	1.049	-0.625	0.880	-0.407	1.040	2.150	-1.359	0.000	0.747	-0.144	0.847	2.215	0.560	-1.829	0.698	0.000	1.663	-0.668	0.267	0.000	0.845	0.964	0.996	0.820	0.789	0.668	0.668
-0	1.659	-0.705	-1.057	1.803	-1.436	1.008	0.693	0.005	0.000	0.895	-0.007	0.681	1.107	1.085	0.125	1.476	2.548	1.214	1.068	0.486	0.000	0.867	0.919	0.986	1.069	0.692	1.026	1.313
-0	0.829	-0.153	0.861	0.615	-0.548	0.589	1.077	-0.041	2.173	1.056	0.763	-1.737	0.000	0.639	0.970	0.725	0.000	0.955	1.227	-0.799	3.102	1.020	1.024	0.985	0.750	0.525	0.685	0.671
-1	0.920	-0.806	-0.840	1.048	0.278	0.973	-0.077	-1.364	2.173	1.029	0.309	0.133	0.000	1.444	1.484	1.618	1.274	1.419	-0.482	0.417	0.000	0.831	1.430	1.151	1.829	1.560	1.343	1.224
-1	0.686	0.249	-0.905	0.343	-1.731	0.724	-2.823	-0.901	0.000	0.982	0.303	1.312	1.107	1.016	0.245	0.610	0.000	1.303	-0.557	-0.360	3.102	1.384	1.030	0.984	0.862	1.144	0.866	0.779
-0	1.603	0.444	0.508	0.586	0.401	0.610	0.467	-1.735	2.173	0.914	0.626	-1.019	0.000	0.812	0.422	-0.408	2.548	0.902	1.679	1.490	0.000	1.265	0.929	0.990	1.004	0.816	0.753	0.851
-1	0.623	0.780	-0.203	0.056	0.015	0.899	0.793	1.326	1.087	0.803	1.478	-1.499	2.215	1.561	1.492	-0.120	0.000	0.904	0.795	0.137	0.000	0.548	1.009	0.850	0.924	0.838	0.914	0.860
-0	1.654	-2.032	-1.160	0.859	-1.583	0.689	-1.965	0.891	0.000	0.646	-1.014	-0.288	2.215	0.630	-0.815	0.402	0.000	0.638	0.316	0.655	3.102	0.845	0.879	0.993	1.067	0.625	1.041	0.958
-1	0.828	-1.269	-1.203	0.744	-0.213	0.626	-1.017	-0.404	0.000	1.281	-0.931	1.733	2.215	0.699	-0.351	1.287	0.000	1.251	-1.171	0.197	0.000	0.976	1.186	0.987	0.646	0.655	0.733	0.671
-1	0.677	0.111	1.090	1.580	1.591	1.560	0.654	-0.341	2.173	0.794	-0.266	0.702	0.000	0.823	0.651	-1.239	2.548	0.730	1.467	-1.530	0.000	1.492	1.023	0.983	1.909	1.022	1.265	1.127
-1	0.736	0.882	-1.060	0.589	0.168	1.663	0.781	1.022	2.173	2.025	1.648	-1.292	0.000	1.240	0.924	-0.421	1.274	1.354	0.065	0.501	0.000	0.316	0.925	0.988	0.664	1.736	0.992	0.807
-1	1.040	-0.822	1.638	0.974	-0.674	0.393	0.830	0.011	2.173	0.770	-0.140	-0.402	0.000	0.294	-0.133	0.030	0.000	1.220	0.807	0.638	0.000	0.826	1.063	1.216	1.026	0.705	0.934	0.823
-1	0.711	0.602	0.048	1.145	0.966	0.934	0.263	-1.589	2.173	0.971	-0.496	-0.421	1.107	0.628	-0.865	0.845	0.000	0.661	-0.008	-0.565	0.000	0.893	0.705	0.988	0.998	1.339	0.908	0.872
-1	0.953	-1.651	-0.167	0.885	1.053	1.013	-1.239	0.133	0.000	1.884	-1.122	1.222	2.215	1.906	-0.860	-1.184	1.274	1.413	-0.668	-1.647	0.000	1.873	1.510	1.133	1.050	1.678	1.246	1.061
-1	0.986	-0.892	-1.380	0.917	1.134	0.950	-1.162	-0.469	0.000	0.569	-1.393	0.215	0.000	0.320	2.667	1.712	0.000	1.570	-0.375	1.457	3.102	0.925	1.128	1.011	0.598	0.824	0.913	0.833
-1	1.067	0.099	1.154	0.527	-0.789	1.085	0.623	-1.602	2.173	1.511	-0.230	0.022	2.215	0.269	-0.377	0.883	0.000	0.571	-0.540	-0.512	0.000	0.414	0.803	1.022	0.959	2.053	1.041	0.780
-0	0.825	-2.118	0.217	1.453	-0.493	0.819	0.313	-0.942	0.000	2.098	-0.725	1.096	2.215	0.484	1.336	1.458	0.000	0.482	0.100	1.163	0.000	0.913	0.536	0.990	1.679	0.957	1.095	1.143
-1	1.507	0.054	1.120	0.698	-1.340	0.912	0.384	0.015	1.087	0.720	0.247	-0.820	0.000	0.286	0.154	1.578	2.548	0.629	1.582	-0.576	0.000	0.828	0.893	1.136	0.514	0.632	0.699	0.709
-1	0.610	1.180	-0.993	0.816	0.301	0.932	0.758	1.539	0.000	0.726	-0.830	0.248	2.215	0.883	0.857	-1.305	0.000	1.338	1.009	-0.252	3.102	0.901	1.074	0.987	0.875	1.159	1.035	0.858
-1	1.247	-1.360	1.502	1.525	-1.332	0.618	1.063	0.755	0.000	0.582	-0.155	0.473	2.215	1.214	-0.422	-0.551	2.548	0.838	-1.171	-1.166	0.000	2.051	1.215	1.062	1.091	0.725	0.896	1.091
-0	0.373	-0.600	1.291	2.573	0.207	0.765	-0.209	1.667	0.000	0.668	0.724	-1.499	0.000	1.045	-0.338	-0.754	2.548	0.558	-0.469	0.029	3.102	0.868	0.939	1.124	0.519	0.383	0.636	0.838
-0	0.791	0.336	-0.307	0.494	1.213	1.158	0.336	1.081	2.173	0.918	1.289	-0.449	0.000	0.735	-0.521	-0.969	0.000	1.052	0.499	-1.188	3.102	0.699	1.013	0.987	0.622	1.050	0.712	0.661
-0	1.321	0.856	0.464	0.202	0.901	1.144	0.120	-1.651	0.000	0.803	0.577	-0.509	2.215	0.695	-0.114	0.423	2.548	0.621	1.852	-0.420	0.000	0.697	0.964	0.983	0.527	0.659	0.719	0.729
-0	0.563	2.081	0.913	0.982	-0.533	0.549	-0.481	-1.730	0.000	0.962	0.921	0.569	2.215	0.731	1.184	-0.679	1.274	0.918	0.931	-1.432	0.000	1.008	0.919	0.993	0.895	0.819	0.810	0.878
-1	1.148	0.345	0.953	0.921	0.617	0.991	1.103	-0.484	0.000	0.970	1.978	1.525	0.000	1.150	0.689	-0.757	2.548	0.517	0.995	1.245	0.000	1.093	1.140	0.998	1.006	0.756	0.864	0.838
-1	1.400	0.128	-1.695	1.169	1.070	1.094	-0.345	-0.249	0.000	1.224	0.364	-0.036	2.215	1.178	0.530	-1.544	0.000	1.334	0.933	1.604	0.000	0.560	1.267	1.073	0.716	0.780	0.832	0.792
-0	0.330	-2.133	1.403	0.628	0.379	1.686	-0.995	0.030	1.087	2.071	0.127	-0.457	0.000	4.662	-0.855	1.477	0.000	2.072	-0.917	-1.416	3.102	5.403	3.074	0.977	0.936	1.910	2.325	1.702
-0	0.989	0.473	0.968	1.970	1.368	0.844	0.574	-0.290	2.173	0.866	-0.345	-1.019	0.000	1.130	0.605	-0.752	0.000	0.956	-0.888	0.870	3.102	0.885	0.886	0.982	1.157	1.201	1.100	1.068
-1	0.773	0.418	0.753	1.388	1.070	1.104	-0.378	-0.758	0.000	1.027	0.397	-0.496	2.215	1.234	0.027	1.084	2.548	0.936	0.209	1.677	0.000	1.355	1.020	0.983	0.550	1.206	0.916	0.931
-0	0.319	2.015	1.534	0.570	-1.134	0.632	0.124	0.757	0.000	0.477	0.598	-1.109	1.107	0.449	0.438	-0.755	2.548	0.574	-0.659	0.691	0.000	0.440	0.749	0.985	0.517	0.158	0.505	0.522
-0	1.215	1.453	-1.386	1.276	1.298	0.643	0.570	-0.196	2.173	0.588	2.104	0.498	0.000	0.617	-0.296	-0.801	2.548	0.452	0.110	0.313	0.000	0.815	0.953	1.141	1.166	0.547	0.892	0.807
-1	1.257	-1.869	-0.060	0.265	0.653	1.527	-0.346	1.163	2.173	0.758	-2.119	-0.604	0.000	1.473	-1.133	-1.290	2.548	0.477	-0.428	-0.066	0.000	0.818	0.841	0.984	1.446	1.729	1.211	1.054
-1	1.449	0.464	1.585	1.418	-1.488	1.540	0.942	0.087	0.000	0.898	0.402	-0.631	2.215	0.753	0.039	-1.729	0.000	0.859	0.849	-1.054	0.000	0.791	0.677	0.995	0.687	0.527	0.703	0.606
-1	1.084	-1.997	0.900	1.333	1.024	0.872	-0.864	-1.500	2.173	1.072	-0.813	-0.421	2.215	0.924	0.478	0.304	0.000	0.992	-0.398	-1.022	0.000	0.741	1.085	0.980	1.221	1.176	1.032	0.961
-0	1.712	1.129	0.125	1.120	-1.402	1.749	0.951	-1.575	2.173	1.711	0.445	0.578	0.000	1.114	0.234	-1.011	0.000	1.577	-0.088	0.086	3.102	2.108	1.312	1.882	1.597	2.009	1.441	1.308
-0	0.530	0.248	1.622	1.450	-1.012	1.221	-1.154	-0.763	2.173	1.698	-0.586	0.733	0.000	0.889	1.042	1.038	1.274	0.657	0.008	0.701	0.000	0.430	1.005	0.983	0.930	2.264	1.357	1.146
-1	0.921	1.735	0.883	0.699	-1.614	0.821	1.463	0.319	1.087	1.099	0.814	-1.600	2.215	1.375	0.702	-0.691	0.000	0.869	1.326	-0.790	0.000	0.980	0.900	0.988	0.832	1.452	0.816	0.709
-0	2.485	-0.823	-0.297	0.886	-1.404	0.989	0.835	1.615	2.173	0.382	0.588	-0.224	0.000	1.029	-0.456	1.546	2.548	0.613	-0.359	-0.789	0.000	0.768	0.977	1.726	2.007	0.913	1.338	1.180
-1	0.657	-0.069	-0.078	1.107	1.549	0.804	1.335	-1.630	2.173	1.271	0.481	0.153	1.107	1.028	0.144	-0.762	0.000	1.098	0.132	1.570	0.000	0.830	0.979	1.175	1.069	1.624	1.000	0.868
-1	2.032	0.329	-1.003	0.493	-0.136	1.159	-0.224	0.750	1.087	0.396	0.546	0.587	0.000	0.620	1.805	0.982	0.000	1.236	0.744	-1.621	0.000	0.930	1.200	0.988	0.482	0.771	0.887	0.779
-0	0.524	-1.319	0.634	0.471	1.221	0.599	-0.588	-0.461	0.000	1.230	-1.504	-1.517	1.107	1.436	-0.035	0.104	2.548	0.629	1.997	-1.282	0.000	2.084	1.450	0.984	1.084	1.827	1.547	1.213
-1	0.871	0.618	-1.544	0.718	0.186	1.041	-1.180	0.434	2.173	1.133	1.558	-1.301	0.000	0.452	-0.595	0.522	0.000	0.665	0.567	0.130	3.102	1.872	1.114	1.095	1.398	0.979	1.472	1.168
-1	3.308	1.037	-0.634	0.690	-0.619	1.975	0.949	1.280	0.000	0.826	0.546	-0.139	2.215	0.635	-0.045	0.427	0.000	1.224	0.112	1.339	3.102	1.756	1.050	0.992	0.738	0.903	0.968	1.238
-0	0.588	2.104	-0.872	1.136	1.743	0.842	0.638	0.015	0.000	0.481	0.928	1.000	2.215	0.595	0.125	1.429	0.000	0.951	-1.140	-0.511	3.102	1.031	1.057	0.979	0.673	1.064	1.001	0.891
-0	0.289	0.823	0.013	0.615	-1.601	0.177	2.403	-0.015	0.000	0.258	1.151	1.036	2.215	0.694	0.553	-1.326	2.548	0.411	0.366	0.106	0.000	0.482	0.562	0.989	0.670	0.404	0.516	0.561
-1	0.294	-0.660	-1.162	1.752	0.384	0.860	0.513	1.119	0.000	2.416	0.107	-1.342	0.000	1.398	0.361	-0.350	2.548	1.126	-0.902	0.040	1.551	0.650	1.125	0.988	0.531	0.843	0.912	0.911
-0	0.599	-0.616	1.526	1.381	0.507	0.955	-0.646	-0.085	2.173	0.775	-0.533	1.116	2.215	0.789	-0.136	-1.176	0.000	2.449	1.435	-1.433	0.000	1.692	1.699	1.000	0.869	1.119	1.508	1.303
-1	1.100	-1.174	-1.114	1.601	-1.576	1.056	-1.343	0.547	2.173	0.555	0.367	0.592	2.215	0.580	-1.862	-0.914	0.000	0.904	0.508	-0.444	0.000	1.439	1.105	0.986	1.408	1.104	1.190	1.094
-1	2.237	-0.701	1.470	0.719	-0.199	0.745	-0.132	-0.737	1.087	0.976	-0.227	0.093	2.215	0.699	0.057	1.133	0.000	0.661	0.573	-0.679	0.000	0.785	0.772	1.752	1.235	0.856	0.990	0.825
-1	0.455	-0.880	-1.482	1.260	-0.178	1.499	0.158	1.022	0.000	1.867	-0.435	-0.675	2.215	1.234	0.783	1.586	0.000	0.641	-0.454	-0.409	3.102	1.002	0.964	0.986	0.761	0.240	1.190	0.995
-1	1.158	-0.778	-0.159	0.823	1.641	1.341	-0.830	-1.169	2.173	0.840	-1.554	0.934	0.000	0.693	0.488	-1.218	2.548	1.042	1.395	0.276	0.000	0.946	0.785	1.350	1.079	0.893	1.267	1.151
-1	0.902	-0.078	-0.055	0.872	-0.012	0.843	1.276	1.739	2.173	0.838	1.492	0.918	0.000	0.626	0.904	-0.648	2.548	0.412	-2.027	-0.883	0.000	2.838	1.664	0.988	1.803	0.768	1.244	1.280
-1	0.649	-1.028	-1.521	1.097	0.774	1.216	-0.383	-0.318	2.173	1.643	-0.285	-1.705	0.000	0.911	-0.091	0.341	0.000	0.592	0.537	0.732	3.102	0.911	0.856	1.027	1.160	0.874	0.986	0.893
-1	1.192	1.846	-0.781	1.326	-0.747	1.550	1.177	1.366	0.000	1.196	0.151	0.387	2.215	0.527	2.261	-0.190	0.000	0.390	1.474	0.381	0.000	0.986	1.025	1.004	1.392	0.761	0.965	1.043
-0	0.438	-0.358	-1.549	0.836	0.436	0.818	0.276	-0.708	2.173	0.707	0.826	0.392	0.000	1.050	1.741	-1.066	0.000	1.276	-1.583	0.842	0.000	1.475	1.273	0.986	0.853	1.593	1.255	1.226
-1	1.083	0.142	1.701	0.605	-0.253	1.237	0.791	1.183	2.173	0.842	2.850	-0.082	0.000	0.724	-0.464	-0.694	0.000	1.499	0.456	-0.226	3.102	0.601	0.799	1.102	0.995	1.389	1.013	0.851
-0	0.828	1.897	-0.615	0.572	-0.545	0.572	0.461	0.464	2.173	0.393	0.356	1.069	2.215	1.840	0.088	1.500	0.000	0.407	-0.663	-0.787	0.000	0.950	0.965	0.979	0.733	0.363	0.618	0.733
-0	0.735	1.438	1.197	1.123	-0.214	0.641	0.949	0.858	0.000	1.162	0.524	-0.896	2.215	0.992	0.454	-1.475	2.548	0.902	1.079	0.019	0.000	0.822	0.917	1.203	1.032	0.569	0.780	0.764
-0	0.437	-2.102	0.044	1.779	-1.042	1.231	-0.181	-0.515	1.087	2.666	0.863	1.466	2.215	1.370	0.345	-1.371	0.000	0.906	0.363	1.611	0.000	1.140	1.362	1.013	3.931	3.004	2.724	2.028
-1	0.881	1.814	-0.987	0.384	0.800	2.384	1.422	0.640	0.000	1.528	0.292	-0.962	1.107	2.126	-0.371	-1.401	2.548	0.700	0.109	0.203	0.000	0.450	0.813	0.985	0.956	1.013	0.993	0.774
-1	0.630	0.408	0.152	0.194	0.316	0.710	-0.824	-0.358	2.173	0.741	0.535	-0.851	2.215	0.933	0.406	1.148	0.000	0.523	-0.479	-0.625	0.000	0.873	0.960	0.988	0.830	0.921	0.711	0.661
-1	0.870	-0.448	-1.134	0.616	0.135	0.600	0.649	-0.622	2.173	0.768	0.709	-0.123	0.000	1.308	0.500	1.468	0.000	1.973	-0.286	1.462	3.102	0.909	0.944	0.990	0.835	1.250	0.798	0.776
-0	1.290	0.552	1.330	0.615	-1.353	0.661	0.240	-0.393	0.000	0.531	0.053	-1.588	0.000	0.675	0.839	-0.345	1.274	1.597	0.020	0.536	3.102	1.114	0.964	0.987	0.783	0.675	0.662	0.675
-1	0.943	0.936	1.068	1.373	0.671	2.170	-2.011	-1.032	0.000	0.640	0.361	-0.806	0.000	2.239	-0.083	0.590	2.548	1.224	0.646	-1.723	0.000	0.879	0.834	0.981	1.436	0.568	0.916	0.931
-1	0.431	1.686	-1.053	0.388	1.739	0.457	-0.471	-0.743	2.173	0.786	1.432	-0.547	2.215	0.537	-0.413	1.256	0.000	0.413	2.311	-0.408	0.000	1.355	1.017	0.982	0.689	1.014	0.821	0.715
-0	1.620	-0.055	-0.862	1.341	-1.571	0.634	-0.906	0.935	2.173	0.501	-2.198	-0.525	0.000	0.778	-0.708	-0.060	0.000	0.988	-0.621	0.489	3.102	0.870	0.956	1.216	0.992	0.336	0.871	0.889
-1	0.549	0.304	-1.443	1.309	-0.312	1.116	0.644	1.519	2.173	1.078	-0.303	-0.736	0.000	1.261	0.387	0.628	2.548	0.945	-0.190	0.090	0.000	0.893	1.043	1.000	1.124	1.077	1.026	0.886
-0	0.412	-0.618	-1.486	1.133	-0.665	0.646	0.436	1.520	0.000	0.993	0.976	0.106	2.215	0.832	0.091	0.164	2.548	0.672	-0.650	1.256	0.000	0.695	1.131	0.991	1.017	0.455	1.226	1.087
-0	1.183	-0.084	1.644	1.389	0.967	0.843	0.938	-0.670	0.000	0.480	0.256	0.123	2.215	0.437	1.644	0.491	0.000	0.501	-0.416	0.101	3.102	1.060	0.804	1.017	0.775	0.173	0.535	0.760
-0	1.629	-1.486	-0.683	2.786	-0.492	1.347	-2.638	1.453	0.000	1.857	0.208	0.873	0.000	0.519	-1.265	-1.602	1.274	0.903	-1.102	-0.329	1.551	6.892	3.522	0.998	0.570	0.477	2.039	2.006
-1	2.045	-0.671	-1.235	0.490	-0.952	0.525	-1.252	1.289	0.000	1.088	-0.993	0.648	2.215	0.975	-0.109	-0.254	2.548	0.556	-1.095	-0.194	0.000	0.803	0.861	0.980	1.282	0.945	0.925	0.811
-0	0.448	-0.058	-0.974	0.945	-1.633	1.181	-1.139	0.266	2.173	1.118	-0.761	1.502	1.107	1.706	0.585	-0.680	0.000	0.487	-1.951	0.945	0.000	2.347	1.754	0.993	1.161	1.549	1.414	1.176
-0	0.551	0.519	0.448	2.183	1.293	1.220	0.628	-0.627	2.173	1.019	-0.002	-0.652	0.000	1.843	-0.386	1.042	2.548	0.400	-1.102	-1.014	0.000	0.648	0.792	1.049	0.888	2.132	1.262	1.096
-0	1.624	0.488	1.403	0.760	0.559	0.812	0.777	-1.244	2.173	0.613	0.589	-0.030	2.215	0.692	1.058	0.683	0.000	1.054	1.165	-0.765	0.000	0.915	0.875	1.059	0.821	0.927	0.792	0.721
-1	0.774	0.444	1.257	0.515	-0.689	0.515	1.448	-1.271	0.000	0.793	0.118	0.811	1.107	0.679	0.326	-0.426	0.000	1.066	-0.865	-0.049	3.102	0.960	1.046	0.986	0.716	0.772	0.855	0.732
-1	2.093	-1.240	1.615	0.918	-1.202	1.412	-0.541	0.640	1.087	2.019	0.872	-0.639	0.000	0.672	-0.936	0.972	0.000	0.896	0.235	0.212	0.000	0.810	0.700	1.090	0.797	0.862	1.049	0.874
-1	0.908	1.069	0.283	0.400	1.293	0.609	1.452	-1.136	0.000	0.623	0.417	-0.098	2.215	1.023	0.775	1.054	1.274	0.706	2.346	-1.305	0.000	0.744	1.006	0.991	0.606	0.753	0.796	0.753
-0	0.403	-1.328	-0.065	0.901	1.052	0.708	-0.354	-0.718	2.173	0.892	0.633	1.684	2.215	0.999	-1.205	0.941	0.000	0.930	1.072	-0.809	0.000	2.105	1.430	0.989	0.838	1.147	1.042	0.883
-0	1.447	0.453	0.118	1.731	0.650	0.771	0.446	-1.564	0.000	0.973	-2.014	0.354	0.000	1.949	-0.643	-1.531	1.274	1.106	-0.334	-1.163	0.000	0.795	0.821	1.013	1.699	0.918	1.118	1.018
-1	1.794	0.123	-0.454	0.057	1.489	0.966	-1.190	1.090	1.087	0.539	-0.535	1.035	0.000	1.096	-1.069	-1.236	2.548	0.659	-1.196	-0.283	0.000	0.803	0.756	0.985	1.343	1.109	0.993	0.806
-0	1.484	-2.047	0.813	0.591	-0.295	0.923	0.312	-1.164	2.173	0.654	-0.316	0.752	2.215	0.599	1.966	-1.128	0.000	0.626	-0.304	-1.431	0.000	1.112	0.910	1.090	0.986	1.189	1.350	1.472
-0	0.417	-2.016	0.849	1.817	0.040	1.201	-1.676	-1.394	0.000	0.792	0.537	0.641	2.215	0.794	-1.222	0.187	0.000	0.825	-0.217	1.334	3.102	1.470	0.931	0.987	1.203	0.525	0.833	0.827
-1	0.603	1.009	0.033	0.486	1.225	0.884	-0.617	-1.058	0.000	0.500	-1.407	-0.567	0.000	1.476	-0.876	0.605	2.548	0.970	0.560	1.092	3.102	0.853	1.153	0.988	0.846	0.920	0.944	0.835
-1	1.381	-0.326	0.552	0.417	-0.027	1.030	-0.835	-1.287	2.173	0.941	-0.421	1.519	2.215	0.615	-1.650	0.377	0.000	0.606	0.644	0.650	0.000	1.146	0.970	0.990	1.191	0.884	0.897	0.826
-1	0.632	1.200	-0.703	0.438	-1.700	0.779	-0.731	0.958	1.087	0.605	0.393	-1.376	0.000	0.670	-0.827	-1.315	2.548	0.626	-0.501	0.417	0.000	0.904	0.903	0.998	0.673	0.803	0.722	0.640
-1	1.561	-0.569	1.580	0.329	0.237	1.059	0.731	0.415	2.173	0.454	0.016	-0.828	0.000	0.587	0.008	-0.291	1.274	0.597	1.119	1.191	0.000	0.815	0.908	0.988	0.733	0.690	0.892	0.764
-1	2.102	0.087	0.449	1.164	-0.390	1.085	-0.408	-1.116	2.173	0.578	0.197	-0.137	0.000	1.202	0.917	1.523	0.000	0.959	-0.832	1.404	3.102	1.380	1.109	1.486	1.496	0.886	1.066	1.025
-1	1.698	-0.489	-0.552	0.976	-1.009	1.620	-0.721	0.648	1.087	1.481	-1.860	-1.354	0.000	1.142	-1.140	1.401	2.548	1.000	-1.274	-0.158	0.000	1.430	1.130	0.987	1.629	1.154	1.303	1.223
-1	1.111	-0.249	-1.457	0.421	0.939	0.646	-2.076	0.362	0.000	1.315	0.796	-1.436	2.215	0.780	0.130	0.055	0.000	1.662	-0.834	0.461	0.000	0.920	0.948	0.990	1.046	0.905	1.493	1.169
-1	0.945	0.390	-1.159	1.675	0.437	0.356	0.261	0.543	1.087	0.574	0.838	1.599	2.215	0.496	-1.220	-0.022	0.000	0.558	-2.454	1.440	0.000	0.763	0.983	1.728	1.000	0.578	0.922	1.003
-1	2.076	0.014	-1.314	0.854	-0.306	3.446	1.341	0.598	0.000	2.086	0.227	-0.747	2.215	1.564	-0.216	1.649	2.548	0.965	-0.857	-1.062	0.000	0.477	0.734	1.456	1.003	1.660	1.001	0.908
-1	1.992	0.192	-0.103	0.108	-1.599	0.938	0.595	-1.360	2.173	0.869	-1.012	1.432	0.000	1.302	0.850	0.436	2.548	0.487	1.051	-1.027	0.000	0.502	0.829	0.983	1.110	1.394	0.904	0.836
-0	0.460	1.625	1.485	1.331	1.242	0.675	-0.329	-1.039	1.087	0.671	-1.028	-0.514	0.000	1.265	-0.788	0.415	1.274	0.570	-0.683	-1.738	0.000	0.725	0.758	1.004	1.024	1.156	0.944	0.833
-0	0.871	0.839	-1.536	0.428	1.198	0.875	-1.256	-0.466	1.087	0.684	-0.768	0.150	0.000	0.556	-1.793	0.389	0.000	0.942	-1.126	1.339	1.551	0.624	0.734	0.986	1.357	0.960	1.474	1.294
-1	0.951	1.651	0.576	1.273	1.495	0.834	0.048	-0.578	2.173	0.386	-0.056	-1.448	0.000	0.597	-0.196	0.162	2.548	0.524	1.649	1.625	0.000	0.737	0.901	1.124	1.014	0.556	1.039	0.845
-1	1.049	-0.223	0.685	0.256	-1.191	2.506	0.238	-0.359	0.000	1.510	-0.904	1.158	1.107	2.733	-0.902	1.679	2.548	0.407	-0.474	-1.572	0.000	1.513	2.472	0.982	1.238	0.978	1.985	1.510
-0	0.455	-0.028	0.265	1.286	1.373	0.459	0.331	-0.922	0.000	0.343	0.634	0.430	0.000	0.279	-0.084	-0.272	0.000	0.475	0.926	-0.123	3.102	0.803	0.495	0.987	0.587	0.211	0.417	0.445
-1	2.074	0.388	0.878	1.110	1.557	1.077	-0.226	-0.295	2.173	0.865	-0.319	-1.116	2.215	0.707	-0.835	0.722	0.000	0.632	-0.608	-0.728	0.000	0.715	0.802	1.207	1.190	0.960	1.143	0.926
-1	1.390	0.265	1.196	0.919	-1.371	1.858	0.506	0.786	0.000	1.280	-1.367	-0.720	2.215	1.483	-0.441	-0.675	2.548	1.076	0.294	-0.539	0.000	1.126	0.830	1.155	1.551	0.702	1.103	0.933
-1	1.014	-0.079	1.597	1.038	-0.281	1.135	-0.722	-0.177	2.173	0.544	-1.475	-1.501	0.000	1.257	-1.315	1.212	0.000	0.496	-0.060	1.180	1.551	0.815	0.611	1.411	1.110	0.792	0.846	0.853
-0	0.335	1.267	-1.154	2.011	-0.574	0.753	0.618	1.411	0.000	0.474	0.748	0.681	2.215	0.608	-0.446	-0.354	2.548	0.399	1.295	-0.581	0.000	0.911	0.882	0.975	0.832	0.598	0.580	0.678
-1	0.729	-0.189	1.182	0.293	1.310	0.412	0.459	-0.632	0.000	0.869	-1.128	-0.625	2.215	1.173	-0.893	0.478	2.548	0.584	-2.394	-1.727	0.000	2.016	1.272	0.995	1.034	0.905	0.966	1.038
-1	1.225	-1.215	-0.088	0.881	-0.237	0.600	-0.976	1.462	2.173	0.876	0.506	1.583	2.215	0.718	1.228	-0.031	0.000	0.653	-1.292	1.216	0.000	0.838	1.108	0.981	1.805	0.890	1.251	1.197
-1	2.685	-0.444	0.847	0.253	0.183	0.641	-1.541	-0.873	2.173	0.417	2.874	-0.551	0.000	0.706	-1.431	0.764	0.000	1.390	-0.596	-1.397	0.000	0.894	0.829	0.993	0.789	0.654	0.883	0.746
-0	0.638	-0.481	0.683	1.457	-1.024	0.707	-1.338	1.498	0.000	0.980	0.518	0.289	2.215	0.964	-0.531	-0.423	0.000	0.694	-0.654	-1.314	3.102	0.807	1.283	1.335	0.658	0.907	0.797	0.772
-1	1.789	-0.765	-0.732	0.421	-0.020	1.142	-1.353	1.439	2.173	0.725	-1.518	-1.261	0.000	0.812	-2.597	-0.463	0.000	1.203	-0.120	1.001	0.000	0.978	0.673	0.985	1.303	1.400	1.078	0.983
-1	0.784	-1.431	1.724	0.848	0.559	0.615	-1.643	-1.456	0.000	1.339	-0.513	0.040	2.215	0.394	-2.483	1.304	0.000	0.987	0.889	-0.339	0.000	0.732	0.713	0.987	0.973	0.705	0.875	0.759
-1	0.911	1.098	-1.289	0.421	0.823	1.218	-0.503	0.431	0.000	0.775	0.432	-1.680	0.000	0.855	-0.226	-0.460	2.548	0.646	-0.947	-1.243	1.551	2.201	1.349	0.985	0.730	0.451	0.877	0.825
-1	0.959	0.372	-0.269	1.255	0.702	1.151	0.097	0.805	2.173	0.993	1.011	0.767	2.215	1.096	0.185	0.381	0.000	1.001	-0.205	0.059	0.000	0.979	0.997	1.168	0.796	0.771	0.839	0.776
-0	0.283	-1.864	-1.663	0.219	1.624	0.955	-1.213	0.932	2.173	0.889	0.395	-0.268	0.000	0.597	-1.083	-0.921	2.548	0.584	1.325	-1.072	0.000	0.856	0.927	0.996	0.937	0.936	1.095	0.892
-0	2.017	-0.488	-0.466	1.029	-0.870	3.157	0.059	-0.343	2.173	3.881	0.872	1.502	1.107	3.631	1.720	0.963	0.000	0.633	-1.264	-1.734	0.000	4.572	3.339	1.005	1.407	5.590	3.614	3.110
-1	1.088	0.414	-0.841	0.485	0.605	0.860	1.110	-0.568	0.000	1.152	-0.325	1.203	2.215	0.324	1.652	-0.104	0.000	0.510	1.095	-1.728	0.000	0.880	0.722	0.989	0.977	0.711	0.888	0.762
-0	0.409	-1.717	0.712	0.809	-1.301	0.701	-1.529	-1.411	0.000	1.191	-0.582	0.438	2.215	1.147	0.813	-0.571	2.548	1.039	0.543	0.892	0.000	0.636	0.810	0.986	0.861	1.411	0.907	0.756
-1	1.094	1.577	-0.988	0.497	-0.149	0.891	-2.459	1.034	0.000	0.646	0.792	-1.022	0.000	1.573	0.254	-0.053	2.548	1.428	0.190	-1.641	3.102	4.322	2.687	0.985	0.881	1.135	1.907	1.831
-1	0.613	1.993	-0.280	0.544	0.931	0.909	1.526	1.559	0.000	0.840	1.473	-0.483	2.215	0.856	0.352	0.408	2.548	1.058	1.733	-1.396	0.000	0.801	1.066	0.984	0.639	0.841	0.871	0.748
-0	0.958	-1.202	0.600	0.434	0.170	0.783	-0.214	1.319	0.000	0.835	-0.454	-0.615	2.215	0.658	-1.858	-0.891	0.000	0.640	0.172	-1.204	3.102	1.790	1.086	0.997	0.804	0.403	0.793	0.756
-1	1.998	-0.238	0.972	0.058	0.266	0.759	1.576	-0.357	2.173	1.004	-0.349	-0.747	2.215	0.962	0.490	-0.453	0.000	1.592	0.661	-1.405	0.000	0.874	1.086	0.990	1.436	1.527	1.177	0.993
-1	0.796	-0.171	-0.818	0.574	-1.625	1.201	-0.737	1.451	2.173	0.651	0.404	-0.452	0.000	1.150	-0.652	-0.120	0.000	1.008	-0.093	0.531	3.102	0.884	0.706	0.979	1.193	0.937	0.943	0.881
-1	0.773	1.023	0.527	1.537	-0.201	2.967	-0.574	-1.534	2.173	2.346	-0.307	0.394	2.215	1.393	0.135	-0.027	0.000	3.015	0.187	0.516	0.000	0.819	1.260	0.982	2.552	3.862	2.179	1.786
-0	1.823	1.008	-1.489	0.234	-0.962	0.591	0.461	0.996	2.173	0.568	-1.297	-0.410	0.000	0.887	2.157	1.194	0.000	2.079	0.369	-0.085	3.102	0.770	0.945	0.995	1.179	0.971	0.925	0.983
-0	0.780	0.640	0.490	0.680	-1.301	0.715	-0.137	0.152	2.173	0.616	-0.831	1.668	0.000	1.958	0.528	-0.982	2.548	0.966	-1.551	0.462	0.000	1.034	1.079	1.008	0.827	1.369	1.152	0.983
-1	0.543	0.801	1.543	1.134	-0.772	0.954	-0.849	0.410	1.087	0.851	-1.988	1.686	0.000	0.799	-0.912	-1.156	0.000	0.479	0.097	1.334	0.000	0.923	0.597	0.989	1.231	0.759	0.975	0.867
-0	1.241	-0.014	0.129	1.158	0.670	0.445	-0.732	1.739	2.173	0.918	0.659	-1.340	2.215	0.557	2.410	-1.404	0.000	0.966	-1.545	-1.120	0.000	0.874	0.918	0.987	1.001	0.798	0.904	0.937
-0	1.751	-0.266	-1.575	0.489	1.292	1.112	1.533	0.137	2.173	1.204	-0.414	-0.928	0.000	0.879	1.237	-0.415	2.548	1.479	1.469	0.913	0.000	2.884	1.747	0.989	1.742	0.600	1.363	1.293
-1	1.505	1.208	-1.476	0.995	-0.836	2.800	-1.600	0.111	0.000	2.157	1.241	1.110	2.215	1.076	2.619	-0.913	0.000	1.678	2.204	-1.575	0.000	0.849	1.224	0.990	1.412	0.976	1.271	1.105
-0	0.816	0.611	0.779	1.694	0.278	0.575	-0.787	1.592	2.173	1.148	1.076	-0.831	2.215	0.421	1.316	0.632	0.000	0.589	0.452	-1.466	0.000	0.779	0.909	0.990	1.146	1.639	1.236	0.949
-1	0.551	-0.808	0.330	1.188	-0.294	0.447	-0.035	-0.993	0.000	0.432	-0.276	-0.481	2.215	1.959	-0.288	1.195	2.548	0.638	0.583	1.107	0.000	0.832	0.924	0.993	0.723	0.976	0.968	0.895
-0	1.316	-0.093	0.995	0.860	-0.621	0.593	-0.560	-1.599	2.173	0.524	-0.318	-0.240	2.215	0.566	0.759	-0.368	0.000	0.483	-2.030	-1.104	0.000	1.468	1.041	1.464	0.811	0.778	0.690	0.722
-1	1.528	0.067	-0.855	0.959	-1.464	1.143	-0.082	1.023	0.000	0.702	-0.763	-0.244	0.000	0.935	-0.881	0.206	2.548	0.614	-0.831	1.657	3.102	1.680	1.105	0.983	1.078	0.559	0.801	0.809
-0	0.558	-0.833	-0.598	1.436	-1.724	1.316	-0.661	1.593	2.173	1.148	-0.503	-0.132	1.107	1.584	-0.125	0.380	0.000	1.110	-1.216	-0.181	0.000	1.258	0.860	1.053	0.790	1.814	1.159	1.007
-1	0.819	0.879	1.221	0.598	-1.450	0.754	0.417	-0.369	2.173	0.477	1.199	0.274	0.000	1.073	0.368	0.273	2.548	1.599	2.047	1.690	0.000	0.933	0.984	0.983	0.788	0.613	0.728	0.717
-0	0.981	-1.007	0.489	0.923	1.261	0.436	-0.698	-0.506	2.173	0.764	-1.105	-1.241	2.215	0.577	-2.573	-0.036	0.000	0.565	-1.628	1.610	0.000	0.688	0.801	0.991	0.871	0.554	0.691	0.656
-0	2.888	0.568	-1.416	1.461	-1.157	1.756	-0.900	0.522	0.000	0.657	0.409	1.076	2.215	1.419	0.672	-0.019	0.000	1.436	-0.184	-0.980	3.102	0.946	0.919	0.995	1.069	0.890	0.834	0.856
-1	0.522	1.805	-0.963	1.136	0.418	0.727	-0.195	-1.695	2.173	0.309	2.559	-0.178	0.000	0.521	1.794	0.919	0.000	0.788	0.174	-0.406	3.102	0.555	0.729	1.011	1.385	0.753	0.927	0.832
-1	0.793	-0.162	-1.643	0.634	0.337	0.898	-0.633	1.689	0.000	0.806	-0.826	-0.356	2.215	0.890	-0.142	-1.268	0.000	1.293	0.574	0.725	0.000	0.833	1.077	0.988	0.721	0.679	0.867	0.753
-0	1.298	1.098	0.280	0.371	-0.373	0.855	-0.306	-1.186	0.000	0.977	-0.421	1.003	0.000	0.978	0.956	-1.249	2.548	0.735	0.577	-0.037	3.102	0.974	1.002	0.992	0.549	0.587	0.725	0.954
-1	0.751	-0.520	-1.653	0.168	-0.419	0.878	-1.023	-1.364	2.173	1.310	-0.667	0.863	0.000	1.196	-0.827	0.358	0.000	1.154	-0.165	-0.360	1.551	0.871	0.950	0.983	0.907	0.955	0.959	0.874
-0	1.730	0.666	-1.432	0.446	1.302	0.921	-0.203	0.621	0.000	1.171	-0.365	-0.611	1.107	0.585	0.807	1.150	0.000	0.415	-0.843	1.311	0.000	0.968	0.786	0.986	1.059	0.371	0.790	0.848
-1	0.596	-1.486	0.690	1.045	-1.344	0.928	0.867	0.820	2.173	0.610	0.999	-1.329	2.215	0.883	-0.001	-0.106	0.000	1.145	2.184	-0.808	0.000	2.019	1.256	1.056	1.751	1.037	1.298	1.518
-1	0.656	-1.993	-0.519	1.643	-0.143	0.815	0.256	1.220	1.087	0.399	-1.184	-1.458	0.000	0.738	1.361	-1.443	0.000	0.842	0.033	0.293	0.000	0.910	0.891	0.993	0.668	0.562	0.958	0.787
-1	1.127	-0.542	0.645	0.318	-1.496	0.661	-0.640	0.369	2.173	0.992	0.358	1.702	0.000	1.004	0.316	-1.109	0.000	1.616	-0.936	-0.707	1.551	0.875	1.191	0.985	0.651	0.940	0.969	0.834
-0	0.916	-1.423	-1.490	1.248	-0.538	0.625	-0.535	-0.174	0.000	0.769	-0.389	1.608	2.215	0.667	-1.138	-1.738	1.274	0.877	-0.019	0.482	0.000	0.696	0.917	1.121	0.678	0.347	0.647	0.722
-1	2.756	-0.637	-1.715	1.331	1.124	0.913	-0.296	-0.491	0.000	0.983	-0.831	0.000	2.215	1.180	-0.428	0.742	0.000	1.113	0.005	-1.157	1.551	1.681	1.096	1.462	0.976	0.917	1.009	1.040
-0	0.755	1.754	0.701	2.111	0.256	1.243	0.057	-1.502	2.173	0.565	-0.034	-1.078	1.107	0.529	1.696	-1.090	0.000	0.665	0.292	0.107	0.000	0.870	0.780	0.990	2.775	0.465	1.876	1.758
-1	0.593	-0.762	1.743	0.908	0.442	0.773	-1.357	-0.768	2.173	0.432	1.421	1.236	0.000	0.579	0.291	-0.403	0.000	0.966	-0.309	1.016	3.102	0.893	0.743	0.989	0.857	1.030	0.943	0.854
-1	0.891	-1.151	-1.269	0.504	-0.622	0.893	-0.549	0.700	0.000	0.828	-0.825	0.154	2.215	1.083	0.632	-1.141	0.000	1.059	-0.557	1.526	3.102	2.117	1.281	0.987	0.819	0.802	0.917	0.828
-1	2.358	-0.248	0.080	0.747	-0.975	1.019	1.374	1.363	0.000	0.935	0.127	-1.707	2.215	0.312	-0.827	0.017	0.000	0.737	1.059	-0.327	0.000	0.716	0.828	1.495	0.953	0.704	0.880	0.745
-0	0.660	-0.017	-1.138	0.453	1.002	0.645	0.518	0.703	2.173	0.751	0.705	-0.592	2.215	0.744	-0.909	-1.596	0.000	0.410	-1.135	0.481	0.000	0.592	0.922	0.989	0.897	0.948	0.777	0.701
-1	0.718	0.518	0.225	1.710	-0.022	1.888	-0.424	1.092	0.000	4.134	0.185	-1.366	0.000	1.415	1.293	0.242	2.548	2.351	0.264	-0.057	3.102	0.830	1.630	0.976	1.215	0.890	1.422	1.215
-1	1.160	0.203	0.941	0.594	0.212	0.636	-0.556	0.679	2.173	1.089	-0.481	-1.008	1.107	1.245	-0.056	-1.357	0.000	0.587	1.007	0.056	0.000	1.106	0.901	0.987	0.786	1.224	0.914	0.837
-1	0.697	0.542	0.619	0.985	1.481	0.745	0.415	1.644	2.173	0.903	0.495	-0.958	2.215	1.165	1.195	0.346	0.000	1.067	-0.881	-0.264	0.000	0.830	1.025	0.987	0.690	0.863	0.894	0.867
-0	1.430	0.190	-0.700	0.246	0.518	1.302	0.660	-0.247	2.173	1.185	-0.539	1.504	0.000	1.976	-0.401	1.079	0.000	0.855	-0.958	-1.110	3.102	0.886	0.953	0.993	0.889	1.400	1.376	1.119
-1	1.122	-0.795	0.202	0.397	-1.553	0.597	-1.459	-0.734	2.173	0.522	1.044	1.027	2.215	0.783	-1.243	1.701	0.000	0.371	1.737	0.199	0.000	1.719	1.176	0.988	0.723	1.583	1.063	0.914
-0	1.153	0.526	1.236	0.266	0.001	1.139	-1.236	-0.585	2.173	1.337	-0.215	-1.356	2.215	1.780	1.129	0.902	0.000	1.608	-0.391	-0.161	0.000	1.441	1.633	0.990	1.838	1.516	1.635	1.373
-1	0.760	1.012	0.758	0.937	0.051	0.941	0.687	-1.247	2.173	1.288	-0.743	0.822	0.000	1.552	1.782	-1.533	0.000	0.767	1.349	0.168	0.000	0.716	0.862	0.988	0.595	0.359	0.697	0.623
-1	1.756	-1.469	1.395	1.345	-1.595	0.817	0.017	-0.741	2.173	0.483	-0.008	0.293	0.000	1.768	-0.663	0.438	1.274	1.202	-1.387	-0.222	0.000	1.022	1.058	0.992	1.407	1.427	1.356	1.133
-0	0.397	0.582	-0.758	1.260	-1.735	0.889	-0.515	1.139	2.173	0.973	1.616	0.460	0.000	1.308	1.001	-0.709	2.548	0.858	0.995	-0.231	0.000	0.749	0.888	0.979	1.487	1.804	1.208	1.079
-0	0.515	-0.984	0.425	1.114	-0.439	1.999	0.818	1.561	0.000	1.407	0.009	-0.380	0.000	1.332	0.230	0.397	0.000	1.356	-0.616	-1.057	3.102	0.978	1.017	0.990	1.118	0.862	0.835	0.919
-1	1.368	-0.921	-0.866	0.842	-0.598	0.456	-1.176	1.219	1.087	0.419	-1.974	-0.819	0.000	0.791	-1.640	0.881	0.000	1.295	-0.782	0.442	3.102	0.945	0.761	0.974	0.915	0.535	0.733	0.651
-0	2.276	0.134	0.399	2.525	0.376	1.111	-1.078	-1.571	0.000	0.657	2.215	-0.900	0.000	1.183	-0.662	-0.508	2.548	1.436	-0.517	0.960	3.102	0.569	0.931	0.993	1.170	0.967	0.879	1.207
-0	0.849	0.907	0.124	0.652	1.585	0.715	0.355	-1.200	0.000	0.599	-0.892	1.301	0.000	1.106	1.151	0.582	0.000	1.895	-0.279	-0.568	3.102	0.881	0.945	0.998	0.559	0.649	0.638	0.660
-1	2.105	0.248	-0.797	0.530	0.206	1.957	-2.175	0.797	0.000	1.193	0.637	-1.646	2.215	0.881	1.111	-1.046	0.000	0.872	-0.185	1.085	1.551	0.986	1.343	1.151	1.069	0.714	2.063	1.951
-1	1.838	1.060	1.637	1.017	1.370	0.913	0.461	-0.609	1.087	0.766	-0.461	0.303	2.215	0.724	-0.061	0.886	0.000	0.941	1.123	-0.745	0.000	0.858	0.847	0.979	1.313	1.083	1.094	0.910
-0	0.364	1.274	1.066	1.570	-0.394	0.485	0.012	-1.716	0.000	0.317	-1.233	0.534	2.215	0.548	-2.165	0.762	0.000	0.729	0.169	-0.318	3.102	0.892	0.944	1.013	0.594	0.461	0.688	0.715
-1	0.503	1.343	-0.031	1.134	-1.204	0.590	-0.309	0.174	2.173	0.408	2.372	-0.628	0.000	1.850	0.400	1.147	2.548	0.664	-0.458	-0.885	0.000	1.445	1.283	0.989	1.280	1.118	1.127	1.026
-0	1.873	0.258	0.103	2.491	0.530	1.678	0.644	-1.738	2.173	1.432	0.848	-1.340	0.000	0.621	1.323	-1.316	0.000	0.628	0.789	-0.206	1.551	0.426	0.802	1.125	0.688	1.079	1.338	1.239
-1	0.826	-0.732	1.587	0.582	-1.236	0.495	0.757	-0.741	2.173	0.940	1.474	0.354	2.215	0.474	1.055	-1.657	0.000	0.415	1.758	0.841	0.000	0.451	0.578	0.984	0.757	0.922	0.860	0.696
-0	0.935	-1.614	-0.597	0.299	1.223	0.707	-0.853	-1.026	0.000	0.751	0.007	-1.691	0.000	1.062	-0.125	0.976	2.548	0.877	1.275	0.646	0.000	0.962	1.074	0.980	0.608	0.726	0.741	0.662
-1	0.643	0.542	-1.285	0.474	-0.366	0.667	-0.446	1.195	2.173	1.076	0.145	-0.126	0.000	0.970	-0.661	0.394	1.274	1.218	-0.184	-1.722	0.000	1.331	1.019	0.985	1.192	0.677	0.973	0.910
-0	0.713	0.164	1.080	1.427	-0.460	0.960	-0.152	-0.940	2.173	1.427	-0.901	1.036	1.107	0.440	-1.269	-0.194	0.000	0.452	1.932	-0.532	0.000	1.542	1.210	1.374	1.319	1.818	1.220	1.050
-0	0.876	-0.463	-1.224	2.458	-1.689	1.007	-0.752	0.398	0.000	2.456	-1.285	-0.152	1.107	1.641	1.838	1.717	0.000	0.458	0.194	0.488	3.102	4.848	2.463	0.986	1.981	0.974	2.642	2.258
-1	0.384	-0.275	0.387	1.403	-0.994	0.620	-1.529	1.685	0.000	1.091	-1.644	1.078	0.000	0.781	-1.311	0.326	2.548	1.228	-0.728	-0.633	1.551	0.920	0.854	0.987	0.646	0.609	0.740	0.884
-0	0.318	-1.818	-1.008	0.977	1.268	0.457	2.451	-1.522	0.000	0.881	1.351	0.461	2.215	0.929	0.239	-0.380	2.548	0.382	-0.613	1.330	0.000	1.563	1.193	0.994	0.829	0.874	0.901	1.026
-1	0.612	-1.120	1.098	0.402	-0.480	0.818	0.188	1.511	0.000	0.800	-0.253	0.977	0.000	1.175	0.271	-1.289	1.274	2.531	0.226	-0.409	3.102	0.889	0.947	0.979	1.486	0.940	1.152	1.119
-1	0.587	-0.737	-0.228	0.970	1.119	0.823	0.184	1.594	0.000	1.104	0.301	-0.818	2.215	0.819	0.712	-0.560	0.000	2.240	-0.419	0.340	3.102	1.445	1.103	0.988	0.715	1.363	1.019	0.926
-0	1.030	-0.694	-1.638	0.893	-1.074	1.160	-0.766	0.485	0.000	1.632	-0.698	-1.142	2.215	1.050	-1.092	0.952	0.000	1.475	0.286	0.125	3.102	0.914	1.075	0.982	0.732	1.493	1.219	1.079
-1	2.142	0.617	1.517	0.387	-0.862	0.345	1.203	-1.014	2.173	0.609	1.092	0.275	0.000	1.331	0.582	-0.183	2.548	0.557	1.540	-1.642	0.000	0.801	0.737	1.060	0.715	0.626	0.749	0.674
-0	1.076	0.240	-0.246	0.871	-1.241	0.496	0.282	0.746	2.173	1.095	-0.648	1.100	2.215	0.446	-1.756	0.764	0.000	0.434	0.788	-0.991	0.000	1.079	0.868	1.047	0.818	0.634	0.795	0.733
-0	1.400	0.901	-1.617	0.625	-0.163	0.661	-0.411	-1.616	2.173	0.685	0.524	0.425	0.000	0.881	-0.766	0.312	0.000	0.979	0.255	-0.667	3.102	0.898	1.105	1.253	0.730	0.716	0.738	0.795
-0	3.302	1.132	1.051	0.658	0.768	1.308	0.251	-0.374	1.087	1.673	0.015	-0.898	0.000	0.688	-0.535	1.363	1.274	0.871	1.325	-1.583	0.000	1.646	1.249	0.995	1.919	1.288	1.330	1.329
-0	1.757	0.202	0.750	0.767	-0.362	0.932	-1.033	-1.366	0.000	1.529	-1.012	-0.771	0.000	1.161	-0.287	0.059	0.000	2.185	1.147	1.099	3.102	0.795	0.529	1.354	1.144	1.491	1.319	1.161
-0	1.290	0.905	-1.711	1.017	-0.695	1.008	-1.038	0.693	2.173	1.202	-0.595	0.187	0.000	1.011	0.139	-1.607	0.000	0.789	-0.613	-1.041	3.102	1.304	0.895	1.259	1.866	0.955	1.211	1.200
-1	1.125	-0.004	1.694	0.373	0.329	0.978	0.640	-0.391	0.000	1.122	-0.376	1.521	2.215	0.432	2.413	-1.259	0.000	0.969	0.730	0.512	3.102	0.716	0.773	0.991	0.624	0.977	0.981	0.875
-0	1.081	0.861	1.252	1.621	1.474	1.293	0.600	0.630	0.000	1.991	-0.090	-0.675	2.215	0.861	1.105	-0.201	0.000	1.135	2.489	-1.659	0.000	1.089	0.657	0.991	2.179	0.412	1.334	1.071
-1	0.652	-0.294	1.241	1.034	0.490	1.033	0.551	-0.963	2.173	0.661	1.031	-1.654	2.215	1.376	-0.018	0.843	0.000	0.943	-0.329	-0.269	0.000	1.085	1.067	0.991	1.504	0.773	1.135	0.993
-1	1.408	-1.028	-1.018	0.252	-0.242	0.465	-0.364	-0.200	0.000	1.466	0.669	0.739	1.107	1.031	0.415	-1.468	2.548	0.457	-1.091	-1.722	0.000	0.771	0.811	0.979	1.459	1.204	1.041	0.866
-1	0.781	-1.143	-0.659	0.961	1.266	1.183	-0.686	0.119	2.173	1.126	-0.064	1.447	0.000	0.730	1.430	-1.535	0.000	1.601	0.513	1.658	0.000	0.871	1.345	1.184	1.058	0.620	1.107	0.978
-1	1.300	-0.616	1.032	0.751	-0.731	0.961	-0.716	1.592	0.000	2.079	-1.063	-0.271	2.215	0.475	0.518	1.695	1.274	0.395	-2.204	0.349	0.000	1.350	0.983	1.369	1.265	1.428	1.135	0.982
-1	0.833	0.809	1.657	1.637	1.019	0.705	1.077	-0.968	2.173	1.261	0.114	-0.298	1.107	1.032	0.017	0.236	0.000	0.640	-0.026	-1.598	0.000	0.894	0.982	0.981	1.250	1.054	1.018	0.853
-1	1.686	-1.090	-0.301	0.890	0.557	1.304	-0.284	-1.393	2.173	0.388	2.118	0.513	0.000	0.514	-0.015	0.891	0.000	0.460	0.547	0.627	3.102	0.942	0.524	1.186	1.528	0.889	1.015	1.122
-1	0.551	0.911	0.879	0.379	-0.796	1.154	-0.808	-0.966	0.000	1.168	-0.513	0.355	2.215	0.646	-1.309	0.773	0.000	0.544	-0.283	1.301	3.102	0.847	0.705	0.990	0.772	0.546	0.790	0.719
-1	1.597	0.793	-1.119	0.691	-1.455	0.370	0.337	1.354	0.000	0.646	-1.005	0.732	2.215	1.019	0.040	0.209	0.000	0.545	0.958	0.239	3.102	0.962	0.793	0.994	0.719	0.745	0.812	0.739
-0	1.033	-1.193	-0.452	0.247	0.970	0.503	-1.424	1.362	0.000	1.062	-0.416	-1.156	2.215	0.935	-0.023	0.555	2.548	0.410	-1.766	0.379	0.000	0.590	0.953	0.991	0.717	1.081	0.763	0.690
-1	0.859	-1.004	1.521	0.781	-0.993	0.677	0.643	-0.338	2.173	0.486	0.409	1.283	0.000	0.679	0.110	0.285	0.000	0.715	-0.735	-0.157	1.551	0.702	0.773	0.984	0.627	0.633	0.694	0.643
-0	0.612	-1.127	1.074	1.225	-0.426	0.927	-2.141	-0.473	0.000	1.290	-0.927	-1.085	2.215	1.183	1.981	-1.687	0.000	2.176	0.406	-1.581	0.000	0.945	0.651	1.170	0.895	1.604	1.179	1.142
-1	0.535	0.321	-1.095	0.281	-0.960	0.876	-0.709	-0.076	0.000	1.563	-0.666	1.536	2.215	0.773	-0.321	0.435	0.000	0.682	-0.801	-0.952	3.102	0.711	0.667	0.985	0.888	0.741	0.872	0.758
-1	0.745	1.586	1.578	0.863	-1.423	0.530	1.714	1.085	0.000	1.174	0.679	1.015	0.000	1.158	0.609	-1.186	2.548	1.851	0.832	-0.248	3.102	0.910	1.164	0.983	0.947	0.858	0.928	0.823
-0	0.677	-1.014	-1.648	1.455	1.461	0.596	-2.358	0.517	0.000	0.800	0.849	-0.743	2.215	1.024	-0.282	-1.004	0.000	1.846	-0.977	0.378	3.102	2.210	1.423	0.982	1.074	1.623	1.417	1.258
-1	0.815	-1.263	0.057	1.018	-0.208	0.339	-0.347	-1.646	2.173	1.223	0.600	-1.658	2.215	1.435	0.042	0.926	0.000	0.777	1.698	-0.698	0.000	1.022	1.058	1.000	0.784	0.477	0.886	0.836
-0	3.512	-1.094	-0.220	0.338	-0.328	1.962	-1.099	1.544	1.087	1.461	-1.305	-0.922	2.215	1.219	-1.289	0.400	0.000	0.731	0.155	1.249	0.000	1.173	1.366	0.993	2.259	2.000	1.626	1.349
-0	0.904	1.248	0.325	0.317	-1.624	0.685	-0.538	1.665	2.173	0.685	-2.145	-1.106	0.000	0.632	-1.460	1.017	0.000	1.085	-0.182	0.162	3.102	0.885	0.801	0.989	0.930	0.904	1.012	0.961

contrib/gbdt/lightgbm/lightgbm-example.ipynb

@@ -1,270 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.  \n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/contrib/gbdt/lightgbm/lightgbm-example.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Use LightGBM Estimator in Azure Machine Learning\n",
-        "In this notebook we will demonstrate how to run a training job using LightGBM Estimator. [LightGBM](https://lightgbm.readthedocs.io/en/latest/) is a gradient boosting framework that uses tree based learning algorithms. "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Prerequisites\n",
-        "This notebook uses azureml-contrib-gbdt package, if you don't already have the package, please install by uncommenting below cell."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#!pip install azureml-contrib-gbdt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Workspace, Run, Experiment\n",
-        "import shutil, os\n",
-        "from azureml.widgets import RunDetails\n",
-        "from azureml.contrib.gbdt import LightGBM\n",
-        "from azureml.train.dnn import Mpi\n",
-        "from azureml.core.compute import AmlCompute, ComputeTarget\n",
-        "from azureml.core.compute_target import ComputeTargetException"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "If you are using an AzureML Compute Instance, you are all set. Otherwise, go through the [configuration.ipynb](../../../configuration.ipynb) notebook to install the Azure Machine Learning Python SDK and create an Azure ML Workspace"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Set up machine learning resources"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "print('Workspace name: ' + ws.name, \n",
-        "      'Azure region: ' + ws.location, \n",
-        "      'Subscription id: ' + ws.subscription_id, \n",
-        "      'Resource group: ' + ws.resource_group, sep = '\\n')"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "cluster_vm_size = \"STANDARD_DS14_V2\"\n",
-        "cluster_min_nodes = 0\n",
-        "cluster_max_nodes = 20\n",
-        "cpu_cluster_name = 'TrainingCompute2' \n",
-        "\n",
-        "try:\n",
-        "    cpu_cluster = AmlCompute(ws, cpu_cluster_name)\n",
-        "    if cpu_cluster and type(cpu_cluster) is AmlCompute:\n",
-        "        print('found compute target: ' + cpu_cluster_name)\n",
-        "except ComputeTargetException:\n",
-        "    print('creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = cluster_vm_size, \n",
-        "                                                                vm_priority = 'lowpriority', \n",
-        "                                                                min_nodes = cluster_min_nodes, \n",
-        "                                                                max_nodes = cluster_max_nodes)\n",
-        "    cpu_cluster = ComputeTarget.create(ws, cpu_cluster_name, provisioning_config)\n",
-        "    \n",
-        "    # can poll for a minimum number of nodes and for a specific timeout. \n",
-        "    # if no min node count is provided it will use the scale settings for the cluster\n",
-        "    cpu_cluster.wait_for_completion(show_output=True, min_node_count=None, timeout_in_minutes=20)\n",
-        "    \n",
-        "     # For a more detailed view of current Azure Machine Learning Compute  status, use get_status()\n",
-        "    print(cpu_cluster.get_status().serialize())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "From this point, you can either upload training data file directly or use Datastore for training data storage\n",
-        "## Upload training file from local"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "scripts_folder = \"scripts_folder\"\n",
-        "if not os.path.isdir(scripts_folder):\n",
-        "    os.mkdir(scripts_folder)\n",
-        "shutil.copy('./train.conf', os.path.join(scripts_folder, 'train.conf'))\n",
-        "shutil.copy('./binary0.train', os.path.join(scripts_folder, 'binary0.train'))\n",
-        "shutil.copy('./binary1.train', os.path.join(scripts_folder, 'binary1.train'))\n",
-        "shutil.copy('./binary0.test', os.path.join(scripts_folder, 'binary0.test'))\n",
-        "shutil.copy('./binary1.test', os.path.join(scripts_folder, 'binary1.test'))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_data_list=[\"binary0.train\", \"binary1.train\"]\n",
-        "validation_data_list = [\"binary0.test\", \"binary1.test\"]\n",
-        "lgbm = LightGBM(source_directory=scripts_folder, \n",
-        "                compute_target=cpu_cluster, \n",
-        "                distributed_training=Mpi(),\n",
-        "                node_count=2,\n",
-        "                lightgbm_config='train.conf',\n",
-        "                data=training_data_list,\n",
-        "                valid=validation_data_list\n",
-        "               )\n",
-        "experiment_name = 'lightgbm-estimator-test'\n",
-        "experiment = Experiment(ws, name=experiment_name)\n",
-        "run = experiment.submit(lgbm, tags={\"test public docker image\": None})\n",
-        "RunDetails(run).show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "run.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Use data reference"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.datastore import Datastore\n",
-        "from azureml.data.data_reference import DataReference\n",
-        "datastore = ws.get_default_datastore()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "datastore.upload(src_dir='.',\n",
-        "                 target_path='.',\n",
-        "                 show_progress=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "training_data_list=[\"binary0.train\", \"binary1.train\"]\n",
-        "validation_data_list = [\"binary0.test\", \"binary1.test\"]\n",
-        "lgbm = LightGBM(source_directory='.', \n",
-        "                compute_target=cpu_cluster, \n",
-        "                distributed_training=Mpi(),\n",
-        "                node_count=2,\n",
-        "                inputs=[datastore.as_mount()],\n",
-        "                lightgbm_config='train.conf',\n",
-        "                data=training_data_list,\n",
-        "                valid=validation_data_list\n",
-        "               )\n",
-        "experiment_name = 'lightgbm-estimator-test'\n",
-        "experiment = Experiment(ws, name=experiment_name)\n",
-        "run = experiment.submit(lgbm, tags={\"use datastore.as_mount()\": None})\n",
-        "RunDetails(run).show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "run.wait_for_completion(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# uncomment below and run if compute resources are no longer needed\n",
-        "# cpu_cluster.delete() "
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jingywa"
-      }
-    ],
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "python",
-      "name": "python36"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.9"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

contrib/gbdt/lightgbm/lightgbm-example.yml

@@ -1,7 +0,0 @@
-name: lightgbm-example
-dependencies:
-- pip:
-  - azureml-sdk
-  - azureml-contrib-gbdt
-  - azureml-widgets
-  - azureml-core

contrib/gbdt/lightgbm/train.conf

@@ -1,111 +0,0 @@
-# task type, support train and predict
-task = train
-
-# boosting type, support gbdt for now, alias: boosting, boost
-boosting_type = gbdt
-
-# application type, support following application
-# regression , regression task
-# binary , binary classification task
-# lambdarank , lambdarank task
-# alias: application, app
-objective = binary
-
-# eval metrics, support multi metric, delimite by ',' , support following metrics
-# l1 
-# l2 , default metric for regression
-# ndcg , default metric for lambdarank
-# auc 
-# binary_logloss , default metric for binary
-# binary_error
-metric = binary_logloss,auc
-
-# frequence for metric output
-metric_freq = 1
-
-# true if need output metric for training data, alias: tranining_metric, train_metric
-is_training_metric = true
-
-# number of bins for feature bucket, 255 is a recommend setting, it can save memories, and also has good accuracy. 
-max_bin = 255
-
-# training data
-# if exsting weight file, should name to "binary.train.weight"
-# alias: train_data, train
-data = binary.train
-
-# validation data, support multi validation data, separated by ','
-# if exsting weight file, should name to "binary.test.weight"
-# alias: valid, test, test_data, 
-valid_data = binary.test
-
-# number of trees(iterations), alias: num_tree, num_iteration, num_iterations, num_round, num_rounds
-num_trees = 100
-
-# shrinkage rate , alias: shrinkage_rate
-learning_rate = 0.1
-
-# number of leaves for one tree, alias: num_leaf
-num_leaves = 63
-
-# type of tree learner, support following types:
-# serial , single machine version
-# feature , use feature parallel to train
-# data , use data parallel to train
-# voting , use voting based parallel to train
-# alias: tree
-tree_learner = feature
-
-# number of threads for multi-threading. One thread will use one CPU, defalut is setted to #cpu. 
-# num_threads = 8
-
-# feature sub-sample, will random select 80% feature to train on each iteration 
-# alias: sub_feature
-feature_fraction = 0.8
-
-# Support bagging (data sub-sample), will perform bagging every 5 iterations
-bagging_freq = 5
-
-# Bagging farction, will random select 80% data on bagging
-# alias: sub_row
-bagging_fraction = 0.8
-
-# minimal number data for one leaf, use this to deal with over-fit
-# alias : min_data_per_leaf, min_data
-min_data_in_leaf = 50
-
-# minimal sum hessians for one leaf, use this to deal with over-fit
-min_sum_hessian_in_leaf = 5.0
-
-# save memory and faster speed for sparse feature, alias: is_sparse
-is_enable_sparse = true
-
-# when data is bigger than memory size, set this to true. otherwise set false will have faster speed
-# alias: two_round_loading, two_round
-use_two_round_loading = false
-
-# true if need to save data to binary file and application will auto load data from binary file next time
-# alias: is_save_binary, save_binary
-is_save_binary_file = false
-
-# output model file
-output_model = LightGBM_model.txt
-
-# support continuous train from trained gbdt model
-# input_model= trained_model.txt
-
-# output prediction file for predict task
-# output_result= prediction.txt
-
-# support continuous train from initial score file
-# input_init_score= init_score.txt
-
-
-# number of machines in parallel training, alias: num_machine
-num_machines = 2
-
-# local listening port in parallel training, alias: local_port
-local_listen_port = 12400
-
-# machines list file for parallel training, alias: mlist
-machine_list_file = mlist.txt

how-to-use-azureml/README.md

@@ -4,12 +4,11 @@ Learn how to use Azure Machine Learning services for experimentation and model m
 
 As a pre-requisite, run the [configuration Notebook](../configuration.ipynb) notebook first to set up your Azure ML Workspace. Then, run the notebooks in following recommended order.
 
-* [train-within-notebook](./training/train-within-notebook): Train a model hile tracking run history, and learn how to deploy the model as web service to Azure Container Instance.
+* [train-within-notebook](./training/train-within-notebook): Train a model while tracking run history, and learn how to deploy the model as web service to Azure Container Instance.
 * [train-on-local](./training/train-on-local): Learn how to submit a run to local computer and use Azure ML managed run configuration.
 * [train-on-amlcompute](./training/train-on-amlcompute): Use a 1-n node Azure ML managed compute cluster for remote runs on Azure CPU or GPU infrastructure.
 * [train-on-remote-vm](./training/train-on-remote-vm): Use Data Science Virtual Machine as a target for remote runs.
 * [logging-api](./track-and-monitor-experiments/logging-api): Learn about the details of logging metrics to run history.
-* [register-model-create-image-deploy-service](./deployment/register-model-create-image-deploy-service): Learn about the details of model management.
 * [production-deploy-to-aks](./deployment/production-deploy-to-aks) Deploy a model to production at scale on Azure Kubernetes Service.
 * [enable-app-insights-in-production-service](./deployment/enable-app-insights-in-production-service) Learn how to use App Insights with production web service.
  

how-to-use-azureml/automated-machine-learning/README.md

@@ -1,8 +1,8 @@
 # Table of Contents
 1. [Automated ML Introduction](#introduction)
-1. [Setup using Azure Notebooks](#jupyter)
-1. [Setup using Azure Databricks](#databricks)
+1. [Setup using Compute Instances](#jupyter)
 1. [Setup using a Local Conda environment](#localconda)
+1. [Setup using Azure Databricks](#databricks)
 1. [Automated ML SDK Sample Notebooks](#samples)
 1. [Documentation](#documentation)
 1. [Running using python command](#pythoncommand)
@@ -21,13 +21,13 @@ Below are the three execution environments supported by automated ML.
 
 
  <a name="jupyter"></a>
-## Setup using Notebook VMs - Jupyter based notebooks from a Azure VM
+## Setup using Compute Instances - Jupyter based notebooks from a Azure Virtual Machine
 
 1. Open the [ML Azure portal](https://ml.azure.com)
 1. Select Compute
-1. Select Notebook VMs
+1. Select Compute Instances
 1. Click New
-1. Type a name for the Vm and select a VM type
+1. Type a Compute Name, select a Virtual Machine type and select a Virtual Machine size
 1. Click Create
 
 <a name="localconda"></a>
@@ -97,68 +97,96 @@ jupyter notebook
  <a name="databricks"></a>
 ## Setup using Azure Databricks
 
-**NOTE**: Please create your Azure Databricks cluster as v6.0 (high concurrency preferred) with **Python 3** (dropdown).
+**NOTE**: Please create your Azure Databricks cluster as v7.1 (high concurrency preferred) with **Python 3** (dropdown).
 **NOTE**: You should at least have contributor access to your Azure subcription to run the notebook.
-- Please remove the previous SDK version if there is any and install the latest SDK by installing **azureml-sdk[automl]** as a PyPi library in Azure Databricks workspace.
-- You can find the detail Readme instructions at [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks).
-- Download the sample notebook automl-databricks-local-01.ipynb from [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks) and import into the Azure databricks workspace.
+- You can find the detail Readme instructions at [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks/automl).
+- Download the sample notebook automl-databricks-local-01.ipynb from [GitHub](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks/automl) and import into the Azure databricks workspace.
 - Attach the notebook to the cluster.
 
 <a name="samples"></a>
 # Automated ML SDK Sample Notebooks
 
-- [auto-ml-classification-credit-card-fraud.ipynb](classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb)
-    - Dataset: Kaggle's [credit card fraud detection dataset](https://www.kaggle.com/mlg-ulb/creditcardfraud)
-    - Simple example of using automated ML for classification to fraudulent credit card transactions
-    - Uses azure compute for training
+## Classification
+- **Classify Credit Card Fraud**
+    - Dataset: [Kaggle's credit card fraud detection dataset](https://www.kaggle.com/mlg-ulb/creditcardfraud)
+      - **[Jupyter Notebook (remote run)](classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb)**
+          - run the experiment remotely on AML Compute cluster
+          - test the performance of the best model in the local environment
+      - **[Jupyter Notebook (local run)](local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.ipynb)**
+          - run experiment in the local environment
+          - use Mimic Explainer for computing feature importance
+          - deploy the best model along with the explainer to an Azure Kubernetes (AKS) cluster, which will compute the raw and engineered feature importances at inference time
+- **Predict Term Deposit Subscriptions in a Bank**
+    - Dataset: [UCI's bank marketing dataset](https://www.kaggle.com/janiobachmann/bank-marketing-dataset)
+        - **[Jupyter Notebook](classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb)**
+          - run experiment remotely on AML Compute cluster to generate ONNX compatible models
+          - view the featurization steps that were applied during training
+          - view feature importance for the best model
+          - download the best model in ONNX format and use it for inferencing using ONNXRuntime
+          - deploy the best model in PKL format to Azure Container Instance (ACI)
+- **Predict Newsgroup based on Text from News Article**
+    - Dataset: [20 newsgroups text dataset](https://scikit-learn.org/0.19/datasets/twenty_newsgroups.html)
+        - **[Jupyter Notebook](classification-text-dnn/auto-ml-classification-text-dnn.ipynb)**
+          - AutoML highlights here include using deep neural networks (DNNs) to create embedded features from text data
+          - AutoML will use Bidirectional Encoder Representations from Transformers (BERT) when a GPU compute is used
+          - Bidirectional Long-Short Term neural network (BiLSTM) will be utilized when a CPU compute is used, thereby optimizing the choice of DNN
 
-- [auto-ml-regression.ipynb](regression/auto-ml-regression.ipynb)
+## Regression
+- **Predict Performance of Hardware Parts**
     - Dataset: Hardware Performance Dataset
-    - Simple example of using automated ML for regression
-    - Uses azure compute for training
+        - **[Jupyter Notebook](regression/auto-ml-regression.ipynb)**
+            - run the experiment remotely on AML Compute cluster
+            - get best trained model for a different metric than the one the experiment was optimized for
+            - test the performance of the best model in the local environment
+        - **[Jupyter Notebook (advanced)](regression/auto-ml-regression.ipynb)**
+            - run the experiment remotely on AML Compute cluster
+            - customize featurization: override column purpose within the dataset, configure transformer parameters
+            - get best trained model for a different metric than the one the experiment was optimized for
+            - run a model explanation experiment on the remote cluster
+            - deploy the model along the explainer and run online inferencing
 
-- [auto-ml-regression-hardware-performance-explanation-and-featurization.ipynb](regression-hardware-performance-explanation-and-featurization/auto-ml-regression-hardware-performance-explanation-and-featurization.ipynb)
-    - Dataset: Hardware Performance Dataset
-    - Shows featurization and excplanation
-    - Uses azure compute for training
-
-- [auto-ml-forecasting-energy-demand.ipynb](forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb)
-    - Dataset: [NYC energy demand data](forecasting-a/nyc_energy.csv)
-    - Example of using automated ML for training a forecasting model
-
-- [auto-ml-classification-credit-card-fraud-local.ipynb](local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.ipynb)
-    - Dataset: Kaggle's [credit card fraud detection dataset](https://www.kaggle.com/mlg-ulb/creditcardfraud)
-    - Simple example of using automated ML for classification to fraudulent credit card transactions
-    - Uses local compute for training
-
-- [auto-ml-classification-bank-marketing-all-features.ipynb](classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb)
-    - Dataset: UCI's [bank marketing dataset](https://www.kaggle.com/janiobachmann/bank-marketing-dataset)
-    - Simple example of using automated ML for classification to predict term deposit subscriptions for a bank
-    - Uses azure compute for training
-
-- [auto-ml-forecasting-orange-juice-sales.ipynb](forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb)
-    - Dataset: [Dominick's grocery sales of orange juice](forecasting-b/dominicks_OJ.csv)
-    - Example of training an automated ML forecasting model on multiple time-series
-
-- [auto-ml-forecasting-bike-share.ipynb](forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb)
-    - Dataset: forecasting for a bike-sharing
-    - Example of training an automated ML forecasting model on multiple time-series
-
-- [automl-forecasting-function.ipynb](forecasting-high-frequency/automl-forecasting-function.ipynb)
-    - Example of training an automated ML forecasting model on multiple time-series
-
-- [auto-ml-forecasting-beer-remote.ipynb](forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb)
-    - Example of training an automated ML forecasting model on multiple time-series
-    - Beer Production Forecasting
-
-- [auto-ml-continuous-retraining.ipynb](continuous-retraining/auto-ml-continuous-retraining.ipynb)
-    - Continous retraining using Pipelines and Time-Series TabularDataset
-
-- [auto-ml-classification-text-dnn.ipynb](classification-text-dnn/auto-ml-classification-text-dnn.ipynb)
-    - Classification with text data using deep learning in AutoML
-    - AutoML highlights here include using deep neural networks (DNNs) to create embedded features from text data.
-    - Depending on the compute cluster the user provides, AutoML tried out Bidirectional Encoder Representations from Transformers (BERT) when a GPU compute is used.
-    - Bidirectional Long-Short Term neural network (BiLSTM) when a CPU compute is used, thereby optimizing the choice of DNN for the uesr's setup.
+## Time Series Forecasting
+- **Forecast Energy Demand**
+    - Dataset: [NYC energy demand data](http://mis.nyiso.com/public/P-58Blist.htm)
+        - **[Jupyter Notebook](forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb)**
+          - run experiment remotely on AML Compute cluster
+          - use lags and rolling window features
+          - view the featurization steps that were applied during training
+          - get the best model, use it to forecast on test data and compare the accuracy of predictions against real data
+- **Forecast Orange Juice Sales (Multi-Series)**
+    - Dataset: [Dominick's grocery sales of orange juice](forecasting-orange-juice-sales/dominicks_OJ.csv)
+        - **[Jupyter Notebook](forecasting-orange-juice-sales/dominicks_OJ.csv)**
+          - run experiment remotely on AML Compute cluster
+          - customize time-series featurization, change column purpose and override transformer hyper parameters
+          - evaluate locally the performance of the generated best model
+          - deploy the best model as a webservice on Azure Container Instance (ACI)
+          - get online predictions from the deployed model
+- **Forecast Demand of a Bike-Sharing Service**
+    - Dataset: [Bike demand data](forecasting-bike-share/bike-no.csv)
+        - **[Jupyter Notebook](forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb)**
+          - run experiment remotely on AML Compute cluster
+          - integrate holiday features
+          - run rolling forecast for test set that is longer than the forecast horizon
+          - compute metrics on the predictions from the remote forecast
+- **The Forecast Function Interface**
+    - Dataset: Generated for sample purposes
+        - **[Jupyter Notebook](forecasting-forecast-function/auto-ml-forecasting-function.ipynb)**
+          - train a forecaster using a remote AML Compute cluster
+          - capabilities of forecast function (e.g. forecast farther into the horizon)
+          - generate confidence intervals
+- **Forecast Beverage Production**
+    - Dataset: [Monthly beer production data](forecasting-beer-remote/Beer_no_valid_split_train.csv)
+        - **[Jupyter Notebook](forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb)**
+          - train using a remote AML Compute cluster
+          - enable the DNN learning model
+          - forecast on a remote compute cluster and compare different model performance
+- **Continuous Retraining with NOAA Weather Data**
+    - Dataset: [NOAA weather data from Azure Open Datasets](https://azure.microsoft.com/en-us/services/open-datasets/)
+        - **[Jupyter Notebook](continuous-retraining/auto-ml-continuous-retraining.ipynb)**
+          - continuously retrain a model using Pipelines and AutoML
+          - create a Pipeline to upload a time series dataset to an Azure blob
+          - create a Pipeline to run an AutoML experiment and register the best resulting model in the Workspace
+          - publish the training pipeline created and schedule it to run daily
 
 <a name="documentation"></a>
 See [Configure automated machine learning experiments](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-auto-train) to learn how more about the the settings and features available for automated machine learning experiments.
@@ -179,7 +207,7 @@ The main code of the file must be indented so that it is under this condition.
 ## automl_setup fails
 1. On Windows, make sure that you are running automl_setup from an Anconda Prompt window rather than a regular cmd window.  You can launch the "Anaconda Prompt" window by hitting the Start button and typing "Anaconda Prompt".  If you don't see the application "Anaconda Prompt", you might not have conda or mini conda installed.  In that case, you can install it [here](https://conda.io/miniconda.html)
 2. Check that you have conda 64-bit installed rather than 32-bit.  You can check this with the command `conda info`.  The `platform` should be `win-64` for Windows or `osx-64` for Mac.
-3. Check that you have conda 4.4.10 or later.  You can check the version with the command `conda -V`.  If you have a previous version installed, you can update it using the command: `conda update conda`.
+3. Check that you have conda 4.7.8 or later.  You can check the version with the command `conda -V`.  If you have a previous version installed, you can update it using the command: `conda update conda`.
 4. On Linux, if the error is `gcc: error trying to exec 'cc1plus': execvp: No such file or directory`, install build essentials using the command `sudo apt-get install build-essential`.
 5. Pass a new name as the first parameter to automl_setup so that it creates a new conda environment. You can view existing conda environments using `conda env list` and remove them with `conda env remove -n <environmentname>`.
 
@@ -197,6 +225,17 @@ If automl_setup_linux.sh fails on Ubuntu Linux with the error: `unable to execut
 4) Check that the region is one of the supported regions: `eastus2`, `eastus`, `westcentralus`, `southeastasia`, `westeurope`, `australiaeast`, `westus2`, `southcentralus`
 5) Check that you have access to the region using the Azure Portal.
 
+## import AutoMLConfig fails after upgrade from before 1.0.76 to 1.0.76 or later
+There were package changes in automated machine learning version 1.0.76, which require the previous version to be uninstalled before upgrading to the new version.
+If you have manually upgraded from a version of automated machine learning before 1.0.76 to 1.0.76 or later, you may get the error:
+`ImportError: cannot import name 'AutoMLConfig'`
+
+This can be resolved by running:
+`pip uninstall azureml-train-automl` and then 
+`pip install azureml-train-automl`
+
+The automl_setup.cmd script does this automatically.
+
 ## workspace.from_config fails
 If the call `ws = Workspace.from_config()` fails:
 1) Make sure that you have run the `configuration.ipynb` notebook successfully.
@@ -219,6 +258,15 @@ You may check the version of tensorflow and uninstall as follows
 2) enter `pip freeze` and look for `tensorflow` , if found, the version listed should be < 1.13
 3) If the listed version is a not a supported version,  `pip uninstall tensorflow` in the command shell and enter y for confirmation.
 
+## KeyError: 'brand' when running AutoML on local compute or Azure Databricks cluster**
+If a new environment was created after 10 June 2020 using SDK 1.7.0 or lower, training may fail with the above error due to an update in the py-cpuinfo package. (Environments created on or before 10 June 2020 are unaffected, as well as experiments run on remote compute as cached training images are used.) To work around this issue, either of the two following steps can be taken:
+
+1) Update the SDK version to 1.8.0 or higher (this will also downgrade py-cpuinfo to 5.0.0):
+`pip install --upgrade azureml-sdk[automl]`
+
+2) Downgrade the installed version of py-cpuinfo to 5.0.0:
+`pip install py-cpuinfo==5.0.0`
+
 ## Remote run: DsvmCompute.create fails
 There are several reasons why the DsvmCompute.create can fail.  The reason is usually in the error message but you have to look at the end of the error message for the detailed reason.  Some common reasons are:
 1) `Compute name is invalid, it should start with a letter, be between 2 and 16 character, and only include letters (a-zA-Z), numbers (0-9) and \'-\'.`  Note that underscore is not allowed in the name.

how-to-use-azureml/automated-machine-learning/automl_env.yml

@@ -2,37 +2,29 @@ name: azure_automl
 dependencies:
   # The python interpreter version.
   # Currently Azure ML only supports 3.5.2 and later.
-- pip
-- python>=3.5.2,<3.6.8
+- pip==21.1.2
+- python>=3.5.2,<3.8
 - nb_conda
+- boto3==1.15.18
 - matplotlib==2.1.0
-- numpy>=1.16.0,<=1.16.2
+- numpy==1.18.5
 - cython
 - urllib3<1.24
-- scipy>=1.0.0,<=1.1.0
-- scikit-learn>=0.19.0,<=0.20.3
-- pandas>=0.22.0,<=0.23.4
-- py-xgboost<=0.80
-- pyarrow>=0.11.0
-- fbprophet==0.5
-- pytorch=1.1.0
-- cudatoolkit=9.0
+- scipy>=1.4.1,<=1.5.2
+- scikit-learn==0.22.1
+- pandas==0.25.1
+- py-xgboost<=0.90
+- conda-forge::fbprophet==0.5
+- holidays==0.9.11
+- pytorch::pytorch=1.4.0
+- cudatoolkit=10.1.243
+- tornado==6.1.0
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-defaults
-  - azureml-train-automl
-  - azureml-train
-  - azureml-widgets
-  - azureml-explain-model
-  - azureml-pipeline
-  - azureml-contrib-interpret
-  - pandas_ml
+  - azureml-widgets~=1.34.0
   - pytorch-transformers==1.0.0
   - spacy==2.1.8
-  - joblib
   - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
-
-channels:
-- conda-forge
-- pytorch
+  - -r https://automlresources-prod.azureedge.net/validated-requirements/1.34.0/validated_win32_requirements.txt [--no-deps]
+  - arch==4.14

how-to-use-azureml/automated-machine-learning/automl_env_linux.yml

@@ -0,0 +1,30 @@
+name: azure_automl
+dependencies:
+  # The python interpreter version.
+  # Currently Azure ML only supports 3.5.2 and later.
+- pip==21.1.2
+- python>=3.5.2,<3.8
+- nb_conda
+- boto3==1.15.18
+- matplotlib==2.1.0
+- numpy==1.18.5
+- cython
+- urllib3<1.24
+- scipy>=1.4.1,<=1.5.2
+- scikit-learn==0.22.1
+- pandas==0.25.1
+- py-xgboost<=0.90
+- conda-forge::fbprophet==0.5
+- holidays==0.9.11
+- pytorch::pytorch=1.4.0
+- cudatoolkit=10.1.243
+- tornado==6.1.0
+
+- pip:
+  # Required packages for AzureML execution, history, and data preparation.
+  - azureml-widgets~=1.34.0
+  - pytorch-transformers==1.0.0
+  - spacy==2.1.8
+  - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
+  - -r https://automlresources-prod.azureedge.net/validated-requirements/1.34.0/validated_linux_requirements.txt [--no-deps]
+  - arch==4.14

how-to-use-azureml/automated-machine-learning/automl_env_mac.yml

@@ -2,38 +2,30 @@ name: azure_automl
 dependencies:
   # The python interpreter version.
   # Currently Azure ML only supports 3.5.2 and later.
-- pip
+- pip==21.1.2
 - nomkl
-- python>=3.5.2,<3.6.8
+- python>=3.5.2,<3.8
 - nb_conda
+- boto3==1.15.18
 - matplotlib==2.1.0
-- numpy>=1.16.0,<=1.16.2
+- numpy==1.18.5
 - cython
 - urllib3<1.24
-- scipy>=1.0.0,<=1.1.0
-- scikit-learn>=0.19.0,<=0.20.3
-- pandas>=0.22.0,<0.23.0
-- py-xgboost<=0.80
-- pyarrow>=0.11.0
-- fbprophet==0.5
-- pytorch=1.1.0
+- scipy>=1.4.1,<=1.5.2
+- scikit-learn==0.22.1
+- pandas==0.25.1
+- py-xgboost<=0.90
+- conda-forge::fbprophet==0.5
+- holidays==0.9.11
+- pytorch::pytorch=1.4.0
 - cudatoolkit=9.0
+- tornado==6.1.0
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-defaults
-  - azureml-train-automl
-  - azureml-train
-  - azureml-widgets
-  - azureml-explain-model
-  - azureml-pipeline
-  - azureml-contrib-interpret
-  - pandas_ml
+  - azureml-widgets~=1.34.0
   - pytorch-transformers==1.0.0
   - spacy==2.1.8
-  - joblib
   - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
-
-channels:
-- conda-forge
-- pytorch
+  - -r https://automlresources-prod.azureedge.net/validated-requirements/1.34.0/validated_darwin_requirements.txt [--no-deps]
+  - arch==4.14

how-to-use-azureml/automated-machine-learning/automl_setup.cmd

@@ -6,16 +6,28 @@ set PIP_NO_WARN_SCRIPT_LOCATION=0
 
 IF "%conda_env_name%"=="" SET conda_env_name="azure_automl"
 IF "%automl_env_file%"=="" SET automl_env_file="automl_env.yml"
+SET check_conda_version_script="check_conda_version.py"
 
 IF NOT EXIST %automl_env_file% GOTO YmlMissing
 
 IF "%CONDA_EXE%"=="" GOTO CondaMissing
 
+IF NOT EXIST %check_conda_version_script% GOTO VersionCheckMissing
+
+python "%check_conda_version_script%"
+IF errorlevel 1 GOTO ErrorExit:
+
+SET replace_version_script="replace_latest_version.ps1"
+IF EXIST %replace_version_script% (
+  powershell -file %replace_version_script% %automl_env_file%
+)
+
 call conda activate %conda_env_name% 2>nul:
 
 if not errorlevel 1 (
-  echo Upgrading azureml-sdk[automl,notebooks,explain] in existing conda environment %conda_env_name%
-  call pip install --upgrade azureml-sdk[automl,notebooks,explain]
+  echo Upgrading existing conda environment %conda_env_name%
+  call pip uninstall azureml-train-automl -y -q
+  call conda env update --name %conda_env_name% --file %automl_env_file%
   if errorlevel 1 goto ErrorExit
 ) else (
   call conda env create -f %automl_env_file% -n %conda_env_name%
@@ -53,6 +65,10 @@ echo If you are running an older version of Miniconda or Anaconda,
 echo you can upgrade using the command: conda update conda
 goto End
 
+:VersionCheckMissing
+echo File %check_conda_version_script% not found.
+goto End
+
 :YmlMissing
 echo File %automl_env_file% not found.
 

how-to-use-azureml/automated-machine-learning/automl_setup_linux.sh

@@ -4,6 +4,7 @@ CONDA_ENV_NAME=$1
 AUTOML_ENV_FILE=$2
 OPTIONS=$3
 PIP_NO_WARN_SCRIPT_LOCATION=0
+CHECK_CONDA_VERSION_SCRIPT="check_conda_version.py"
 
 if [ "$CONDA_ENV_NAME" == "" ]
 then
@@ -12,7 +13,7 @@ fi
 
 if [ "$AUTOML_ENV_FILE" == "" ]
 then
-  AUTOML_ENV_FILE="automl_env.yml"
+  AUTOML_ENV_FILE="automl_env_linux.yml"
 fi
 
 if [ ! -f $AUTOML_ENV_FILE ]; then
@@ -20,10 +21,23 @@ if [ ! -f $AUTOML_ENV_FILE ]; then
     exit 1
 fi
 
+if [ ! -f $CHECK_CONDA_VERSION_SCRIPT ]; then
+    echo "File $CHECK_CONDA_VERSION_SCRIPT not found"
+    exit 1
+fi
+
+python "$CHECK_CONDA_VERSION_SCRIPT"
+if [ $? -ne 0 ]; then
+    exit 1
+fi
+
+sed -i 's/AZUREML-SDK-VERSION/latest/' $AUTOML_ENV_FILE
+
 if source activate $CONDA_ENV_NAME 2> /dev/null
 then
-   echo "Upgrading azureml-sdk[automl,notebooks,explain] in existing conda environment" $CONDA_ENV_NAME
-   pip install --upgrade azureml-sdk[automl,notebooks,explain] &&
+   echo "Upgrading existing conda environment" $CONDA_ENV_NAME
+   pip uninstall azureml-train-automl -y -q
+   conda env update --name $CONDA_ENV_NAME --file $AUTOML_ENV_FILE &&
    jupyter nbextension uninstall --user --py azureml.widgets
 else
    conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&

how-to-use-azureml/automated-machine-learning/automl_setup_mac.sh

@@ -4,6 +4,7 @@ CONDA_ENV_NAME=$1
 AUTOML_ENV_FILE=$2
 OPTIONS=$3
 PIP_NO_WARN_SCRIPT_LOCATION=0
+CHECK_CONDA_VERSION_SCRIPT="check_conda_version.py"
 
 if [ "$CONDA_ENV_NAME" == "" ]
 then
@@ -20,10 +21,24 @@ if [ ! -f $AUTOML_ENV_FILE ]; then
     exit 1
 fi
 
+if [ ! -f $CHECK_CONDA_VERSION_SCRIPT ]; then
+    echo "File $CHECK_CONDA_VERSION_SCRIPT not found"
+    exit 1
+fi
+
+python "$CHECK_CONDA_VERSION_SCRIPT"
+if [ $? -ne 0 ]; then
+    exit 1
+fi
+
+sed -i '' 's/AZUREML-SDK-VERSION/latest/' $AUTOML_ENV_FILE
+brew install libomp
+
 if source activate $CONDA_ENV_NAME 2> /dev/null
 then
-   echo "Upgrading azureml-sdk[automl,notebooks,explain] in existing conda environment" $CONDA_ENV_NAME
-   pip install --upgrade azureml-sdk[automl,notebooks,explain] &&
+   echo "Upgrading existing conda environment" $CONDA_ENV_NAME
+   pip uninstall azureml-train-automl -y -q
+   conda env update --name $CONDA_ENV_NAME --file $AUTOML_ENV_FILE &&
    jupyter nbextension uninstall --user --py azureml.widgets
 else
    conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&

how-to-use-azureml/automated-machine-learning/check_conda_version.py

@@ -0,0 +1,26 @@
+from distutils.version import LooseVersion
+import platform
+
+try:
+    import conda
+except:
+    print('Failed to import conda.')
+    print('This setup is usually run from the base conda environment.')
+    print('You can activate the base environment using the command "conda activate base"')
+    exit(1)
+
+architecture = platform.architecture()[0]
+
+if architecture != "64bit":
+    print('This setup requires 64bit Anaconda or Miniconda.  Found: ' + architecture)
+    exit(1)
+
+minimumVersion = "4.7.8"
+
+versionInvalid = (LooseVersion(conda.__version__) < LooseVersion(minimumVersion))
+
+if versionInvalid:
+    print('Setup requires conda version ' + minimumVersion + ' or higher.')
+    print('You can use the command "conda update conda" to upgrade conda.')
+
+exit(versionInvalid)

how-to-use-azureml/automated-machine-learning/classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb

@@ -41,7 +41,7 @@
         "\n",
         "In this example we use the UCI Bank Marketing dataset to showcase how you can use AutoML for a  classification problem and deploy it to an Azure Container Instance (ACI). The classification goal is to predict if the client will subscribe to a term deposit with the bank.\n",
         "\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set.  Otherwise, go through the [configuration](../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
+        "If you are using an Azure Machine Learning Compute Instance, you are all set.  Otherwise, go through the [configuration](../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
         "\n",
         "Please find the ONNX related documentations [here](https://github.com/onnx/onnx).\n",
         "\n",
@@ -57,7 +57,7 @@
         "9. Test the ACI service.\n",
         "\n",
         "In addition this notebook showcases the following features\n",
-        "- **Blacklisting** certain pipelines\n",
+        "- **Blocking** certain pipelines\n",
         "- Specifying **target metrics** to indicate stopping criteria\n",
         "- Handling **missing data** in the input"
       ]
@@ -86,10 +86,52 @@
         "import azureml.core\n",
         "from azureml.core.experiment import Experiment\n",
         "from azureml.core.workspace import Workspace\n",
-        "from azureml.automl.core.featurization import FeaturizationConfig\n",
         "from azureml.core.dataset import Dataset\n",
         "from azureml.train.automl import AutoMLConfig\n",
-        "from azureml.explain.model._internal.explanation_client import ExplanationClient"
+        "from azureml.interpret import ExplanationClient"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Accessing the Azure ML workspace requires authentication with Azure.\n",
+        "\n",
+        "The default authentication is interactive authentication using the default tenant.  Executing the `ws = Workspace.from_config()` line in the cell below will prompt for authentication the first time that it is run.\n",
+        "\n",
+        "If you have multiple Azure tenants, you can specify the tenant by replacing the `ws = Workspace.from_config()` line in the cell below with the following:\n",
+        "\n",
+        "```\n",
+        "from azureml.core.authentication import InteractiveLoginAuthentication\n",
+        "auth = InteractiveLoginAuthentication(tenant_id = 'mytenantid')\n",
+        "ws = Workspace.from_config(auth = auth)\n",
+        "```\n",
+        "\n",
+        "If you need to run in an environment where interactive login is not possible, you can use Service Principal authentication by replacing the `ws = Workspace.from_config()` line in the cell below with the following:\n",
+        "\n",
+        "```\n",
+        "from azureml.core.authentication import ServicePrincipalAuthentication\n",
+        "auth = auth = ServicePrincipalAuthentication('mytenantid', 'myappid', 'mypassword')\n",
+        "ws = Workspace.from_config(auth = auth)\n",
+        "```\n",
+        "For more details, see [aka.ms/aml-notebook-auth](http://aka.ms/aml-notebook-auth)"
       ]
     },
     {
@@ -106,7 +148,6 @@
         "experiment=Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
@@ -123,9 +164,12 @@
       "source": [
         "## Create or Attach existing AmlCompute\n",
         "You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+        "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\n",
         "#### Creation of AmlCompute takes approximately 5 minutes. \n",
         "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
+        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
       ]
     },
     {
@@ -134,35 +178,22 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.compute import AmlCompute\n",
-        "from azureml.core.compute import ComputeTarget\n",
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
-        "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpu-cluster-4\"\n",
+        "# Choose a name for your CPU cluster\n",
+        "cpu_cluster_name = \"cpu-cluster-4\"\n",
         "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "    \n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
         "                                                           max_nodes=6)\n",
+        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
         "\n",
-        "    # Create the cluster.\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "    \n",
-        "print('Checking cluster status...')\n",
-        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
-        "    \n",
-        "# For a more detailed view of current AmlCompute status, use get_status()."
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
@@ -285,15 +316,15 @@
         "|**task**|classification or regression or forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
         "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
-        "|**blacklist_models** or **whitelist_models** |*List* of *strings* indicating machine learning algorithms for AutoML to avoid in this run.<br><br> Allowed values for **Classification**<br><i>LogisticRegression</i><br><i>SGD</i><br><i>MultinomialNaiveBayes</i><br><i>BernoulliNaiveBayes</i><br><i>SVM</i><br><i>LinearSVM</i><br><i>KNN</i><br><i>DecisionTree</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>GradientBoosting</i><br><i>TensorFlowDNN</i><br><i>TensorFlowLinearClassifier</i><br><br>Allowed values for **Regression**<br><i>ElasticNet</i><br><i>GradientBoosting</i><br><i>DecisionTree</i><br><i>KNN</i><br><i>LassoLars</i><br><i>SGD</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>TensorFlowLinearRegressor</i><br><i>TensorFlowDNN</i><br><br>Allowed values for **Forecasting**<br><i>ElasticNet</i><br><i>GradientBoosting</i><br><i>DecisionTree</i><br><i>KNN</i><br><i>LassoLars</i><br><i>SGD</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>TensorFlowLinearRegressor</i><br><i>TensorFlowDNN</i><br><i>Arima</i><br><i>Prophet</i>|\n",
+        "|**blocked_models** | *List* of *strings* indicating machine learning algorithms for AutoML to avoid in this run. <br><br> Allowed values for **Classification**<br><i>LogisticRegression</i><br><i>SGD</i><br><i>MultinomialNaiveBayes</i><br><i>BernoulliNaiveBayes</i><br><i>SVM</i><br><i>LinearSVM</i><br><i>KNN</i><br><i>DecisionTree</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>GradientBoosting</i><br><i>TensorFlowDNN</i><br><i>TensorFlowLinearClassifier</i><br><br>Allowed values for **Regression**<br><i>ElasticNet</i><br><i>GradientBoosting</i><br><i>DecisionTree</i><br><i>KNN</i><br><i>LassoLars</i><br><i>SGD</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>TensorFlowLinearRegressor</i><br><i>TensorFlowDNN</i><br><br>Allowed values for **Forecasting**<br><i>ElasticNet</i><br><i>GradientBoosting</i><br><i>DecisionTree</i><br><i>KNN</i><br><i>LassoLars</i><br><i>SGD</i><br><i>RandomForest</i><br><i>ExtremeRandomTrees</i><br><i>LightGBM</i><br><i>TensorFlowLinearRegressor</i><br><i>TensorFlowDNN</i><br><i>Arima</i><br><i>Prophet</i>|\n",
+        "|**allowed_models** |  *List* of *strings* indicating machine learning algorithms for AutoML to use in this run. Same values listed above for **blocked_models** allowed for **allowed_models**.|\n",
         "|**experiment_exit_score**| Value indicating the target for *primary_metric*. <br>Once the target is surpassed the run terminates.|\n",
-        "|**experiment_timeout_minutes**| Maximum amount of time in minutes that all iterations combined can take before the experiment terminates.|\n",
+        "|**experiment_timeout_hours**| Maximum amount of time in hours that all iterations combined can take before the experiment terminates.|\n",
         "|**enable_early_stopping**| Flag to enble early termination if the score is not improving in the short term.|\n",
         "|**featurization**| 'auto' / 'off'  Indicator for whether featurization step should be done automatically or not. Note: If the input data is sparse, featurization cannot be turned on.|\n",
         "|**n_cross_validations**|Number of cross validation splits.|\n",
         "|**training_data**|Input dataset, containing both features and label column.|\n",
         "|**label_column_name**|The name of the label column.|\n",
-        "|**model_explainability**|Indicate to explain each trained pipeline or not.|\n",
         "\n",
         "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
       ]
@@ -305,7 +336,7 @@
       "outputs": [],
       "source": [
         "automl_settings = {\n",
-        "    \"experiment_timeout_minutes\" : 20,\n",
+        "    \"experiment_timeout_hours\" : 0.3,\n",
         "    \"enable_early_stopping\" : True,\n",
         "    \"iteration_timeout_minutes\": 5,\n",
         "    \"max_concurrent_iterations\": 4,\n",
@@ -320,12 +351,11 @@
         "                             debug_log = 'automl_errors.log',\n",
         "                             compute_target=compute_target,\n",
         "                             experiment_exit_score = 0.9984,\n",
-        "                             blacklist_models = ['KNN','LinearSVM'],\n",
+        "                             blocked_models = ['KNN','LinearSVM'],\n",
         "                             enable_onnx_compatible_models=True,\n",
         "                             training_data = train_data,\n",
         "                             label_column_name = label,\n",
         "                             validation_data = validation_dataset,\n",
-        "                             model_explainability=True,\n",
         "                             **automl_settings\n",
         "                            )"
       ]
@@ -334,8 +364,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
-        "In this example, we specify `show_output = True` to print currently running iterations to the console."
+        "Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
       ]
     },
     {
@@ -347,15 +376,6 @@
         "remote_run = experiment.submit(automl_config, show_output = False)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -370,8 +390,6 @@
       "outputs": [],
       "source": [
         "#from azureml.train.automl.run import AutoMLRun\n",
-        "#experiment_name = 'automl-classification-bmarketing'\n",
-        "#experiment = Experiment(ws, experiment_name)\n",
         "#remote_run = AutoMLRun(experiment=experiment, run_id='<run_ID_goes_here')\n",
         "#remote_run"
       ]
@@ -474,11 +492,10 @@
       "outputs": [],
       "source": [
         "# Wait for the best model explanation run to complete\n",
-        "from azureml.train.automl.run import AutoMLRun\n",
-        "model_explainability_run_id = remote_run.get_properties().get('ModelExplainRunId')\n",
+        "from azureml.core.run import Run\n",
+        "model_explainability_run_id = remote_run.id + \"_\" + \"ModelExplain\"\n",
         "print(model_explainability_run_id)\n",
-        "if model_explainability_run_id is not None:\n",
-        "    model_explainability_run = AutoMLRun(experiment=experiment, run_id=model_explainability_run_id)\n",
+        "model_explainability_run = Run(experiment=experiment, run_id=model_explainability_run_id)\n",
         "model_explainability_run.wait_for_completion()\n",
         "\n",
         "# Get the best run object\n",
@@ -558,7 +575,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.automl.core.onnx_convert import OnnxConverter\n",
+        "from azureml.automl.runtime.onnx_convert import OnnxConverter\n",
         "onnx_fl_path = \"./best_model.onnx\"\n",
         "OnnxConverter.save_onnx_model(onnx_mdl, onnx_fl_path)"
       ]
@@ -567,17 +584,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Predict with the ONNX model, using onnxruntime package\n",
-        "#### Note: The code will install the onnxruntime==0.4.0 if not installed. Newer versions of the onnxruntime have compatibility issues."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "test_df = test_dataset.to_pandas_dataframe()"
+        "### Predict with the ONNX model, using onnxruntime package"
       ]
     },
     {
@@ -591,48 +598,27 @@
         "from azureml.automl.core.onnx_convert import OnnxConvertConstants\n",
         "from azureml.train.automl import constants\n",
         "\n",
-        "if sys.version_info < OnnxConvertConstants.OnnxIncompatiblePythonVersion:\n",
-        "    python_version_compatible = True\n",
-        "else:\n",
-        "    python_version_compatible = False\n",
-        "\n",
-        "onnxrt_present = False\n",
-        "try:\n",
-        "    import onnxruntime\n",
-        "    from azureml.automl.core.onnx_convert import OnnxInferenceHelper    \n",
-        "    from onnxruntime import __version__ as ORT_VER\n",
-        "    if ORT_VER == '0.4.0':\n",
-        "        onnxrt_present = True\n",
-        "except ImportError:\n",
-        "    onnxrt_present = False\n",
-        "    \n",
-        "# Install the onnxruntime if the version 0.4.0 is not installed.\n",
-        "if not onnxrt_present:\n",
-        "    print(\"Installing the onnxruntime version 0.4.0.\")\n",
-        "    !{sys.executable} -m pip install --user --force-reinstall onnxruntime==0.4.0\n",
-        "    onnxrt_present = True\n",
+        "from azureml.automl.runtime.onnx_convert import OnnxInferenceHelper\n",
         "\n",
         "def get_onnx_res(run):\n",
         "    res_path = 'onnx_resource.json'\n",
         "    run.download_file(name=constants.MODEL_RESOURCE_PATH_ONNX, output_file_path=res_path)\n",
         "    with open(res_path) as f:\n",
-        "        onnx_res = json.load(f)\n",
-        "    return onnx_res\n",
+        "        result = json.load(f)\n",
+        "    return result\n",
         "\n",
-        "if onnxrt_present and python_version_compatible:    \n",
+        "if sys.version_info < OnnxConvertConstants.OnnxIncompatiblePythonVersion:\n",
+        "    test_df = test_dataset.to_pandas_dataframe()\n",
         "    mdl_bytes = onnx_mdl.SerializeToString()\n",
-        "    onnx_res = get_onnx_res(best_run)\n",
+        "    onnx_result = get_onnx_res(best_run)\n",
         "\n",
-        "    onnxrt_helper = OnnxInferenceHelper(mdl_bytes, onnx_res)\n",
+        "    onnxrt_helper = OnnxInferenceHelper(mdl_bytes, onnx_result)\n",
         "    pred_onnx, pred_prob_onnx = onnxrt_helper.predict(test_df)\n",
         "\n",
         "    print(pred_onnx)\n",
         "    print(pred_prob_onnx)\n",
         "else:\n",
-        "    if not python_version_compatible:\n",
-        "        print('Please use Python version 3.6 or 3.7 to run the inference helper.')    \n",
-        "    if not onnxrt_present:\n",
-        "        print('Please install the onnxruntime package to do the prediction with ONNX model.')"
+        "    print('Please use Python version 3.6 or 3.7 to run the inference helper.')"
       ]
     },
     {
@@ -643,7 +629,7 @@
         "\n",
         "### Retrieve the Best Model\n",
         "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+        "Below we select the best pipeline from our iterations.  The `get_output` method returns the best run and the fitted model. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
       ]
     },
     {
@@ -666,20 +652,6 @@
         "best_run, fitted_model = remote_run.get_output()"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import shutil\n",
-        "\n",
-        "sript_folder = os.path.join(os.getcwd(), 'inference')\n",
-        "project_folder = '/inference'\n",
-        "os.makedirs(project_folder, exist_ok=True)"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -689,10 +661,8 @@
         "model_name = best_run.properties['model_name']\n",
         "\n",
         "script_file_name = 'inference/score.py'\n",
-        "conda_env_file_name = 'inference/env.yml'\n",
         "\n",
-        "best_run.download_file('outputs/scoring_file_v_1_0_0.py', 'inference/score.py')\n",
-        "best_run.download_file('outputs/conda_env_v_1_0_0.yml', 'inference/env.yml')"
+        "best_run.download_file('outputs/scoring_file_v_1_0_0.py', 'inference/score.py')"
       ]
     },
     {
@@ -731,15 +701,12 @@
       "source": [
         "from azureml.core.model import InferenceConfig\n",
         "from azureml.core.webservice import AciWebservice\n",
-        "from azureml.core.webservice import Webservice\n",
         "from azureml.core.model import Model\n",
         "\n",
-        "inference_config = InferenceConfig(runtime = \"python\", \n",
-        "                                   entry_script = script_file_name,\n",
-        "                                   conda_file = conda_env_file_name)\n",
+        "inference_config = InferenceConfig(entry_script=script_file_name)\n",
         "\n",
-        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
-        "                                               memory_gb = 1, \n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 2, \n",
+        "                                               memory_gb = 2, \n",
         "                                               tags = {'area': \"bmData\", 'type': \"automl_classification\"}, \n",
         "                                               description = 'sample service for Automl Classification')\n",
         "\n",
@@ -750,24 +717,6 @@
         "print(aci_service.state)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Delete a Web Service\n",
-        "\n",
-        "Deletes the specified web service."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#aci_service.delete()"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -792,7 +741,9 @@
       "source": [
         "## Test\n",
         "\n",
-        "Now that the model is trained, run the test data through the trained model to get the predicted values."
+        "Now that the model is trained, run the test data through the trained model to get the predicted values.  This calls the ACI web service to do the prediction.\n",
+        "\n",
+        "Note that the JSON passed to the ACI web service is an array of rows of data.  Each row should either be an array of values in the same order that was used for training or a dictionary where the keys are the same as the column names used for training.  The example below uses dictionary rows."
       ]
     },
     {
@@ -832,10 +783,26 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "y_pred  = fitted_model.predict(X_test)\n",
+        "import requests\n",
+        "\n",
+        "X_test_json = X_test.to_json(orient='records')\n",
+        "data = \"{\\\"data\\\": \" + X_test_json +\"}\"\n",
+        "headers = {'Content-Type': 'application/json'}\n",
+        "\n",
+        "resp = requests.post(aci_service.scoring_uri, data, headers=headers)\n",
+        "\n",
+        "y_pred = json.loads(json.loads(resp.text))['result']"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
         "actual = array(y_test)\n",
         "actual = actual[:,0]\n",
-        "print(y_pred.shape, \" \", actual.shape)"
+        "print(len(y_pred), \" \", len(actual))"
       ]
     },
     {
@@ -844,8 +811,7 @@
       "source": [
         "### Calculate metrics for the prediction\n",
         "\n",
-        "Now visualize the data on a scatter plot to show what our truth (actual) values are compared to the predicted values \n",
-        "from the trained model that was returned."
+        "Now visualize the data as a confusion matrix that compared the predicted values against the actual values.\n"
       ]
     },
     {
@@ -855,12 +821,44 @@
       "outputs": [],
       "source": [
         "%matplotlib notebook\n",
-        "test_pred = plt.scatter(actual, y_pred, color='b')\n",
-        "test_test = plt.scatter(actual, actual, color='g')\n",
-        "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+        "from sklearn.metrics import confusion_matrix\n",
+        "import itertools\n",
+        "\n",
+        "cf =confusion_matrix(actual,y_pred)\n",
+        "plt.imshow(cf,cmap=plt.cm.Blues,interpolation='nearest')\n",
+        "plt.colorbar()\n",
+        "plt.title('Confusion Matrix')\n",
+        "plt.xlabel('Predicted')\n",
+        "plt.ylabel('Actual')\n",
+        "class_labels = ['no','yes']\n",
+        "tick_marks = np.arange(len(class_labels))\n",
+        "plt.xticks(tick_marks,class_labels)\n",
+        "plt.yticks([-0.5,0,1,1.5],['','no','yes',''])\n",
+        "# plotting text value inside cells\n",
+        "thresh = cf.max() / 2.\n",
+        "for i,j in itertools.product(range(cf.shape[0]),range(cf.shape[1])):\n",
+        "    plt.text(j,i,format(cf[i,j],'d'),horizontalalignment='center',color='white' if cf[i,j] >thresh else 'black')\n",
         "plt.show()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete a Web Service\n",
+        "\n",
+        "Deletes the specified web service."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aci_service.delete()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -884,7 +882,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "anumamah"
+        "name": "ratanase"
       }
     ],
     "category": "tutorial",

how-to-use-azureml/automated-machine-learning/classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.yml

@@ -2,12 +2,3 @@ name: auto-ml-classification-bank-marketing-all-features
 dependencies:
 - pip:
   - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - onnxruntime==0.4.0
-  - azureml-explain-model
-  - azureml-contrib-interpret

how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb

@@ -42,7 +42,7 @@
         "\n",
         "This notebook is using remote compute to train the model.\n",
         "\n",
-        "If you are using an Azure Machine Learning [Notebook VM](https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-1st-experiment-sdk-setup), you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
+        "If you are using an Azure Machine Learning Compute Instance, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
         "\n",
         "In this notebook you will learn how to:\n",
         "1. Create an experiment using an existing workspace.\n",
@@ -80,6 +80,23 @@
         "from azureml.train.automl import AutoMLConfig"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -94,7 +111,6 @@
         "experiment=Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
@@ -111,6 +127,9 @@
       "source": [
         "## Create or Attach existing AmlCompute\n",
         "A compute target is required to execute the Automated ML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+        "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\n",
         "#### Creation of AmlCompute takes approximately 5 minutes. \n",
         "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
         "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
@@ -122,35 +141,22 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.compute import AmlCompute\n",
-        "from azureml.core.compute import ComputeTarget\n",
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
-        "# Choose a name for your AmlCompute cluster.\n",
-        "amlcompute_cluster_name = \"cpu-cluster-1\"\n",
+        "# Choose a name for your CPU cluster\n",
+        "cpu_cluster_name = \"cpu-cluster-1\"\n",
         "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'cpu-cluster-1':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "    \n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_DS12_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
         "                                                           max_nodes=6)\n",
+        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
         "\n",
-        "    # Create the cluster.\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "    \n",
-        "print('Checking cluster status...')\n",
-        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
-        "\n",
-        "# For a more detailed view of current AmlCompute status, use get_status()."
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
@@ -209,11 +215,10 @@
       "source": [
         "automl_settings = {\n",
         "    \"n_cross_validations\": 3,\n",
-        "    \"primary_metric\": 'average_precision_score_weighted',\n",
-        "    \"preprocess\": True,\n",
+        "    \"primary_metric\": 'AUC_weighted',\n",
         "    \"enable_early_stopping\": True,\n",
         "    \"max_concurrent_iterations\": 2, # This is a limit for testing purpose, please increase it as per cluster size\n",
-        "    \"experiment_timeout_minutes\": 10, # This is a time limit for testing purposes, remove it for real use cases, this will drastically limit ablity to find the best model possible\n",
+        "    \"experiment_timeout_hours\": 0.25, # This is a time limit for testing purposes, remove it for real use cases, this will drastically limit ablity to find the best model possible\n",
         "    \"verbosity\": logging.INFO,\n",
         "}\n",
         "\n",
@@ -230,8 +235,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. Depending on the data and the number of iterations this can run for a while.\n",
-        "In this example, we specify `show_output = True` to print currently running iterations to the console."
+        "Call the `submit` method on the experiment object and pass the run configuration. Depending on the data and the number of iterations this can run for a while. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
       ]
     },
     {
@@ -254,15 +258,6 @@
         "#remote_run = AutoMLRun(experiment = experiment, run_id = '<replace with your run id>')"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -284,7 +279,11 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "metadata": {},
+      "metadata": {
+        "tags": [
+          "widget-rundetails-sample"
+        ]
+      },
       "outputs": [],
       "source": [
         "from azureml.widgets import RunDetails\n",
@@ -306,7 +305,7 @@
       "source": [
         "#### Explain model\n",
         "\n",
-        "Automated ML models can be explained and visualized using the SDK Explainability library. [Learn how to use the explainer](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/model-explanation-remote-amlcompute/auto-ml-model-explanations-remote-compute.ipynb)."
+        "Automated ML models can be explained and visualized using the SDK Explainability library. "
       ]
     },
     {
@@ -317,7 +316,7 @@
         "\n",
         "### Retrieve the Best Model\n",
         "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
       ]
     },
     {
@@ -335,17 +334,7 @@
       "metadata": {},
       "source": [
         "#### Print the properties of the model\n",
-        "The fitted_model is a python object and you can read the different properties of the object.\n",
-        "See *Print the properties of the model* section in [this sample notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification/auto-ml-classification.ipynb)."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Deploy\n",
-        "\n",
-        "To deploy the model into a web service endpoint, see _Deploy_ section in [this sample notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification-with-deployment/auto-ml-classification-with-deployment.ipynb)"
+        "The fitted_model is a python object and you can read the different properties of the object.\n"
       ]
     },
     {
@@ -429,22 +418,33 @@
       "source": [
         "This Credit Card fraud Detection dataset is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/ and is available at: https://www.kaggle.com/mlg-ulb/creditcardfraud\n",
         "\n",
+        "The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Universit\u00c3\u00a9 Libre de Bruxelles) on big data mining and fraud detection.\n",
+        "More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project\n",
         "\n",
-        "The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Universit\u00c3\u0192\u00c2\u00a9 Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project\n",
         "Please cite the following works:\n",
-        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tAndrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
-        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tDal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
-        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tDal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE\n",
-        "o\tDal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
-        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tCarcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-A\u00c3\u0192\u00c2\u00abl; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier\n",
-        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tCarcillo, Fabrizio; Le Borgne, Yann-A\u00c3\u0192\u00c2\u00abl; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing"
+        "\n",
+        "Andrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
+        "\n",
+        "Dal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
+        "\n",
+        "Dal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE\n",
+        "\n",
+        "Dal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
+        "\n",
+        "Carcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-A\u00c3\u00abl; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier\n",
+        "\n",
+        "Carcillo, Fabrizio; Le Borgne, Yann-A\u00c3\u00abl; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing\n",
+        "\n",
+        "Bertrand Lebichot, Yann-A\u00c3\u00abl Le Borgne, Liyun He, Frederic Obl\u00c3\u00a9, Gianluca Bontempi Deep-Learning Domain Adaptation Techniques for Credit Cards Fraud Detection, INNSBDDL 2019: Recent Advances in Big Data and Deep Learning, pp 78-88, 2019\n",
+        "\n",
+        "Fabrizio Carcillo, Yann-A\u00c3\u00abl Le Borgne, Olivier Caelen, Frederic Obl\u00c3\u00a9, Gianluca Bontempi Combining Unsupervised and Supervised Learning in Credit Card Fraud Detection Information Sciences, 2019"
       ]
     }
   ],
   "metadata": {
     "authors": [
       {
-        "name": "tzvikei"
+        "name": "ratanase"
       }
     ],
     "category": "tutorial",
@@ -452,7 +452,7 @@
       "AML Compute"
     ],
     "datasets": [
-      "creditcard"
+      "Creditcard"
     ],
     "deployment": [
       "None"

how-to-use-azureml/automated-machine-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.yml

@@ -2,10 +2,3 @@ name: auto-ml-classification-credit-card-fraud
 dependencies:
 - pip:
   - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-explain-model
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml

how-to-use-azureml/automated-machine-learning/classification-text-dnn/auto-ml-classification-text-dnn.ipynb

@@ -42,13 +42,12 @@
         "\n",
         "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
         "\n",
-        "An Enterprise workspace is required for this notebook. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade).\n",
-        "\n",
         "Notebook synopsis:\n",
+        "\n",
         "1. Creating an Experiment in an existing Workspace\n",
         "2. Configuration and remote run of AutoML for a text dataset (20 Newsgroups dataset from scikit-learn) for classification\n",
-        "3. Evaluating the final model on a test set\n",
-        "4. Deploying the model on ACI"
+        "3. Registering the best model for future use\n",
+        "4. Evaluating the final model on a test set"
       ]
     },
     {
@@ -84,6 +83,23 @@
         "from sklearn.datasets import fetch_20newsgroups"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -105,7 +121,6 @@
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace Name'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
@@ -121,9 +136,11 @@
       "metadata": {},
       "source": [
         "## Set up a compute cluster\n",
-        "This section uses a user-provided compute cluster (named \"cpu-cluster\" in this example). If a cluster with this name does not exist in the user's workspace, the below code will create a new cluster. You can choose the parameters of the cluster as mentioned in the comments.\n",
+        "This section uses a user-provided compute cluster (named \"dnntext-cluster\" in this example). If a cluster with this name does not exist in the user's workspace, the below code will create a new cluster. You can choose the parameters of the cluster as mentioned in the comments.\n",
         "\n",
-        "Whether you provide/select a CPU or GPU cluster, AutoML will choose the appropriate DNN for that setup - BiLSTM or BERT text featurizer will be included in the candidate featurizers on CPU and GPU respectively."
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\n",
+        "Whether you provide/select a CPU or GPU cluster, AutoML will choose the appropriate DNN for that setup - BiLSTM or BERT text featurizer will be included in the candidate featurizers on CPU and GPU respectively.  If your goal is to obtain the most accurate model, we recommend you use GPU clusters since BERT featurizers usually outperform BiLSTM featurizers."
       ]
     },
     {
@@ -132,34 +149,27 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "num_nodes = 2\n",
+        "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpu-dnntext\"\n",
+        "amlcompute_cluster_name = \"dnntext-cluster\"\n",
         "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "\n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # CPU for BiLSTM\n",
-        "                                                                # To use BERT, select a GPU such as \"STANDARD_NC6\" \n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_NC6\", # CPU for BiLSTM, such as \"STANDARD_DS12_V2\" \n",
+        "                                                           # To use BERT (this is recommended for best performance), select a GPU such as \"STANDARD_NC6\" \n",
         "                                                           # or similar GPU option\n",
         "                                                           # available in your workspace\n",
-        "                                                                max_nodes = 6)\n",
+        "                                                           max_nodes = num_nodes)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
         "\n",
-        "    # Create the cluster\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "\n",
-        "print('Checking cluster status...')\n",
-        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
-        "\n",
-        "# For a more detailed view of current AmlCompute status, use get_status()."
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
@@ -187,8 +197,8 @@
         "    '''\n",
         "    remove = ('headers', 'footers', 'quotes')\n",
         "    categories = [\n",
-        "        'alt.atheism',\n",
-        "        'talk.religion.misc',\n",
+        "        'rec.sport.baseball',\n",
+        "        'rec.sport.hockey',\n",
         "        'comp.graphics',\n",
         "        'sci.space',\n",
         "        ]\n",
@@ -218,7 +228,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Featch data and upload to datastore for use in training"
+        "#### Fetch data and upload to datastore for use in training"
       ]
     },
     {
@@ -263,7 +273,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "This step requires an Enterprise workspace to gain access to this feature. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade)."
+        "This notebook uses the blocked_models parameter to exclude some models that can take a longer time to train on some text datasets. You can choose to remove models from the blocked_models list but you may need to increase the experiment_timeout_hours parameter value to get results."
       ]
     },
     {
@@ -273,10 +283,9 @@
       "outputs": [],
       "source": [
         "automl_settings = {\n",
-        "    \"experiment_timeout_minutes\": 20,\n",
-        "    \"primary_metric\": 'accuracy',\n",
-        "    \"preprocess\": True,\n",
-        "    \"max_concurrent_iterations\": 4, \n",
+        "    \"experiment_timeout_minutes\": 30,\n",
+        "    \"primary_metric\": 'AUC_weighted',\n",
+        "    \"max_concurrent_iterations\": num_nodes, \n",
         "    \"max_cores_per_iteration\": -1,\n",
         "    \"enable_dnn\": True,\n",
         "    \"enable_early_stopping\": True,\n",
@@ -291,6 +300,7 @@
         "                             compute_target=compute_target,\n",
         "                             training_data=train_dataset,\n",
         "                             label_column_name=target_column_name,\n",
+        "                             blocked_models = ['LightGBM', 'XGBoostClassifier'],\n",
         "                             **automl_settings\n",
         "                            )"
       ]
@@ -308,25 +318,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "automl_run = experiment.submit(automl_config, show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_run"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_run.wait_for_completion()"
+        "automl_run = experiment.submit(automl_config, show_output=True)"
       ]
     },
     {
@@ -348,7 +340,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "You can test the model locally to get a feel of the input/output. This step may require additional package installations such as pytorch."
+        "You can test the model locally to get a feel of the input/output. When the model contains BERT, this step will require pytorch and pytorch-transformers installed in your local environment. The exact versions of these packages can be found in the **automl_env.yml** file located in the local copy of your MachineLearningNotebooks folder here:\n",
+        "MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/automl_env.yml"
       ]
     },
     {
@@ -357,15 +350,34 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "#best_run, fitted_model = local_run.get_output()"
+        "best_run, fitted_model = automl_run.get_output()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Deploying the model\n",
-        "We now use the best fitted model from the AutoML Run to make predictions on the test set.  "
+        "You can now see what text transformations are used to convert text data to features for this dataset, including deep learning transformations based on BiLSTM or Transformer (BERT is one implementation of a Transformer) models."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "text_transformations_used = []\n",
+        "for column_group in fitted_model.named_steps['datatransformer'].get_featurization_summary():\n",
+        "    text_transformations_used.extend(column_group['Transformations'])\n",
+        "text_transformations_used"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Registering the best model\n",
+        "We now register the best fitted model from the AutoML Run for use in future deployments.  "
       ]
     },
     {
@@ -465,7 +477,7 @@
       "source": [
         "script_folder = os.path.join(os.getcwd(), 'inference')\n",
         "os.makedirs(script_folder, exist_ok=True)\n",
-        "shutil.copy2('infer.py', script_folder)"
+        "shutil.copy('infer.py', script_folder)"
       ]
     },
     {
@@ -474,8 +486,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "test_run = run_inference(test_experiment, compute_target, script_folder, best_dnn_run, test_dataset,\n",
-        "                 target_column_name, model_name)"
+        "test_run = run_inference(test_experiment, compute_target, script_folder, best_dnn_run,\n",
+        "                         test_dataset, target_column_name, model_name)"
       ]
     },
     {
@@ -528,6 +540,9 @@
         "name": "anshirga"
       }
     ],
+    "compute": [
+      "AML Compute"
+    ],
     "datasets": [
       "None"
     ],

how-to-use-azureml/automated-machine-learning/classification-text-dnn/auto-ml-classification-text-dnn.yml

@@ -2,9 +2,3 @@ name: auto-ml-classification-text-dnn
 dependencies:
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-train
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels

how-to-use-azureml/automated-machine-learning/classification-text-dnn/helper.py

@@ -1,6 +1,5 @@
 import pandas as pd
 from azureml.core import Environment
-from azureml.core.conda_dependencies import CondaDependencies
 from azureml.train.estimator import Estimator
 from azureml.core.run import Run
 
@@ -8,13 +7,7 @@ from azureml.core.run import Run
 def run_inference(test_experiment, compute_target, script_folder, train_run,
                   test_dataset, target_column_name, model_name):
 
-    train_run.download_file('outputs/conda_env_v_1_0_0.yml',
-                            'inference/condafile.yml')
-
-    inference_env = Environment("myenv")
-    inference_env.docker.enabled = True
-    inference_env.python.conda_dependencies = CondaDependencies(
-        conda_dependencies_file_path='inference/condafile.yml')
+    inference_env = train_run.get_environment()
 
     est = Estimator(source_directory=script_folder,
                     entry_script='infer.py',
@@ -22,7 +15,9 @@ def run_inference(test_experiment, compute_target, script_folder, train_run,
                         '--target_column_name': target_column_name,
                         '--model_name': model_name
                     },
-                    inputs=[test_dataset.as_named_input('test_data')],
+                    inputs=[
+                        test_dataset.as_named_input('test_data')
+                    ],
                     compute_target=compute_target,
                     environment_definition=inference_env)
 

how-to-use-azureml/automated-machine-learning/classification-text-dnn/infer.py

@@ -1,9 +1,12 @@
-import numpy as np
 import argparse
-from azureml.core import Run
+
+import pandas as pd
+import numpy as np
+
 from sklearn.externals import joblib
-from azureml.automl.core._vendor.automl.client.core.common import metrics
-from automl.client.core.common import constants
+
+from azureml.automl.runtime.shared.score import scoring, constants
+from azureml.core import Run
 from azureml.core.model import Model
 
 
@@ -39,13 +42,16 @@ y_test_df = test_dataset.with_timestamp_columns(None) \
 
 predicted = model.predict_proba(X_test_df)
 
-# use automl metrics module
-scores = metrics.compute_metrics_classification(
-    np.array(predicted),
-    np.array(y_test_df),
-    class_labels=model.classes_,
-    metrics=list(constants.Metric.SCALAR_CLASSIFICATION_SET)
-)
+if isinstance(predicted, pd.DataFrame):
+    predicted = predicted.values
+
+# Use the AutoML scoring module
+train_labels = model.classes_
+class_labels = np.unique(np.concatenate((y_test_df.values, np.reshape(train_labels, (-1, 1)))))
+classification_metrics = list(constants.CLASSIFICATION_SCALAR_SET)
+scores = scoring.score_classification(y_test_df.values, predicted,
+                                      classification_metrics,
+                                      class_labels, train_labels)
 
 print("scores:")
 print(scores)

how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.ipynb

@@ -20,7 +20,7 @@
       "metadata": {},
       "source": [
         "# Automated Machine Learning \n",
-        "**Continous retraining using Pipelines and Time-Series TabularDataset**\n",
+        "**Continuous retraining using Pipelines and Time-Series TabularDataset**\n",
         "## Contents\n",
         "1. [Introduction](#Introduction)\n",
         "2. [Setup](#Setup)\n",
@@ -32,13 +32,6 @@
         "8. [Test Retraining](#Test-Retraining)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "An Enterprise workspace is required for this notebook. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page.](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -75,6 +68,23 @@
         "from azureml.train.automl import AutoMLConfig"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -112,7 +122,6 @@
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
@@ -132,9 +141,12 @@
         "#### Create or Attach existing AmlCompute\n",
         "\n",
         "You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+        "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\n",
         "#### Creation of AmlCompute takes approximately 5 minutes. \n",
         "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
+        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
       ]
     },
     {
@@ -143,33 +155,22 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.compute import AmlCompute, ComputeTarget\n",
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
-        "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpu-cluster-42\"\n",
+        "# Choose a name for your CPU cluster\n",
+        "amlcompute_cluster_name = \"cont-cluster\"\n",
         "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "    \n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
         "                                                           max_nodes=4)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
         "\n",
-        "    # Create the cluster.\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "    \n",
-        "    # Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "    # If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "    compute_target.wait_for_completion(show_output = True, min_node_count = 0, timeout_in_minutes = 10)\n",
-        "    \n",
-        "     # For a more detailed view of current AmlCompute status, use get_status()."
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
@@ -185,7 +186,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.runconfig import CondaDependencies, DEFAULT_CPU_IMAGE, RunConfiguration\n",
+        "from azureml.core.runconfig import CondaDependencies, RunConfiguration\n",
         "\n",
         "# create a new RunConfig object\n",
         "conda_run_config = RunConfiguration(framework=\"python\")\n",
@@ -194,12 +195,10 @@
         "conda_run_config.target = compute_target\n",
         "\n",
         "conda_run_config.environment.docker.enabled = True\n",
-        "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
         "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]', 'applicationinsights', 'azureml-opendatasets'], \n",
-        "                              conda_packages=['numpy', 'py-xgboost'], \n",
+        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]', 'applicationinsights', 'azureml-opendatasets', 'azureml-defaults'], \n",
+        "                              conda_packages=['numpy==1.16.2'], \n",
         "                              pin_sdk_version=False)\n",
-        "#cd.add_pip_package('azureml-explain-model')\n",
         "conda_run_config.environment.python.conda_dependencies = cd\n",
         "\n",
         "print('run config is ready')"
@@ -210,7 +209,24 @@
       "metadata": {},
       "source": [
         "## Data Ingestion Pipeline \n",
-        "For this demo, we will use NOAA weather data from [Azure Open Datasets](https://azure.microsoft.com/services/open-datasets/). You can replace this with your own dataset, or you can skip this pipeline if you already have a time-series based `TabularDataset`.\n",
+        "For this demo, we will use NOAA weather data from [Azure Open Datasets](https://azure.microsoft.com/services/open-datasets/). You can replace this with your own dataset, or you can skip this pipeline if you already have a time-series based `TabularDataset`.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# The name and target column of the Dataset to create \n",
+        "dataset = \"NOAA-Weather-DS4\"\n",
+        "target_column_name = \"temperature\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
         "\n",
         "### Upload Data Step\n",
         "The data ingestion pipeline has a single step with a script to query the latest weather data and upload it to the blob store. During the first run, the script will create and register a time-series based `TabularDataset` with the past one week of weather data. For each subsequent run, the script will create a partition in the blob store by querying NOAA for new weather data since the last modified time of the dataset (`dataset.data_changed_time`) and creating a data.csv file."
@@ -225,8 +241,6 @@
         "from azureml.pipeline.core import Pipeline, PipelineParameter\n",
         "from azureml.pipeline.steps import PythonScriptStep\n",
         "\n",
-        "# The name of the Dataset to create \n",
-        "dataset = \"NOAA-Weather-DS4\"\n",
         "ds_name = PipelineParameter(name=\"ds_name\", default_value=dataset)\n",
         "upload_data_step = PythonScriptStep(script_name=\"upload_weather_data.py\", \n",
         "                                         allow_reuse=False,\n",
@@ -262,7 +276,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "data_pipeline_run.wait_for_completion()"
+        "data_pipeline_run.wait_for_completion(show_output=False)"
       ]
     },
     {
@@ -272,7 +286,7 @@
         "## Training Pipeline\n",
         "### Prepare Training Data Step\n",
         "\n",
-        "Script to bring data into common X,y format. We need to set allow_reuse flag to False to allow the pipeline to run even when inputs don't change. We also need the name of the model to check the time the model was last trained."
+        "Script to check if new data is available since the model was last trained. If no new data is available, we cancel the remaining pipeline steps. We need to set allow_reuse flag to False to allow the pipeline to run even when inputs don't change. We also need the name of the model to check the time the model was last trained."
       ]
     },
     {
@@ -283,11 +297,8 @@
       "source": [
         "from azureml.pipeline.core import PipelineData\n",
         "\n",
-        "target_column = PipelineParameter(\"target_column\", default_value=\"y\")\n",
         "# The model name with which to register the trained model in the workspace.\n",
-        "model_name = PipelineParameter(\"model_name\", default_value=\"y\")\n",
-        "output_x = PipelineData(\"output_x\", datastore=dstor)\n",
-        "output_y = PipelineData(\"output_y\", datastore=dstor)"
+        "model_name = PipelineParameter(\"model_name\", default_value=\"noaaweatherds\")"
       ]
     },
     {
@@ -299,16 +310,23 @@
         "data_prep_step = PythonScriptStep(script_name=\"check_data.py\", \n",
         "                                         allow_reuse=False,\n",
         "                                         name=\"check_data\",\n",
-        "                                         arguments=[\"--target_column\", target_column,\n",
-        "                                                       \"--output_x\", output_x,\n",
-        "                                                       \"--output_y\", output_y,\n",
-        "                                                       \"--ds_name\", ds_name,\n",
+        "                                         arguments=[\"--ds_name\", ds_name,\n",
         "                                                    \"--model_name\", model_name],\n",
-        "                                         outputs=[output_x, output_y], \n",
         "                                         compute_target=compute_target, \n",
         "                                         runconfig=conda_run_config)"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core import Dataset\n",
+        "train_ds = Dataset.get_by_name(ws, dataset)\n",
+        "train_ds = train_ds.drop_columns([\"partition_date\"])"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -323,14 +341,14 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.train.automl import AutoMLStep, AutoMLConfig\n",
+        "from azureml.train.automl import AutoMLConfig\n",
+        "from azureml.pipeline.steps import AutoMLStep\n",
         "\n",
         "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 20,\n",
-        "    \"experiment_timeout_minutes\": 30,\n",
+        "    \"iteration_timeout_minutes\": 10,\n",
+        "    \"experiment_timeout_hours\": 0.25,\n",
         "    \"n_cross_validations\": 3,\n",
-        "    \"primary_metric\": 'r2_score',\n",
-        "    \"preprocess\": True,\n",
+        "    \"primary_metric\": 'normalized_root_mean_squared_error',\n",
         "    \"max_concurrent_iterations\": 3,\n",
         "    \"max_cores_per_iteration\": -1,\n",
         "    \"verbosity\": logging.INFO,\n",
@@ -341,8 +359,8 @@
         "                             debug_log = 'automl_errors.log',\n",
         "                             path = \".\",\n",
         "                             compute_target=compute_target,\n",
-        "                             run_configuration=conda_run_config,\n",
-        "                             data_script = \"get_data.py\",\n",
+        "                             training_data = train_ds,\n",
+        "                             label_column_name = target_column_name,\n",
         "                             **automl_settings\n",
         "                            )"
       ]
@@ -358,7 +376,7 @@
         "metrics_output_name = 'metrics_output'\n",
         "best_model_output_name = 'best_model_output'\n",
         "\n",
-        "metirics_data = PipelineData(name='metrics_data',\n",
+        "metrics_data = PipelineData(name='metrics_data',\n",
         "                           datastore=dstor,\n",
         "                           pipeline_output_name=metrics_output_name,\n",
         "                           training_output=TrainingOutput(type='Metrics'))\n",
@@ -377,8 +395,7 @@
         "automl_step = AutoMLStep(\n",
         "    name='automl_module',\n",
         "    automl_config=automl_config,\n",
-        "    inputs=[output_x, output_y],\n",
-        "    outputs=[metirics_data, model_data],\n",
+        "    outputs=[metrics_data, model_data],\n",
         "    allow_reuse=False)"
       ]
     },
@@ -431,7 +448,7 @@
       "outputs": [],
       "source": [
         "training_pipeline_run = experiment.submit(training_pipeline, pipeline_parameters={\n",
-        "        \"target_column\": \"temperature\", \"ds_name\": dataset, \"model_name\": \"noaaweatherds\"})"
+        "        \"ds_name\": dataset, \"model_name\": \"noaaweatherds\"})"
       ]
     },
     {
@@ -440,7 +457,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "training_pipeline_run.wait_for_completion()"
+        "training_pipeline_run.wait_for_completion(show_output=False)"
       ]
     },
     {
@@ -474,7 +491,7 @@
       "source": [
         "from azureml.pipeline.core import Schedule\n",
         "schedule = Schedule.create(workspace=ws, name=\"RetrainingSchedule\",\n",
-        "                           pipeline_parameters={\"target_column\": \"temperature\",\"ds_name\": dataset, \"model_name\": \"noaaweatherds\"},\n",
+        "                           pipeline_parameters={\"ds_name\": dataset, \"model_name\": \"noaaweatherds\"},\n",
         "                           pipeline_id=published_pipeline.id, \n",
         "                           experiment_name=experiment_name, \n",
         "                           datastore=dstor,\n",

how-to-use-azureml/automated-machine-learning/continuous-retraining/auto-ml-continuous-retraining.yml

@@ -2,8 +2,3 @@ name: auto-ml-continuous-retraining
 dependencies:
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-pipeline
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml

how-to-use-azureml/automated-machine-learning/continuous-retraining/check_data.py

@@ -15,32 +15,16 @@ if type(run) == _OfflineRun:
 else:
     ws = run.experiment.workspace
 
-
-def write_output(df, path):
-    os.makedirs(path, exist_ok=True)
-    print("%s created" % path)
-    df.to_csv(path + "/part-00000", index=False)
-
-
-print("Check for new data and prepare the data")
+print("Check for new data.")
 
 parser = argparse.ArgumentParser("split")
-parser.add_argument("--target_column", type=str, help="input split features")
 parser.add_argument("--ds_name", help="input dataset name")
 parser.add_argument("--model_name", help="name of the deployed model")
-parser.add_argument("--output_x", type=str,
-                    help="output features")
-parser.add_argument("--output_y", type=str,
-                    help="output labels")
-
 
 args = parser.parse_args()
 
 print("Argument 1(ds_name): %s" % args.ds_name)
-print("Argument 2(target_column): %s" % args.target_column)
-print("Argument 3(model_name): %s" % args.model_name)
-print("Argument 4(output_x): %s" % args.output_x)
-print("Argument 5(output_y): %s" % args.output_y)
+print("Argument 2(model_name): %s" % args.model_name)
 
 # Get the latest registered model
 try:
@@ -54,22 +38,9 @@ except Exception as e:
 train_ds = Dataset.get_by_name(ws, args.ds_name)
 dataset_changed_time = train_ds.data_changed_time
 
-if dataset_changed_time > last_train_time:
-    # New data is available since the model was last trained
-    print("Dataset was last updated on {0}. Retraining...".format(dataset_changed_time))
-    train_ds = train_ds.drop_columns(["partition_date"])
-    X_train = train_ds.drop_columns(
-        columns=[args.target_column]).to_pandas_dataframe()
-    y_train = train_ds.keep_columns(
-        columns=[args.target_column]).to_pandas_dataframe()
-
-    non_null = y_train[args.target_column].notnull()
-    y = y_train[non_null]
-    X = X_train[non_null]
-
-    if not (args.output_x is None and args.output_y is None):
-        write_output(X, args.output_x)
-        write_output(y, args.output_y)
-else:
+if not dataset_changed_time > last_train_time:
     print("Cancelling run since there is no new data.")
     run.parent.cancel()
+else:
+    # New data is available since the model was last trained
+    print("Dataset was last updated on {0}. Retraining...".format(dataset_changed_time))

how-to-use-azureml/automated-machine-learning/continuous-retraining/get_data.py

@@ -1,15 +0,0 @@
-import os
-import pandas as pd
-
-
-def get_data():
-    print("In get_data")
-    print(os.environ['AZUREML_DATAREFERENCE_output_x'])
-    X_train = pd.read_csv(
-        os.environ['AZUREML_DATAREFERENCE_output_x'] + "/part-00000")
-    y_train = pd.read_csv(
-        os.environ['AZUREML_DATAREFERENCE_output_y'] + "/part-00000")
-
-    print(X_train.head(3))
-
-    return {"X": X_train.values, "y": y_train.values.flatten()}

how-to-use-azureml/automated-machine-learning/continuous-retraining/upload_weather_data.py

@@ -49,22 +49,24 @@ print("Argument 1(ds_name): %s" % args.ds_name)
 
 dstor = ws.get_default_datastore()
 register_dataset = False
+end_time = datetime.utcnow()
+
 try:
     ds = Dataset.get_by_name(ws, args.ds_name)
     end_time_last_slice = ds.data_changed_time.replace(tzinfo=None)
     print("Dataset {0} last updated on {1}".format(args.ds_name,
                                                    end_time_last_slice))
-except Exception as e:
+except Exception:
     print(traceback.format_exc())
     print("Dataset with name {0} not found, registering new dataset.".format(args.ds_name))
     register_dataset = True
-    end_time_last_slice = datetime.today() - relativedelta(weeks=1)
+    end_time = datetime(2021, 5, 1, 0, 0)
+    end_time_last_slice = end_time - relativedelta(weeks=2)
 
-end_time = datetime.utcnow()
 train_df = get_noaa_data(end_time_last_slice, end_time)
 
 if train_df.size > 0:
-    print("Received {0} rows of new data after {0}.".format(
+    print("Received {0} rows of new data after {1}.".format(
         train_df.shape[0], end_time_last_slice))
     folder_name = "{}/{:04d}/{:02d}/{:02d}/{:02d}/{:02d}/{:02d}".format(args.ds_name, end_time.year,
                                                                         end_time.month, end_time.day,
@@ -80,10 +82,10 @@ if train_df.size > 0:
                        target_path=folder_name,
                        overwrite=True,
                        show_progress=True)
+else:
+    print("No new data since {0}.".format(end_time_last_slice))
 
 if register_dataset:
     ds = Dataset.Tabular.from_delimited_files(dstor.path("{}/**/*.csv".format(
-            args.ds_name)), partition_format='/{partition_date:yyyy/MM/dd/hh/mm/ss}/data.csv')
+        args.ds_name)), partition_format='/{partition_date:yyyy/MM/dd/HH/mm/ss}/data.csv')
     ds.register(ws, name=args.ds_name)
-else:
-    print("No new data since {0}.".format(end_time_last_slice))

how-to-use-azureml/automated-machine-learning/experimental/README.md

@@ -0,0 +1,92 @@
+# Experimental Notebooks for Automated ML
+Notebooks listed in this folder are leveraging experimental features. Namespaces or function signitures may change in future SDK releases. The notebooks published here will reflect the latest supported APIs. All of these notebooks can run on a client-only installation of the Automated ML SDK.
+The client only installation doesn't contain any of the machine learning libraries, such as scikit-learn, xgboost, or tensorflow, making it much faster to install and is less likely to conflict with any packages in an existing environment. However, since the ML libraries are not available locally, models cannot be downloaded and loaded directly in the client. To replace the functionality of having models locally, these notebooks also demonstrate the ModelProxy feature which will allow you to submit a predict/forecast to the training environment. 
+
+<a name="localconda"></a>
+## Setup using a Local Conda environment
+
+To run these notebook on your own notebook server, use these installation instructions.
+The instructions below will install everything you need and then start a Jupyter notebook.
+If you would like to use a lighter-weight version of the client that does not install all of the machine learning libraries locally, you can leverage the [experimental notebooks.](experimental/README.md)
+
+### 1. Install mini-conda from [here](https://conda.io/miniconda.html), choose 64-bit Python 3.7 or higher.
+- **Note**: if you already have conda installed, you can keep using it but it should be version 4.4.10 or later (as shown by: conda -V).  If you have a previous version installed, you can update it using the command: conda update conda.
+There's no need to install mini-conda specifically.
+
+### 2. Downloading the sample notebooks
+- Download the sample notebooks from [GitHub](https://github.com/Azure/MachineLearningNotebooks) as zip and extract the contents to a local directory.  The automated ML sample notebooks are in the "automated-machine-learning" folder.
+
+### 3. Setup a new conda environment
+The **automl_setup_thin_client** script creates a new conda environment, installs the necessary packages, configures the widget and starts a jupyter notebook. It takes the conda environment name as an optional parameter.  The default conda environment name is azure_automl_experimental.  The exact command depends on the operating system.  See the specific sections below for Windows, Mac and Linux.  It can take about 10 minutes to execute.
+
+Packages installed by the **automl_setup** script:
+    <ul><li>python</li><li>nb_conda</li><li>matplotlib</li><li>numpy</li><li>cython</li><li>urllib3</li><li>pandas</li><li>azureml-sdk</li><li>azureml-widgets</li><li>pandas-ml</li></ul>
+
+For more details refer to the [automl_env_thin_client.yml](./automl_env_thin_client.yml)
+## Windows
+Start an **Anaconda Prompt** window, cd to the **how-to-use-azureml/automated-machine-learning/experimental** folder where the sample notebooks were extracted and then run:
+```
+automl_setup_thin_client
+```
+## Mac
+Install "Command line developer tools" if it is not already installed (you can use the command: `xcode-select --install`).
+
+Start a Terminal windows, cd to the **how-to-use-azureml/automated-machine-learning/experimental** folder where the sample notebooks were extracted and then run:
+
+```
+bash automl_setup_thin_client_mac.sh
+```
+
+## Linux
+cd to the **how-to-use-azureml/automated-machine-learning/experimental** folder where the sample notebooks were extracted and then run:
+
+```
+bash automl_setup_thin_client_linux.sh
+```
+
+### 4. Running configuration.ipynb
+- Before running any samples you next need to run the configuration notebook. Click on [configuration](../../configuration.ipynb) notebook
+- Execute the cells in the notebook to Register Machine Learning Services Resource Provider and create a workspace. (*instructions in notebook*)
+
+### 5. Running Samples
+- Please make sure you use the Python [conda env:azure_automl_experimental] kernel when trying the sample Notebooks.
+- Follow the instructions in the individual notebooks to explore various features in automated ML.
+
+### 6. Starting jupyter notebook manually
+To start your Jupyter notebook manually, use:
+
+```
+conda activate azure_automl
+jupyter notebook
+```
+
+or on Mac or Linux:
+
+```
+source activate azure_automl
+jupyter notebook
+```
+
+
+<a name="samples"></a>
+# Automated ML SDK Sample Notebooks
+
+- [auto-ml-regression-model-proxy.ipynb](regression-model-proxy/auto-ml-regression-model-proxy.ipynb)
+    - Dataset: Hardware Performance Dataset
+    - Simple example of using automated ML for regression
+    - Uses azure compute for training
+    - Uses ModelProxy for submitting prediction to training environment on azure compute
+
+<a name="documentation"></a>
+See [Configure automated machine learning experiments](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-auto-train) to learn how more about the the settings and features available for automated machine learning experiments.
+
+<a name="pythoncommand"></a>
+# Running using python command
+Jupyter notebook provides a File / Download as / Python (.py) option for saving the notebook as a Python file.
+You can then run this file using the python command.
+However, on Windows the file needs to be modified before it can be run.
+The following condition must be added to the main code in the file:
+
+    if __name__ == "__main__":
+
+The main code of the file must be indented so that it is under this condition.

how-to-use-azureml/automated-machine-learning/experimental/automl_setup_thin_client.cmd

@@ -0,0 +1,63 @@
+@echo off
+set conda_env_name=%1
+set automl_env_file=%2
+set options=%3
+set PIP_NO_WARN_SCRIPT_LOCATION=0
+
+IF "%conda_env_name%"=="" SET conda_env_name="azure_automl_experimental"
+IF "%automl_env_file%"=="" SET automl_env_file="automl_thin_client_env.yml"
+
+IF NOT EXIST %automl_env_file% GOTO YmlMissing
+
+IF "%CONDA_EXE%"=="" GOTO CondaMissing
+
+call conda activate %conda_env_name% 2>nul:
+
+if not errorlevel 1 (
+  echo Upgrading existing conda environment %conda_env_name%
+  call pip uninstall azureml-train-automl -y -q
+  call conda env update --name %conda_env_name% --file %automl_env_file%
+  if errorlevel 1 goto ErrorExit
+) else (
+  call conda env create -f %automl_env_file% -n %conda_env_name%
+)
+
+call conda activate %conda_env_name% 2>nul:
+if errorlevel 1 goto ErrorExit
+
+call python -m ipykernel install --user --name %conda_env_name% --display-name "Python (%conda_env_name%)"
+
+REM azureml.widgets is now installed as part of the pip install under the conda env.
+REM Removing the old user install so that the notebooks will use the latest widget.
+call jupyter nbextension uninstall --user --py azureml.widgets
+
+echo.
+echo.
+echo ***************************************
+echo * AutoML setup completed successfully *
+echo ***************************************
+IF NOT "%options%"=="nolaunch" (
+  echo.
+  echo Starting jupyter notebook - please run the configuration notebook 
+  echo.
+  jupyter notebook --log-level=50 --notebook-dir='..\..'
+)
+
+goto End
+
+:CondaMissing
+echo Please run this script from an Anaconda Prompt window.
+echo You can start an Anaconda Prompt window by
+echo typing Anaconda Prompt on the Start menu.
+echo If you don't see the Anaconda Prompt app, install Miniconda.
+echo If you are running an older version of Miniconda or Anaconda,
+echo you can upgrade using the command: conda update conda
+goto End
+
+:YmlMissing
+echo File %automl_env_file% not found.
+
+:ErrorExit
+echo Install failed
+
+:End

how-to-use-azureml/automated-machine-learning/experimental/automl_setup_thin_client_linux.sh

@@ -0,0 +1,53 @@
+#!/bin/bash
+
+CONDA_ENV_NAME=$1
+AUTOML_ENV_FILE=$2
+OPTIONS=$3
+PIP_NO_WARN_SCRIPT_LOCATION=0
+
+if [ "$CONDA_ENV_NAME" == "" ]
+then
+  CONDA_ENV_NAME="azure_automl_experimental"
+fi
+
+if [ "$AUTOML_ENV_FILE" == "" ]
+then
+  AUTOML_ENV_FILE="automl_thin_client_env.yml"
+fi
+
+if [ ! -f $AUTOML_ENV_FILE ]; then
+    echo "File $AUTOML_ENV_FILE not found"
+    exit 1
+fi
+
+if source activate $CONDA_ENV_NAME 2> /dev/null
+then
+   echo "Upgrading existing conda environment" $CONDA_ENV_NAME
+   pip uninstall azureml-train-automl -y -q
+   conda env update --name $CONDA_ENV_NAME --file $AUTOML_ENV_FILE &&
+   jupyter nbextension uninstall --user --py azureml.widgets
+else
+   conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&
+   source activate $CONDA_ENV_NAME &&
+   python -m ipykernel install --user --name $CONDA_ENV_NAME --display-name "Python ($CONDA_ENV_NAME)" &&
+   jupyter nbextension uninstall --user --py azureml.widgets &&
+   echo "" &&
+   echo "" &&
+   echo "***************************************" &&
+   echo "* AutoML setup completed successfully *" &&
+   echo "***************************************" &&
+   if [ "$OPTIONS" != "nolaunch" ]
+   then
+      echo "" &&
+      echo "Starting jupyter notebook - please run the configuration notebook" &&
+      echo "" &&
+      jupyter notebook --log-level=50 --notebook-dir '../..'
+   fi
+fi
+
+if [ $? -gt 0 ]
+then
+   echo "Installation failed"
+fi
+
+

how-to-use-azureml/automated-machine-learning/experimental/automl_setup_thin_client_mac.sh

@@ -0,0 +1,55 @@
+#!/bin/bash
+
+CONDA_ENV_NAME=$1
+AUTOML_ENV_FILE=$2
+OPTIONS=$3
+PIP_NO_WARN_SCRIPT_LOCATION=0
+
+if [ "$CONDA_ENV_NAME" == "" ]
+then
+  CONDA_ENV_NAME="azure_automl_experimental"
+fi
+
+if [ "$AUTOML_ENV_FILE" == "" ]
+then
+  AUTOML_ENV_FILE="automl_thin_client_env_mac.yml"
+fi
+
+if [ ! -f $AUTOML_ENV_FILE ]; then
+    echo "File $AUTOML_ENV_FILE not found"
+    exit 1
+fi
+
+if source activate $CONDA_ENV_NAME 2> /dev/null
+then
+   echo "Upgrading existing conda environment" $CONDA_ENV_NAME
+   pip uninstall azureml-train-automl -y -q
+   conda env update --name $CONDA_ENV_NAME --file $AUTOML_ENV_FILE &&
+   jupyter nbextension uninstall --user --py azureml.widgets
+else
+   conda env create -f $AUTOML_ENV_FILE -n $CONDA_ENV_NAME &&
+   source activate $CONDA_ENV_NAME &&
+   conda install lightgbm -c conda-forge -y &&
+   python -m ipykernel install --user --name $CONDA_ENV_NAME --display-name "Python ($CONDA_ENV_NAME)" &&
+   jupyter nbextension uninstall --user --py azureml.widgets &&
+   echo "" &&
+   echo "" &&
+   echo "***************************************" &&
+   echo "* AutoML setup completed successfully *" &&
+   echo "***************************************" &&
+   if [ "$OPTIONS" != "nolaunch" ]
+   then
+      echo "" &&
+      echo "Starting jupyter notebook - please run the configuration notebook" &&
+      echo "" &&
+      jupyter notebook --log-level=50 --notebook-dir '../..'
+   fi
+fi
+
+if [ $? -gt 0 ]
+then
+   echo "Installation failed"
+fi
+
+
+

how-to-use-azureml/automated-machine-learning/experimental/automl_thin_client_env.yml

@@ -0,0 +1,18 @@
+name: azure_automl_experimental
+dependencies:
+  # The python interpreter version.
+  # Currently Azure ML only supports 3.5.2 and later.
+- pip<=19.3.1
+- python>=3.5.2,<3.8
+- nb_conda
+- cython
+- urllib3<1.24
+- PyJWT < 2.0.0
+- numpy==1.18.5
+
+- pip:
+  # Required packages for AzureML execution, history, and data preparation.
+  - azureml-defaults
+  - azureml-sdk
+  - azureml-widgets
+  - pandas

how-to-use-azureml/automated-machine-learning/experimental/automl_thin_client_env_mac.yml

@@ -0,0 +1,19 @@
+name: azure_automl_experimental
+dependencies:
+  # The python interpreter version.
+  # Currently Azure ML only supports 3.5.2 and later.
+- pip<=19.3.1
+- nomkl
+- python>=3.5.2,<3.8
+- nb_conda
+- cython
+- urllib3<1.24
+- PyJWT < 2.0.0
+- numpy==1.18.5
+
+- pip:
+  # Required packages for AzureML execution, history, and data preparation.
+  - azureml-defaults
+  - azureml-sdk
+  - azureml-widgets
+  - pandas

how-to-use-azureml/automated-machine-learning/experimental/classification-credit-card-fraud-local-managed/auto-ml-classification-credit-card-fraud-local-managed.ipynb

@@ -0,0 +1,420 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/experimental/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Classification of credit card fraudulent transactions on local managed compute **_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)\n",
+        "1. [Acknowledgements](#Acknowledgements)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "\n",
+        "In this example we use the associated credit card dataset to showcase how you can use AutoML for a simple classification problem. The goal is to predict if a credit card transaction is considered a fraudulent charge.\n",
+        "\n",
+        "This notebook is using local managed compute to train the model.\n",
+        "\n",
+        "If you are using an Azure Machine Learning Compute Instance, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Create an experiment using an existing workspace.\n",
+        "2. Configure AutoML using `AutoMLConfig`.\n",
+        "3. Train the model using local managed compute.\n",
+        "4. Explore the results.\n",
+        "5. Test the fitted model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "\n",
+        "import pandas as pd\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.compute_target import LocalTarget\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.core.dataset import Dataset\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# choose a name for experiment\n",
+        "experiment_name = 'automl-local-managed'\n",
+        "\n",
+        "experiment=Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Experiment Name'] = experiment.name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Determine if local docker is configured for Linux images\n",
+        "\n",
+        "Local managed runs will leverage a Linux docker container to submit the run to. Due to this, the docker needs to be configured to use Linux containers."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Check if Docker is installed and Linux containers are enabled\n",
+        "import subprocess\n",
+        "from subprocess import CalledProcessError\n",
+        "try:\n",
+        "    assert subprocess.run(\"docker -v\", shell=True).returncode == 0, 'Local Managed runs require docker to be installed.'\n",
+        "    out = subprocess.check_output(\"docker system info\", shell=True).decode('ascii')\n",
+        "    assert \"OSType: linux\" in out, 'Docker engine needs to be configured to use Linux containers.' \\\n",
+        "        'https://docs.docker.com/docker-for-windows/#switch-between-windows-and-linux-containers'\n",
+        "except CalledProcessError as ex:\n",
+        "    raise Exception('Local Managed runs require docker to be installed.') from ex"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load Data\n",
+        "\n",
+        "Load the credit card dataset from a csv file containing both training features and labels. The features are inputs to the model, while the training labels represent the expected output of the model. Next, we'll split the data using random_split and extract the training data for the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard.csv\"\n",
+        "dataset = Dataset.Tabular.from_delimited_files(data)\n",
+        "training_data, validation_data = dataset.random_split(percentage=0.8, seed=223)\n",
+        "label_column_name = 'Class'"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**enable_early_stopping**|Stop the run if the metric score is not showing improvement.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**training_data**|Input dataset, containing both features and label column.|\n",
+        "|**label_column_name**|The name of the label column.|\n",
+        "|**enable_local_managed**|Enable the experimental local-managed scenario.|\n",
+        "\n",
+        "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"n_cross_validations\": 3,\n",
+        "    \"primary_metric\": 'average_precision_score_weighted',\n",
+        "    \"enable_early_stopping\": True,\n",
+        "    \"experiment_timeout_hours\": 0.3, #for real scenarios we recommend a timeout of at least one hour \n",
+        "    \"verbosity\": logging.INFO,\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             compute_target = LocalTarget(),\n",
+        "                             enable_local_managed = True,\n",
+        "                             training_data = training_data,\n",
+        "                             label_column_name = label_column_name,\n",
+        "                             **automl_settings\n",
+        "                            )"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the `submit` method on the experiment object and pass the run configuration. Depending on the data and the number of iterations this can run for a while. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "parent_run = experiment.submit(automl_config, show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# If you need to retrieve a run that already started, use the following code\n",
+        "#from azureml.train.automl.run import AutoMLRun\n",
+        "#parent_run = AutoMLRun(experiment = experiment, run_id = '<replace with your run id>')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "parent_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Explain model\n",
+        "\n",
+        "Automated ML models can be explained and visualized using the SDK Explainability library. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Analyze results\n",
+        "\n",
+        "### Retrieve the Best Child Run\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_best_child` method returns the best run. Overloads on `get_best_child` allow you to retrieve the best run for *any* logged metric."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run = parent_run.get_best_child()\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Test the fitted model\n",
+        "\n",
+        "Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_test_df = validation_data.drop_columns(columns=[label_column_name])\n",
+        "y_test_df = validation_data.keep_columns(columns=[label_column_name], validate=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Creating ModelProxy for submitting prediction runs to the training environment.\n",
+        "We will create a ModelProxy for the best child run, which will allow us to submit a run that does the prediction in the training environment. Unlike the local client, which can have different versions of some libraries, the training environment will have all the compatible libraries for the model already."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.automl.model_proxy import ModelProxy\n",
+        "best_model_proxy = ModelProxy(best_run)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# call the predict functions on the model proxy\n",
+        "y_pred = best_model_proxy.predict(X_test_df).to_pandas_dataframe()\n",
+        "y_pred"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Acknowledgements"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This Credit Card fraud Detection dataset is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/ and is available at: https://www.kaggle.com/mlg-ulb/creditcardfraud\n",
+        "\n",
+        "\n",
+        "The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Universit\u00c3\u0192\u00c2\u00a9 Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project\n",
+        "Please cite the following works: \n",
+        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tAndrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
+        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tDal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
+        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tDal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE\n",
+        "o\tDal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
+        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tCarcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-A\u00c3\u0192\u00c2\u00abl; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier\n",
+        "\u00c3\u00a2\u00e2\u201a\u00ac\u00c2\u00a2\tCarcillo, Fabrizio; Le Borgne, Yann-A\u00c3\u0192\u00c2\u00abl; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "sekrupa"
+      }
+    ],
+    "category": "tutorial",
+    "compute": [
+      "AML Compute"
+    ],
+    "datasets": [
+      "Creditcard"
+    ],
+    "deployment": [
+      "None"
+    ],
+    "exclude_from_index": false,
+    "file_extension": ".py",
+    "framework": [
+      "None"
+    ],
+    "friendly_name": "Classification of credit card fraudulent transactions using Automated ML",
+    "index_order": 5,
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.7"
+    },
+    "mimetype": "text/x-python",
+    "name": "python",
+    "nbconvert_exporter": "python",
+    "pygments_lexer": "ipython3",
+    "tags": [
+      "AutomatedML"
+    ],
+    "task": "Classification",
+    "version": "3.6.7"
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/experimental/classification-credit-card-fraud-local-managed/auto-ml-classification-credit-card-fraud-local-managed.yml

@@ -0,0 +1,4 @@
+name: auto-ml-classification-credit-card-fraud-local-managed
+dependencies:
+- pip:
+  - azureml-sdk

how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.ipynb

@@ -0,0 +1,435 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Regression with Aml Compute**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "In this example we use an experimental feature, Model Proxy, to do a predict on the best generated model without downloading the model locally. The prediction will happen on same compute and environment that was used to train the model. This feature is currently in the experimental state, which means that the API is prone to changing, please make sure to run on the latest version of this notebook if you face any issues.\n",
+        "This notebook will also leverage MLFlow for saving models, allowing for more portability of the resulting models. See https://docs.microsoft.com/en-us/azure/machine-learning/how-to-use-mlflow for more details around MLFlow is AzureML.\n",
+        "\n",
+        "If you are using an Azure Machine Learning Compute Instance, you are all set.  Otherwise, go through the [configuration](../../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Create an `Experiment` in an existing `Workspace`.\n",
+        "2. Configure AutoML using `AutoMLConfig`.\n",
+        "3. Train the model using remote compute.\n",
+        "4. Explore the results.\n",
+        "5. Test the best fitted model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\n",
+        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "\n",
+        "import json\n",
+        "\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.core.dataset import Dataset\n",
+        "from azureml.train.automl import AutoMLConfig"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose a name for the experiment.\n",
+        "experiment_name = 'automl-regression-model-proxy'\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Run History Name'] = experiment_name\n",
+        "output"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Using AmlCompute\n",
+        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you use `AmlCompute` as your training compute resource."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "# Choose a name for your CPU cluster\n",
+        "# Try to ensure that the cluster name is unique across the notebooks\n",
+        "cpu_cluster_name = \"reg-model-proxy\"\n",
+        "\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
+        "                                                           max_nodes=4)\n",
+        "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
+        "\n",
+        "compute_target.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Load Data\n",
+        "Load the hardware dataset from a csv file containing both training features and labels. The features are inputs to the model, while the training labels represent the expected output of the model. Next, we'll split the data using random_split and extract the training data for the model. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/machineData.csv\"\n",
+        "dataset = Dataset.Tabular.from_delimited_files(data)\n",
+        "\n",
+        "# Split the dataset into train and test datasets\n",
+        "train_data, test_data = dataset.random_split(percentage=0.8, seed=223)\n",
+        "\n",
+        "label = \"ERP\"\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification, regression or forecasting|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**training_data**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**label_column_name**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
+        "\n",
+        "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "automlconfig-remarks-sample"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"n_cross_validations\": 3,\n",
+        "    \"primary_metric\": 'r2_score',\n",
+        "    \"enable_early_stopping\": True, \n",
+        "    \"experiment_timeout_hours\": 0.3, #for real scenarios we recommend a timeout of at least one hour \n",
+        "    \"max_concurrent_iterations\": 4,\n",
+        "    \"max_cores_per_iteration\": -1,\n",
+        "    \"verbosity\": logging.INFO,\n",
+        "    \"save_mlflow\": True,\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'regression',\n",
+        "                             compute_target = compute_target,\n",
+        "                             training_data = train_data,\n",
+        "                             label_column_name = label,\n",
+        "                             **automl_settings\n",
+        "                            )"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Call the `submit` method on the experiment object and pass the run configuration. Execution of remote runs is asynchronous. Depending on the data and the number of iterations this can run for a while.  Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run = experiment.submit(automl_config, show_output = False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# If you need to retrieve a run that already started, use the following code\n",
+        "#from azureml.train.automl.run import AutoMLRun\n",
+        "#remote_run = AutoMLRun(experiment = experiment, run_id = '<replace with your run id>')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Results"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Child Run\n",
+        "\n",
+        "Below we select the best pipeline from our iterations. The `get_best_child` method returns the best run. Overloads on `get_best_child` allow you to retrieve the best run for *any* logged metric."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run = remote_run.get_best_child()\n",
+        "print(best_run)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Show hyperparameters\n",
+        "Show the model pipeline used for the best run with its hyperparameters."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "run_properties = json.loads(best_run.get_details()['properties']['pipeline_script'])\n",
+        "print(json.dumps(run_properties, indent = 1)) "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Best Child Run Based on Any Other Metric\n",
+        "Show the run and the model that has the smallest `root_mean_squared_error` value (which turned out to be the same as the one with largest `spearman_correlation` value):"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "lookup_metric = \"root_mean_squared_error\"\n",
+        "best_run = remote_run.get_best_child(metric = lookup_metric)\n",
+        "print(best_run)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "y_test = test_data.keep_columns('ERP')\n",
+        "test_data = test_data.drop_columns('ERP')\n",
+        "\n",
+        "\n",
+        "y_train = train_data.keep_columns('ERP')\n",
+        "train_data = train_data.drop_columns('ERP')\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Creating ModelProxy for submitting prediction runs to the training environment.\n",
+        "We will create a ModelProxy for the best child run, which will allow us to submit a run that does the prediction in the training environment. Unlike the local client, which can have different versions of some libraries, the training environment will have all the compatible libraries for the model already."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.automl.model_proxy import ModelProxy\n",
+        "best_model_proxy = ModelProxy(best_run)\n",
+        "y_pred_train = best_model_proxy.predict(train_data)\n",
+        "y_pred_test = best_model_proxy.predict(test_data)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Exploring results"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "y_pred_train = y_pred_train.to_pandas_dataframe().values.flatten()\n",
+        "y_train = y_train.to_pandas_dataframe().values.flatten()\n",
+        "y_residual_train = y_train - y_pred_train\n",
+        "\n",
+        "y_pred_test = y_pred_test.to_pandas_dataframe().values.flatten()\n",
+        "y_test = y_test.to_pandas_dataframe().values.flatten()\n",
+        "y_residual_test = y_test - y_pred_test\n",
+        "print(y_residual_train)\n",
+        "print(y_residual_test)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "sekrupa"
+      }
+    ],
+    "categories": [
+      "how-to-use-azureml",
+      "automated-machine-learning"
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.2"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/experimental/regression-model-proxy/auto-ml-regression-model-proxy.yml

@@ -0,0 +1,4 @@
+name: auto-ml-regression-model-proxy
+dependencies:
+- pip:
+  - azureml-sdk

how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/auto-ml-forecasting-beer-remote.ipynb

@@ -54,9 +54,8 @@
         "\n",
         "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
         "\n",
-        "An Enterprise workspace is required for this notebook. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page.](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade)\n",
-        "\n",
         "Notebook synopsis:\n",
+        "\n",
         "1. Creating an Experiment in an existing Workspace\n",
         "2. Configuration and remote run of AutoML for a time-series model exploring Regression learners, Arima, Prophet and DNNs\n",
         "4. Evaluating the fitted model using a rolling test "
@@ -101,6 +100,23 @@
         "from azureml.train.estimator import Estimator"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -128,7 +144,6 @@
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
@@ -147,7 +162,9 @@
       },
       "source": [
         "### Using AmlCompute\n",
-        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you use `AmlCompute` as your training compute resource."
+        "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you use `AmlCompute` as your training compute resource.\n",
+        "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
       ]
     },
     {
@@ -163,14 +180,14 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpu-cluster\"\n",
+        "cpu_cluster_name = \"beer-cluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
         "    compute_target = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
         "    print('Found existing cluster, use it.')\n",
         "except ComputeTargetException:\n",
-        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_D2_V2',\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
         "                                                           max_nodes=4)\n",
         "    compute_target = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
         "\n",
@@ -201,7 +218,9 @@
         "\n",
         "**Time column** is the time axis along which to predict.\n",
         "\n",
-        "**Grain** is another word for an individual time series in your dataset. Grains are identified by values of the columns listed `grain_column_names`, for example \"store\" and \"item\" if your data has multiple time series of sales, one series for each combination of store and item sold.\n",
+        "**Time series identifier columns** are identified by values of the columns listed `time_series_id_column_names`, for example \"store\" and \"item\" if your data has multiple time series of sales, one series for each combination of store and item sold.\n",
+        "\n",
+        "**Forecast frequency (freq)** This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.\n",
         "\n",
         "This dataset has only one time series. Please see the [orange juice notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales) for an example of a multi-time series dataset."
       ]
@@ -218,19 +237,18 @@
         "import pandas as pd\n",
         "from pandas import DataFrame\n",
         "from pandas import Grouper\n",
-        "from matplotlib import pyplot\n",
         "from pandas import concat\n",
-        "from matplotlib import pyplot\n",
         "from pandas.plotting import register_matplotlib_converters\n",
+        "\n",
         "register_matplotlib_converters()\n",
-        "plt.tight_layout()\n",
         "plt.figure(figsize=(20, 10))\n",
+        "plt.tight_layout()\n",
         "\n",
         "plt.subplot(2, 1, 1)\n",
         "plt.title('Beer Production By Year')\n",
         "df = pd.read_csv(\"Beer_no_valid_split_train.csv\", parse_dates=True, index_col= 'DATE').drop(columns='grain')\n",
         "test_df = pd.read_csv(\"Beer_no_valid_split_test.csv\", parse_dates=True, index_col= 'DATE').drop(columns='grain')\n",
-        "pyplot.plot(df)\n",
+        "plt.plot(df)\n",
         "\n",
         "plt.subplot(2, 1, 2)\n",
         "plt.title('Beer Production By Month')\n",
@@ -239,7 +257,8 @@
         "months = DataFrame(months)\n",
         "months.columns = range(1,13)\n",
         "months.boxplot()\n",
-        "pyplot.show()\n"
+        "\n",
+        "plt.show()"
       ]
     },
     {
@@ -253,7 +272,7 @@
       "source": [
         "target_column_name = 'BeerProduction'\n",
         "time_column_name = 'DATE'\n",
-        "grain_column_names = []\n",
+        "time_series_id_column_names = []\n",
         "freq = 'M' #Monthly data"
       ]
     },
@@ -301,7 +320,7 @@
       "source": [
         "### Setting forecaster maximum horizon \n",
         "\n",
-        "The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 4 periods (i.e. 4 months). Notice that this is much shorter than the number of days in the test set; we will need to use a rolling test to evaluate the performance on the whole test set. For more discussion of forecast horizons and guiding principles for setting them, please see the [energy demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand).  "
+        "The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 12 periods (i.e. 12 months). Notice that this is much shorter than the number of months in the test set; we will need to use a rolling test to evaluate the performance on the whole test set. For more discussion of forecast horizons and guiding principles for setting them, please see the [energy demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand).  "
       ]
     },
     {
@@ -313,7 +332,7 @@
       },
       "outputs": [],
       "source": [
-        "max_horizon = 12"
+        "forecast_horizon = 12"
       ]
     },
     {
@@ -334,11 +353,7 @@
         "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
         "|**training_data**|Input dataset, containing both features and label column.|\n",
         "|**label_column_name**|The name of the label column.|\n",
-        "|**enable_dnn**|Enable Forecasting DNNs|\n",
-        "\n",
-        "This notebook uses the blacklist_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blacklist_models list but you may need to increase the iteration_timeout_minutes parameter value to get results.\n",
-        "\n",
-        "This step requires an Enterprise workspace to gain access to this feature. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page.](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade)."
+        "|**enable_dnn**|Enable Forecasting DNNs|\n"
       ]
     },
     {
@@ -350,15 +365,17 @@
       },
       "outputs": [],
       "source": [
-        "automl_settings = {\n",
-        "    'time_column_name': time_column_name,\n",
-        "    'max_horizon': max_horizon,\n",
-        "    'enable_dnn' : True,\n",
-        "}\n",
+        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
+        "forecasting_parameters = ForecastingParameters(\n",
+        "    time_column_name=time_column_name,\n",
+        "    forecast_horizon=forecast_horizon,\n",
+        "    freq='MS' # Set the forecast frequency to be monthly (start of the month)\n",
+        ")\n",
         "\n",
+        "# We will disable the enable_early_stopping flag to ensure the DNN model is recommended for demonstration purpose.\n",
         "automl_config = AutoMLConfig(task='forecasting',\n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             experiment_timeout_minutes = 60,\n",
+        "                             experiment_timeout_hours = 1,\n",
         "                             training_data=train_dataset,\n",
         "                             label_column_name=target_column_name,\n",
         "                             validation_data=valid_dataset, \n",
@@ -366,7 +383,9 @@
         "                             compute_target=compute_target,\n",
         "                             max_concurrent_iterations=4,\n",
         "                             max_cores_per_iteration=-1,\n",
-        "                            **automl_settings)"
+        "                             enable_dnn=True,\n",
+        "                             enable_early_stopping=False,\n",
+        "                             forecasting_parameters=forecasting_parameters)"
       ]
     },
     {
@@ -376,7 +395,7 @@
         "hidePrompt": false
       },
       "source": [
-        "We will now run the experiment, starting with 10 iterations of model search. The experiment can be continued for more iterations if more accurate results are required. You will see the currently running iterations printing to the console."
+        "We will now run the experiment, starting with 10 iterations of model search. The experiment can be continued for more iterations if more accurate results are required. Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
       ]
     },
     {
@@ -388,8 +407,7 @@
       },
       "outputs": [],
       "source": [
-        "remote_run = experiment.submit(automl_config, show_output= False)\n",
-        "remote_run"
+        "remote_run = experiment.submit(automl_config, show_output= True)"
       ]
     },
     {
@@ -406,15 +424,6 @@
         "# remote_run = AutoMLRun(experiment = experiment, run_id = '<replace with your run id>')"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.wait_for_completion()"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -538,7 +547,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "compute_target = ws.compute_targets['cpu-cluster']\n",
+        "compute_target = ws.compute_targets['beer-cluster']\n",
         "test_experiment = Experiment(ws, experiment_name + \"_test\")"
       ]
     },
@@ -556,7 +565,7 @@
         "\n",
         "script_folder = os.path.join(os.getcwd(), 'inference')\n",
         "os.makedirs(script_folder, exist_ok=True)\n",
-        "shutil.copy2('infer.py', script_folder)"
+        "shutil.copy('infer.py', script_folder)"
       ]
     },
     {
@@ -567,7 +576,7 @@
       "source": [
         "from helper import run_inference\n",
         "\n",
-        "test_run = run_inference(test_experiment, compute_target, script_folder, best_dnn_run, test_dataset, valid_dataset, max_horizon,\n",
+        "test_run = run_inference(test_experiment, compute_target, script_folder, best_dnn_run, test_dataset, valid_dataset, forecast_horizon,\n",
         "                 target_column_name, time_column_name, freq)"
       ]
     },
@@ -589,7 +598,7 @@
         "from helper import run_multiple_inferences\n",
         "\n",
         "summary_df = run_multiple_inferences(summary_df, experiment, test_experiment, compute_target, script_folder, test_dataset, \n",
-        "                  valid_dataset, max_horizon, target_column_name, time_column_name, freq)"
+        "                  valid_dataset, forecast_horizon, target_column_name, time_column_name, freq)"
       ]
     },
     {
@@ -636,7 +645,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "omkarm"
+        "name": "jialiu"
       }
     ],
     "hide_code_all_hidden": false,
@@ -655,7 +664,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.7"
+      "version": "3.6.9"
     }
   },
   "nbformat": 4,

how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/auto-ml-forecasting-beer-remote.yml

@@ -1,12 +1,4 @@
 name: auto-ml-forecasting-beer-remote
 dependencies:
-- fbprophet==0.5
-- py-xgboost<=0.80
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-train
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels

how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/helper.py

@@ -3,11 +3,11 @@ from azureml.core import Environment
 from azureml.core.conda_dependencies import CondaDependencies
 from azureml.train.estimator import Estimator
 from azureml.core.run import Run
+from azureml.automl.core.shared import constants
 
 
 def split_fraction_by_grain(df, fraction, time_column_name,
                             grain_column_names=None):
-
     if not grain_column_names:
         df['tmp_grain_column'] = 'grain'
         grain_column_names = ['tmp_grain_column']
@@ -59,7 +59,9 @@ def get_result_df(remote_run):
                                      'primary_metric', 'Score'])
     goal_minimize = False
     for run in children:
-        if('run_algorithm' in run.properties and 'score' in run.properties):
+        if run.get_status().lower() == constants.RunState.COMPLETE_RUN \
+                and 'run_algorithm' in run.properties and 'score' in run.properties:
+            # We only count in the completed child runs.
             summary_df[run.id] = [run.id, run.properties['run_algorithm'],
                                   run.properties['primary_metric'],
                                   float(run.properties['score'])]
@@ -76,9 +78,12 @@ def get_result_df(remote_run):
 def run_inference(test_experiment, compute_target, script_folder, train_run,
                   test_dataset, lookback_dataset, max_horizon,
                   target_column_name, time_column_name, freq):
-    train_run.download_file('outputs/model.pkl', 'inference/model.pkl')
-    train_run.download_file('outputs/conda_env_v_1_0_0.yml',
-                            'inference/condafile.yml')
+    model_base_name = 'model.pkl'
+    if 'model_data_location' in train_run.properties:
+        model_location = train_run.properties['model_data_location']
+        _, model_base_name = model_location.rsplit('/', 1)
+    train_run.download_file('outputs/{}'.format(model_base_name), 'inference/{}'.format(model_base_name))
+    train_run.download_file('outputs/conda_env_v_1_0_0.yml', 'inference/condafile.yml')
 
     inference_env = Environment("myenv")
     inference_env.docker.enabled = True
@@ -91,7 +96,8 @@ def run_inference(test_experiment, compute_target, script_folder, train_run,
                         '--max_horizon': max_horizon,
                         '--target_column_name': target_column_name,
                         '--time_column_name': time_column_name,
-                        '--frequency': freq
+                        '--frequency': freq,
+                        '--model_path': model_base_name
                     },
                     inputs=[test_dataset.as_named_input('test_data'),
                             lookback_dataset.as_named_input('lookback_data')],
@@ -114,7 +120,6 @@ def run_multiple_inferences(summary_df, train_experiment, test_experiment,
                             compute_target, script_folder, test_dataset,
                             lookback_dataset, max_horizon, target_column_name,
                             time_column_name, freq):
-
     for run_name, run_summary in summary_df.iterrows():
         print(run_name)
         print(run_summary)

how-to-use-azureml/automated-machine-learning/forecasting-beer-remote/infer.py

@@ -1,12 +1,22 @@
-import pandas as pd
-import numpy as np
 import argparse
-from azureml.core import Run
+import os
+
+import numpy as np
+import pandas as pd
+
+from pandas.tseries.frequencies import to_offset
 from sklearn.externals import joblib
 from sklearn.metrics import mean_absolute_error, mean_squared_error
-from azureml.automl.core._vendor.automl.client.core.common import metrics
-from automl.client.core.common import constants
-from pandas.tseries.frequencies import to_offset
+
+from azureml.automl.runtime.shared.score import scoring, constants
+from azureml.core import Run
+
+try:
+    import torch
+
+    _torch_present = True
+except ImportError:
+    _torch_present = False
 
 
 def align_outputs(y_predicted, X_trans, X_test, y_test,
@@ -81,8 +91,7 @@ def do_rolling_forecast_with_lookback(fitted_model, X_test, y_test,
         if origin_time != X[time_column_name].min():
             # Set the context by including actuals up-to the origin time
             test_context_expand_wind = (X[time_column_name] < origin_time)
-            context_expand_wind = (
-                X_test_expand[time_column_name] < origin_time)
+            context_expand_wind = (X_test_expand[time_column_name] < origin_time)
             y_query_expand[context_expand_wind] = y[test_context_expand_wind]
 
         # Print some debug info
@@ -113,8 +122,7 @@ def do_rolling_forecast_with_lookback(fitted_model, X_test, y_test,
         # Align forecast with test set for dates within
         # the current rolling window
         trans_tindex = X_trans.index.get_level_values(time_column_name)
-        trans_roll_wind = (trans_tindex >= origin_time) & (
-            trans_tindex < horizon_time)
+        trans_roll_wind = (trans_tindex >= origin_time) & (trans_tindex < horizon_time)
         test_roll_wind = expand_wind & (X[time_column_name] >= origin_time)
         df_list.append(align_outputs(
             y_fcst[trans_roll_wind], X_trans[trans_roll_wind],
@@ -153,8 +161,7 @@ def do_rolling_forecast(fitted_model, X_test, y_test, max_horizon, freq='D'):
         if origin_time != X_test[time_column_name].min():
             # Set the context by including actuals up-to the origin time
             test_context_expand_wind = (X_test[time_column_name] < origin_time)
-            context_expand_wind = (
-                X_test_expand[time_column_name] < origin_time)
+            context_expand_wind = (X_test_expand[time_column_name] < origin_time)
             y_query_expand[context_expand_wind] = y_test[
                 test_context_expand_wind]
 
@@ -184,10 +191,8 @@ def do_rolling_forecast(fitted_model, X_test, y_test, max_horizon, freq='D'):
         # Align forecast with test set for dates within the
         # current rolling window
         trans_tindex = X_trans.index.get_level_values(time_column_name)
-        trans_roll_wind = (trans_tindex >= origin_time) & (
-            trans_tindex < horizon_time)
-        test_roll_wind = expand_wind & (
-            X_test[time_column_name] >= origin_time)
+        trans_roll_wind = (trans_tindex >= origin_time) & (trans_tindex < horizon_time)
+        test_roll_wind = expand_wind & (X_test[time_column_name] >= origin_time)
         df_list.append(align_outputs(y_fcst[trans_roll_wind],
                                      X_trans[trans_roll_wind],
                                      X_test[test_roll_wind],
@@ -219,6 +224,10 @@ def MAPE(actual, pred):
     return np.mean(APE(actual_safe, pred_safe))
 
 
+def map_location_cuda(storage, loc):
+    return storage.cuda()
+
+
 parser = argparse.ArgumentParser()
 parser.add_argument(
     '--max_horizon', type=int, dest='max_horizon',
@@ -232,20 +241,23 @@ parser.add_argument(
 parser.add_argument(
     '--frequency', type=str, dest='freq',
     help='Frequency of prediction')
-
+parser.add_argument(
+    '--model_path', type=str, dest='model_path',
+    default='model.pkl', help='Filename of model to be loaded')
 
 args = parser.parse_args()
 max_horizon = args.max_horizon
 target_column_name = args.target_column_name
 time_column_name = args.time_column_name
 freq = args.freq
-
+model_path = args.model_path
 
 print('args passed are: ')
 print(max_horizon)
 print(target_column_name)
 print(time_column_name)
 print(freq)
+print(model_path)
 
 run = Run.get_context()
 # get input dataset by name
@@ -267,7 +279,19 @@ X_lookback_df = lookback_dataset.drop_columns(columns=[target_column_name])
 y_lookback_df = lookback_dataset.with_timestamp_columns(
     None).keep_columns(columns=[target_column_name])
 
-fitted_model = joblib.load('model.pkl')
+_, ext = os.path.splitext(model_path)
+if ext == '.pt':
+    # Load the fc-tcn torch model.
+    assert _torch_present
+    if torch.cuda.is_available():
+        map_location = map_location_cuda
+    else:
+        map_location = 'cpu'
+    with open(model_path, 'rb') as fh:
+        fitted_model = torch.load(fh, map_location=map_location)
+else:
+    # Load the sklearn pipeline.
+    fitted_model = joblib.load(model_path)
 
 if hasattr(fitted_model, 'get_lookback'):
     lookback = fitted_model.get_lookback()
@@ -294,12 +318,11 @@ print(df_all[target_column_name])
 print("predicted values:::")
 print(df_all['predicted'])
 
-# use automl metrics module
-scores = metrics.compute_metrics_regression(
-    df_all['predicted'],
-    df_all[target_column_name],
-    list(constants.Metric.SCALAR_REGRESSION_SET),
-    None, None, None)
+# Use the AutoML scoring module
+regression_metrics = list(constants.REGRESSION_SCALAR_SET)
+y_test = np.array(df_all[target_column_name])
+y_pred = np.array(df_all['predicted'])
+scores = scoring.score_regression(y_test, y_pred, regression_metrics)
 
 print("scores:")
 print(scores)

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.ipynb

@@ -42,7 +42,7 @@
         "\n",
         "AutoML highlights here include built-in holiday featurization, accessing engineered feature names, and working with the `forecast` function. Please also look at the additional forecasting notebooks, which document lagging, rolling windows, forecast quantiles, other ways to use the forecast function, and forecaster deployment.\n",
         "\n",
-        "Make sure you have executed the [configuration](../configuration.ipynb) before running this notebook.\n",
+        "Make sure you have executed the [configuration notebook](../../../configuration.ipynb) before running this notebook.\n",
         "\n",
         "Notebook synopsis:\n",
         "1. Creating an Experiment in an existing Workspace\n",
@@ -71,7 +71,25 @@
         "\n",
         "from azureml.core import Workspace, Experiment, Dataset\n",
         "from azureml.train.automl import AutoMLConfig\n",
-        "from datetime import datetime"
+        "from datetime import datetime\n",
+        "from azureml.automl.core.featurization import FeaturizationConfig"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
     {
@@ -95,7 +113,6 @@
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace'] = ws.name\n",
         "output['SKU'] = ws.sku\n",
@@ -113,9 +130,12 @@
       "source": [
         "## Compute\n",
         "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+        "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\n",
         "#### Creation of AmlCompute takes approximately 5 minutes. \n",
         "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
+        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
       ]
     },
     {
@@ -124,35 +144,22 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.compute import AmlCompute\n",
-        "from azureml.core.compute import ComputeTarget\n",
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpu-cluster-bike\"\n",
+        "amlcompute_cluster_name = \"bike-cluster\"\n",
         "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "    \n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
         "                                                           max_nodes=4)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
         "\n",
-        "    # Create the cluster.\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "    \n",
-        "print('Checking cluster status...')\n",
-        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
-        "    \n",
-        "# For a more detailed view of current AmlCompute status, use get_status()."
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
@@ -161,7 +168,7 @@
       "source": [
         "## Data\n",
         "\n",
-        "The [Machine Learning service workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-workspace), is paired with the storage account, which contains the default data store. We will use it to upload the bike share data and create [tabular dataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py) for training. A tabular dataset defines a series of lazily-evaluated, immutable operations to load data from the data source into tabular representation."
+        "The [Machine Learning service workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-workspace) is paired with the storage account, which contains the default data store. We will use it to upload the bike share data and create [tabular dataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py) for training. A tabular dataset defines a series of lazily-evaluated, immutable operations to load data from the data source into tabular representation."
       ]
     },
     {
@@ -202,7 +209,11 @@
       "outputs": [],
       "source": [
         "dataset = Dataset.Tabular.from_delimited_files(path = [(datastore, 'dataset/bike-no.csv')]).with_timestamp_columns(fine_grain_timestamp=time_column_name) \n",
-        "dataset.take(5).to_pandas_dataframe()"
+        "\n",
+        "# Drop the columns 'casual' and 'registered' as these columns are a breakdown of the total and therefore a leak.\n",
+        "dataset = dataset.drop_columns(columns=['casual', 'registered'])\n",
+        "\n",
+        "dataset.take(5).to_pandas_dataframe().reset_index(drop=True)"
       ]
     },
     {
@@ -221,8 +232,8 @@
       "outputs": [],
       "source": [
         "# select data that occurs before a specified date\n",
-        "train = dataset.time_before(datetime(2012, 9, 1))\n",
-        "train.to_pandas_dataframe().tail(5)"
+        "train = dataset.time_before(datetime(2012, 8, 31), include_boundary=True)\n",
+        "train.to_pandas_dataframe().tail(5).reset_index(drop=True)"
       ]
     },
     {
@@ -231,8 +242,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "test = dataset.time_after(datetime(2012, 8, 31))\n",
-        "test.to_pandas_dataframe().head(5)"
+        "test = dataset.time_after(datetime(2012, 9, 1), include_boundary=True)\n",
+        "test.to_pandas_dataframe().head(5).reset_index(drop=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Forecasting Parameters\n",
+        "To define forecasting parameters for your experiment training, you can leverage the ForecastingParameters class. The table below details the forecasting parameter we will be passing into our experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**time_column_name**|The name of your time column.|\n",
+        "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
+        "|**country_or_region_for_holidays**|The country/region used to generate holiday features. These should be ISO 3166 two-letter country/region codes (i.e. 'US', 'GB').|\n",
+        "|**target_lags**|The target_lags specifies how far back we will construct the lags of the target variable.|\n",
+        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
       ]
     },
     {
@@ -247,20 +274,16 @@
         "|-|-|\n",
         "|**task**|forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
-        "|**blacklist_models**|Models in blacklist won't be used by AutoML. All supported models can be found at [here](https://docs.microsoft.com/en-us/python/api/azureml-train-automl/azureml.train.automl.constants.supportedmodels.regression?view=azure-ml-py).|\n",
-        "|**experiment_timeout_minutes**|Experimentation timeout in minutes.|\n",
+        "|**blocked_models**|Models in blocked_models won't be used by AutoML. All supported models can be found at [here](https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.constants.supportedmodels.forecasting?view=azure-ml-py).|\n",
+        "|**experiment_timeout_hours**|Experimentation timeout in hours.|\n",
         "|**training_data**|Input dataset, containing both features and label column.|\n",
         "|**label_column_name**|The name of the label column.|\n",
         "|**compute_target**|The remote compute for training.|\n",
         "|**n_cross_validations**|Number of cross validation splits.|\n",
         "|**enable_early_stopping**|If early stopping is on, training will stop when the primary metric is no longer improving.|\n",
-        "|**time_column_name**|Name of the datetime column in the input data|\n",
-        "|**max_horizon**|Maximum desired forecast horizon in units of time-series frequency|\n",
-        "|**country_or_region**|The country/region used to generate holiday features. These should be ISO 3166 two-letter country/region codes (i.e. 'US', 'GB').|\n",
-        "|**target_lags**|The target_lags specifies how far back we will construct the lags of the target variable.|\n",
-        "|**drop_column_names**|Name(s) of columns to drop prior to modeling|\n",
+        "|**forecasting_parameters**|A class that holds all the forecasting related parameters.|\n",
         "\n",
-        "This notebook uses the blacklist_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blacklist_models list but you may need to increase the experiment_timeout_minutes parameter value to get results."
+        "This notebook uses the blocked_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blocked_models list but you may need to increase the experiment_timeout_hours parameter value to get results."
       ]
     },
     {
@@ -278,7 +301,26 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "max_horizon = 14"
+        "forecast_horizon = 14"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Convert prediction type to integer\n",
+        "The featurization configuration can be used to change the default prediction type from decimal numbers to integer. This customization can be used in the scenario when the target column is expected to contain whole values as the number of rented bikes per day."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "featurization_config = FeaturizationConfig()\n",
+        "# Force the target column, to be integer type.\n",
+        "featurization_config.add_prediction_transform_type('Integer')"
       ]
     },
     {
@@ -294,18 +336,20 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "time_series_settings = {\n",
-        "    'time_column_name': time_column_name,\n",
-        "    'max_horizon': max_horizon,    \n",
-        "    'country_or_region': 'US', # set country_or_region will trigger holiday featurizer\n",
-        "    'target_lags': 'auto', # use heuristic based lag setting    \n",
-        "    'drop_column_names': ['casual', 'registered'] # these columns are a breakdown of the total and therefore a leak\n",
-        "}\n",
+        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
+        "forecasting_parameters = ForecastingParameters(\n",
+        "    time_column_name=time_column_name,\n",
+        "    forecast_horizon=forecast_horizon,\n",
+        "    country_or_region_for_holidays='US', # set country_or_region will trigger holiday featurizer\n",
+        "    target_lags='auto', # use heuristic based lag setting\n",
+        "    freq='D' # Set the forecast frequency to be daily\n",
+        ")\n",
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',                             \n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             blacklist_models = ['ExtremeRandomTrees'],                             \n",
-        "                             experiment_timeout_minutes=20,\n",
+        "                             featurization=featurization_config,\n",
+        "                             blocked_models = ['ExtremeRandomTrees'],                             \n",
+        "                             experiment_timeout_hours=0.3,\n",
         "                             training_data=train,\n",
         "                             label_column_name=target_column_name,\n",
         "                             compute_target=compute_target,\n",
@@ -314,7 +358,7 @@
         "                             max_concurrent_iterations=4,\n",
         "                             max_cores_per_iteration=-1,\n",
         "                             verbosity=logging.INFO,\n",
-        "                            **time_series_settings)"
+        "                             forecasting_parameters=forecasting_parameters)"
       ]
     },
     {
@@ -330,8 +374,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "remote_run = experiment.submit(automl_config, show_output=False)\n",
-        "remote_run"
+        "remote_run = experiment.submit(automl_config, show_output=False)"
       ]
     },
     {
@@ -419,7 +462,7 @@
       "source": [
         "We now use the best fitted model from the AutoML Run to make forecasts for the test set. We will do batch scoring on the test dataset which should have the same schema as training dataset.\n",
         "\n",
-        "The scoring will run on a remote compute. In this example, it will reuse the training compute.|"
+        "The scoring will run on a remote compute. In this example, it will reuse the training compute."
       ]
     },
     {
@@ -436,7 +479,7 @@
       "metadata": {},
       "source": [
         "### Retrieving forecasts from the model\n",
-        "To run the forecast on the remote compute we will use two helper scripts: forecasting_script and forecasting_helper. These scripts contain the utility methods which will be used by the remote estimator. We copy these scripts to the project folder to upload them to remote compute."
+        "To run the forecast on the remote compute we will use a helper script: forecasting_script. This script contains the utility methods which will be used by the remote estimator. We copy the script to the project folder to upload it to remote compute."
       ]
     },
     {
@@ -450,15 +493,14 @@
         "\n",
         "script_folder = os.path.join(os.getcwd(), 'forecast')\n",
         "os.makedirs(script_folder, exist_ok=True)\n",
-        "shutil.copy2('forecasting_script.py', script_folder)\n",
-        "shutil.copy2('forecasting_helper.py', script_folder)"
+        "shutil.copy('forecasting_script.py', script_folder)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "For brevity we have created the function called run_forecast. It submits the test data to the best model and run the estimation on the selected compute target."
+        "For brevity, we have created a function called run_forecast that submits the test data to the best model determined during the training run and retrieves forecasts. The test set is longer than the forecast horizon specified at train time, so the forecasting script uses a so-called rolling evaluation to generate predictions over the whole test set. A rolling evaluation iterates the forecaster over the test set, using the actuals in the test set to make lag features as needed. "
       ]
     },
     {
@@ -469,8 +511,7 @@
       "source": [
         "from run_forecast import run_rolling_forecast\n",
         "\n",
-        "remote_run = run_rolling_forecast(test_experiment, compute_target, best_run, test, max_horizon,\n",
-        "                 target_column_name, time_column_name)\n",
+        "remote_run = run_rolling_forecast(test_experiment, compute_target, best_run, test, target_column_name)\n",
         "remote_run"
       ]
     },
@@ -487,7 +528,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Download the prediction result for metrics calcuation\n",
+        "### Download the prediction result for metrics calculation\n",
         "The test data with predictions are saved in artifact outputs/predictions.csv. You can download it and calculation some error metrics for the forecasts and vizualize the predictions vs. the actuals."
       ]
     },
@@ -507,17 +548,16 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.automl.core._vendor.automl.client.core.common import metrics\n",
+        "from azureml.automl.core.shared import constants\n",
+        "from azureml.automl.runtime.shared.score import scoring\n",
         "from sklearn.metrics import mean_absolute_error, mean_squared_error\n",
         "from matplotlib import pyplot as plt\n",
-        "from automl.client.core.common import constants\n",
         "\n",
         "# use automl metrics module\n",
-        "scores = metrics.compute_metrics_regression(\n",
-        "    df_all['predicted'],\n",
-        "    df_all[target_column_name],\n",
-        "    list(constants.Metric.SCALAR_REGRESSION_SET),\n",
-        "    None, None, None)\n",
+        "scores = scoring.score_regression(\n",
+        "    y_test=df_all[target_column_name],\n",
+        "    y_pred=df_all['predicted'],\n",
+        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET))\n",
         "\n",
         "print(\"[Test data scores]\\n\")\n",
         "for key, value in scores.items():    \n",
@@ -535,7 +575,10 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "The MAPE seems high; it is being skewed by an actual with a small absolute value. For a more informative evaluation, we can calculate the metrics by forecast horizon:"
+        "For more details on what metrics are included and how they are calculated, please refer to [supported metrics](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#regressionforecasting-metrics). You could also calculate residuals, like described [here](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#residuals).\n",
+        "\n",
+        "\n",
+        "Since we did a rolling evaluation on the test set, we can analyze the predictions by their forecast horizon relative to the rolling origin. The model was initially trained at a forecast horizon of 14, so each prediction from the model is associated with a horizon value from 1 to 14. The horizon values are in a column named, \"horizon_origin,\" in the prediction set. For example, we can calculate some of the error metrics grouped by the horizon:"
       ]
     },
     {
@@ -555,7 +598,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "It's also interesting to see the distributions of APE (absolute percentage error) by horizon. On a log scale, the outlying APE in the horizon-3 group is clear."
+        "To drill down more, we can look at the distributions of APE (absolute percentage error) by horizon. From the chart, it is clear that the overall MAPE is being skewed by one particular point where the actual value is of small absolute value."
       ]
     },
     {
@@ -565,7 +608,7 @@
       "outputs": [],
       "source": [
         "df_all_APE = df_all.assign(APE=APE(df_all[target_column_name], df_all['predicted']))\n",
-        "APEs = [df_all_APE[df_all['horizon_origin'] == h].APE.values for h in range(1, max_horizon + 1)]\n",
+        "APEs = [df_all_APE[df_all['horizon_origin'] == h].APE.values for h in range(1, forecast_horizon + 1)]\n",
         "\n",
         "%matplotlib inline\n",
         "plt.boxplot(APEs)\n",
@@ -581,12 +624,12 @@
   "metadata": {
     "authors": [
       {
-        "name": "erwright"
+        "name": "jialiu"
       }
     ],
     "category": "tutorial",
     "compute": [
-      "remote"
+      "Remote"
     ],
     "datasets": [
       "BikeShare"
@@ -625,9 +668,9 @@
     "tags": [
       "Forecasting"
     ],
-    "task": "forecasting",
+    "task": "Forecasting",
     "version": 3
   },
   "nbformat": 4,
-  "nbformat_minor": 2
+  "nbformat_minor": 4
 }

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.yml

@@ -1,11 +1,4 @@
 name: auto-ml-forecasting-bike-share
 dependencies:
-- fbprophet==0.5
-- py-xgboost<=0.80
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/forecasting_helper.py

@@ -1,99 +0,0 @@
-import pandas as pd
-import numpy as np
-from pandas.tseries.frequencies import to_offset
-
-
-def align_outputs(y_predicted, X_trans, X_test, y_test, target_column_name,
-                  predicted_column_name='predicted',
-                  horizon_colname='horizon_origin'):
-    """
-    Demonstrates how to get the output aligned to the inputs
-    using pandas indexes. Helps understand what happened if
-    the output's shape differs from the input shape, or if
-    the data got re-sorted by time and grain during forecasting.
-
-    Typical causes of misalignment are:
-    * we predicted some periods that were missing in actuals -> drop from eval
-    * model was asked to predict past max_horizon -> increase max horizon
-    * data at start of X_test was needed for lags -> provide previous periods
-    """
-
-    if (horizon_colname in X_trans):
-        df_fcst = pd.DataFrame({predicted_column_name: y_predicted,
-                                horizon_colname: X_trans[horizon_colname]})
-    else:
-        df_fcst = pd.DataFrame({predicted_column_name: y_predicted})
-
-    # y and X outputs are aligned by forecast() function contract
-    df_fcst.index = X_trans.index
-
-    # align original X_test to y_test
-    X_test_full = X_test.copy()
-    X_test_full[target_column_name] = y_test
-
-    # X_test_full's index does not include origin, so reset for merge
-    df_fcst.reset_index(inplace=True)
-    X_test_full = X_test_full.reset_index().drop(columns='index')
-    together = df_fcst.merge(X_test_full, how='right')
-
-    # drop rows where prediction or actuals are nan
-    # happens because of missing actuals
-    # or at edges of time due to lags/rolling windows
-    clean = together[together[[target_column_name,
-                               predicted_column_name]].notnull().all(axis=1)]
-    return(clean)
-
-
-def do_rolling_forecast(fitted_model, X_test, y_test, target_column_name,
-                        time_column_name, max_horizon, freq='D'):
-    """
-    Produce forecasts on a rolling origin over the given test set.
-
-    Each iteration makes a forecast for the next 'max_horizon' periods
-    with respect to the current origin, then advances the origin by the
-    horizon time duration. The prediction context for each forecast is set so
-    that the forecaster uses the actual target values prior to the current
-    origin time for constructing lag features.
-
-    This function returns a concatenated DataFrame of rolling forecasts.
-     """
-    df_list = []
-    origin_time = X_test[time_column_name].min()
-    while origin_time <= X_test[time_column_name].max():
-        # Set the horizon time - end date of the forecast
-        horizon_time = origin_time + max_horizon * to_offset(freq)
-
-        # Extract test data from an expanding window up-to the horizon
-        expand_wind = (X_test[time_column_name] < horizon_time)
-        X_test_expand = X_test[expand_wind]
-        y_query_expand = np.zeros(len(X_test_expand)).astype(np.float)
-        y_query_expand.fill(np.NaN)
-
-        if origin_time != X_test[time_column_name].min():
-            # Set the context by including actuals up-to the origin time
-            test_context_expand_wind = (X_test[time_column_name] < origin_time)
-            context_expand_wind = (
-                X_test_expand[time_column_name] < origin_time)
-            y_query_expand[context_expand_wind] = y_test[
-                test_context_expand_wind]
-
-        # Make a forecast out to the maximum horizon
-        y_fcst, X_trans = fitted_model.forecast(X_test_expand, y_query_expand)
-
-        # Align forecast with test set for dates within the
-        # current rolling window
-        trans_tindex = X_trans.index.get_level_values(time_column_name)
-        trans_roll_wind = (trans_tindex >= origin_time) & (
-            trans_tindex < horizon_time)
-        test_roll_wind = expand_wind & (
-            X_test[time_column_name] >= origin_time)
-        df_list.append(align_outputs(y_fcst[trans_roll_wind],
-                                     X_trans[trans_roll_wind],
-                                     X_test[test_roll_wind],
-                                     y_test[test_roll_wind],
-                                     target_column_name))
-
-        # Advance the origin time
-        origin_time = horizon_time
-
-    return pd.concat(df_list, ignore_index=True)

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/forecasting_script.py

@@ -1,53 +1,36 @@
 import argparse
-import azureml.train.automl
-from azureml.automl.core._vendor.automl.client.core.runtime import forecasting_models
-from azureml.core import Run
+from azureml.core import Dataset, Run
 from sklearn.externals import joblib
-import forecasting_helper
-
 
 parser = argparse.ArgumentParser()
-parser.add_argument(
-    '--max_horizon', type=int, dest='max_horizon',
-    default=10, help='Max Horizon for forecasting')
 parser.add_argument(
     '--target_column_name', type=str, dest='target_column_name',
     help='Target Column Name')
 parser.add_argument(
-    '--time_column_name', type=str, dest='time_column_name',
-    help='Time Column Name')
-parser.add_argument(
-    '--frequency', type=str, dest='freq',
-    help='Frequency of prediction')
+    '--test_dataset', type=str, dest='test_dataset',
+    help='Test Dataset')
 
 args = parser.parse_args()
-max_horizon = args.max_horizon
 target_column_name = args.target_column_name
-time_column_name = args.time_column_name
-freq = args.freq
+test_dataset_id = args.test_dataset
 
 run = Run.get_context()
-# get input dataset by name
-test_dataset = run.input_datasets['test_data']
+ws = run.experiment.workspace
 
-grain_column_names = []
+# get the input dataset by id
+test_dataset = Dataset.get_by_id(ws, id=test_dataset_id)
 
-df = test_dataset.to_pandas_dataframe()
-
-X_test_df = test_dataset.drop_columns(columns=[target_column_name])
-y_test_df = test_dataset.with_timestamp_columns(
-    None).keep_columns(columns=[target_column_name])
+X_test_df = test_dataset.drop_columns(columns=[target_column_name]).to_pandas_dataframe().reset_index(drop=True)
+y_test_df = test_dataset.with_timestamp_columns(None).keep_columns(columns=[target_column_name]).to_pandas_dataframe()
 
 fitted_model = joblib.load('model.pkl')
 
-df_all = forecasting_helper.do_rolling_forecast(
-    fitted_model,
-    X_test_df.to_pandas_dataframe(),
-    y_test_df.to_pandas_dataframe().values.T[0],
-    target_column_name,
-    time_column_name,
-    max_horizon,
-    freq)
+y_pred, X_trans = fitted_model.rolling_evaluation(X_test_df, y_test_df.values)
+
+# Add predictions, actuals, and horizon relative to rolling origin to the test feature data
+assign_dict = {'horizon_origin': X_trans['horizon_origin'].values, 'predicted': y_pred,
+               target_column_name: y_test_df[target_column_name].values}
+df_all = X_test_df.assign(**assign_dict)
 
 file_name = 'outputs/predictions.csv'
 export_csv = df_all.to_csv(file_name, header=True)

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/run_forecast.py

@@ -1,41 +1,32 @@
-from azureml.core import Environment
-from azureml.core.conda_dependencies import CondaDependencies
-from azureml.train.estimator import Estimator
-from azureml.core.run import Run
+from azureml.core import ScriptRunConfig
 
 
-def run_rolling_forecast(test_experiment, compute_target, train_run, test_dataset,
-                         max_horizon, target_column_name, time_column_name,
-                         freq='D', inference_folder='./forecast'):
-    condafile = inference_folder + '/condafile.yml'
+def run_rolling_forecast(test_experiment, compute_target, train_run,
+                         test_dataset, target_column_name,
+                         inference_folder='./forecast'):
     train_run.download_file('outputs/model.pkl',
                             inference_folder + '/model.pkl')
-    train_run.download_file('outputs/conda_env_v_1_0_0.yml', condafile)
 
-    inference_env = Environment("myenv")
-    inference_env.docker.enabled = True
-    inference_env.python.conda_dependencies = CondaDependencies(
-        conda_dependencies_file_path=condafile)
+    inference_env = train_run.get_environment()
 
-    est = Estimator(source_directory=inference_folder,
-                    entry_script='forecasting_script.py',
-                    script_params={
-                        '--max_horizon': max_horizon,
-                        '--target_column_name': target_column_name,
-                        '--time_column_name': time_column_name,
-                        '--frequency': freq
-                    },
-                    inputs=[test_dataset.as_named_input('test_data')],
+    config = ScriptRunConfig(source_directory=inference_folder,
+                             script='forecasting_script.py',
+                             arguments=['--target_column_name',
+                                        target_column_name,
+                                        '--test_dataset',
+                                        test_dataset.as_named_input(test_dataset.name)],
                              compute_target=compute_target,
-                    environment_definition=inference_env)
+                             environment=inference_env)
 
-    run = test_experiment.submit(est,
-                                 tags={
-                                     'training_run_id': train_run.id,
-                                     'run_algorithm': train_run.properties['run_algorithm'],
-                                     'valid_score': train_run.properties['score'],
-                                     'primary_metric': train_run.properties['primary_metric']
-                                 })
+    run = test_experiment.submit(config,
+                                 tags={'training_run_id':
+                                       train_run.id,
+                                       'run_algorithm':
+                                       train_run.properties['run_algorithm'],
+                                       'valid_score':
+                                       train_run.properties['score'],
+                                       'primary_metric':
+                                       train_run.properties['primary_metric']})
 
     run.log("run_algorithm", run.tags['run_algorithm'])
     return run

how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb

@@ -24,41 +24,42 @@
         "_**Forecasting using the Energy Demand Dataset**_\n",
         "\n",
         "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Data and Forecasting Configurations](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Results](#Results)\n",
+        "1. [Introduction](#introduction)\n",
+        "1. [Setup](#setup)\n",
+        "1. [Data and Forecasting Configurations](#data)\n",
+        "1. [Train](#train)\n",
+        "1. [Generate and Evaluate the Forecast](#forecast)\n",
         "\n",
         "Advanced Forecasting\n",
-        "1. [Advanced Training](#Advanced Training)\n",
-        "1. [Advanced Results](#Advanced Results)"
+        "1. [Advanced Training](#advanced_training)\n",
+        "1. [Advanced Results](#advanced_results)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Introduction\n",
+        "# Introduction<a id=\"introduction\"></a>\n",
         "\n",
         "In this example we use the associated New York City energy demand dataset to showcase how you can use AutoML for a simple forecasting problem and explore the results. The goal is predict the energy demand for the next 48 hours based on historic time-series data.\n",
         "\n",
-        "If you are using an Azure Machine Learning [Notebook VM](https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-1st-experiment-sdk-setup), you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) first, if you haven't already, to establish your connection to the AzureML Workspace.\n",
+        "If you are using an Azure Machine Learning Compute Instance, you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) first, if you haven't already, to establish your connection to the AzureML Workspace.\n",
         "\n",
         "In this notebook you will learn how to:\n",
         "1. Creating an Experiment using an existing Workspace\n",
         "1. Configure AutoML using 'AutoMLConfig'\n",
         "1. Train the model using AmlCompute\n",
         "1. Explore the engineered features and results\n",
+        "1. Generate the forecast and compute the out-of-sample accuracy metrics\n",
         "1. Configuration and remote run of AutoML for a time-series model with lag and rolling window features\n",
-        "1. Run and explore the forecast"
+        "1. Run and explore the forecast with lagging features"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Setup"
+        "# Setup<a id=\"setup\"></a>"
       ]
     },
     {
@@ -85,6 +86,23 @@
         "from datetime import datetime"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -109,7 +127,6 @@
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
@@ -140,42 +157,29 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.compute import AmlCompute\n",
-        "from azureml.core.compute import ComputeTarget\n",
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"aml-compute\"\n",
+        "amlcompute_cluster_name = \"energy-cluster\"\n",
         "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "\n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_DS12_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
         "                                                           max_nodes=6)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
         "\n",
-        "    # Create the cluster.\\n\",\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "\n",
-        "print('Checking cluster status...')\n",
-        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
-        "\n",
-        "# For a more detailed view of current AmlCompute status, use get_status()."
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# Data\n",
+        "# Data<a id=\"data\"></a>\n",
         "\n",
         "We will use energy consumption [data from New York City](http://mis.nyiso.com/public/P-58Blist.htm) for model training. The data is stored in a tabular format and includes energy demand and basic weather data at an hourly frequency. \n",
         "\n",
@@ -211,7 +215,7 @@
       "outputs": [],
       "source": [
         "dataset = Dataset.Tabular.from_delimited_files(path = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/nyc_energy.csv\").with_timestamp_columns(fine_grain_timestamp=time_column_name) \n",
-        "dataset.take(5).to_pandas_dataframe()"
+        "dataset.take(5).to_pandas_dataframe().reset_index(drop=True)"
       ]
     },
     {
@@ -253,7 +257,7 @@
       "source": [
         "# split into train based on time\n",
         "train = dataset.time_before(datetime(2017, 8, 8, 5), include_boundary=True)\n",
-        "train.to_pandas_dataframe().sort_values(time_column_name).tail(5)"
+        "train.to_pandas_dataframe().reset_index(drop=True).sort_values(time_column_name).tail(5)"
       ]
     },
     {
@@ -263,8 +267,8 @@
       "outputs": [],
       "source": [
         "# split into test based on time\n",
-        "test = dataset.time_between(datetime(2017, 8, 8, 5), datetime(2017, 8, 10, 5))\n",
-        "test.to_pandas_dataframe().head(5)"
+        "test = dataset.time_between(datetime(2017, 8, 8, 6), datetime(2017, 8, 10, 5))\n",
+        "test.to_pandas_dataframe().reset_index(drop=True).head(5)"
       ]
     },
     {
@@ -286,37 +290,50 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "max_horizon = 48"
+        "forecast_horizon = 48"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Train\n",
+        "## Forecasting Parameters\n",
+        "To define forecasting parameters for your experiment training, you can leverage the ForecastingParameters class. The table below details the forecasting parameter we will be passing into our experiment.\n",
         "\n",
-        "Instantiate an AutoMLConfig object. This config defines the settings and data used to run the experiment. We can provide extra configurations within 'automl_settings', for this forecasting task we add the name of the time column and the maximum forecast horizon.\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**time_column_name**|The name of your time column.|\n",
+        "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
+        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Train<a id=\"train\"></a>\n",
+        "\n",
+        "Instantiate an AutoMLConfig object. This config defines the settings and data used to run the experiment. We can provide extra configurations within 'automl_settings', for this forecasting task we add the forecasting parameters to hold all the additional forecasting parameters.\n",
         "\n",
         "|Property|Description|\n",
         "|-|-|\n",
         "|**task**|forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
-        "|**blacklist_models**|Models in blacklist won't be used by AutoML. All supported models can be found at [here](https://docs.microsoft.com/en-us/python/api/azureml-train-automl/azureml.train.automl.constants.supportedmodels.regression?view=azure-ml-py).|\n",
-        "|**experiment_timeout_minutes**|Maximum amount of time in minutes that the experiment take before it terminates.|\n",
+        "|**blocked_models**|Models in blocked_models won't be used by AutoML. All supported models can be found at [here](https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.constants.supportedmodels.forecasting?view=azure-ml-py).|\n",
+        "|**experiment_timeout_hours**|Maximum amount of time in hours that the experiment take before it terminates.|\n",
         "|**training_data**|The training data to be used within the experiment.|\n",
         "|**label_column_name**|The name of the label column.|\n",
         "|**compute_target**|The remote compute for training.|\n",
         "|**n_cross_validations**|Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way.|\n",
         "|**enable_early_stopping**|Flag to enble early termination if the score is not improving in the short term.|\n",
-        "|**time_column_name**|The name of your time column.|\n",
-        "|**max_horizon**|The number of periods out you would like to predict past your training data. Periods are inferred from your data.|\n"
+        "|**forecasting_parameters**|A class holds all the forecasting related parameters.|\n"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "This notebook uses the blacklist_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blacklist_models list but you may need to increase the experiment_timeout_minutes parameter value to get results."
+        "This notebook uses the blocked_models parameter to exclude some models that take a longer time to train on this dataset. You can choose to remove models from the blocked_models list but you may need to increase the experiment_timeout_hours parameter value to get results."
       ]
     },
     {
@@ -325,22 +342,24 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "automl_settings = {\n",
-        "    'time_column_name': time_column_name,\n",
-        "    'max_horizon': max_horizon,\n",
-        "}\n",
+        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
+        "forecasting_parameters = ForecastingParameters(\n",
+        "    time_column_name=time_column_name,\n",
+        "    forecast_horizon=forecast_horizon,\n",
+        "    freq='H' # Set the forecast frequency to be hourly\n",
+        ")\n",
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',                             \n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             blacklist_models = ['ExtremeRandomTrees', 'AutoArima', 'Prophet'],                             \n",
-        "                             experiment_timeout_minutes=20,\n",
+        "                             blocked_models = ['ExtremeRandomTrees', 'AutoArima', 'Prophet'],                             \n",
+        "                             experiment_timeout_hours=0.3,\n",
         "                             training_data=train,\n",
         "                             label_column_name=target_column_name,\n",
         "                             compute_target=compute_target,\n",
         "                             enable_early_stopping=True,\n",
         "                             n_cross_validations=3,                             \n",
         "                             verbosity=logging.INFO,\n",
-        "                            **automl_settings)"
+        "                             forecasting_parameters=forecasting_parameters)"
       ]
     },
     {
@@ -360,15 +379,6 @@
         "remote_run = experiment.submit(automl_config, show_output=False)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -443,9 +453,11 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Forecasting\n",
+        "# Forecasting<a id=\"forecast\"></a>\n",
         "\n",
-        "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. First, we remove the target values from the test set:"
+        "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. We will do batch scoring on the test dataset which should have the same schema as training dataset.\n",
+        "\n",
+        "The inference will run on a remote compute. In this example, it will re-use the training compute."
       ]
     },
     {
@@ -454,20 +466,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_test = test.to_pandas_dataframe()\n",
-        "y_test = X_test.pop(target_column_name).values"
+        "test_experiment = Experiment(ws, experiment_name + \"_inference\")"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Forecast Function\n",
-        "For forecasting, we will use the forecast function instead of the predict function. There are two reasons for this.\n",
-        "\n",
-        "We need to pass the recent values of the target variable y, whereas the scikit-compatible predict function only takes the non-target variables 'test'. In our case, the test data immediately follows the training data, and we fill the target variable with NaN. The NaN serves as a question mark for the forecaster to fill with the actuals. Using the forecast function will produce forecasts using the shortest possible forecast horizon. The last time at which a definite (non-NaN) value is seen is the forecast origin - the last time when the value of the target is known.\n",
-        "\n",
-        "Using the predict method would result in getting predictions for EVERY horizon the forecaster can predict at. This is useful when training and evaluating the performance of the forecaster at various horizons, but the level of detail is excessive for normal use."
+        "### Retreiving forecasts from the model\n",
+        "We have created a function called `run_forecast` that submits the test data to the best model determined during the training run and retrieves forecasts. This function uses a helper script `forecasting_script` which is uploaded and expecuted on the remote compute."
       ]
     },
     {
@@ -476,15 +483,16 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Replace ALL values in y by NaN.\n",
-        "# The forecast origin will be at the beginning of the first forecast period.\n",
-        "# (Which is the same time as the end of the last training period.)\n",
-        "y_query = y_test.copy().astype(np.float)\n",
-        "y_query.fill(np.nan)\n",
-        "# The featurized data, aligned to y, will also be returned.\n",
-        "# This contains the assumptions that were made in the forecast\n",
-        "# and helps align the forecast to the original data\n",
-        "y_predictions, X_trans = fitted_model.forecast(X_test, y_query)"
+        "from run_forecast import run_remote_inference\n",
+        "remote_run_infer = run_remote_inference(test_experiment=test_experiment,\n",
+        "                                        compute_target=compute_target,\n",
+        "                                        train_run=best_run,\n",
+        "                                        test_dataset=test,\n",
+        "                                        target_column_name=target_column_name)\n",
+        "remote_run_infer.wait_for_completion(show_output=False)\n",
+        "\n",
+        "# download the inference output file to the local machine\n",
+        "remote_run_infer.download_file('outputs/predictions.csv', 'predictions.csv')"
       ]
     },
     {
@@ -492,9 +500,7 @@
       "metadata": {},
       "source": [
         "### Evaluate\n",
-        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE).\n",
-        "\n",
-        "It is a good practice to always align the output explicitly to the input, as the count and order of the rows may have changed during transformations that span multiple rows."
+        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE). For more metrics that can be used for evaluation after training, please see [supported metrics](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#regressionforecasting-metrics), and [how to calculate residuals](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#residuals)."
       ]
     },
     {
@@ -503,9 +509,9 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from forecasting_helper import align_outputs\n",
-        "\n",
-        "df_all = align_outputs(y_predictions, X_trans, X_test, y_test, target_column_name)"
+        "# load forecast data frame\n",
+        "fcst_df = pd.read_csv('predictions.csv', parse_dates=[time_column_name])\n",
+        "fcst_df.head()"
       ]
     },
     {
@@ -514,16 +520,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.automl.core._vendor.automl.client.core.common import metrics\n",
+        "from azureml.automl.core.shared import constants\n",
+        "from azureml.automl.runtime.shared.score import scoring\n",
         "from matplotlib import pyplot as plt\n",
-        "from automl.client.core.common import constants\n",
         "\n",
         "# use automl metrics module\n",
-        "scores = metrics.compute_metrics_regression(\n",
-        "    df_all['predicted'],\n",
-        "    df_all[target_column_name],\n",
-        "    list(constants.Metric.SCALAR_REGRESSION_SET),\n",
-        "    None, None, None)\n",
+        "scores = scoring.score_regression(\n",
+        "    y_test=fcst_df[target_column_name],\n",
+        "    y_pred=fcst_df['predicted'],\n",
+        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET))\n",
         "\n",
         "print(\"[Test data scores]\\n\")\n",
         "for key, value in scores.items():    \n",
@@ -531,8 +536,8 @@
         "    \n",
         "# Plot outputs\n",
         "%matplotlib inline\n",
-        "test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], color='b')\n",
-        "test_test = plt.scatter(df_all[target_column_name], df_all[target_column_name], color='g')\n",
+        "test_pred = plt.scatter(fcst_df[target_column_name], fcst_df['predicted'], color='b')\n",
+        "test_test = plt.scatter(fcst_df[target_column_name], fcst_df[target_column_name], color='g')\n",
         "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
         "plt.show()"
       ]
@@ -541,24 +546,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Looking at `X_trans` is also useful to see what featurization happened to the data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_trans"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Advanced Training\n",
-        "We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, grain and any additional features. This is often a very good prediction as common time series patterns like seasonality and trends can be captured in this manner. Such simple regression is horizon-less: it doesn't matter how far into the future we are predicting, because we are not using past data. In the previous example, the horizon was only used to split the data for cross-validation."
+        "# Advanced Training <a id=\"advanced_training\"></a>\n",
+        "We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, time series identifier columns and any additional features. This is often a very good prediction as common time series patterns like seasonality and trends can be captured in this manner. Such simple regression is horizon-less: it doesn't matter how far into the future we are predicting, because we are not using past data. In the previous example, the horizon was only used to split the data for cross-validation."
       ]
     },
     {
@@ -566,9 +555,9 @@
       "metadata": {},
       "source": [
         "### Using lags and rolling window features\n",
-        "Now we will configure the target lags, that is the previous values of the target variables, meaning the prediction is no longer horizon-less. We therefore must still specify the `max_horizon` that the model will learn to forecast. The `target_lags` keyword specifies how far back we will construct the lags of the target variable, and the `target_rolling_window_size` specifies the size of the rolling window over which we will generate the `max`, `min` and `sum` features.\n",
+        "Now we will configure the target lags, that is the previous values of the target variables, meaning the prediction is no longer horizon-less. We therefore must still specify the `forecast_horizon` that the model will learn to forecast. The `target_lags` keyword specifies how far back we will construct the lags of the target variable, and the `target_rolling_window_size` specifies the size of the rolling window over which we will generate the `max`, `min` and `sum` features.\n",
         "\n",
-        "This notebook uses the blacklist_models parameter to exclude some models that take a longer time to train on this dataset.  You can choose to remove models from the blacklist_models list but you may need to increase the iteration_timeout_minutes parameter value to get results."
+        "This notebook uses the blocked_models parameter to exclude some models that take a longer time to train on this dataset.  You can choose to remove models from the blocked_models list but you may need to increase the iteration_timeout_minutes parameter value to get results."
       ]
     },
     {
@@ -577,24 +566,22 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "automl_advanced_settings = {\n",
-        "    'time_column_name': time_column_name,\n",
-        "    'max_horizon': max_horizon,\n",
-        "    'target_lags': 12,\n",
-        "    'target_rolling_window_size': 4,\n",
-        "}\n",
+        "advanced_forecasting_parameters = ForecastingParameters(\n",
+        "    time_column_name=time_column_name, forecast_horizon=forecast_horizon,\n",
+        "    target_lags=12, target_rolling_window_size=4\n",
+        ")\n",
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',                             \n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             blacklist_models = ['ElasticNet','ExtremeRandomTrees','GradientBoosting','XGBoostRegressor','ExtremeRandomTrees', 'AutoArima', 'Prophet'], #These models are blacklisted for tutorial purposes, remove this for real use cases.                            \n",
-        "                             experiment_timeout_minutes=20,\n",
+        "                             blocked_models = ['ElasticNet','ExtremeRandomTrees','GradientBoosting','XGBoostRegressor','ExtremeRandomTrees', 'AutoArima', 'Prophet'], #These models are blocked for tutorial purposes, remove this for real use cases.                            \n",
+        "                             experiment_timeout_hours=0.3,\n",
         "                             training_data=train,\n",
         "                             label_column_name=target_column_name,\n",
         "                             compute_target=compute_target,\n",
         "                             enable_early_stopping = True,\n",
         "                             n_cross_validations=3,                             \n",
         "                             verbosity=logging.INFO,\n",
-        "                            **automl_advanced_settings)"
+        "                             forecasting_parameters=advanced_forecasting_parameters)"
       ]
     },
     {
@@ -642,8 +629,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Advanced Results\n",
-        "We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, grain and any additional features. This is often a very good prediction as common time series patterns like seasonality and trends can be captured in this manner. Such simple regression is horizon-less: it doesn't matter how far into the future we are predicting, because we are not using past data. In the previous example, the horizon was only used to split the data for cross-validation."
+        "# Advanced Results<a id=\"advanced_results\"></a>\n",
+        "We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, time series identifier columns and any additional features. This is often a very good prediction as common time series patterns like seasonality and trends can be captured in this manner. Such simple regression is horizon-less: it doesn't matter how far into the future we are predicting, because we are not using past data. In the previous example, the horizon was only used to split the data for cross-validation."
       ]
     },
     {
@@ -652,26 +639,17 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Replace ALL values in y by NaN.\n",
-        "# The forecast origin will be at the beginning of the first forecast period.\n",
-        "# (Which is the same time as the end of the last training period.)\n",
-        "y_query = y_test.copy().astype(np.float)\n",
-        "y_query.fill(np.nan)\n",
-        "# The featurized data, aligned to y, will also be returned.\n",
-        "# This contains the assumptions that were made in the forecast\n",
-        "# and helps align the forecast to the original data\n",
-        "y_predictions, X_trans = fitted_model_lags.forecast(X_test, y_query)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from forecasting_helper import align_outputs\n",
+        "test_experiment_advanced = Experiment(ws, experiment_name + \"_inference_advanced\")\n",
+        "advanced_remote_run_infer = run_remote_inference(test_experiment=test_experiment_advanced,\n",
+        "                                                 compute_target=compute_target,\n",
+        "                                                 train_run=best_run_lags,\n",
+        "                                                 test_dataset=test,\n",
+        "                                                 target_column_name=target_column_name,\n",
+        "                                                 inference_folder='./forecast_advanced')\n",
+        "advanced_remote_run_infer.wait_for_completion(show_output=False)\n",
         "\n",
-        "df_all = align_outputs(y_predictions, X_trans, X_test, y_test, target_column_name)"
+        "# download the inference output file to the local machine\n",
+        "advanced_remote_run_infer.download_file('outputs/predictions.csv', 'predictions_advanced.csv')"
       ]
     },
     {
@@ -680,16 +658,25 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.automl.core._vendor.automl.client.core.common import metrics\n",
+        "fcst_adv_df = pd.read_csv('predictions_advanced.csv', parse_dates=[time_column_name])\n",
+        "fcst_adv_df.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.automl.core.shared import constants\n",
+        "from azureml.automl.runtime.shared.score import scoring\n",
         "from matplotlib import pyplot as plt\n",
-        "from automl.client.core.common import constants\n",
         "\n",
         "# use automl metrics module\n",
-        "scores = metrics.compute_metrics_regression(\n",
-        "    df_all['predicted'],\n",
-        "    df_all[target_column_name],\n",
-        "    list(constants.Metric.SCALAR_REGRESSION_SET),\n",
-        "    None, None, None)\n",
+        "scores = scoring.score_regression(\n",
+        "    y_test=fcst_adv_df[target_column_name],\n",
+        "    y_pred=fcst_adv_df['predicted'],\n",
+        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET))\n",
         "\n",
         "print(\"[Test data scores]\\n\")\n",
         "for key, value in scores.items():    \n",
@@ -697,8 +684,8 @@
         "    \n",
         "# Plot outputs\n",
         "%matplotlib inline\n",
-        "test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], color='b')\n",
-        "test_test = plt.scatter(df_all[target_column_name], df_all[target_column_name], color='g')\n",
+        "test_pred = plt.scatter(fcst_adv_df[target_column_name], fcst_adv_df['predicted'], color='b')\n",
+        "test_test = plt.scatter(fcst_adv_df[target_column_name], fcst_adv_df[target_column_name], color='g')\n",
         "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
         "plt.show()"
       ]
@@ -707,7 +694,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "erwright"
+        "name": "jialiu"
       }
     ],
     "categories": [
@@ -729,15 +716,8 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.8"
-    },
-    "star_tag": [
-      "featured"
-    ],
-    "tags": [
-      ""
-    ],
-    "task": "Forecasting"
+      "version": "3.6.9"
+    }
   },
   "nbformat": 4,
   "nbformat_minor": 2

how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.yml

@@ -2,11 +2,3 @@ name: auto-ml-forecasting-energy-demand
 dependencies:
 - pip:
   - azureml-sdk
-  - interpret
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels
-  - azureml-explain-model
-  - azureml-contrib-interpret

how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/forecasting_script.py

@@ -1,5 +1,15 @@
+"""
+This is the script that is executed on the compute instance. It relies
+on the model.pkl file which is uploaded along with this script to the
+compute instance.
+"""
+
+import argparse
 import pandas as pd
 import numpy as np
+from azureml.core import Dataset, Run
+from azureml.automl.core.shared.constants import TimeSeriesInternal
+from sklearn.externals import joblib
 from pandas.tseries.frequencies import to_offset
 
 
@@ -42,3 +52,38 @@ def align_outputs(y_predicted, X_trans, X_test, y_test, target_column_name,
     clean = together[together[[target_column_name,
                                predicted_column_name]].notnull().all(axis=1)]
     return(clean)
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument(
+    '--target_column_name', type=str, dest='target_column_name',
+    help='Target Column Name')
+parser.add_argument(
+    '--test_dataset', type=str, dest='test_dataset',
+    help='Test Dataset')
+
+args = parser.parse_args()
+target_column_name = args.target_column_name
+test_dataset_id = args.test_dataset
+
+run = Run.get_context()
+ws = run.experiment.workspace
+
+# get the input dataset by id
+test_dataset = Dataset.get_by_id(ws, id=test_dataset_id)
+
+X_test = test_dataset.to_pandas_dataframe().reset_index(drop=True)
+y_test = X_test.pop(target_column_name).values
+
+# generate forecast
+fitted_model = joblib.load('model.pkl')
+y_predictions, X_trans = fitted_model.forecast(X_test)
+
+# align output
+df_all = align_outputs(y_predictions, X_trans, X_test, y_test, target_column_name)
+
+file_name = 'outputs/predictions.csv'
+export_csv = df_all.to_csv(file_name, header=True, index=False)  # added Index
+
+# Upload the predictions into artifacts
+run.upload_file(name=file_name, path_or_stream=file_name)

how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/metrics_helper.py

@@ -1,22 +0,0 @@
-import pandas as pd
-import numpy as np
-
-
-def APE(actual, pred):
-    """
-    Calculate absolute percentage error.
-    Returns a vector of APE values with same length as actual/pred.
-    """
-    return 100 * np.abs((actual - pred) / actual)
-
-
-def MAPE(actual, pred):
-    """
-    Calculate mean absolute percentage error.
-    Remove NA and values where actual is close to zero
-    """
-    not_na = ~(np.isnan(actual) | np.isnan(pred))
-    not_zero = ~np.isclose(actual, 0.0)
-    actual_safe = actual[not_na & not_zero]
-    pred_safe = pred[not_na & not_zero]
-    return np.mean(APE(actual_safe, pred_safe))

how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/run_forecast.py

@@ -0,0 +1,38 @@
+import os
+import shutil
+from azureml.core import ScriptRunConfig
+
+
+def run_remote_inference(test_experiment, compute_target, train_run,
+                         test_dataset, target_column_name, inference_folder='./forecast'):
+    # Create local directory to copy the model.pkl and forecsting_script.py files into.
+    # These files will be uploaded to and executed on the compute instance.
+    os.makedirs(inference_folder, exist_ok=True)
+    shutil.copy('forecasting_script.py', inference_folder)
+
+    train_run.download_file('outputs/model.pkl',
+                            os.path.join(inference_folder, 'model.pkl'))
+
+    inference_env = train_run.get_environment()
+
+    config = ScriptRunConfig(source_directory=inference_folder,
+                             script='forecasting_script.py',
+                             arguments=['--target_column_name',
+                                        target_column_name,
+                                        '--test_dataset',
+                                        test_dataset.as_named_input(test_dataset.name)],
+                             compute_target=compute_target,
+                             environment=inference_env)
+
+    run = test_experiment.submit(config,
+                                 tags={'training_run_id':
+                                       train_run.id,
+                                       'run_algorithm':
+                                       train_run.properties['run_algorithm'],
+                                       'valid_score':
+                                       train_run.properties['score'],
+                                       'primary_metric':
+                                       train_run.properties['primary_metric']})
+
+    run.log("run_algorithm", run.tags['run_algorithm'])
+    return run

how-to-use-azureml/automated-machine-learning/forecasting-forecast-function/auto-ml-forecasting-function.ipynb

@@ -24,7 +24,7 @@
       "metadata": {},
       "source": [
         "## Introduction\n",
-        "This notebook demonstrates the full interface to the `forecast()` function. \n",
+        "This notebook demonstrates the full interface of the `forecast()` function. \n",
         "\n",
         "The best known and most frequent usage of `forecast` enables forecasting on test sets that immediately follows training data. \n",
         "\n",
@@ -35,7 +35,6 @@
         "Terminology:\n",
         "* forecast origin: the last period when the target value is known\n",
         "* forecast periods(s): the period(s) for which the value of the target is desired.\n",
-        "* forecast horizon: the number of forecast periods\n",
         "* lookback: how many past periods (before forecast origin) the model function depends on. The larger of number of lags and length of rolling window.\n",
         "* prediction context: `lookback` periods immediately preceding the forecast origin\n",
         "\n",
@@ -68,6 +67,7 @@
         "import logging\n",
         "import warnings\n",
         "\n",
+        "import azureml.core\n",
         "from azureml.core.dataset import Dataset\n",
         "from pandas.tseries.frequencies import to_offset\n",
         "from azureml.core.compute import AmlCompute\n",
@@ -81,13 +81,29 @@
         "np.set_printoptions(precision=4, suppress=True, linewidth=120)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {},
       "outputs": [],
       "source": [
-        "import azureml.core\n",
         "from azureml.core.workspace import Workspace\n",
         "from azureml.core.experiment import Experiment\n",
         "from azureml.train.automl import AutoMLConfig\n",
@@ -100,7 +116,6 @@
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace'] = ws.name\n",
         "output['SKU'] = ws.sku\n",
@@ -127,15 +142,15 @@
       "outputs": [],
       "source": [
         "TIME_COLUMN_NAME = 'date'\n",
-        "GRAIN_COLUMN_NAME = 'grain'\n",
+        "TIME_SERIES_ID_COLUMN_NAME = 'time_series_id'\n",
         "TARGET_COLUMN_NAME = 'y'\n",
         "\n",
         "def get_timeseries(train_len: int,\n",
         "                   test_len: int,\n",
         "                   time_column_name: str,\n",
         "                   target_column_name: str,\n",
-        "                   grain_column_name: str,\n",
-        "                   grains: int = 1,\n",
+        "                   time_series_id_column_name: str,\n",
+        "                   time_series_number: int = 1,\n",
         "                   freq: str = 'H'):\n",
         "    \"\"\"\n",
         "    Return the time series of designed length.\n",
@@ -146,9 +161,8 @@
         "    :type test_len: int\n",
         "    :param time_column_name: The desired name of a time column.\n",
         "    :type time_column_name: str\n",
-        "    :param\n",
-        "    :param grains: The number of grains.\n",
-        "    :type grains: int\n",
+        "    :param time_series_number: The number of time series in the data set.\n",
+        "    :type time_series_number: int\n",
         "    :param freq: The frequency string representing pandas offset.\n",
         "                 see https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html\n",
         "    :type freq: str\n",
@@ -159,14 +173,14 @@
         "    data_train = []  # type: List[pd.DataFrame]\n",
         "    data_test = []  # type: List[pd.DataFrame]\n",
         "    data_length = train_len + test_len\n",
-        "    for i in range(grains):\n",
+        "    for i in range(time_series_number):\n",
         "        X = pd.DataFrame({\n",
         "            time_column_name: pd.date_range(start='2000-01-01',\n",
         "                                            periods=data_length,\n",
         "                                            freq=freq),\n",
         "            target_column_name: np.arange(data_length).astype(float) + np.random.rand(data_length) + i*5,\n",
         "            'ext_predictor': np.asarray(range(42, 42 + data_length)),\n",
-        "            grain_column_name: np.repeat('g{}'.format(i), data_length)\n",
+        "            time_series_id_column_name: np.repeat('ts{}'.format(i), data_length)\n",
         "        })\n",
         "        data_train.append(X[:train_len])\n",
         "        data_test.append(X[train_len:])\n",
@@ -182,8 +196,8 @@
         "                                                  test_len=n_test_periods,\n",
         "                                                  time_column_name=TIME_COLUMN_NAME,\n",
         "                                                  target_column_name=TARGET_COLUMN_NAME,\n",
-        "                                                  grain_column_name=GRAIN_COLUMN_NAME,\n",
-        "                                                  grains=2)"
+        "                                                  time_series_id_column_name=TIME_SERIES_ID_COLUMN_NAME,\n",
+        "                                                  time_series_number=2)"
       ]
     },
     {
@@ -213,7 +227,7 @@
         "whole_data = X_train.copy()\n",
         "target_label = 'y'\n",
         "whole_data[target_label] = y_train\n",
-        "for g in whole_data.groupby('grain'):    \n",
+        "for g in whole_data.groupby('time_series_id'):    \n",
         "    plt.plot(g[1]['date'].values, g[1]['y'].values, label=g[0])\n",
         "plt.legend()\n",
         "plt.show()"
@@ -249,7 +263,9 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource."
+        "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+        "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
       ]
     },
     {
@@ -258,29 +274,22 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "amlcompute_cluster_name = \"cpu-cluster-fcfn\"\n",
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
+        "# Choose a name for your CPU cluster\n",
+        "amlcompute_cluster_name = \"fcfn-cluster\"\n",
         "\n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
         "                                                           max_nodes=6)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
         "\n",
-        "    # Create the cluster.\\n\",\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "\n",
-        "print('Checking cluster status...')\n",
-        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)"
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
@@ -289,13 +298,14 @@
       "source": [
         "## Create the configuration and train a forecaster <a id=\"train\"></a>\n",
         "First generate the configuration, in which we:\n",
-        "* Set metadata columns: target, time column and grain column names.\n",
+        "* Set metadata columns: target, time column and time-series id column names.\n",
         "* Validate our data using cross validation with rolling window method.\n",
         "* Set normalized root mean squared error as a metric to select the best model.\n",
         "* Set early termination to True, so the iterations through the models will stop when no improvements in accuracy score will be made.\n",
         "* Set limitations on the length of experiment run to 15 minutes.\n",
         "* Finally, we set the task to be forecasting.\n",
-        "* We apply the lag lead operator to the target value i.e. we use the previous values as a predictor for the future ones."
+        "* We apply the lag lead operator to the target value i.e. we use the previous values as a predictor for the future ones.\n",
+        "* [Optional] Forecast frequency parameter (freq) represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
       ]
     },
     {
@@ -304,21 +314,23 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
         "lags = [1,2,3]\n",
-        "max_horizon = n_test_periods\n",
-        "time_series_settings = {    \n",
-        "    'time_column_name': TIME_COLUMN_NAME,\n",
-        "    'grain_column_names': [ GRAIN_COLUMN_NAME ],\n",
-        "    'max_horizon': max_horizon,\n",
-        "    'target_lags': lags\n",
-        "}"
+        "forecast_horizon = n_test_periods\n",
+        "forecasting_parameters = ForecastingParameters(\n",
+        "    time_column_name=TIME_COLUMN_NAME,\n",
+        "    forecast_horizon=forecast_horizon,\n",
+        "    time_series_id_column_names=[ TIME_SERIES_ID_COLUMN_NAME ],\n",
+        "    target_lags=lags,\n",
+        "    freq='H' # Set the forecast frequency to be hourly\n",
+        ")"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Run the model selection and training process."
+        "Run the model selection and training process.  Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
       ]
     },
     {
@@ -335,7 +347,7 @@
         "automl_config = AutoMLConfig(task='forecasting',\n",
         "                             debug_log='automl_forecasting_function.log',\n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             experiment_timeout_minutes=15,\n",
+        "                             experiment_timeout_hours=0.25,\n",
         "                             enable_early_stopping=True,\n",
         "                             training_data=train_data,\n",
         "                             compute_target=compute_target,\n",
@@ -344,11 +356,26 @@
         "                             max_concurrent_iterations=4,\n",
         "                             max_cores_per_iteration=-1,\n",
         "                             label_column_name=target_label,\n",
-        "                             **time_series_settings)\n",
-        "\n",
-        "remote_run = experiment.submit(automl_config, show_output=False)\n",
-        "remote_run.wait_for_completion()\n",
+        "                             forecasting_parameters=forecasting_parameters)\n",
         "\n",
+        "remote_run = experiment.submit(automl_config, show_output=False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run.wait_for_completion()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
         "# Retrieve the best model to use it further.\n",
         "_, fitted_model = remote_run.get_output()"
       ]
@@ -377,9 +404,7 @@
         "\n",
         "![Forecasting after training](forecast_function_at_train.png)\n",
         "\n",
-        "The `X_test` and `y_query` below, taken together, form the **forecast request**. The two are interpreted as aligned - `y_query` could actally be a column in `X_test`. `NaN`s in `y_query` are the question marks. These will be filled with the forecasts.\n",
-        "\n",
-        "When the forecast period immediately follows the training period, the models retain the last few points of data. You can simply fill `y_query` filled with question marks - the model has the data for the lookback already.\n"
+        "We use `X_test` as a **forecast request** to generate the predictions."
       ]
     },
     {
@@ -408,8 +433,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "y_query = np.repeat(np.NaN, X_test.shape[0])\n",
-        "y_pred_no_gap, xy_nogap =  fitted_model.forecast(X_test, y_query)\n",
+        "y_pred_no_gap, xy_nogap =  fitted_model.forecast(X_test)\n",
         "\n",
         "# xy_nogap contains the predictions in the _automl_target_col column.\n",
         "# Those same numbers are output in y_pred_no_gap\n",
@@ -437,7 +461,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "quantiles =  fitted_model.forecast_quantiles(X_test, y_query)\n",
+        "quantiles =  fitted_model.forecast_quantiles(X_test)\n",
         "quantiles"
       ]
     },
@@ -448,7 +472,7 @@
         "#### Distribution forecasts\n",
         "\n",
         "Often the figure of interest is not just the point prediction, but the prediction at some quantile of the distribution. \n",
-        "This arises when the forecast is used to control some kind of inventory, for example of grocery items of virtual machines for a cloud service. In such case, the control point is usually something like \"we want the item to be in stock and not run out 99% of the time\". This is called a \"service level\". Here is how you get quantile forecasts."
+        "This arises when the forecast is used to control some kind of inventory, for example of grocery items or virtual machines for a cloud service. In such case, the control point is usually something like \"we want the item to be in stock and not run out 99% of the time\". This is called a \"service level\". Here is how you get quantile forecasts."
       ]
     },
     {
@@ -460,10 +484,10 @@
         "# specify which quantiles you would like \n",
         "fitted_model.quantiles = [0.01, 0.5, 0.95]\n",
         "# use forecast_quantiles function, not the forecast() one\n",
-        "y_pred_quantiles =  fitted_model.forecast_quantiles(X_test, y_query)\n",
+        "y_pred_quantiles =  fitted_model.forecast_quantiles(X_test)\n",
         "\n",
-        "# it all nicely aligns column-wise\n",
-        "pd.concat([X_test.reset_index(), pd.DataFrame({'query' : y_query}), y_pred_quantiles], axis=1)"
+        "# quantile forecasts returned in a Dataframe along with the time and time series id columns \n",
+        "y_pred_quantiles"
       ]
     },
     {
@@ -472,7 +496,7 @@
       "source": [
         "#### Destination-date forecast: \"just do something\"\n",
         "\n",
-        "In some scenarios, the X_test is not known. The forecast is likely to be weak, becaus it is missing contemporaneous predictors, which we will need to impute. If you still wish to predict forward under the assumption that the last known values will be carried forward, you can forecast out to \"destination date\". The destination date still needs to fit within the maximum horizon from training."
+        "In some scenarios, the X_test is not known. The forecast is likely to be weak, because it is missing contemporaneous predictors, which we will need to impute. If you still wish to predict forward under the assumption that the last known values will be carried forward, you can forecast out to \"destination date\". The destination date still needs to fit within the forecast horizon from training."
       ]
     },
     {
@@ -499,7 +523,7 @@
         "\n",
         "![Forecasting after training](forecast_function_away_from_train.png)\n",
         "\n",
-        "The notion of forecast origin comes into play: the forecast origin is **the last period for which we have seen the target value**. This applies per grain, so each grain can have a different forecast origin. \n",
+        "The notion of forecast origin comes into play: the forecast origin is **the last period for which we have seen the target value**. This applies per time-series, so each time-series can have a different forecast origin. \n",
         "\n",
         "The part of data before the forecast origin is the **prediction context**. To provide the context values the model needs when it looks back, we pass definite values in `y_test` (aligned with corresponding times in `X_test`)."
       ]
@@ -516,13 +540,13 @@
         "                                      test_len=4,\n",
         "                                      time_column_name=TIME_COLUMN_NAME,\n",
         "                                      target_column_name=TARGET_COLUMN_NAME,\n",
-        "                                      grain_column_name=GRAIN_COLUMN_NAME,\n",
-        "                                      grains=2)\n",
+        "                                      time_series_id_column_name=TIME_SERIES_ID_COLUMN_NAME,\n",
+        "                                      time_series_number=2)\n",
         "\n",
         "# end of the data we trained on\n",
-        "print(X_train.groupby(GRAIN_COLUMN_NAME)[TIME_COLUMN_NAME].max())\n",
+        "print(X_train.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].max())\n",
         "# start of the data we want to predict on\n",
-        "print(X_away.groupby(GRAIN_COLUMN_NAME)[TIME_COLUMN_NAME].min())"
+        "print(X_away.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].min())"
       ]
     },
     {
@@ -539,9 +563,7 @@
       "outputs": [],
       "source": [
         "try: \n",
-        "    y_query = y_away.copy()\n",
-        "    y_query.fill(np.NaN)\n",
-        "    y_pred_away, xy_away = fitted_model.forecast(X_away, y_query)\n",
+        "    y_pred_away, xy_away = fitted_model.forecast(X_away)\n",
         "    xy_away\n",
         "except Exception as e:\n",
         "    print(e)"
@@ -551,7 +573,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "How should we read that eror message? The forecast origin is at the last time themodel saw an actual values of `y` (the target). That was at the end of the training data! Because the model received all `NaN` (and not an actual target value), it is attempting to forecast from the end of training data. But the requested forecast periods are past the maximum horizon. We need to provide a define `y` value to establish the forecast origin.\n",
+        "How should we read that eror message? The forecast origin is at the last time the model saw an actual value of `y` (the target). That was at the end of the training data! The model is attempting to forecast from the end of training data. But the requested forecast periods are past the forecast horizon. We need to provide a define `y` value to establish the forecast origin.\n",
         "\n",
         "We will use this helper function to take the required amount of context from the data preceding the testing data. It's definition is intentionally simplified to keep the idea in the clear."
       ]
@@ -566,7 +588,7 @@
         "\n",
         "    \"\"\"\n",
         "    This function will take the full dataset, and create the query\n",
-        "    to predict all values of the grain from the `forecast_origin`\n",
+        "    to predict all values of the time series from the `forecast_origin`\n",
         "    forward for the next `horizon` horizons. Context from previous\n",
         "    `lookback` periods will be included.\n",
         "\n",
@@ -636,8 +658,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "print(X_context.groupby(GRAIN_COLUMN_NAME)[TIME_COLUMN_NAME].agg(['min','max','count']))\n",
-        "print(X_away.groupby(GRAIN_COLUMN_NAME)[TIME_COLUMN_NAME].agg(['min','max','count']))\n",
+        "print(X_context.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].agg(['min','max','count']))\n",
+        "print(X_away.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].agg(['min','max','count']))\n",
         "X_context.tail(5)"
       ]
     },
@@ -667,7 +689,7 @@
         "n_lookback_periods = max(lags)\n",
         "lookback = pd.DateOffset(hours=n_lookback_periods)\n",
         "\n",
-        "horizon = pd.DateOffset(hours=max_horizon)\n",
+        "horizon = pd.DateOffset(hours=forecast_horizon)\n",
         "\n",
         "# now make the forecast query from context (refer to figure)\n",
         "X_pred, y_pred = make_forecasting_query(fulldata, TIME_COLUMN_NAME, TARGET_COLUMN_NAME,\n",
@@ -683,7 +705,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Note that the forecast origin is at 17:00 for both grains, and periods from 18:00 are to be forecast."
+        "Note that the forecast origin is at 17:00 for both time-series, and periods from 18:00 are to be forecast."
       ]
     },
     {
@@ -698,20 +720,105 @@
         "# show the forecast aligned\n",
         "X_show = xy_away.reset_index()\n",
         "# without the generated features\n",
-        "X_show[['date', 'grain', 'ext_predictor', '_automl_target_col']]\n",
+        "X_show[['date', 'time_series_id', 'ext_predictor', '_automl_target_col']]\n",
         "# prediction is in _automl_target_col"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Forecasting farther than the forecast horizon <a id=\"recursive forecasting\"></a>\n",
+        "When the forecast destination, or the latest date in the prediction data frame, is farther into the future than the specified forecast horizon, the `forecast()` function will still make point predictions out to the later date using a recursive operation mode. Internally, the method recursively applies the regular forecaster to generate context so that we can forecast further into the future. \n",
+        "\n",
+        "To illustrate the use-case and operation of recursive forecasting, we'll consider an example with a single time-series where the forecasting period directly follows the training period and is twice as long as the forecasting horizon given at training time.\n",
+        "\n",
+        "![Recursive_forecast_overview](recursive_forecast_overview_small.png)\n",
+        "\n",
+        "Internally, we apply the forecaster in an iterative manner and finish the forecast task in two interations. In the first iteration, we apply the forecaster and get the prediction for the first forecast-horizon periods (y_pred1). In the second iteraction, y_pred1 is used as the context to produce the prediction for the next forecast-horizon periods (y_pred2). The combination of (y_pred1 and y_pred2) gives the results for the total forecast periods. \n",
+        "\n",
+        "A caveat: forecast accuracy will likely be worse the farther we predict into the future since errors are compounded with recursive application of the forecaster.\n",
+        "\n",
+        "![Recursive_forecast_iter1](recursive_forecast_iter1.png)\n",
+        "![Recursive_forecast_iter2](recursive_forecast_iter2.png)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# generate the same kind of test data we trained on, but with a single time-series and test period twice as long\n",
+        "# as the forecast_horizon.\n",
+        "_, _, X_test_long, y_test_long = get_timeseries(train_len=n_train_periods,\n",
+        "                                                  test_len=forecast_horizon*2,\n",
+        "                                                  time_column_name=TIME_COLUMN_NAME,\n",
+        "                                                  target_column_name=TARGET_COLUMN_NAME,\n",
+        "                                                  time_series_id_column_name=TIME_SERIES_ID_COLUMN_NAME,\n",
+        "                                                  time_series_number=1)\n",
+        "\n",
+        "print(X_test_long.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].min())\n",
+        "print(X_test_long.groupby(TIME_SERIES_ID_COLUMN_NAME)[TIME_COLUMN_NAME].max())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# forecast() function will invoke the recursive forecast method internally.\n",
+        "y_pred_long, X_trans_long = fitted_model.forecast(X_test_long)\n",
+        "y_pred_long"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# What forecast() function does in this case is equivalent to iterating it twice over the test set as the following. \n",
+        "y_pred1, _ = fitted_model.forecast(X_test_long[:forecast_horizon])\n",
+        "y_pred_all, _ = fitted_model.forecast(X_test_long, np.concatenate((y_pred1, np.full(forecast_horizon, np.nan))))\n",
+        "np.array_equal(y_pred_all, y_pred_long)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Confidence interval and distributional forecasts\n",
+        "AutoML cannot currently estimate forecast errors beyond the forecast horizon set during training, so the `forecast_quantiles()` function will return missing values for quantiles not equal to 0.5 beyond the forecast horizon. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "fitted_model.forecast_quantiles(X_test_long)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Similarly with the simple senarios illustrated above, forecasting farther than the forecast horizon in other senarios like 'multiple time-series', 'Destination-date forecast', and 'forecast away from the training data' are also automatically handled by the `forecast()` function. "
+      ]
     }
   ],
   "metadata": {
     "authors": [
       {
-        "name": "erwright, nirovins"
+        "name": "jialiu"
       }
     ],
     "category": "tutorial",
     "compute": [
-      "remote"
+      "Remote"
     ],
     "datasets": [
       "None"
@@ -740,13 +847,13 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.7"
+      "version": "3.6.8"
     },
     "tags": [
       "Forecasting",
       "Confidence Intervals"
     ],
-    "task": "forecasting"
+    "task": "Forecasting"
   },
   "nbformat": 4,
   "nbformat_minor": 2

how-to-use-azureml/automated-machine-learning/forecasting-forecast-function/auto-ml-forecasting-function.yml

@@ -0,0 +1,4 @@
+name: auto-ml-forecasting-function
+dependencies:
+- pip:
+  - azureml-sdk

how-to-use-azureml/automated-machine-learning/forecasting-grouping/auto-ml-forecasting-grouping.ipynb

@@ -1,551 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-grouping/auto-ml-forecasting-grouping.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "\n",
-        "_**Forecasting with grouping using Pipelines**_\n",
-        "\n",
-        "## Contents\n",
-        "\n",
-        "1. [Introduction](#Introduction)\n",
-        "2. [Setup](#Setup)\n",
-        "3. [Data](#Data)\n",
-        "4. [Compute](#Compute)\n",
-        "4. [AutoMLConfig](#AutoMLConfig)\n",
-        "5. [Pipeline](#Pipeline)\n",
-        "5. [Train](#Train)\n",
-        "6. [Test](#Test)\n",
-        "\n",
-        "\n",
-        "## Introduction\n",
-        "In this example we use Automated ML and Pipelines to train, select, and operationalize forecasting models for multiple time-series.\n",
-        "\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) first if you haven't already to establish your connection to the AzureML Workspace.\n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "\n",
-        "* Create an Experiment in an existing Workspace.\n",
-        "* Configure AutoML using AutoMLConfig.\n",
-        "* Use our helper script to generate pipeline steps to split, train, and deploy the models.\n",
-        "* Explore the results.\n",
-        "* Test the models.\n",
-        "\n",
-        "It is advised you ensure your cluster has at least one node per group.\n",
-        "\n",
-        "An Enterprise workspace is required for this notebook. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page.](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade)\n",
-        "\n",
-        "## Setup\n",
-        "As part of the setup you have already created an Azure ML `Workspace` object. For Automated ML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "import logging\n",
-        "import warnings\n",
-        "\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "\n",
-        "import azureml.core\n",
-        "\n",
-        "from azureml.core.workspace import Workspace\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Accessing the Azure ML workspace requires authentication with Azure.\n",
-        "\n",
-        "The default authentication is interactive authentication using the default tenant. Executing the ws = Workspace.from_config() line in the cell below will prompt for authentication the first time that it is run.\n",
-        "\n",
-        "If you have multiple Azure tenants, you can specify the tenant by replacing the ws = Workspace.from_config() line in the cell below with the following:\n",
-        "```\n",
-        "from azureml.core.authentication import InteractiveLoginAuthentication\n",
-        "auth = InteractiveLoginAuthentication(tenant_id = 'mytenantid')\n",
-        "ws = Workspace.from_config(auth = auth)\n",
-        "```\n",
-        "If you need to run in an environment where interactive login is not possible, you can use Service Principal authentication by replacing the ws = Workspace.from_config() line in the cell below with the following:\n",
-        "```\n",
-        "from azureml.core.authentication import ServicePrincipalAuthentication\n",
-        "auth = auth = ServicePrincipalAuthentication('mytenantid', 'myappid', 'mypassword')\n",
-        "ws = Workspace.from_config(auth = auth)\n",
-        "```\n",
-        "For more details, see aka.ms/aml-notebook-auth"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "ds = ws.get_default_datastore()\n",
-        "\n",
-        "# choose a name for the run history container in the workspace\n",
-        "experiment_name = 'automl-grouping-oj'\n",
-        "# project folder\n",
-        "project_folder = './sample_projects/{}'.format(experiment_name)\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
-        "output['Run History Name'] = experiment_name\n",
-        "pd.set_option('display.max_colwidth', -1)\n",
-        "outputDf = pd.DataFrame(data = output, index = [''])\n",
-        "outputDf.T"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "Upload data to your default datastore and then load it as a `TabularDataset`"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.dataset import Dataset"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# upload data to your default datastore\n",
-        "ds = ws.get_default_datastore()\n",
-        "ds.upload(src_dir='./data', target_path='groupdata', overwrite=True, show_progress=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# load data from your datastore\n",
-        "data = Dataset.Tabular.from_delimited_files(path=ds.path('groupdata/dominicks_OJ_2_5_8_train.csv'))\n",
-        "data_test = Dataset.Tabular.from_delimited_files(path=ds.path('groupdata/dominicks_OJ_2_5_8_test.csv'))\n",
-        "\n",
-        "data.take(5).to_pandas_dataframe()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Compute \n",
-        "\n",
-        "#### Create or Attach existing AmlCompute\n",
-        "\n",
-        "You will need to create a compute target for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
-        "#### Creation of AmlCompute takes approximately 5 minutes. \n",
-        "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import AmlCompute\n",
-        "from azureml.core.compute import ComputeTarget\n",
-        "\n",
-        "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpu-cluster-11\"\n",
-        "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "    \n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
-        "                                                                max_nodes = 6)\n",
-        "\n",
-        "    # Create the cluster.\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "    \n",
-        "print('Checking cluster status...')\n",
-        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
-        "    \n",
-        "# For a more detailed view of current AmlCompute status, use get_status()."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## AutoMLConfig\n",
-        "#### Create a base AutoMLConfig\n",
-        "This configuration will be used for all the groups in the pipeline."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "target_column = 'Quantity'\n",
-        "time_column_name = 'WeekStarting'\n",
-        "grain_column_names = ['Brand']\n",
-        "group_column_names = ['Store']\n",
-        "max_horizon = 20"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\" : 5,\n",
-        "    \"experiment_timeout_minutes\" : 15,\n",
-        "    \"primary_metric\" : 'normalized_mean_absolute_error',\n",
-        "    \"time_column_name\": time_column_name,\n",
-        "    \"grain_column_names\": grain_column_names,\n",
-        "    \"max_horizon\": max_horizon,\n",
-        "    \"drop_column_names\": ['logQuantity'],\n",
-        "    \"max_concurrent_iterations\": 2,\n",
-        "    \"max_cores_per_iteration\": -1\n",
-        "}\n",
-        "base_configuration = AutoMLConfig(task = 'forecasting',\n",
-        "                             path = project_folder,\n",
-        "                             n_cross_validations=3,\n",
-        "                             **automl_settings\n",
-        "                            )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Pipeline\n",
-        "We've written a script to generate the individual pipeline steps used to create each automl step. Calling this script will return a list of PipelineSteps that will train multiple groups concurrently and then deploy these models.\n",
-        "\n",
-        "This step requires an Enterprise workspace to gain access to this feature. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page.](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade).\n",
-        "\n",
-        "### Call the method to build pipeline steps\n",
-        "\n",
-        "`build_pipeline_steps()` takes as input:\n",
-        "* **automlconfig**: This is the configuration used for every automl step\n",
-        "* **df**: This is the dataset to be used for training\n",
-        "* **target_column**: This is the target column of the dataset\n",
-        "* **compute_target**: The compute to be used for training\n",
-        "* **deploy**: The option on to deploy the models after training, if set to true an extra step will be added to deploy a webservice with all the models (default is `True`)\n",
-        "* **service_name**: The service name for the model query endpoint\n",
-        "* **time_column_name**: The time column of the data"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.webservice import Webservice\n",
-        "from azureml.exceptions import WebserviceException\n",
-        "\n",
-        "service_name = 'grouped-model'\n",
-        "try:\n",
-        "    # if you want to get existing service below is the command\n",
-        "    # since aci name needs to be unique in subscription deleting existing aci if any\n",
-        "    # we use aci_service_name to create azure aci\n",
-        "    service = Webservice(ws, name=service_name)\n",
-        "    if service:\n",
-        "        service.delete()\n",
-        "except WebserviceException as e:\n",
-        "    pass"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from build import build_pipeline_steps\n",
-        "\n",
-        "steps = build_pipeline_steps(\n",
-        "    base_configuration, \n",
-        "    data, \n",
-        "    target_column,\n",
-        "    compute_target, \n",
-        "    group_column_names=group_column_names, \n",
-        "    deploy=True, \n",
-        "    service_name=service_name, \n",
-        "    time_column_name=time_column_name\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "Use the list of steps generated from above to build the pipeline and submit it to your compute for remote training."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.pipeline.core import Pipeline\n",
-        "pipeline = Pipeline(\n",
-        "    description=\"A pipeline with one model per data group using Automated ML.\",\n",
-        "    workspace=ws,    \n",
-        "    steps=steps)\n",
-        "\n",
-        "pipeline_run = experiment.submit(pipeline)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "RunDetails(pipeline_run).show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "pipeline_run.wait_for_completion(show_output=False)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test\n",
-        "\n",
-        "Now we can use the holdout set to test our models and ensure our web-service is running as expected."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.webservice import AciWebservice\n",
-        "service = AciWebservice(ws, service_name)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_test = data_test.to_pandas_dataframe()\n",
-        "# Drop the column we are trying to predict (target column)\n",
-        "x_pred = X_test.drop(target_column, inplace=False, axis=1)\n",
-        "x_pred.head()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Get Predictions\n",
-        "test_sample = X_test.drop(target_column, inplace=False, axis=1).to_json()\n",
-        "predictions = service.run(input_data=test_sample)\n",
-        "print(predictions)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Convert predictions from JSON to DataFrame\n",
-        "pred_dict =json.loads(predictions)\n",
-        "X_pred = pd.read_json(pred_dict['predictions'])\n",
-        "X_pred.head()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Fix the index\n",
-        "PRED = 'pred_target'\n",
-        "X_pred[time_column_name] = pd.to_datetime(X_pred[time_column_name], unit='ms')\n",
-        "\n",
-        "X_pred.set_index([time_column_name] + grain_column_names, inplace=True, drop=True)\n",
-        "X_pred.rename({'_automl_target_col': PRED}, inplace=True, axis=1)\n",
-        "# Drop all but the target column and index\n",
-        "X_pred.drop(list(set(X_pred.columns.values).difference({PRED})), axis=1, inplace=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_test[time_column_name] = pd.to_datetime(X_test[time_column_name])\n",
-        "X_test.set_index([time_column_name] + grain_column_names, inplace=True, drop=True)\n",
-        "# Merge predictions with raw features\n",
-        "pred_test = X_test.merge(X_pred, left_index=True, right_index=True)\n",
-        "pred_test.head()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn.metrics import mean_absolute_error, mean_squared_error\n",
-        "def MAPE(actual, pred):\n",
-        "    \"\"\"\n",
-        "    Calculate mean absolute percentage error.\n",
-        "    Remove NA and values where actual is close to zero\n",
-        "    \"\"\"\n",
-        "    not_na = ~(np.isnan(actual) | np.isnan(pred))\n",
-        "    not_zero = ~np.isclose(actual, 0.0)\n",
-        "    actual_safe = actual[not_na & not_zero]\n",
-        "    pred_safe = pred[not_na & not_zero]\n",
-        "    APE = 100*np.abs((actual_safe - pred_safe)/actual_safe)\n",
-        "    return np.mean(APE)\n",
-        "\n",
-        "def get_metrics(actuals, preds):\n",
-        "    return pd.Series(\n",
-        "    {\n",
-        "        \"RMSE\": np.sqrt(mean_squared_error(actuals, preds)),\n",
-        "        \"NormRMSE\": np.sqrt(mean_squared_error(actuals, preds))/np.abs(actuals.max()-actuals.min()),\n",
-        "        \"MAE\": mean_absolute_error(actuals, preds),\n",
-        "        \"MAPE\": MAPE(actuals, preds)},\n",
-        "    )"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "get_metrics(pred_test[PRED].values, pred_test[target_column].values)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "alyerman"
-      }
-    ],
-    "category": "other",
-    "compute": [
-      "AML Compute"
-    ],
-    "datasets": [
-      "Orange Juice Sales"
-    ],
-    "deployment": [
-      "Azure Container Instance"
-    ],
-    "exclude_from_index": false,
-    "framework": [
-      "Scikit-learn",
-      "Pytorch"
-    ],
-    "friendly_name": "Automated ML Grouping with Pipeline.",
-    "index_order": 10,
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "python",
-      "name": "python36"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.6.6"
-    },
-    "tags": [
-      "AutomatedML"
-    ],
-    "task": "Use AzureML Pipeline to trigger multiple Automated ML runs."
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/forecasting-grouping/auto-ml-forecasting-grouping.yml

@@ -1,10 +0,0 @@
-name: auto-ml-forecasting-grouping
-dependencies:
-- pip:
-  - azureml-sdk
-  - azureml-train-automl
-  - azureml-pipeline
-  - azureml-widgets
-  - pandas_ml
-  - statsmodels
-  - matplotlib

how-to-use-azureml/automated-machine-learning/forecasting-grouping/build.py

@@ -1,135 +0,0 @@
-from typing import List, Dict
-import copy
-import json
-import pandas as pd
-import re
-
-from azureml.core import RunConfiguration
-from azureml.core.compute import ComputeTarget
-from azureml.core.conda_dependencies import CondaDependencies
-from azureml.core.dataset import Dataset
-from azureml.pipeline.core import PipelineData, PipelineParameter, TrainingOutput, StepSequence
-from azureml.pipeline.steps import PythonScriptStep
-from azureml.train.automl import AutoMLConfig
-from azureml.train.automl import AutoMLStep
-
-
-def _get_groups(data: Dataset, group_column_names: List[str]) -> pd.DataFrame:
-    return data._dataflow.distinct(columns=group_column_names)\
-        .keep_columns(columns=group_column_names).to_pandas_dataframe()
-
-
-def _get_configs(automlconfig: AutoMLConfig,
-                 data: Dataset,
-                 target_column: str,
-                 compute_target: ComputeTarget,
-                 group_column_names: List[str]) -> Dict[str, AutoMLConfig]:
-    # remove invalid characters regex
-    valid_chars = re.compile('[^a-zA-Z0-9-]')
-    groups = _get_groups(data, group_column_names)
-    configs = {}
-    for i, group in groups.iterrows():
-        single = data
-        group_name = "#####".join(str(x) for x in group.values)
-        group_name = valid_chars.sub('', group_name)
-        for key in group.index:
-            single = data._dataflow.filter(data._dataflow[key] == group[key])
-        group_conf = copy.deepcopy(automlconfig)
-        group_conf.user_settings['training_data'] = single
-        group_conf.user_settings['label_column_name'] = target_column
-        group_conf.user_settings['compute_target'] = compute_target
-        configs[group_name] = group_conf
-    return configs
-
-
-def build_pipeline_steps(automlconfig: AutoMLConfig,
-                         data: Dataset,
-                         target_column: str,
-                         compute_target: ComputeTarget,
-                         group_column_names: list,
-                         time_column_name: str,
-                         deploy: bool,
-                         service_name: str = 'grouping-demo') -> StepSequence:
-    steps = []
-
-    metrics_output_name = 'metrics_{}'
-    best_model_output_name = 'best_model_{}'
-    count = 0
-    model_names = []
-
-    # get all automl configs by group
-    configs = _get_configs(automlconfig, data, target_column, compute_target, group_column_names)
-
-    # build a runconfig for register model
-    register_config = RunConfiguration()
-    cd = CondaDependencies()
-    cd.add_pip_package('azureml-pipeline')
-    register_config.environment.python.conda_dependencies = cd
-
-    # create each automl step end-to-end (train, register)
-    for group_name, conf in configs.items():
-        # create automl metrics output
-        metirics_data = PipelineData(
-            name='metrics_data_{}'.format(group_name),
-            pipeline_output_name=metrics_output_name.format(group_name),
-            training_output=TrainingOutput(type='Metrics'))
-        # create automl model output
-        model_data = PipelineData(
-            name='model_data_{}'.format(group_name),
-            pipeline_output_name=best_model_output_name.format(group_name),
-            training_output=TrainingOutput(type='Model', metric=conf.user_settings['primary_metric']))
-
-        automl_step = AutoMLStep(
-            name='automl_{}'.format(group_name),
-            automl_config=conf,
-            outputs=[metirics_data, model_data],
-            allow_reuse=True)
-        steps.append(automl_step)
-
-        # pass the group name as a parameter to the register step ->
-        # this will become the name of the model for this group.
-        group_name_param = PipelineParameter("group_name_{}".format(count), default_value=group_name)
-        count += 1
-
-        reg_model_step = PythonScriptStep(
-            'register.py',
-            name='register_{}'.format(group_name),
-            arguments=["--model_name", group_name_param, "--model_path", model_data],
-            inputs=[model_data],
-            compute_target=compute_target,
-            runconfig=register_config,
-            source_directory="register",
-            allow_reuse=True
-        )
-        steps.append(reg_model_step)
-        model_names.append(group_name)
-
-    final_steps = steps
-    if deploy:
-        # add deployment step
-        pp_group_column_names = PipelineParameter(
-            "group_column_names",
-            default_value="#####".join(list(reversed(group_column_names))))
-
-        pp_model_names = PipelineParameter(
-            "model_names",
-            default_value=json.dumps(model_names))
-
-        pp_service_name = PipelineParameter(
-            "service_name",
-            default_value=service_name)
-
-        deployment_step = PythonScriptStep(
-            'deploy.py',
-            name='service_deploy',
-            arguments=["--group_column_names", pp_group_column_names,
-                       "--model_names", pp_model_names,
-                       "--service_name", pp_service_name,
-                       "--time_column_name", time_column_name],
-            compute_target=compute_target,
-            runconfig=RunConfiguration(),
-            source_directory="deploy"
-        )
-        final_steps = StepSequence(steps=[steps, deployment_step])
-
-    return final_steps

how-to-use-azureml/automated-machine-learning/forecasting-grouping/data/dominicks_OJ_2_5_8_test.csv

@@ -1,61 +0,0 @@
-WeekStarting,Store,Brand,Quantity,logQuantity,Advert,Price,Age60,COLLEGE,INCOME,Hincome150,Large HH,Minorities,WorkingWoman,SSTRDIST,SSTRVOL,CPDIST5,CPWVOL5
-1992-08-20,2,minute.maid,23488,10.06424493,1,1.94,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-20,2,tropicana,13376,9.501217335,1,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-27,2,tropicana,8128,9.00307017,0,2.75,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-27,2,minute.maid,19008,9.852615222,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-27,2,dominicks,9024,9.107642974,0,1.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-03,2,tropicana,19456,9.875910785,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-03,2,minute.maid,11584,9.357380115,0,1.81,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-03,2,dominicks,2048,7.624618986000001,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-10,2,tropicana,10048,9.215128888999999,0,2.64,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-10,2,minute.maid,26752,10.19436452,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-10,2,dominicks,1984,7.592870287999999,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-17,2,tropicana,6336,8.754002933999999,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-17,2,minute.maid,3904,8.269756948,0,2.83,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-17,2,dominicks,4160,8.333270353,0,1.77,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-24,2,tropicana,16192,9.692272572,1,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-24,2,minute.maid,3712,8.219326094,0,2.67,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-09-24,2,dominicks,35264,10.47061789,0,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-10-01,2,dominicks,8640,9.064157862,0,1.82,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-10-01,2,minute.maid,41216,10.62658181,1,2.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-10-01,2,tropicana,5824,8.66974259,0,2.97,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-20,5,tropicana,17728,9.78290059,1,2.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-20,5,minute.maid,27072,10.20625526,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-27,5,tropicana,9600,9.169518378,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-27,5,minute.maid,3840,8.253227646000001,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-27,5,dominicks,1856,7.526178913,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-03,5,tropicana,25664,10.15284451,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-03,5,minute.maid,6144,8.723231275,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-03,5,dominicks,3712,8.219326094,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-10,5,tropicana,9984,9.208739091,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-10,5,dominicks,2688,7.896552702,0,1.85,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-10,5,minute.maid,36416,10.50276352,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-17,5,tropicana,8576,9.056722882999999,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-17,5,minute.maid,5440,8.60153434,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-17,5,dominicks,6464,8.774003599999999,0,1.85,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-24,5,tropicana,13184,9.486759252,1,2.78,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-24,5,dominicks,40896,10.61878754,0,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-09-24,5,minute.maid,7680,8.946374826,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-10-01,5,dominicks,6144,8.723231275,0,1.85,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-10-01,5,minute.maid,50304,10.82583988,1,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-10-01,5,tropicana,7488,8.921057017999999,0,2.78,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-20,8,minute.maid,55552,10.9250748,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-20,8,tropicana,8576,9.056722882999999,1,2.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-27,8,tropicana,8000,8.987196821,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-27,8,minute.maid,18688,9.835636886,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-27,8,dominicks,19200,9.862665558,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-03,8,tropicana,21760,9.987828701,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-03,8,minute.maid,14656,9.592605087,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-03,8,dominicks,12800,9.45720045,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-10,8,tropicana,12800,9.45720045,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-10,8,minute.maid,30144,10.31374118,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-10,8,dominicks,15296,9.635346635,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-17,8,tropicana,10112,9.221478116,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-17,8,minute.maid,6208,8.733594062,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-17,8,dominicks,20992,9.951896692,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-24,8,tropicana,10304,9.240287448,1,2.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-24,8,minute.maid,7104,8.868413285,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-09-24,8,dominicks,73856,11.20987253,0,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-10-01,8,minute.maid,65856,11.09522582,1,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-10-01,8,dominicks,16192,9.692272572,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-10-01,8,tropicana,6400,8.764053269,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947

how-to-use-azureml/automated-machine-learning/forecasting-grouping/data/dominicks_OJ_2_5_8_train.csv

@@ -1,973 +0,0 @@
-WeekStarting,Store,Brand,Quantity,logQuantity,Advert,Price,Age60,COLLEGE,INCOME,Hincome150,Large HH,Minorities,WorkingWoman,SSTRDIST,SSTRVOL,CPDIST5,CPWVOL5
-1990-06-14,2,dominicks,10560,9.264828557000001,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-06-14,2,minute.maid,4480,8.407378325,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-06-14,2,tropicana,8256,9.018695487999999,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-07-26,2,dominicks,8000,8.987196821,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-07-26,2,minute.maid,4672,8.449342525,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-07-26,2,tropicana,6144,8.723231275,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-02,2,tropicana,3840,8.253227646000001,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-02,2,minute.maid,20160,9.911455722000001,1,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-02,2,dominicks,6848,8.831711918,1,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-09,2,dominicks,2880,7.965545572999999,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-09,2,minute.maid,2688,7.896552702,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-09,2,tropicana,8000,8.987196821,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-23,2,dominicks,1600,7.377758908,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-23,2,minute.maid,3008,8.009030685,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-23,2,tropicana,8896,9.093357017,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-30,2,tropicana,7168,8.877381955,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-30,2,minute.maid,4672,8.449342525,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-08-30,2,dominicks,25344,10.140297300000002,1,1.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-06,2,dominicks,10752,9.282847063,0,1.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-06,2,minute.maid,2752,7.920083199,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-06,2,tropicana,10880,9.29468152,0,3.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-13,2,minute.maid,26176,10.17259824,1,2.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-13,2,dominicks,6656,8.803273982999999,0,1.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-13,2,tropicana,7744,8.954673629,0,3.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-20,2,dominicks,6592,8.793612072,0,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-20,2,minute.maid,3712,8.219326094,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-09-20,2,tropicana,8512,9.049232212,0,3.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-11,2,tropicana,5504,8.61323038,0,3.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-11,2,minute.maid,30656,10.33058368,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-11,2,dominicks,1728,7.454719948999999,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-18,2,tropicana,5888,8.68067166,0,3.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-18,2,minute.maid,3840,8.253227646000001,0,2.98,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-18,2,dominicks,33792,10.42797937,1,1.24,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-25,2,tropicana,8384,9.034080407000001,0,3.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-25,2,minute.maid,2816,7.943072717000001,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-10-25,2,dominicks,1920,7.560080465,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-01,2,tropicana,5952,8.691482577,0,3.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-01,2,minute.maid,23104,10.04776104,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-01,2,dominicks,8960,9.100525506,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-08,2,dominicks,11392,9.340666634,0,1.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-08,2,tropicana,6848,8.831711918,0,3.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-08,2,minute.maid,3392,8.129174997,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-15,2,tropicana,9216,9.128696383,0,3.87,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-15,2,minute.maid,26304,10.1774763,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-15,2,dominicks,28416,10.25470765,0,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-22,2,dominicks,17152,9.749870064,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-22,2,tropicana,12160,9.405907156,0,2.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-22,2,minute.maid,6336,8.754002933999999,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-29,2,tropicana,12672,9.447150114,0,2.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-29,2,minute.maid,9920,9.2023082,0,3.17,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-11-29,2,dominicks,26560,10.1871616,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-06,2,dominicks,6336,8.754002933999999,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-06,2,minute.maid,25280,10.13776885,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-06,2,tropicana,6528,8.783855897,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-13,2,dominicks,26368,10.17990643,1,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-13,2,tropicana,6144,8.723231275,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-13,2,minute.maid,14848,9.605620455,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-20,2,tropicana,21120,9.957975738,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-20,2,minute.maid,12288,9.416378455,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-20,2,dominicks,896,6.797940412999999,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-27,2,tropicana,12416,9.426741242,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-27,2,minute.maid,6272,8.743850562,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-12-27,2,dominicks,1472,7.294377299,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-03,2,tropicana,9472,9.156095357,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-03,2,minute.maid,9152,9.121727714,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-03,2,dominicks,1344,7.2034055210000005,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-10,2,tropicana,17920,9.793672686,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-10,2,minute.maid,4160,8.333270353,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-10,2,dominicks,111680,11.62339292,1,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-17,2,tropicana,9408,9.14931567,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-17,2,minute.maid,10176,9.227787286,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-17,2,dominicks,1856,7.526178913,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-24,2,tropicana,6272,8.743850562,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-24,2,minute.maid,29056,10.27698028,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-24,2,dominicks,5568,8.624791202,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-31,2,tropicana,6912,8.841014311,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-31,2,minute.maid,7104,8.868413285,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-01-31,2,dominicks,32064,10.37548918,1,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-07,2,tropicana,16768,9.727227587,0,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-07,2,dominicks,4352,8.378390789,0,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-07,2,minute.maid,7488,8.921057017999999,0,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-14,2,dominicks,704,6.556778356000001,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-14,2,minute.maid,4224,8.348537825,0,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-14,2,tropicana,6272,8.743850562,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-21,2,tropicana,7936,8.979164649,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-21,2,minute.maid,8960,9.100525506,0,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-21,2,dominicks,13760,9.529521112000001,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-28,2,tropicana,6144,8.723231275,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-28,2,minute.maid,22464,10.01966931,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-02-28,2,dominicks,43328,10.67655436,1,1.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-07,2,tropicana,7936,8.979164649,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-07,2,minute.maid,3840,8.253227646000001,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-07,2,dominicks,57600,10.96127785,1,1.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-14,2,tropicana,7808,8.962904128,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-14,2,minute.maid,12992,9.472089062,0,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-14,2,dominicks,704,6.556778356000001,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-21,2,tropicana,6080,8.712759975,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-21,2,minute.maid,70144,11.15830555,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-21,2,dominicks,6016,8.702177866,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-28,2,tropicana,42176,10.64960662,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-28,2,dominicks,10368,9.246479419,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-03-28,2,minute.maid,21248,9.964018052,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-04,2,dominicks,12608,9.442086812000001,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-04,2,minute.maid,5696,8.647519453,1,2.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-04,2,tropicana,4928,8.502688505,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-11,2,tropicana,29504,10.29228113,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-11,2,minute.maid,7680,8.946374826,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-11,2,dominicks,6336,8.754002933999999,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-18,2,tropicana,9984,9.208739091,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-18,2,minute.maid,6336,8.754002933999999,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-18,2,dominicks,140736,11.85464107,1,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-25,2,tropicana,35200,10.46880136,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-25,2,dominicks,960,6.866933285,1,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-04-25,2,minute.maid,8576,9.056722882999999,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-02,2,dominicks,1216,7.103322062999999,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-02,2,minute.maid,15104,9.622714887999999,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-02,2,tropicana,23936,10.08313888,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-09,2,tropicana,7104,8.868413285,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-09,2,minute.maid,76480,11.24478455,1,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-09,2,dominicks,1664,7.416979621,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-16,2,dominicks,4992,8.51559191,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-16,2,minute.maid,5056,8.528330936,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-16,2,tropicana,24512,10.10691807,1,2.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-23,2,tropicana,6336,8.754002933999999,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-23,2,minute.maid,4736,8.462948177000001,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-23,2,dominicks,27968,10.23881628,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-30,2,dominicks,12160,9.405907156,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-30,2,minute.maid,4480,8.407378325,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-05-30,2,tropicana,6080,8.712759975,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-06,2,tropicana,33536,10.42037477,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-06,2,minute.maid,4032,8.30201781,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-06,2,dominicks,2240,7.714231145,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-13,2,dominicks,5504,8.61323038,1,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-13,2,minute.maid,14784,9.601300794,1,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-13,2,tropicana,13248,9.491601877,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-20,2,tropicana,6208,8.733594062,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-20,2,dominicks,8832,9.086136769,0,1.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-20,2,minute.maid,12096,9.400630097999999,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-27,2,dominicks,2624,7.87245515,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-27,2,minute.maid,41792,10.64046021,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-06-27,2,tropicana,10624,9.270870872,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-04,2,tropicana,44672,10.70710219,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-04,2,minute.maid,10560,9.264828557000001,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-04,2,dominicks,10432,9.252633284,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-18,2,tropicana,20096,9.908276069,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-18,2,dominicks,8320,9.026417534,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-18,2,minute.maid,4224,8.348537825,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-25,2,dominicks,6784,8.822322178,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-25,2,minute.maid,2880,7.965545572999999,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-07-25,2,tropicana,9152,9.121727714,1,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-01,2,tropicana,21952,9.996613531,0,2.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-01,2,minute.maid,3968,8.286017467999999,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-01,2,dominicks,60544,11.01112565,1,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-08,2,dominicks,20608,9.933434629,0,0.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-08,2,minute.maid,3712,8.219326094,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-08,2,tropicana,13568,9.515469357999999,0,2.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-29,2,tropicana,4160,8.333270353,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-29,2,minute.maid,2816,7.943072717000001,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-08-29,2,dominicks,16064,9.684336023,0,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-05,2,tropicana,39424,10.58213005,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-05,2,minute.maid,4288,8.363575702999999,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-05,2,dominicks,12480,9.431882642,0,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-12,2,tropicana,5632,8.636219898,0,3.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-12,2,minute.maid,18240,9.811372264,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-12,2,dominicks,17024,9.742379392,0,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-19,2,dominicks,13440,9.505990614,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-19,2,minute.maid,7360,8.903815212,0,1.95,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-19,2,tropicana,9024,9.107642974,1,2.68,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-26,2,tropicana,6016,8.702177866,0,3.44,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-26,2,minute.maid,7808,8.962904128,0,1.83,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-09-26,2,dominicks,10112,9.221478116,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-03,2,dominicks,9088,9.114710141,0,1.56,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-03,2,minute.maid,13504,9.510741217,0,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-03,2,tropicana,7744,8.954673629,0,3.14,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-10,2,tropicana,6784,8.822322178,0,3.07,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-10,2,dominicks,22848,10.03661887,1,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-10,2,minute.maid,10048,9.215128888999999,0,1.91,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-17,2,dominicks,6976,8.850230966,0,1.65,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-17,2,minute.maid,135936,11.81993947,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-17,2,tropicana,6784,8.822322178,0,3.07,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-24,2,tropicana,6272,8.743850562,0,3.07,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-24,2,minute.maid,5056,8.528330936,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-24,2,dominicks,4160,8.333270353,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-31,2,tropicana,5312,8.577723691000001,0,3.07,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-31,2,minute.maid,27968,10.23881628,0,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-10-31,2,dominicks,3328,8.110126802,0,1.83,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-07,2,tropicana,9216,9.128696383,0,3.11,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-07,2,minute.maid,4736,8.462948177000001,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-07,2,dominicks,12096,9.400630097999999,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-14,2,tropicana,7296,8.895081532,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-14,2,minute.maid,7808,8.962904128,0,2.14,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-14,2,dominicks,6208,8.733594062,0,1.76,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-21,2,tropicana,34240,10.44114983,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-21,2,minute.maid,12480,9.431882642,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-21,2,dominicks,3008,8.009030685,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-28,2,dominicks,19456,9.875910785,1,1.5,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-28,2,minute.maid,9664,9.17616292,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-11-28,2,tropicana,7168,8.877381955,0,2.64,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-05,2,minute.maid,7168,8.877381955,0,2.06,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-05,2,dominicks,16768,9.727227587,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-05,2,tropicana,6080,8.712759975,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-12,2,dominicks,13568,9.515469357999999,1,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-12,2,minute.maid,4480,8.407378325,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-12,2,tropicana,5120,8.540909718,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-19,2,tropicana,8320,9.026417534,0,2.74,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-19,2,minute.maid,5952,8.691482577,0,2.22,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-19,2,dominicks,6080,8.712759975,0,1.61,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-26,2,dominicks,10432,9.252633284,1,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-26,2,minute.maid,21696,9.984883191,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1991-12-26,2,tropicana,17728,9.78290059,0,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-02,2,minute.maid,12032,9.395325046,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-02,2,dominicks,11712,9.368369236,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-02,2,tropicana,13120,9.481893063,0,2.35,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-09,2,dominicks,4032,8.30201781,0,1.76,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-09,2,minute.maid,7040,8.859363449,0,2.12,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-09,2,tropicana,13120,9.481893063,0,2.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-16,2,dominicks,6336,8.754002933999999,0,1.82,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-16,2,tropicana,9792,9.189321005,0,2.43,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-16,2,minute.maid,10240,9.234056899,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-23,2,tropicana,3520,8.166216269,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-23,2,minute.maid,6848,8.831711918,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-23,2,dominicks,13632,9.520175249,0,1.47,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-30,2,tropicana,5504,8.61323038,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-30,2,minute.maid,3968,8.286017467999999,0,2.61,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-01-30,2,dominicks,45120,10.71708089,0,1.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-06,2,tropicana,6720,8.812843434,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-06,2,minute.maid,5888,8.68067166,0,2.26,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-06,2,dominicks,9984,9.208739091,0,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-13,2,tropicana,20224,9.914625297,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-13,2,dominicks,4800,8.476371197,0,1.82,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-13,2,minute.maid,6208,8.733594062,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-20,2,dominicks,11776,9.373818841,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-20,2,minute.maid,72256,11.18797065,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-20,2,tropicana,5056,8.528330936,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-27,2,tropicana,43584,10.68244539,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-27,2,minute.maid,11520,9.351839934,0,2.11,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-02-27,2,dominicks,11584,9.357380115,0,1.54,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-05,2,tropicana,25728,10.15533517,0,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-05,2,minute.maid,5824,8.66974259,0,2.35,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-05,2,dominicks,51264,10.84474403,1,1.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-12,2,tropicana,31808,10.36747311,0,1.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-12,2,minute.maid,19392,9.872615889,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-12,2,dominicks,14976,9.614204199,0,1.44,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-19,2,tropicana,20736,9.939626599,0,1.91,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-19,2,minute.maid,9536,9.162829389,0,2.1,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-19,2,dominicks,30784,10.33475035,0,1.59,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-26,2,tropicana,15168,9.626943225,0,2.81,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-26,2,minute.maid,5312,8.577723691000001,0,2.28,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-03-26,2,dominicks,12480,9.431882642,0,1.6,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-02,2,tropicana,28096,10.2433825,1,2.5,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-02,2,dominicks,3264,8.090708716,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-02,2,minute.maid,14528,9.583833101,1,1.9,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-09,2,dominicks,8768,9.078864009,0,1.48,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-09,2,minute.maid,12416,9.426741242,0,2.12,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-09,2,tropicana,12416,9.426741242,0,2.58,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-16,2,tropicana,5376,8.589699882,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-16,2,minute.maid,5376,8.589699882,0,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-16,2,dominicks,70848,11.16829202,1,1.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-23,2,tropicana,9792,9.189321005,0,2.67,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-23,2,minute.maid,19008,9.852615222,1,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-23,2,dominicks,18560,9.828764006,0,1.42,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-30,2,tropicana,16960,9.738612909,1,2.39,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-30,2,minute.maid,3904,8.269756948,0,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-04-30,2,dominicks,9152,9.121727714,0,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-07,2,tropicana,8320,9.026417534,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-07,2,minute.maid,6336,8.754002933999999,0,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-07,2,dominicks,9600,9.169518378,0,2.0,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-14,2,tropicana,6912,8.841014311,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-14,2,minute.maid,5440,8.60153434,0,2.79,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-14,2,dominicks,4800,8.476371197,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-21,2,tropicana,6976,8.850230966,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-21,2,minute.maid,22400,10.01681624,1,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-21,2,dominicks,9664,9.17616292,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-28,2,minute.maid,3968,8.286017467999999,0,2.84,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-28,2,tropicana,7232,8.886270902,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-05-28,2,dominicks,45568,10.726961,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-04,2,tropicana,51520,10.84972536,1,2.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-04,2,minute.maid,3264,8.090708716,0,2.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-04,2,dominicks,20992,9.951896692,0,1.74,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-11,2,minute.maid,4352,8.378390789,0,2.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-11,2,tropicana,22272,10.01108556,0,2.21,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-11,2,dominicks,6592,8.793612072,0,2.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-18,2,dominicks,4992,8.51559191,0,2.05,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-18,2,minute.maid,4480,8.407378325,0,2.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-18,2,tropicana,46144,10.73952222,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-25,2,tropicana,4352,8.378390789,1,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-25,2,minute.maid,3840,8.253227646000001,0,2.52,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-06-25,2,dominicks,8064,8.99516499,0,1.24,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-02,2,tropicana,17280,9.757305042,0,2.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-02,2,minute.maid,13312,9.496421162999999,1,2.0,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-02,2,dominicks,7360,8.903815212,0,1.61,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-09,2,tropicana,5696,8.647519453,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-09,2,minute.maid,3776,8.236420527,1,2.33,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-09,2,dominicks,10048,9.215128888999999,0,1.4,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-16,2,tropicana,6848,8.831711918,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-16,2,dominicks,10112,9.221478116,0,1.91,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-16,2,minute.maid,4800,8.476371197,0,2.89,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-23,2,dominicks,9152,9.121727714,0,1.69,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-23,2,minute.maid,24960,10.12502982,1,2.29,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-23,2,tropicana,4416,8.392989587999999,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-30,2,tropicana,4672,8.449342525,0,3.16,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-30,2,minute.maid,4544,8.42156296,0,2.86,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-07-30,2,dominicks,36288,10.49924239,1,1.49,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-06,2,tropicana,7168,8.877381955,1,3.09,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-06,2,minute.maid,3968,8.286017467999999,1,2.81,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-06,2,dominicks,3776,8.236420527,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-13,2,tropicana,5056,8.528330936,0,3.19,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-13,2,dominicks,3328,8.110126802,0,1.97,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-13,2,minute.maid,49600,10.81174611,1,1.99,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1992-08-20,2,dominicks,13824,9.534161491,0,1.36,0.232864734,0.248934934,10.55320518,0.463887065,0.103953406,0.114279949,0.303585347,2.110122129,1.142857143,1.927279669,0.37692661299999997
-1990-06-14,5,dominicks,1792,7.491087594,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-14,5,minute.maid,4224,8.348537825,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-14,5,tropicana,5888,8.68067166,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-28,5,minute.maid,4352,8.378390789,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-28,5,dominicks,2496,7.82244473,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-28,5,tropicana,6976,8.850230966,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-05,5,dominicks,2944,7.98752448,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-05,5,minute.maid,4928,8.502688505,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-05,5,tropicana,6528,8.783855897,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-12,5,dominicks,1024,6.931471806,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-12,5,minute.maid,31168,10.34714721,1,2.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-12,5,tropicana,4928,8.502688505,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-26,5,dominicks,4224,8.348537825,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-26,5,minute.maid,10048,9.215128888999999,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-07-26,5,tropicana,5312,8.577723691000001,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-02,5,minute.maid,21760,9.987828701,1,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-02,5,tropicana,5120,8.540909718,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-02,5,dominicks,4544,8.42156296,1,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-09,5,dominicks,1728,7.454719948999999,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-09,5,minute.maid,4544,8.42156296,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-09,5,tropicana,7936,8.979164649,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-16,5,tropicana,6080,8.712759975,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-16,5,minute.maid,52224,10.86329744,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-16,5,dominicks,1216,7.103322062999999,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-23,5,dominicks,1152,7.049254841000001,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-23,5,minute.maid,3584,8.184234774,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-23,5,tropicana,4160,8.333270353,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-30,5,minute.maid,5120,8.540909718,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-30,5,tropicana,5888,8.68067166,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-08-30,5,dominicks,30144,10.31374118,1,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-06,5,dominicks,8960,9.100525506,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-06,5,minute.maid,4416,8.392989587999999,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-06,5,tropicana,9536,9.162829389,0,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-13,5,tropicana,8320,9.026417534,0,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-13,5,dominicks,8192,9.010913347,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-13,5,minute.maid,30208,10.31586207,1,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-20,5,dominicks,6528,8.783855897,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-20,5,minute.maid,4160,8.333270353,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-20,5,tropicana,8000,8.987196821,0,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-27,5,dominicks,34688,10.45414909,1,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-27,5,minute.maid,4992,8.51559191,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-09-27,5,tropicana,5824,8.66974259,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-04,5,dominicks,4672,8.449342525,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-04,5,minute.maid,13952,9.543378146,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-04,5,tropicana,10624,9.270870872,1,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-11,5,tropicana,6656,8.803273982999999,0,3.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-11,5,dominicks,1088,6.992096427000001,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-11,5,minute.maid,47680,10.772267300000001,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-18,5,tropicana,5184,8.553332238,0,3.51,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-18,5,minute.maid,7616,8.938006577000001,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-18,5,dominicks,69440,11.14821835,1,1.24,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-25,5,tropicana,4928,8.502688505,0,3.51,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-25,5,minute.maid,8896,9.093357017,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-10-25,5,dominicks,1280,7.154615357000001,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-01,5,tropicana,5888,8.68067166,0,3.51,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-01,5,minute.maid,28544,10.25920204,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-01,5,dominicks,35456,10.47604777,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-08,5,tropicana,5312,8.577723691000001,0,3.51,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-08,5,dominicks,13824,9.534161491,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-08,5,minute.maid,5440,8.60153434,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-15,5,tropicana,9984,9.208739091,0,3.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-15,5,minute.maid,52416,10.86696717,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-15,5,dominicks,14208,9.561560465,0,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-22,5,tropicana,8448,9.041685006,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-22,5,dominicks,29312,10.28575227,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-22,5,minute.maid,11712,9.368369236,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-29,5,tropicana,10880,9.29468152,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-29,5,minute.maid,13952,9.543378146,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-11-29,5,dominicks,52992,10.87789624,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-06,5,dominicks,15680,9.660141293999999,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-06,5,minute.maid,36160,10.49570882,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-06,5,tropicana,5696,8.647519453,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-13,5,tropicana,5696,8.647519453,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-13,5,minute.maid,12864,9.462187991,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-13,5,dominicks,43520,10.68097588,1,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-20,5,tropicana,32384,10.38541975,0,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-20,5,minute.maid,22208,10.00820786,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-20,5,dominicks,3904,8.269756948,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-27,5,tropicana,10752,9.282847063,0,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-27,5,minute.maid,9984,9.208739091,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-12-27,5,dominicks,896,6.797940412999999,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-03,5,tropicana,6912,8.841014311,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-03,5,minute.maid,14016,9.547954812999999,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-03,5,dominicks,2240,7.714231145,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-10,5,tropicana,13440,9.505990614,0,2.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-10,5,minute.maid,6080,8.712759975,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-10,5,dominicks,125760,11.74213061,1,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-17,5,tropicana,7808,8.962904128,0,2.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-17,5,minute.maid,7808,8.962904128,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-17,5,dominicks,1408,7.249925537,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-24,5,tropicana,5248,8.565602331000001,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-24,5,minute.maid,40896,10.61878754,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-24,5,dominicks,7232,8.886270902,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-31,5,tropicana,6208,8.733594062,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-31,5,minute.maid,6272,8.743850562,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-01-31,5,dominicks,41216,10.62658181,1,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-07,5,tropicana,21440,9.973013615,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-07,5,minute.maid,7872,8.971067439,0,2.41,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-07,5,dominicks,9024,9.107642974,0,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-14,5,dominicks,1600,7.377758908,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-14,5,tropicana,7360,8.903815212,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-14,5,minute.maid,6144,8.723231275,0,2.41,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-21,5,tropicana,6720,8.812843434,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-21,5,minute.maid,8448,9.041685006,0,2.41,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-21,5,dominicks,2496,7.82244473,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-28,5,tropicana,6656,8.803273982999999,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-28,5,minute.maid,18688,9.835636886,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-02-28,5,dominicks,6336,8.754002933999999,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-07,5,tropicana,6016,8.702177866,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-07,5,minute.maid,6272,8.743850562,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-07,5,dominicks,56384,10.93994071,1,1.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-14,5,tropicana,6144,8.723231275,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-14,5,minute.maid,12096,9.400630097999999,0,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-14,5,dominicks,1600,7.377758908,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-21,5,tropicana,4928,8.502688505,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-21,5,minute.maid,73216,11.20116926,1,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-21,5,dominicks,2944,7.98752448,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-28,5,tropicana,67712,11.1230187,1,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-28,5,minute.maid,18944,9.849242538,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-03-28,5,dominicks,13504,9.510741217,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-04,5,dominicks,5376,8.589699882,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-04,5,tropicana,8640,9.064157862,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-04,5,minute.maid,6400,8.764053269,1,2.46,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-11,5,tropicana,35520,10.477851199999998,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-11,5,minute.maid,8640,9.064157862,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-11,5,dominicks,6656,8.803273982999999,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-18,5,tropicana,9664,9.17616292,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-18,5,minute.maid,7296,8.895081532,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-18,5,dominicks,95680,11.46876457,1,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-25,5,tropicana,49088,10.80136989,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-25,5,minute.maid,12480,9.431882642,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-04-25,5,dominicks,896,6.797940412999999,1,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-02,5,dominicks,1728,7.454719948999999,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-02,5,minute.maid,14144,9.557045785,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-02,5,tropicana,14912,9.609921537,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-09,5,minute.maid,88256,11.38799696,1,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-09,5,tropicana,6464,8.774003599999999,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-09,5,dominicks,1280,7.154615357000001,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-16,5,dominicks,5696,8.647519453,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-16,5,minute.maid,6848,8.831711918,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-16,5,tropicana,25024,10.12759064,1,2.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-23,5,minute.maid,7808,8.962904128,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-23,5,tropicana,6272,8.743850562,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-23,5,dominicks,28288,10.25019297,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-30,5,dominicks,4864,8.489616424,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-30,5,minute.maid,6272,8.743850562,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-05-30,5,tropicana,5056,8.528330936,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-06,5,minute.maid,6144,8.723231275,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-06,5,tropicana,47616,10.77092412,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-06,5,dominicks,2880,7.965545572999999,0,2.09,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-13,5,dominicks,5760,8.658692754,1,1.41,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-13,5,minute.maid,27776,10.23192762,1,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-13,5,tropicana,13888,9.538780437,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-20,5,tropicana,6144,8.723231275,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-20,5,minute.maid,20800,9.942708266,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-20,5,dominicks,15040,9.618468598,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-27,5,dominicks,5120,8.540909718,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-27,5,minute.maid,45696,10.72976605,1,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-06-27,5,tropicana,9344,9.142489705,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-04,5,minute.maid,14336,9.570529135,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-04,5,tropicana,32896,10.40110635,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-04,5,dominicks,3264,8.090708716,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-11,5,dominicks,9536,9.162829389,1,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-11,5,minute.maid,4928,8.502688505,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-11,5,tropicana,21056,9.954940834,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-18,5,tropicana,15360,9.639522007,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-18,5,minute.maid,4608,8.435549202,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-18,5,dominicks,6208,8.733594062,0,1.59,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-25,5,dominicks,6592,8.793612072,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-25,5,tropicana,8000,8.987196821,1,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-07-25,5,minute.maid,5248,8.565602331000001,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-01,5,tropicana,21120,9.957975738,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-01,5,dominicks,63552,11.05961375,1,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-01,5,minute.maid,4224,8.348537825,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-08,5,dominicks,27968,10.23881628,0,0.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-08,5,minute.maid,4288,8.363575702999999,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-08,5,tropicana,11904,9.384629757,0,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-15,5,minute.maid,16896,9.734832187,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-15,5,tropicana,5056,8.528330936,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-15,5,dominicks,21760,9.987828701,1,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-22,5,dominicks,2688,7.896552702,0,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-22,5,minute.maid,77184,11.25394746,1,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-22,5,tropicana,4608,8.435549202,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-29,5,tropicana,6016,8.702177866,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-29,5,minute.maid,5184,8.553332238,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-08-29,5,dominicks,10432,9.252633284,0,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-05,5,tropicana,50752,10.83470631,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-05,5,minute.maid,5248,8.565602331000001,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-05,5,dominicks,9792,9.189321005,0,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-12,5,minute.maid,20672,9.936535407000001,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-12,5,tropicana,5632,8.636219898,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-12,5,dominicks,8448,9.041685006,0,1.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-26,5,tropicana,6400,8.764053269,0,3.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-26,5,dominicks,6912,8.841014311,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-09-26,5,minute.maid,12352,9.421573272,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-03,5,dominicks,8256,9.018695487999999,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-03,5,minute.maid,12032,9.395325046,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-03,5,tropicana,5440,8.60153434,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-10,5,minute.maid,13440,9.505990614,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-10,5,dominicks,28672,10.26367632,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-10,5,tropicana,8128,9.00307017,0,2.94,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-24,5,tropicana,7232,8.886270902,0,2.94,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-24,5,minute.maid,5824,8.66974259,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-24,5,dominicks,4416,8.392989587999999,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-31,5,tropicana,7168,8.877381955,0,2.94,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-31,5,minute.maid,50112,10.82201578,0,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-10-31,5,dominicks,1856,7.526178913,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-07,5,minute.maid,5184,8.553332238,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-07,5,tropicana,7872,8.971067439,0,2.94,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-07,5,dominicks,6528,8.783855897,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-14,5,tropicana,7552,8.929567707999999,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-14,5,minute.maid,8384,9.034080407000001,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-14,5,dominicks,6080,8.712759975,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-21,5,tropicana,69504,11.14913958,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-21,5,dominicks,3456,8.14786713,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-21,5,minute.maid,10112,9.221478116,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-28,5,dominicks,25856,10.16029796,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-28,5,minute.maid,8384,9.034080407000001,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-11-28,5,tropicana,8960,9.100525506,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-05,5,tropicana,6912,8.841014311,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-05,5,dominicks,25728,10.15533517,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-05,5,minute.maid,11456,9.346268889,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-12,5,dominicks,23552,10.06696602,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-12,5,minute.maid,5952,8.691482577,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-12,5,tropicana,6656,8.803273982999999,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-19,5,tropicana,8192,9.010913347,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-19,5,dominicks,2944,7.98752448,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-19,5,minute.maid,8512,9.049232212,0,2.26,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-26,5,dominicks,5888,8.68067166,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-26,5,minute.maid,27968,10.23881628,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1991-12-26,5,tropicana,13440,9.505990614,0,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-02,5,tropicana,12160,9.405907156,0,2.39,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-02,5,dominicks,6848,8.831711918,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-02,5,minute.maid,24000,10.08580911,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-09,5,dominicks,1792,7.491087594,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-09,5,minute.maid,6848,8.831711918,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-09,5,tropicana,11840,9.379238908,0,2.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-16,5,tropicana,8640,9.064157862,0,2.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-16,5,dominicks,5248,8.565602331000001,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-16,5,minute.maid,15104,9.622714887999999,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-23,5,tropicana,5888,8.68067166,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-23,5,minute.maid,11392,9.340666634,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-23,5,dominicks,16768,9.727227587,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-30,5,tropicana,7424,8.912473275,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-30,5,minute.maid,5824,8.66974259,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-01-30,5,dominicks,52160,10.8620712,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-06,5,tropicana,5632,8.636219898,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-06,5,minute.maid,7488,8.921057017999999,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-06,5,dominicks,16640,9.719564714,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-13,5,tropicana,33600,10.42228135,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-13,5,minute.maid,8320,9.026417534,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-13,5,dominicks,1344,7.2034055210000005,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-20,5,dominicks,4608,8.435549202,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-20,5,tropicana,5376,8.589699882,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-20,5,minute.maid,99904,11.511965,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-27,5,tropicana,54272,10.90176372,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-27,5,minute.maid,6976,8.850230966,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-02-27,5,dominicks,12672,9.447150114,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-05,5,tropicana,33600,10.42228135,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-05,5,minute.maid,9984,9.208739091,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-05,5,dominicks,48640,10.79220152,1,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-12,5,tropicana,24448,10.10430369,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-12,5,minute.maid,32832,10.39915893,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-12,5,dominicks,13248,9.491601877,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-19,5,tropicana,22784,10.03381381,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-19,5,minute.maid,8128,9.00307017,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-19,5,dominicks,29248,10.28356647,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-26,5,tropicana,19008,9.852615222,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-26,5,minute.maid,6464,8.774003599999999,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-03-26,5,dominicks,4608,8.435549202,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-02,5,tropicana,15808,9.66827142,1,2.5,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-02,5,minute.maid,36800,10.51325312,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-02,5,dominicks,3136,8.050703382,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-09,5,dominicks,13184,9.486759252,0,1.58,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-09,5,tropicana,14144,9.557045785,0,2.5,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-09,5,minute.maid,12928,9.467150781,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-16,5,tropicana,9600,9.169518378,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-16,5,minute.maid,7424,8.912473275,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-16,5,dominicks,67712,11.1230187,1,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-23,5,tropicana,10112,9.221478116,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-23,5,minute.maid,34176,10.43927892,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-23,5,dominicks,18880,9.84585844,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-30,5,minute.maid,4160,8.333270353,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-30,5,tropicana,31872,10.36948316,1,2.24,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-04-30,5,dominicks,6208,8.733594062,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-07,5,tropicana,9280,9.135616826,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-07,5,minute.maid,5952,8.691482577,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-07,5,dominicks,5952,8.691482577,0,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-14,5,tropicana,7680,8.946374826,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-14,5,minute.maid,6528,8.783855897,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-14,5,dominicks,4160,8.333270353,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-21,5,tropicana,8704,9.071537969,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-21,5,minute.maid,30656,10.33058368,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-21,5,dominicks,23488,10.06424493,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-28,5,tropicana,9920,9.2023082,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-28,5,dominicks,60480,11.01006801,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-05-28,5,minute.maid,6656,8.803273982999999,0,2.66,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-04,5,tropicana,91968,11.42919597,1,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-04,5,minute.maid,4416,8.392989587999999,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-04,5,dominicks,20416,9.924074186,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-11,5,tropicana,44096,10.69412435,0,2.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-11,5,dominicks,6336,8.754002933999999,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-11,5,minute.maid,5696,8.647519453,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-25,5,minute.maid,5696,8.647519453,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-25,5,tropicana,7296,8.895081532,1,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-06-25,5,dominicks,1408,7.249925537,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-02,5,tropicana,12928,9.467150781,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-02,5,minute.maid,39680,10.58860256,1,2.01,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-02,5,dominicks,4672,8.449342525,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-09,5,tropicana,6848,8.831711918,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-09,5,minute.maid,6208,8.733594062,1,2.19,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-09,5,dominicks,19520,9.87919486,0,1.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-16,5,tropicana,8064,8.99516499,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-16,5,minute.maid,7872,8.971067439,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-16,5,dominicks,7872,8.971067439,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-23,5,dominicks,5184,8.553332238,0,1.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-23,5,tropicana,4992,8.51559191,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-23,5,minute.maid,54528,10.90646961,1,2.29,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-30,5,tropicana,7360,8.903815212,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-30,5,minute.maid,6400,8.764053269,0,2.69,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-07-30,5,dominicks,42240,10.65112292,1,1.49,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-06,5,tropicana,8384,9.034080407000001,1,2.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-06,5,minute.maid,5888,8.68067166,1,2.65,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-06,5,dominicks,6592,8.793612072,1,1.89,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-13,5,tropicana,8832,9.086136769,0,2.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-13,5,minute.maid,56384,10.93994071,1,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-13,5,dominicks,2112,7.655390645,0,1.99,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1992-08-20,5,dominicks,21248,9.964018052,0,1.79,0.117368032,0.32122573,10.92237097,0.535883355,0.103091585,0.053875277,0.410568032,3.801997814,0.681818182,1.600573425,0.736306837
-1990-06-14,8,dominicks,14336,9.570529135,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-14,8,minute.maid,6080,8.712759975,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-14,8,tropicana,8896,9.093357017,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-21,8,dominicks,6400,8.764053269,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-21,8,minute.maid,51968,10.85838342,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-21,8,tropicana,7296,8.895081532,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-28,8,tropicana,10368,9.246479419,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-28,8,minute.maid,4928,8.502688505,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-06-28,8,dominicks,3968,8.286017467999999,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-05,8,dominicks,4352,8.378390789,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-05,8,minute.maid,5312,8.577723691000001,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-05,8,tropicana,6976,8.850230966,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-12,8,tropicana,6464,8.774003599999999,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-12,8,dominicks,3520,8.166216269,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-12,8,minute.maid,39424,10.58213005,1,2.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-19,8,tropicana,8192,9.010913347,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-19,8,dominicks,6464,8.774003599999999,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-19,8,minute.maid,5568,8.624791202,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-26,8,dominicks,5952,8.691482577,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-26,8,minute.maid,14592,9.588228712000001,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-07-26,8,tropicana,7936,8.979164649,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-02,8,tropicana,6656,8.803273982999999,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-02,8,minute.maid,22208,10.00820786,1,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-02,8,dominicks,8832,9.086136769,1,2.09,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-09,8,dominicks,7232,8.886270902,0,2.09,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-09,8,minute.maid,5760,8.658692754,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-09,8,tropicana,8256,9.018695487999999,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-16,8,tropicana,5568,8.624791202,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-16,8,minute.maid,54016,10.89703558,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-16,8,dominicks,5504,8.61323038,0,2.09,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-23,8,dominicks,4800,8.476371197,0,2.09,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-23,8,minute.maid,5824,8.66974259,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-23,8,tropicana,7488,8.921057017999999,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-30,8,tropicana,6144,8.723231275,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-30,8,minute.maid,6528,8.783855897,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-08-30,8,dominicks,52672,10.87183928,1,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-06,8,dominicks,16448,9.707959168,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-06,8,minute.maid,5440,8.60153434,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-06,8,tropicana,11008,9.30637756,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-13,8,minute.maid,36544,10.50627229,1,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-13,8,dominicks,19072,9.85597657,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-13,8,tropicana,5760,8.658692754,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-20,8,dominicks,13376,9.501217335,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-20,8,minute.maid,3776,8.236420527,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-20,8,tropicana,10112,9.221478116,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-27,8,tropicana,8448,9.041685006,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-27,8,minute.maid,5504,8.61323038,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-09-27,8,dominicks,61440,11.02581637,1,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-04,8,tropicana,8448,9.041685006,1,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-04,8,dominicks,13760,9.529521112000001,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-04,8,minute.maid,12416,9.426741242,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-11,8,minute.maid,53696,10.89109379,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-11,8,dominicks,3136,8.050703382,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-11,8,tropicana,7424,8.912473275,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-18,8,tropicana,5824,8.66974259,0,3.04,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-18,8,minute.maid,5696,8.647519453,0,2.51,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-18,8,dominicks,186176,12.13444774,1,1.14,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-25,8,tropicana,6656,8.803273982999999,0,3.04,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-25,8,minute.maid,4864,8.489616424,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-10-25,8,dominicks,3712,8.219326094,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-01,8,tropicana,6272,8.743850562,0,3.04,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-01,8,minute.maid,37184,10.52363384,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-01,8,dominicks,35776,10.48503256,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-08,8,tropicana,6912,8.841014311,0,3.04,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-08,8,minute.maid,5504,8.61323038,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-08,8,dominicks,26880,10.1991378,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-15,8,tropicana,10496,9.258749511,0,3.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-15,8,minute.maid,51008,10.83973776,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-15,8,dominicks,71680,11.17996705,0,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-22,8,tropicana,11840,9.379238908,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-22,8,minute.maid,11072,9.312174678,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-22,8,dominicks,25088,10.13014492,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-29,8,tropicana,9664,9.17616292,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-29,8,minute.maid,12160,9.405907156,0,2.62,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-11-29,8,dominicks,91456,11.42361326,1,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-06,8,minute.maid,30528,10.32639957,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-06,8,dominicks,23808,10.07777694,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-06,8,tropicana,6272,8.743850562,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-13,8,dominicks,89856,11.40596367,1,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-13,8,minute.maid,12096,9.400630097999999,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-13,8,tropicana,7168,8.877381955,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-20,8,minute.maid,16448,9.707959168,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-20,8,dominicks,12224,9.411156511,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-20,8,tropicana,29504,10.29228113,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-27,8,minute.maid,9344,9.142489705,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-27,8,dominicks,3776,8.236420527,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1990-12-27,8,tropicana,8704,9.071537969,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-03,8,tropicana,9280,9.135616826,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-03,8,minute.maid,16128,9.688312171,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-03,8,dominicks,13824,9.534161491,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-10,8,minute.maid,5376,8.589699882,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-10,8,dominicks,251072,12.43349503,1,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-10,8,tropicana,12224,9.411156511,0,2.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-17,8,minute.maid,6656,8.803273982999999,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-17,8,tropicana,10368,9.246479419,0,2.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-17,8,dominicks,4864,8.489616424,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-24,8,minute.maid,59712,10.99728828,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-24,8,dominicks,10176,9.227787286,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-24,8,tropicana,8128,9.00307017,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-31,8,tropicana,5952,8.691482577,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-31,8,minute.maid,9856,9.195835686,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-01-31,8,dominicks,105344,11.56498647,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-07,8,minute.maid,6720,8.812843434,0,2.12,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-07,8,dominicks,33600,10.42228135,0,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-07,8,tropicana,21696,9.984883191,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-14,8,dominicks,4736,8.462948177000001,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-14,8,minute.maid,4224,8.348537825,0,2.12,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-14,8,tropicana,7808,8.962904128,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-21,8,tropicana,8128,9.00307017,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-21,8,minute.maid,9728,9.182763604,0,2.12,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-21,8,dominicks,10304,9.240287448,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-28,8,tropicana,7424,8.912473275,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-28,8,minute.maid,40320,10.604602900000001,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-02-28,8,dominicks,5056,8.528330936,1,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-07,8,dominicks,179968,12.10053434,1,0.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-07,8,tropicana,5952,8.691482577,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-07,8,minute.maid,5120,8.540909718,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-14,8,minute.maid,19264,9.865993348,0,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-14,8,dominicks,4992,8.51559191,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-14,8,tropicana,7616,8.938006577000001,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-21,8,tropicana,5312,8.577723691000001,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-21,8,minute.maid,170432,12.04609167,1,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-21,8,dominicks,6400,8.764053269,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-28,8,minute.maid,39680,10.58860256,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-28,8,dominicks,14912,9.609921537,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-03-28,8,tropicana,161792,11.99406684,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-04,8,dominicks,34624,10.45230236,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-04,8,minute.maid,8128,9.00307017,1,2.17,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-04,8,tropicana,17280,9.757305042,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-11,8,tropicana,47040,10.75875358,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-11,8,minute.maid,9088,9.114710141,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-11,8,dominicks,10368,9.246479419,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-18,8,tropicana,14464,9.579418083,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-18,8,minute.maid,6720,8.812843434,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-18,8,dominicks,194880,12.18013926,1,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-25,8,tropicana,52928,10.87668778,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-25,8,dominicks,5696,8.647519453,1,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-04-25,8,minute.maid,7552,8.929567707999999,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-02,8,dominicks,7168,8.877381955,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-02,8,minute.maid,24768,10.11730778,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-02,8,tropicana,21184,9.961001459,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-09,8,tropicana,7360,8.903815212,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-09,8,minute.maid,183296,12.11885761,1,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-09,8,dominicks,2880,7.965545572999999,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-16,8,dominicks,12288,9.416378455,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-16,8,minute.maid,8896,9.093357017,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-05-16,8,tropicana,15744,9.664214619,1,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-06,8,dominicks,9280,9.135616826,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-06,8,tropicana,46912,10.75602879,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-06,8,minute.maid,6656,8.803273982999999,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-13,8,tropicana,18240,9.811372264,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-13,8,dominicks,25856,10.16029796,1,1.26,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-13,8,minute.maid,35456,10.47604777,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-20,8,dominicks,19264,9.865993348,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-20,8,minute.maid,17408,9.76468515,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-20,8,tropicana,6464,8.774003599999999,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-27,8,dominicks,6848,8.831711918,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-27,8,minute.maid,75520,11.2321528,1,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-06-27,8,tropicana,8512,9.049232212,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-04,8,tropicana,28416,10.25470765,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-04,8,minute.maid,21632,9.981928979,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-04,8,dominicks,12928,9.467150781,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-11,8,dominicks,44032,10.69267192,1,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-11,8,minute.maid,8384,9.034080407000001,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-11,8,tropicana,16960,9.738612909,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-18,8,minute.maid,9920,9.2023082,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-18,8,dominicks,25408,10.14281936,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-18,8,tropicana,8320,9.026417534,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-25,8,dominicks,38336,10.55414468,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-25,8,minute.maid,6592,8.793612072,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-07-25,8,tropicana,11136,9.317938383,1,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-01,8,tropicana,27712,10.22962081,0,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-01,8,minute.maid,7168,8.877381955,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-01,8,dominicks,152384,11.93415893,1,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-08,8,dominicks,54464,10.90529521,0,0.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-08,8,minute.maid,6208,8.733594062,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-08,8,tropicana,7744,8.954673629,0,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-15,8,minute.maid,30528,10.32639957,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-15,8,dominicks,47680,10.772267300000001,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-15,8,tropicana,5184,8.553332238,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-22,8,dominicks,14720,9.596962392,0,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-22,8,minute.maid,155840,11.95658512,1,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-22,8,tropicana,6272,8.743850562,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-29,8,tropicana,7744,8.954673629,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-29,8,dominicks,53248,10.88271552,0,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-08-29,8,minute.maid,10752,9.282847063,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-05,8,tropicana,53184,10.88151288,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-05,8,minute.maid,6976,8.850230966,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-05,8,dominicks,40576,10.61093204,0,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-12,8,dominicks,25856,10.16029796,0,1.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-12,8,tropicana,6784,8.822322178,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-12,8,minute.maid,31872,10.36948316,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-19,8,dominicks,24064,10.08847223,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-19,8,minute.maid,5312,8.577723691000001,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-19,8,tropicana,8000,8.987196821,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-26,8,tropicana,6592,8.793612072,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-26,8,minute.maid,33344,10.41463313,0,1.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-09-26,8,dominicks,15680,9.660141293999999,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-03,8,minute.maid,13504,9.510741217,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-03,8,dominicks,16576,9.715711145,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-03,8,tropicana,5248,8.565602331000001,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-10,8,dominicks,49664,10.8130356,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-10,8,tropicana,6592,8.793612072,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-10,8,minute.maid,13504,9.510741217,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-17,8,dominicks,10752,9.282847063,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-17,8,minute.maid,335808,12.72429485,1,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-17,8,tropicana,5888,8.68067166,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-24,8,tropicana,6336,8.754002933999999,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-24,8,dominicks,9792,9.189321005,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-24,8,minute.maid,13120,9.481893063,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-31,8,tropicana,5888,8.68067166,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-31,8,minute.maid,49664,10.8130356,0,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-10-31,8,dominicks,7104,8.868413285,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-07,8,dominicks,9216,9.128696383,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-07,8,tropicana,6080,8.712759975,0,2.94,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-07,8,minute.maid,10880,9.29468152,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-14,8,tropicana,6848,8.831711918,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-14,8,minute.maid,9984,9.208739091,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-14,8,dominicks,12608,9.442086812000001,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-21,8,tropicana,54016,10.89703558,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-21,8,minute.maid,9216,9.128696383,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-21,8,dominicks,16448,9.707959168,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-28,8,tropicana,10368,9.246479419,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-28,8,dominicks,27968,10.23881628,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-11-28,8,minute.maid,7680,8.946374826,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-05,8,minute.maid,7296,8.895081532,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-05,8,dominicks,37824,10.5406991,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-05,8,tropicana,5568,8.624791202,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-12,8,dominicks,33664,10.4241843,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-12,8,minute.maid,8192,9.010913347,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-12,8,tropicana,4864,8.489616424,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-19,8,tropicana,7232,8.886270902,0,2.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-19,8,minute.maid,6080,8.712759975,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-19,8,dominicks,17728,9.78290059,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-26,8,tropicana,15232,9.631153757,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-26,8,dominicks,25088,10.13014492,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1991-12-26,8,minute.maid,15040,9.618468598,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-02,8,minute.maid,9472,9.156095357,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-02,8,dominicks,13184,9.486759252,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-02,8,tropicana,47040,10.75875358,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-09,8,dominicks,3136,8.050703382,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-09,8,minute.maid,5888,8.68067166,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-09,8,tropicana,9280,9.135616826,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-16,8,tropicana,6720,8.812843434,0,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-16,8,minute.maid,14336,9.570529135,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-16,8,dominicks,5696,8.647519453,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-23,8,minute.maid,11712,9.368369236,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-23,8,dominicks,19008,9.852615222,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-23,8,tropicana,5056,8.528330936,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-30,8,minute.maid,7936,8.979164649,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-30,8,dominicks,121664,11.70901843,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-01-30,8,tropicana,6080,8.712759975,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-06,8,tropicana,10496,9.258749511,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-06,8,minute.maid,5184,8.553332238,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-06,8,dominicks,38848,10.56741187,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-13,8,minute.maid,7168,8.877381955,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-13,8,dominicks,6144,8.723231275,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-13,8,tropicana,39040,10.57234204,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-20,8,dominicks,13632,9.520175249,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-20,8,minute.maid,216064,12.28332994,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-20,8,tropicana,4480,8.407378325,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-27,8,tropicana,61760,11.03101119,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-27,8,minute.maid,15040,9.618468598,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-02-27,8,dominicks,9792,9.189321005,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-05,8,tropicana,15360,9.639522007,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-05,8,minute.maid,11840,9.379238908,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-05,8,dominicks,86912,11.37265139,1,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-12,8,minute.maid,25472,10.14533509,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-12,8,dominicks,24512,10.10691807,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-12,8,tropicana,54976,10.91465201,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-19,8,minute.maid,16384,9.704060528,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-19,8,dominicks,58048,10.96902553,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-19,8,tropicana,34368,10.44488118,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-26,8,tropicana,10752,9.282847063,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-26,8,minute.maid,20480,9.927204079,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-03-26,8,dominicks,13952,9.543378146,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-02,8,minute.maid,34688,10.45414909,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-02,8,dominicks,15168,9.626943225,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-02,8,tropicana,20096,9.908276069,1,2.5,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-09,8,dominicks,14592,9.588228712000001,0,1.58,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-09,8,minute.maid,22400,10.01681624,0,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-09,8,tropicana,16192,9.692272572,0,2.5,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-16,8,tropicana,6528,8.783855897,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-16,8,minute.maid,7808,8.962904128,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-16,8,dominicks,145088,11.88509573,1,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-23,8,tropicana,8320,9.026417534,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-23,8,minute.maid,48064,10.78028874,1,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-23,8,dominicks,43712,10.68537794,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-30,8,tropicana,30784,10.33475035,1,2.16,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-30,8,minute.maid,7360,8.903815212,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-04-30,8,dominicks,20608,9.933434629,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-07,8,tropicana,18048,9.800790154,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-07,8,minute.maid,6272,8.743850562,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-07,8,dominicks,18752,9.839055692,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-14,8,tropicana,12864,9.462187991,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-14,8,minute.maid,6400,8.764053269,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-14,8,dominicks,20160,9.911455722000001,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-21,8,tropicana,7168,8.877381955,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-21,8,minute.maid,54592,10.90764263,1,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-21,8,dominicks,18688,9.835636886,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-28,8,minute.maid,8128,9.00307017,0,2.39,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-28,8,tropicana,9024,9.107642974,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-05-28,8,dominicks,133824,11.80428078,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-04,8,tropicana,84992,11.35031241,1,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-04,8,minute.maid,4928,8.502688505,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-04,8,dominicks,63488,11.05860619,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-11,8,minute.maid,5440,8.60153434,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-11,8,tropicana,14144,9.557045785,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-11,8,dominicks,71040,11.17099838,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-25,8,tropicana,7488,8.921057017999999,1,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-25,8,minute.maid,5888,8.68067166,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-06-25,8,dominicks,15360,9.639522007,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-02,8,minute.maid,23872,10.0804615,1,2.02,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-02,8,dominicks,17728,9.78290059,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-02,8,tropicana,12352,9.421573272,0,2.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-09,8,tropicana,5696,8.647519453,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-09,8,minute.maid,6848,8.831711918,1,2.19,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-09,8,dominicks,24256,10.09641929,0,1.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-16,8,minute.maid,8192,9.010913347,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-16,8,dominicks,19968,9.901886271,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-16,8,tropicana,7680,8.946374826,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-23,8,dominicks,15936,9.67633598,0,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-23,8,minute.maid,55040,10.91581547,1,2.29,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-23,8,tropicana,5440,8.60153434,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-30,8,tropicana,5632,8.636219898,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-30,8,minute.maid,6528,8.783855897,0,2.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-07-30,8,dominicks,76352,11.24310951,1,1.49,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-06,8,tropicana,8960,9.100525506,1,2.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-06,8,minute.maid,6208,8.733594062,1,2.45,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-06,8,dominicks,17408,9.76468515,1,1.69,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-13,8,minute.maid,94720,11.45868045,1,1.99,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-13,8,tropicana,6080,8.712759975,0,2.89,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-13,8,dominicks,17536,9.77201119,0,1.79,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947
-1992-08-20,8,dominicks,31232,10.34919849,0,1.59,0.252394035,0.095173274,10.59700966,0.054227156,0.131749698,0.035243328,0.283074736,2.636332801,1.5,2.905384316,0.641015947

how-to-use-azureml/automated-machine-learning/forecasting-grouping/deploy/deploy.py

@@ -1,65 +0,0 @@
-import argparse
-from azureml.core import Run, Model
-from azureml.core import Workspace
-from azureml.core.webservice import AciWebservice
-from azureml.core.model import InferenceConfig
-import json
-
-
-script_file_name = 'score.py'
-conda_env_file_name = 'myenv.yml'
-
-print("In deploy.py")
-parser = argparse.ArgumentParser()
-parser.add_argument("--time_column_name", type=str, help="time column name")
-parser.add_argument("--group_column_names", type=str, help="group column names")
-parser.add_argument("--model_names", type=str, help="model names")
-parser.add_argument("--service_name", type=str, help="service name")
-
-args = parser.parse_args()
-
-# replace the group column names in scoring script to the ones set by user
-print("Update group_column_names")
-print(args.group_column_names)
-
-with open(script_file_name, 'r') as cefr:
-    content = cefr.read()
-with open(script_file_name, 'w') as cefw:
-    content = content.replace('<<groups>>', args.group_column_names.rstrip())
-    cefw.write(content.replace('<<time_colname>>', args.time_column_name.rstrip()))
-
-with open(script_file_name, 'r') as cefr1:
-    content1 = cefr1.read()
-print(content1)
-
-model_list = json.loads(args.model_names)
-print(model_list)
-
-run = Run.get_context()
-ws = run.experiment.workspace
-
-deployment_config = AciWebservice.deploy_configuration(
-    cpu_cores=1,
-    memory_gb=2,
-    tags={"method": "grouping"},
-    description='grouping demo aci deployment'
-)
-
-inference_config = InferenceConfig(
-    entry_script=script_file_name,
-    runtime='python',
-    conda_file=conda_env_file_name
-)
-
-models = []
-for model_name in model_list:
-    models.append(Model(ws, name=model_name))
-
-service = Model.deploy(
-    ws,
-    name=args.service_name,
-    models=models,
-    inference_config=inference_config,
-    deployment_config=deployment_config
-)
-service.wait_for_deployment(True)

how-to-use-azureml/automated-machine-learning/forecasting-grouping/deploy/myenv.yml

@@ -1,15 +0,0 @@
-name: project_environment
-dependencies:
-  # The python interpreter version.
-
-  # Currently Azure ML only supports 3.5.2 and later.
-
-- python=3.6.2
-
-- pip:
-  - azureml-defaults
-  - azureml-train-automl
-- numpy
-- scikit-learn
-- conda-forge::fbprophet==0.5
-

how-to-use-azureml/automated-machine-learning/forecasting-grouping/deploy/score.py

@@ -1,55 +0,0 @@
-import json
-import pickle
-import re
-
-import numpy as np
-import pandas as pd
-from sklearn.externals import joblib
-from sklearn.linear_model import Ridge
-
-from azureml.core.model import Model
-import azureml.train.automl
-
-
-def init():
-    global models
-    models = {}
-    global group_columns_str
-    group_columns_str = "<<groups>>"
-    global time_column_name
-    time_column_name = "<<time_colname>>"
-
-    global group_columns
-    group_columns = group_columns_str.split("#####")
-    global valid_chars
-    valid_chars = re.compile('[^a-zA-Z0-9-]')
-
-
-def run(raw_data):
-    try:
-        data = pd.read_json(raw_data)
-        # Make sure we have correct time points.
-        data[time_column_name] = pd.to_datetime(data[time_column_name], unit='ms')
-        dfs = []
-        for grain, df_one in data.groupby(group_columns):
-            if isinstance(grain, int):
-                cur_group = str(grain)
-            elif isinstance(grain, str):
-                cur_group = grain
-            else:
-                cur_group = "#####".join(list(grain))
-            cur_group = valid_chars.sub('', cur_group)
-            print("Query model for group {}".format(cur_group))
-            if cur_group not in models:
-                model_path = Model.get_model_path(cur_group)
-                model = joblib.load(model_path)
-                models[cur_group] = model
-            _, xtrans = models[cur_group].forecast(df_one, np.repeat(np.nan, len(df_one)))
-            dfs.append(xtrans)
-        df_ret = pd.concat(dfs)
-        df_ret.reset_index(drop=False, inplace=True)
-        return json.dumps({'predictions': df_ret.to_json()})
-
-    except Exception as e:
-        error = str(e)
-        return error

how-to-use-azureml/automated-machine-learning/forecasting-grouping/register/register.py

@@ -1,22 +0,0 @@
-import argparse
-
-from azureml.core import Run, Model
-
-parser = argparse.ArgumentParser()
-parser.add_argument("--model_name")
-parser.add_argument("--model_path")
-
-args = parser.parse_args()
-
-run = Run.get_context()
-ws = run.experiment.workspace
-print('retrieved ws: {}'.format(ws))
-
-print('begin register model')
-model = Model.register(
-    workspace=ws,
-    model_path=args.model_path,
-    model_name=args.model_name
-)
-print('model registered: {}'.format(model))
-print('complete')

how-to-use-azureml/automated-machine-learning/forecasting-high-frequency/automl-forecasting-function.yml

@@ -1,11 +0,0 @@
-name: automl-forecasting-function
-dependencies:
-- fbprophet==0.5
-- py-xgboost<=0.80
-- pip:
-  - azureml-sdk
-  - azureml-train-automl
-  - azureml-widgets
-  - pandas_ml
-  - statsmodels
-  - matplotlib

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb

@@ -24,23 +24,23 @@
         "_**Orange Juice Sales Forecasting**_\n",
         "\n",
         "## Contents\n",
-        "1. [Introduction](#Introduction)\n",
-        "1. [Setup](#Setup)\n",
-        "1. [Compute](#Compute)\n",
-        "1. [Data](#Data)\n",
-        "1. [Train](#Train)\n",
-        "1. [Predict](#Predict)\n",
-        "1. [Operationalize](#Operationalize)"
+        "1. [Introduction](#introduction)\n",
+        "1. [Setup](#setup)\n",
+        "1. [Compute](#compute)\n",
+        "1. [Data](#data)\n",
+        "1. [Train](#train)\n",
+        "1. [Forecast](#forecast)\n",
+        "1. [Operationalize](#operationalize)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Introduction\n",
+        "## Introduction<a id=\"introduction\"></a>\n",
         "In this example, we use AutoML to train, select, and operationalize a time-series forecasting model for multiple time-series.\n",
         "\n",
-        "Make sure you have executed the [configuration notebook](../configuration.ipynb) before running this notebook.\n",
+        "Make sure you have executed the [configuration notebook](../../../configuration.ipynb) before running this notebook.\n",
         "\n",
         "The examples in the follow code samples use the University of Chicago's Dominick's Finer Foods dataset to forecast orange juice sales. Dominick's was a grocery chain in the Chicago metropolitan area."
       ]
@@ -49,7 +49,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Setup"
+        "## Setup<a id=\"setup\"></a>"
       ]
     },
     {
@@ -60,12 +60,29 @@
       "source": [
         "import azureml.core\n",
         "import pandas as pd\n",
-        "import numpy as np\n",
         "import logging\n",
         "\n",
         "from azureml.core.workspace import Workspace\n",
         "from azureml.core.experiment import Experiment\n",
-        "from azureml.train.automl import AutoMLConfig"
+        "from azureml.train.automl import AutoMLConfig\n",
+        "from azureml.automl.core.featurization import FeaturizationConfig"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
     {
@@ -89,7 +106,6 @@
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace'] = ws.name\n",
         "output['SKU'] = ws.sku\n",
@@ -105,11 +121,14 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Compute\n",
+        "## Compute<a id=\"compute\"></a>\n",
         "You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+        "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\n",
         "#### Creation of AmlCompute takes approximately 5 minutes. \n",
         "If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
-        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read this article on the default limits and how to request more quota."
+        "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
       ]
     },
     {
@@ -118,42 +137,29 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.compute import AmlCompute\n",
-        "from azureml.core.compute import ComputeTarget\n",
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
-        "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpu-cluster-oj\"\n",
+        "# Choose a name for your CPU cluster\n",
+        "amlcompute_cluster_name = \"oj-cluster\"\n",
         "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "    \n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_D12_V2',\n",
         "                                                           max_nodes=6)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
         "\n",
-        "    # Create the cluster.\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "    \n",
-        "print('Checking cluster status...')\n",
-        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
-        "    \n",
-        "# For a more detailed view of current AmlCompute status, use get_status()."
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Data\n",
+        "## Data<a id=\"data\"></a>\n",
         "You are now ready to load the historical orange juice sales data. We will load the CSV file into a plain pandas DataFrame; the time column in the CSV is called _WeekStarting_, so it will be specially parsed into the datetime type."
       ]
     },
@@ -165,6 +171,10 @@
       "source": [
         "time_column_name = 'WeekStarting'\n",
         "data = pd.read_csv(\"dominicks_OJ.csv\", parse_dates=[time_column_name])\n",
+        "\n",
+        "# Drop the columns 'logQuantity' as it is a leaky feature.\n",
+        "data.drop('logQuantity', axis=1, inplace=True)\n",
+        "\n",
         "data.head()"
       ]
     },
@@ -174,7 +184,7 @@
       "source": [
         "Each row in the DataFrame holds a quantity of weekly sales for an OJ brand at a single store. The data also includes the sales price, a flag indicating if the OJ brand was advertised in the store that week, and some customer demographic information based on the store location. For historical reasons, the data also include the logarithm of the sales quantity. The Dominick's grocery data is commonly used to illustrate econometric modeling techniques where logarithms of quantities are generally preferred.    \n",
         "\n",
-        "The task is now to build a time-series model for the _Quantity_ column. It is important to note that this dataset is comprised of many individual time-series - one for each unique combination of _Store_ and _Brand_. To distinguish the individual time-series, we thus define the **grain** - the columns whose values determine the boundaries between time-series: "
+        "The task is now to build a time-series model for the _Quantity_ column. It is important to note that this dataset is comprised of many individual time-series - one for each unique combination of _Store_ and _Brand_. To distinguish the individual time-series, we define the **time_series_id_column_names** - the columns whose values determine the boundaries between time-series: "
       ]
     },
     {
@@ -183,8 +193,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "grain_column_names = ['Store', 'Brand']\n",
-        "nseries = data.groupby(grain_column_names).ngroups\n",
+        "time_series_id_column_names = ['Store', 'Brand']\n",
+        "nseries = data.groupby(time_series_id_column_names).ngroups\n",
         "print('Data contains {0} individual time-series.'.format(nseries))"
       ]
     },
@@ -203,7 +213,7 @@
       "source": [
         "use_stores = [2, 5, 8]\n",
         "data_subset = data[data.Store.isin(use_stores)]\n",
-        "nseries = data_subset.groupby(grain_column_names).ngroups\n",
+        "nseries = data_subset.groupby(time_series_id_column_names).ngroups\n",
         "print('Data subset contains {0} individual time-series.'.format(nseries))"
       ]
     },
@@ -212,7 +222,7 @@
       "metadata": {},
       "source": [
         "### Data Splitting\n",
-        "We now split the data into a training and a testing set for later forecast evaluation. The test set will contain the final 20 weeks of observed sales for each time-series. The splits should be stratified by series, so we use a group-by statement on the grain columns."
+        "We now split the data into a training and a testing set for later forecast evaluation. The test set will contain the final 20 weeks of observed sales for each time-series. The splits should be stratified by series, so we use a group-by statement on the time series identifier columns."
       ]
     },
     {
@@ -223,15 +233,15 @@
       "source": [
         "n_test_periods = 20\n",
         "\n",
-        "def split_last_n_by_grain(df, n):\n",
-        "    \"\"\"Group df by grain and split on last n rows for each group.\"\"\"\n",
+        "def split_last_n_by_series_id(df, n):\n",
+        "    \"\"\"Group df by series identifiers and split on last n rows for each group.\"\"\"\n",
         "    df_grouped = (df.sort_values(time_column_name) # Sort by ascending time\n",
-        "                  .groupby(grain_column_names, group_keys=False))\n",
+        "                  .groupby(time_series_id_column_names, group_keys=False))\n",
         "    df_head = df_grouped.apply(lambda dfg: dfg.iloc[:-n])\n",
         "    df_tail = df_grouped.apply(lambda dfg: dfg.iloc[-n:])\n",
         "    return df_head, df_tail\n",
         "\n",
-        "train, test = split_last_n_by_grain(data_subset, n_test_periods)"
+        "train, test = split_last_n_by_series_id(data_subset, n_test_periods)"
       ]
     },
     {
@@ -276,7 +286,8 @@
       "outputs": [],
       "source": [
         "from azureml.core.dataset import Dataset\n",
-        "train_dataset = Dataset.Tabular.from_delimited_files(path=datastore.path('dataset/dominicks_OJ_train.csv'))"
+        "train_dataset = Dataset.Tabular.from_delimited_files(path=datastore.path('dataset/dominicks_OJ_train.csv'))\n",
+        "test_dataset = Dataset.Tabular.from_delimited_files(path=datastore.path('dataset/dominicks_OJ_test.csv'))"
       ]
     },
     {
@@ -297,11 +308,11 @@
         "For forecasting tasks, AutoML uses pre-processing and estimation steps that are specific to time-series. AutoML will undertake the following pre-processing steps:\n",
         "* Detect time-series sample frequency (e.g. hourly, daily, weekly) and create new records for absent time points to make the series regular. A regular time series has a well-defined frequency and has a value at every sample point in a contiguous time span \n",
         "* Impute missing values in the target (via forward-fill) and feature columns (using median column values) \n",
-        "* Create grain-based features to enable fixed effects across different series\n",
+        "* Create features based on time series identifiers to enable fixed effects across different series\n",
         "* Create time-based features to assist in learning seasonal patterns\n",
         "* Encode categorical variables to numeric quantities\n",
         "\n",
-        "In this notebook, AutoML will train a single, regression-type model across **all** time-series in a given training set. This allows the model to generalize across related series. If you're looking for training multiple models for different time-series, please check out the forecasting grouping notebook. \n",
+        "In this notebook, AutoML will train a single, regression-type model across **all** time-series in a given training set. This allows the model to generalize across related series. If you're looking for training multiple models for different time-series, please see the many-models notebook.\n",
         "\n",
         "You are almost ready to start an AutoML training job. First, we need to separate the target column from the rest of the DataFrame: "
       ]
@@ -319,15 +330,72 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Train\n",
+        "## Customization\n",
         "\n",
-        "The AutoMLConfig object defines the settings and data for an AutoML training job. Here, we set necessary inputs like the task type, the number of AutoML iterations to try, the training data, and cross-validation parameters. \n",
+        "The featurization customization in forecasting is an advanced feature in AutoML which allows our customers to change the default forecasting featurization behaviors and column types through `FeaturizationConfig`. The supported scenarios include:\n",
         "\n",
-        "For forecasting tasks, there are some additional parameters that can be set: the name of the column holding the date/time, the grain column names, and the maximum forecast horizon. A time column is required for forecasting, while the grain is optional. If a grain is not given, AutoML assumes that the whole dataset is a single time-series. We also pass a list of columns to drop prior to modeling. The _logQuantity_ column is completely correlated with the target quantity, so it must be removed to prevent a target leak.\n",
+        "1. Column purposes update: Override feature type for the specified column. Currently supports DateTime, Categorical and Numeric. This customization can be used in the scenario that the type of the column cannot correctly reflect its purpose. Some numerical columns, for instance, can be treated as Categorical columns which need to be converted to categorical while some can be treated as epoch timestamp which need to be converted to datetime. To tell our SDK to correctly preprocess these columns, a configuration need to be add with the columns and their desired types.\n",
+        "2. Transformer parameters update: Currently supports parameter change for Imputer only. User can customize imputation methods. The supported imputing methods for target column are constant and ffill (forward fill). The supported imputing methods for feature columns are mean, median, most frequent, constant and ffill (forward fill). This customization can be used for the scenario that our customers know which imputation methods fit best to the input data. For instance, some datasets use NaN to represent 0 which the correct behavior should impute all the missing value with 0. To achieve this behavior, these columns need to be configured as constant imputation with `fill_value` 0.\n",
+        "3. Drop columns: Columns to drop from being featurized. These usually are the columns which are leaky or the columns contain no useful data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "sample-featurizationconfig-remarks"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "featurization_config = FeaturizationConfig()\n",
+        "# Force the CPWVOL5 feature to be numeric type.\n",
+        "featurization_config.add_column_purpose('CPWVOL5', 'Numeric')\n",
+        "# Fill missing values in the target column, Quantity, with zeros.\n",
+        "featurization_config.add_transformer_params('Imputer', ['Quantity'], {\"strategy\": \"constant\", \"fill_value\": 0})\n",
+        "# Fill missing values in the INCOME column with median value.\n",
+        "featurization_config.add_transformer_params('Imputer', ['INCOME'], {\"strategy\": \"median\"})\n",
+        "# Fill missing values in the Price column with forward fill (last value carried forward).\n",
+        "featurization_config.add_transformer_params('Imputer', ['Price'], {\"strategy\": \"ffill\"})"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Forecasting Parameters\n",
+        "To define forecasting parameters for your experiment training, you can leverage the ForecastingParameters class. The table below details the forecasting parameter we will be passing into our experiment.\n",
         "\n",
-        "The forecast horizon is given in units of the time-series frequency; for instance, the OJ series frequency is weekly, so a horizon of 20 means that a trained model will estimate sales up-to 20 weeks beyond the latest date in the training data for each series. In this example, we set the maximum horizon to the number of samples per series in the test set (n_test_periods). Generally, the value of this parameter will be dictated by business needs. For example, a demand planning organizaion that needs to estimate the next month of sales would set the horizon accordingly. Please see the [energy_demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand) for more discussion of forecast horizon.\n",
         "\n",
-        "Finally, a note about the cross-validation (CV) procedure for time-series data. AutoML uses out-of-sample error estimates to select a best pipeline/model, so it is important that the CV fold splitting is done correctly. Time-series can violate the basic statistical assumptions of the canonical K-Fold CV strategy, so AutoML implements a [rolling origin validation](https://robjhyndman.com/hyndsight/tscv/) procedure to create CV folds for time-series data. To use this procedure, you just need to specify the desired number of CV folds in the AutoMLConfig object. It is also possible to bypass CV and use your own validation set by setting the *X_valid* and *y_valid* parameters of AutoMLConfig.\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**time_column_name**|The name of your time column.|\n",
+        "|**forecast_horizon**|The forecast horizon is how many periods forward you would like to forecast. This integer horizon is in units of the timeseries frequency (e.g. daily, weekly).|\n",
+        "|**time_series_id_column_names**|The column names used to uniquely identify the time series in data that has multiple rows with the same timestamp. If the time series identifiers are not defined, the data set is assumed to be one time series.|\n",
+        "|**freq**|Forecast frequency. This optional parameter represents the period with which the forecast is desired, for example, daily, weekly, yearly, etc. Use this parameter for the correction of time series containing irregular data points or for padding of short time series. The frequency needs to be a pandas offset alias. Please refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train<a id=\"train\"></a>\n",
+        "\n",
+        "The [AutoMLConfig](https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.automlconfig.automlconfig?view=azure-ml-py) object defines the settings and data for an AutoML training job. Here, we set necessary inputs like the task type, the number of AutoML iterations to try, the training data, and cross-validation parameters.\n",
+        "\n",
+        "For forecasting tasks, there are some additional parameters that can be set in the `ForecastingParameters` class: the name of the column holding the date/time, the timeseries id column names, and the maximum forecast horizon. A time column is required for forecasting, while the time_series_id is optional. If time_series_id columns are not given, AutoML assumes that the whole dataset is a single time-series. We also pass a list of columns to drop prior to modeling. The _logQuantity_ column is completely correlated with the target quantity, so it must be removed to prevent a target leak.\n",
+        "\n",
+        "The forecast horizon is given in units of the time-series frequency; for instance, the OJ series frequency is weekly, so a horizon of 20 means that a trained model will estimate sales up to 20 weeks beyond the latest date in the training data for each series. In this example, we set the forecast horizon to the number of samples per series in the test set (n_test_periods). Generally, the value of this parameter will be dictated by business needs. For example, a demand planning application that estimates the next month of sales should set the horizon according to suitable planning time-scales. Please see the [energy_demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand) for more discussion of forecast horizon.\n",
+        "\n",
+        "We note here that AutoML can sweep over two types of time-series models:\n",
+        "* Models that are trained for each series such as ARIMA and Facebook's Prophet.\n",
+        "* Models trained across multiple time-series using a regression approach.\n",
+        "\n",
+        "In the first case, AutoML loops over all time-series in your dataset and trains one model (e.g. AutoArima or Prophet, as the case may be) for each series. This can result in long runtimes to train these models if there are a lot of series in the data. One way to mitigate this problem is to fit models for different series in parallel if you have multiple compute cores available. To enable this behavior, set the `max_cores_per_iteration` parameter in your AutoMLConfig as shown in the example in the next cell. \n",
+        "\n",
+        "\n",
+        "Finally, a note about the cross-validation (CV) procedure for time-series data. AutoML uses out-of-sample error estimates to select a best pipeline/model, so it is important that the CV fold splitting is done correctly. Time-series can violate the basic statistical assumptions of the canonical K-Fold CV strategy, so AutoML implements a [rolling origin validation](https://robjhyndman.com/hyndsight/tscv/) procedure to create CV folds for time-series data. To use this procedure, you just need to specify the desired number of CV folds in the AutoMLConfig object. It is also possible to bypass CV and use your own validation set by setting the *validation_data* parameter of AutoMLConfig.\n",
         "\n",
         "Here is a summary of AutoMLConfig parameters used for training the OJ model:\n",
         "\n",
@@ -335,7 +403,7 @@
         "|-|-|\n",
         "|**task**|forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize.<br> Forecasting supports the following primary metrics <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>\n",
-        "|**experiment_timeout_minutes**|Experimentation timeout in minutes.|\n",
+        "|**experiment_timeout_hours**|Experimentation timeout in hours.|\n",
         "|**enable_early_stopping**|If early stopping is on, training will stop when the primary metric is no longer improving.|\n",
         "|**training_data**|Input dataset, containing both features and label column.|\n",
         "|**label_column_name**|The name of the label column.|\n",
@@ -344,10 +412,8 @@
         "|**enable_voting_ensemble**|Allow AutoML to create a Voting ensemble of the best performing models|\n",
         "|**enable_stack_ensemble**|Allow AutoML to create a Stack ensemble of the best performing models|\n",
         "|**debug_log**|Log file path for writing debugging information|\n",
-        "|**time_column_name**|Name of the datetime column in the input data|\n",
-        "|**grain_column_names**|Name(s) of the columns defining individual series in the input data|\n",
-        "|**drop_column_names**|Name(s) of columns to drop prior to modeling|\n",
-        "|**max_horizon**|Maximum desired forecast horizon in units of time-series frequency|"
+        "|**featurization**| 'auto' / 'off' / FeaturizationConfig Indicator for whether featurization step should be done automatically or not, or whether customized featurization should be used. Setting this enables AutoML to perform featurization on the input to handle *missing data*, and to perform some common *feature extraction*.|\n",
+        "|**max_cores_per_iteration**|Maximum number of cores to utilize per iteration. A value of -1 indicates all available cores should be used"
       ]
     },
     {
@@ -356,24 +422,27 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "time_series_settings = {\n",
-        "    'time_column_name': time_column_name,\n",
-        "    'grain_column_names': grain_column_names,\n",
-        "    'drop_column_names': ['logQuantity'],  # 'logQuantity' is a leaky feature, so we remove it.\n",
-        "    'max_horizon': n_test_periods\n",
-        "}\n",
+        "from azureml.automl.core.forecasting_parameters import ForecastingParameters\n",
+        "forecasting_parameters = ForecastingParameters(\n",
+        "    time_column_name=time_column_name,\n",
+        "    forecast_horizon=n_test_periods,\n",
+        "    time_series_id_column_names=time_series_id_column_names,\n",
+        "    freq='W-THU' # Set the forecast frequency to be weekly (start on each Thursday)\n",
+        ")\n",
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',\n",
         "                             debug_log='automl_oj_sales_errors.log',\n",
         "                             primary_metric='normalized_mean_absolute_error',\n",
-        "                             experiment_timeout_minutes=15,\n",
+        "                             experiment_timeout_hours=0.25,\n",
         "                             training_data=train_dataset,\n",
         "                             label_column_name=target_column_name,\n",
         "                             compute_target=compute_target,\n",
         "                             enable_early_stopping=True,\n",
+        "                             featurization=featurization_config,\n",
         "                             n_cross_validations=3,\n",
         "                             verbosity=logging.INFO,\n",
-        "                             **time_series_settings)"
+        "                             max_cores_per_iteration=-1,\n",
+        "                             forecasting_parameters=forecasting_parameters)"
       ]
     },
     {
@@ -381,7 +450,7 @@
       "metadata": {},
       "source": [
         "You can now submit a new training run. Depending on the data and number of iterations this operation may take several minutes.\n",
-        "Information from each iteration will be printed to the console."
+        "Information from each iteration will be printed to the console.  Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
       ]
     },
     {
@@ -390,8 +459,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "remote_run = experiment.submit(automl_config, show_output=False)\n",
-        "remote_run"
+        "remote_run = experiment.submit(automl_config, show_output=False)"
       ]
     },
     {
@@ -426,9 +494,9 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# Forecasting\n",
+        "## Transparency\n",
         "\n",
-        "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. First, we remove the target values from the test set:"
+        "View updated featurization summary"
       ]
     },
     {
@@ -437,8 +505,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_test = test\n",
-        "y_test = X_test.pop(target_column_name).values"
+        "custom_featurizer = fitted_model.named_steps['timeseriestransformer']"
       ]
     },
     {
@@ -447,16 +514,18 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_test.head()"
+        "custom_featurizer.get_featurization_summary()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "To produce predictions on the test set, we need to know the feature values at all dates in the test set. This requirement is somewhat reasonable for the OJ sales data since the features mainly consist of price, which is usually set in advance, and customer demographics which are approximately constant for each store over the 20 week forecast horizon in the testing data. \n",
+        "# Forecast<a id=\"forecast\"></a>\n",
         "\n",
-        "We will first create a query `y_query`, which is aligned index-for-index to `X_test`. This is a vector of target values where each `NaN` serves the function of the question mark to be replaced by forecast. Passing definite values in the `y` argument allows the `forecast` function to make predictions on data that does not immediately follow the train data which contains `y`. In each grain, the last time point where the model sees a definite value of `y` is that grain's _forecast origin_."
+        "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. We will do batch scoring on the test dataset which should have the same schema as training dataset.\n",
+        "\n",
+        "The inference will run on a remote compute. In this example, it will re-use the training compute."
       ]
     },
     {
@@ -465,24 +534,40 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Replace ALL values in y by NaN.\n",
-        "# The forecast origin will be at the beginning of the first forecast period.\n",
-        "# (Which is the same time as the end of the last training period.)\n",
-        "y_query = y_test.copy().astype(np.float)\n",
-        "y_query.fill(np.nan)\n",
-        "# The featurized data, aligned to y, will also be returned.\n",
-        "# This contains the assumptions that were made in the forecast\n",
-        "# and helps align the forecast to the original data\n",
-        "y_predictions, X_trans = fitted_model.forecast(X_test, y_query)"
+        "test_experiment = Experiment(ws, experiment_name + \"_inference\")"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "If you are used to scikit pipelines, perhaps you expected `predict(X_test)`. However, forecasting requires a more general interface that also supplies the past target `y` values. Please use `forecast(X,y)` as `predict(X)` is reserved for internal purposes on forecasting models.\n",
+        "### Retreiving forecasts from the model\n",
+        "We have created a function called `run_forecast` that submits the test data to the best model determined during the training run and retrieves forecasts. This function uses a helper script `forecasting_script` which is uploaded and expecuted on the remote compute."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "To produce predictions on the test set, we need to know the feature values at all dates in the test set. This requirement is somewhat reasonable for the OJ sales data since the features mainly consist of price, which is usually set in advance, and customer demographics which are approximately constant for each store over the 20 week forecast horizon in the testing data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from run_forecast import run_remote_inference\n",
+        "remote_run_infer = run_remote_inference(test_experiment=test_experiment, \n",
+        "                                        compute_target=compute_target,\n",
+        "                                        train_run=best_run,\n",
+        "                                        test_dataset=test_dataset,\n",
+        "                                        target_column_name=target_column_name)\n",
+        "remote_run_infer.wait_for_completion(show_output=False)\n",
         "\n",
-        "The [energy demand forecasting notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand) demonstrates the use of the forecast function in more detail in the context of using lags and rolling window features. "
+        "# download the forecast file to the local machine\n",
+        "remote_run_infer.download_file('outputs/predictions.csv', 'predictions.csv')"
       ]
     },
     {
@@ -491,9 +576,9 @@
       "source": [
         "# Evaluate\n",
         "\n",
-        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE). \n",
+        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE). For more metrics that can be used for evaluation after training, please see [supported metrics](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#regressionforecasting-metrics), and [how to calculate residuals](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#residuals).\n",
         "\n",
-        "It is a good practice to always align the output explicitly to the input, as the count and order of the rows may have changed during transformations that span multiple rows."
+        "We'll add predictions and actuals into a single dataframe for convenience in calculating the metrics."
       ]
     },
     {
@@ -502,9 +587,9 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from forecasting_helper import align_outputs\n",
-        "\n",
-        "df_all = align_outputs(y_predictions, X_trans, X_test, y_test, target_column_name)"
+        "# load forecast data frame\n",
+        "fcst_df = pd.read_csv('predictions.csv', parse_dates=[time_column_name])\n",
+        "fcst_df.head()"
       ]
     },
     {
@@ -513,16 +598,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.automl.core._vendor.automl.client.core.common import metrics\n",
+        "from azureml.automl.core.shared import constants\n",
+        "from azureml.automl.runtime.shared.score import scoring\n",
         "from matplotlib import pyplot as plt\n",
-        "from automl.client.core.common import constants\n",
         "\n",
-        "# use automl metrics module\n",
-        "scores = metrics.compute_metrics_regression(\n",
-        "    df_all['predicted'],\n",
-        "    df_all[target_column_name],\n",
-        "    list(constants.Metric.SCALAR_REGRESSION_SET),\n",
-        "    None, None, None)\n",
+        "# use automl scoring module\n",
+        "scores = scoring.score_regression(\n",
+        "    y_test=fcst_df[target_column_name],\n",
+        "    y_pred=fcst_df['predicted'],\n",
+        "    metrics=list(constants.Metric.SCALAR_REGRESSION_SET))\n",
         "\n",
         "print(\"[Test data scores]\\n\")\n",
         "for key, value in scores.items():    \n",
@@ -530,8 +614,8 @@
         "    \n",
         "# Plot outputs\n",
         "%matplotlib inline\n",
-        "test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], color='b')\n",
-        "test_test = plt.scatter(df_all[target_column_name], df_all[target_column_name], color='g')\n",
+        "test_pred = plt.scatter(fcst_df[target_column_name], fcst_df['predicted'], color='b')\n",
+        "test_test = plt.scatter(fcst_df[target_column_name], fcst_df[target_column_name], color='g')\n",
         "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
         "plt.show()"
       ]
@@ -540,7 +624,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# Operationalize"
+        "# Operationalize<a id=\"operationalize\"></a>"
       ]
     },
     {
@@ -603,8 +687,8 @@
         "inference_config = InferenceConfig(environment = best_run.get_environment(), \n",
         "                                   entry_script = script_file_name)\n",
         "\n",
-        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
-        "                                               memory_gb = 2, \n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 2, \n",
+        "                                               memory_gb = 4, \n",
         "                                               tags = {'type': \"automl-forecasting\"},\n",
         "                                               description = \"Automl forecasting sample service\")\n",
         "\n",
@@ -638,14 +722,13 @@
       "outputs": [],
       "source": [
         "import json\n",
-        "# The request data frame needs to have y_query column which corresponds to query.\n",
-        "X_query = X_test.copy()\n",
-        "X_query['y_query'] = y_query\n",
+        "X_query = test.copy()\n",
+        "X_query.pop(target_column_name)\n",
         "# We have to convert datetime to string, because Timestamps cannot be serialized to JSON.\n",
         "X_query[time_column_name] = X_query[time_column_name].astype(str)\n",
         "# The Service object accept the complex dictionary, which is internally converted to JSON string.\n",
         "# The section 'data' contains the data frame in the form of dictionary.\n",
-        "test_sample = json.dumps({'data': X_query.to_dict(orient='records')})\n",
+        "test_sample = json.dumps({\"data\": json.loads(X_query.to_json(orient=\"records\"))})\n",
         "response = aci_service.run(input_data = test_sample)\n",
         "# translate from networkese to datascientese\n",
         "try: \n",
@@ -687,13 +770,13 @@
   "metadata": {
     "authors": [
       {
-        "name": "erwright"
+        "name": "jialiu"
       }
     ],
     "category": "tutorial",
     "celltoolbar": "Raw Cell Format",
     "compute": [
-      "remote"
+      "Remote"
     ],
     "datasets": [
       "Orange Juice Sales"
@@ -722,10 +805,13 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.7"
+      "version": "3.6.9"
     },
+    "tags": [
+      "None"
+    ],
     "task": "Forecasting"
   },
   "nbformat": 4,
-  "nbformat_minor": 2
+  "nbformat_minor": 4
 }

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.yml

@@ -1,11 +1,4 @@
 name: auto-ml-forecasting-orange-juice-sales
 dependencies:
-- fbprophet==0.5
-- py-xgboost<=0.80
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - statsmodels

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/forecasting_helper.py

@@ -1,98 +0,0 @@
-import pandas as pd
-import numpy as np
-from pandas.tseries.frequencies import to_offset
-
-
-def align_outputs(y_predicted, X_trans, X_test, y_test, target_column_name,
-                  predicted_column_name='predicted',
-                  horizon_colname='horizon_origin'):
-    """
-    Demonstrates how to get the output aligned to the inputs
-    using pandas indexes. Helps understand what happened if
-    the output's shape differs from the input shape, or if
-    the data got re-sorted by time and grain during forecasting.
-
-    Typical causes of misalignment are:
-    * we predicted some periods that were missing in actuals -> drop from eval
-    * model was asked to predict past max_horizon -> increase max horizon
-    * data at start of X_test was needed for lags -> provide previous periods
-    """
-
-    if (horizon_colname in X_trans):
-        df_fcst = pd.DataFrame({predicted_column_name: y_predicted,
-                                horizon_colname: X_trans[horizon_colname]})
-    else:
-        df_fcst = pd.DataFrame({predicted_column_name: y_predicted})
-
-    # y and X outputs are aligned by forecast() function contract
-    df_fcst.index = X_trans.index
-
-    # align original X_test to y_test
-    X_test_full = X_test.copy()
-    X_test_full[target_column_name] = y_test
-
-    # X_test_full's index does not include origin, so reset for merge
-    df_fcst.reset_index(inplace=True)
-    X_test_full = X_test_full.reset_index().drop(columns='index')
-    together = df_fcst.merge(X_test_full, how='right')
-
-    # drop rows where prediction or actuals are nan
-    # happens because of missing actuals
-    # or at edges of time due to lags/rolling windows
-    clean = together[together[[target_column_name,
-                               predicted_column_name]].notnull().all(axis=1)]
-    return(clean)
-
-
-def do_rolling_forecast(fitted_model, X_test, y_test, target_column_name, time_column_name, max_horizon, freq='D'):
-    """
-    Produce forecasts on a rolling origin over the given test set.
-
-    Each iteration makes a forecast for the next 'max_horizon' periods
-    with respect to the current origin, then advances the origin by the
-    horizon time duration. The prediction context for each forecast is set so
-    that the forecaster uses the actual target values prior to the current
-    origin time for constructing lag features.
-
-    This function returns a concatenated DataFrame of rolling forecasts.
-     """
-    df_list = []
-    origin_time = X_test[time_column_name].min()
-    while origin_time <= X_test[time_column_name].max():
-        # Set the horizon time - end date of the forecast
-        horizon_time = origin_time + max_horizon * to_offset(freq)
-
-        # Extract test data from an expanding window up-to the horizon
-        expand_wind = (X_test[time_column_name] < horizon_time)
-        X_test_expand = X_test[expand_wind]
-        y_query_expand = np.zeros(len(X_test_expand)).astype(np.float)
-        y_query_expand.fill(np.NaN)
-
-        if origin_time != X_test[time_column_name].min():
-            # Set the context by including actuals up-to the origin time
-            test_context_expand_wind = (X_test[time_column_name] < origin_time)
-            context_expand_wind = (
-                X_test_expand[time_column_name] < origin_time)
-            y_query_expand[context_expand_wind] = y_test[
-                test_context_expand_wind]
-
-        # Make a forecast out to the maximum horizon
-        y_fcst, X_trans = fitted_model.forecast(X_test_expand, y_query_expand)
-
-        # Align forecast with test set for dates within the
-        # current rolling window
-        trans_tindex = X_trans.index.get_level_values(time_column_name)
-        trans_roll_wind = (trans_tindex >= origin_time) & (
-            trans_tindex < horizon_time)
-        test_roll_wind = expand_wind & (
-            X_test[time_column_name] >= origin_time)
-        df_list.append(align_outputs(y_fcst[trans_roll_wind],
-                                     X_trans[trans_roll_wind],
-                                     X_test[test_roll_wind],
-                                     y_test[test_roll_wind],
-                                     target_column_name))
-
-        # Advance the origin time
-        origin_time = horizon_time
-
-    return pd.concat(df_list, ignore_index=True)

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/forecasting_script.py

@@ -0,0 +1,89 @@
+"""
+This is the script that is executed on the compute instance. It relies
+on the model.pkl file which is uploaded along with this script to the
+compute instance.
+"""
+
+import argparse
+import pandas as pd
+import numpy as np
+from azureml.core import Dataset, Run
+from azureml.automl.core.shared.constants import TimeSeriesInternal
+from sklearn.externals import joblib
+from pandas.tseries.frequencies import to_offset
+
+
+def align_outputs(y_predicted, X_trans, X_test, y_test, target_column_name,
+                  predicted_column_name='predicted',
+                  horizon_colname='horizon_origin'):
+    """
+    Demonstrates how to get the output aligned to the inputs
+    using pandas indexes. Helps understand what happened if
+    the output's shape differs from the input shape, or if
+    the data got re-sorted by time and grain during forecasting.
+
+    Typical causes of misalignment are:
+    * we predicted some periods that were missing in actuals -> drop from eval
+    * model was asked to predict past max_horizon -> increase max horizon
+    * data at start of X_test was needed for lags -> provide previous periods
+    """
+
+    if (horizon_colname in X_trans):
+        df_fcst = pd.DataFrame({predicted_column_name: y_predicted,
+                                horizon_colname: X_trans[horizon_colname]})
+    else:
+        df_fcst = pd.DataFrame({predicted_column_name: y_predicted})
+
+    # y and X outputs are aligned by forecast() function contract
+    df_fcst.index = X_trans.index
+
+    # align original X_test to y_test
+    X_test_full = X_test.copy()
+    X_test_full[target_column_name] = y_test
+
+    # X_test_full's index does not include origin, so reset for merge
+    df_fcst.reset_index(inplace=True)
+    X_test_full = X_test_full.reset_index().drop(columns='index')
+    together = df_fcst.merge(X_test_full, how='right')
+
+    # drop rows where prediction or actuals are nan
+    # happens because of missing actuals
+    # or at edges of time due to lags/rolling windows
+    clean = together[together[[target_column_name,
+                               predicted_column_name]].notnull().all(axis=1)]
+    return(clean)
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument(
+    '--target_column_name', type=str, dest='target_column_name',
+    help='Target Column Name')
+parser.add_argument(
+    '--test_dataset', type=str, dest='test_dataset',
+    help='Test Dataset')
+
+args = parser.parse_args()
+target_column_name = args.target_column_name
+test_dataset_id = args.test_dataset
+
+run = Run.get_context()
+ws = run.experiment.workspace
+
+# get the input dataset by id
+test_dataset = Dataset.get_by_id(ws, id=test_dataset_id)
+
+X_test = test_dataset.to_pandas_dataframe().reset_index(drop=True)
+y_test = X_test.pop(target_column_name).values
+
+# generate forecast
+fitted_model = joblib.load('model.pkl')
+y_predictions, X_trans = fitted_model.forecast(X_test)
+
+# align output
+df_all = align_outputs(y_predictions, X_trans, X_test, y_test, target_column_name)
+
+file_name = 'outputs/predictions.csv'
+export_csv = df_all.to_csv(file_name, header=True, index=False)  # added Index
+
+# Upload the predictions into artifacts
+run.upload_file(name=file_name, path_or_stream=file_name)

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/metrics_helper.py

@@ -1,22 +0,0 @@
-import pandas as pd
-import numpy as np
-
-
-def APE(actual, pred):
-    """
-    Calculate absolute percentage error.
-    Returns a vector of APE values with same length as actual/pred.
-    """
-    return 100 * np.abs((actual - pred) / actual)
-
-
-def MAPE(actual, pred):
-    """
-    Calculate mean absolute percentage error.
-    Remove NA and values where actual is close to zero
-    """
-    not_na = ~(np.isnan(actual) | np.isnan(pred))
-    not_zero = ~np.isclose(actual, 0.0)
-    actual_safe = actual[not_na & not_zero]
-    pred_safe = pred[not_na & not_zero]
-    return np.mean(APE(actual_safe, pred_safe))

how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/run_forecast.py

@@ -0,0 +1,38 @@
+import os
+import shutil
+from azureml.core import ScriptRunConfig
+
+
+def run_remote_inference(test_experiment, compute_target, train_run,
+                         test_dataset, target_column_name, inference_folder='./forecast'):
+    # Create local directory to copy the model.pkl and forecsting_script.py files into.
+    # These files will be uploaded to and executed on the compute instance.
+    os.makedirs(inference_folder, exist_ok=True)
+    shutil.copy('forecasting_script.py', inference_folder)
+
+    train_run.download_file('outputs/model.pkl',
+                            os.path.join(inference_folder, 'model.pkl'))
+
+    inference_env = train_run.get_environment()
+
+    config = ScriptRunConfig(source_directory=inference_folder,
+                             script='forecasting_script.py',
+                             arguments=['--target_column_name',
+                                        target_column_name,
+                                        '--test_dataset',
+                                        test_dataset.as_named_input(test_dataset.name)],
+                             compute_target=compute_target,
+                             environment=inference_env)
+
+    run = test_experiment.submit(config,
+                                 tags={'training_run_id':
+                                       train_run.id,
+                                       'run_algorithm':
+                                       train_run.properties['run_algorithm'],
+                                       'valid_score':
+                                       train_run.properties['score'],
+                                       'primary_metric':
+                                       train_run.properties['primary_metric']})
+
+    run.log("run_algorithm", run.tags['run_algorithm'])
+    return run

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/auto-ml-forecasting-univariate-recipe-experiment-settings.ipynb

@@ -0,0 +1,492 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/1_determine_experiment_settings.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "In this notebook we will explore the univaraite time-series data to determine the settings for an automated ML experiment. We will follow the thought process depicted in the following diagram:<br/>\n",
+        "![Forecasting after training](figures/univariate_settings_map_20210408.jpg)\n",
+        "\n",
+        "The objective is to answer the following questions:\n",
+        "\n",
+        "<ol>\n",
+        "    <li>Is there a seasonal pattern in the data? </li>\n",
+        "        <ul style=\"margin-top:-1px; list-style-type:none\"> \n",
+        "            <li> Importance: If we are able to detect regular seasonal patterns, the forecast accuracy may be improved by extracting these patterns and including them as features into the model.  </li>\n",
+        "        </ul>\n",
+        "    <li>Is the data stationary? </li>\n",
+        "        <ul style=\"margin-top:-1px; list-style-type:none\"> \n",
+        "            <li> Importance: In the absense of features that capture trend behavior, ML models (regression and tree based) are not well equiped to predict stochastic trends. Working with stationary data solves this problem.  </li>\n",
+        "        </ul>\n",
+        "    <li>Is there a detectable auto-regressive pattern in the stationary data? </li>\n",
+        "        <ul style=\"margin-top:-1px; list-style-type:none\"> \n",
+        "            <li> Importance: The accuracy of ML models can be improved if serial correlation is modeled by including lags of the dependent/target varaible as features. Including target lags in every experiment by default will result in a regression in accuracy scores if such setting is not warranted.  </li>\n",
+        "        </ul>\n",
+        "</ol>\n",
+        "\n",
+        "The answers to these questions will help determine the appropriate settings for the automated ML experiment.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import warnings\n",
+        "import pandas as pd\n",
+        "\n",
+        "from statsmodels.graphics.tsaplots import plot_acf, plot_pacf\n",
+        "import matplotlib.pyplot as plt\n",
+        "from pandas.plotting import register_matplotlib_converters\n",
+        "register_matplotlib_converters()  # fixes the future warning issue\n",
+        "\n",
+        "from helper_functions import unit_root_test_wrapper\n",
+        "from statsmodels.tools.sm_exceptions import InterpolationWarning\n",
+        "warnings.simplefilter('ignore', InterpolationWarning)\n",
+        "\n",
+        "\n",
+        "# set printing options\n",
+        "pd.set_option('display.max_columns', 500)\n",
+        "pd.set_option('display.width', 1000)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# load data\n",
+        "main_data_loc = 'data'\n",
+        "train_file_name = 'S4248SM144SCEN.csv'\n",
+        "\n",
+        "TARGET_COLNAME = 'S4248SM144SCEN'\n",
+        "TIME_COLNAME = 'observation_date'\n",
+        "COVID_PERIOD_START = '2020-03-01'\n",
+        "\n",
+        "df = pd.read_csv(os.path.join(main_data_loc, train_file_name))\n",
+        "df[TIME_COLNAME] = pd.to_datetime(df[TIME_COLNAME], format='%Y-%m-%d')\n",
+        "df.sort_values(by=TIME_COLNAME, inplace=True)\n",
+        "df.set_index(TIME_COLNAME, inplace=True)\n",
+        "df.head(2)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# plot the entire dataset\n",
+        "fig, ax = plt.subplots(figsize=(6,2), dpi=180)\n",
+        "ax.plot(df)\n",
+        "ax.title.set_text('Original Data Series')\n",
+        "locs, labels = plt.xticks()\n",
+        "plt.xticks(rotation=45)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The graph plots the alcohol sales in the United States. Because the data is trending, it can be difficult to see cycles, seasonality or other interestng behaviors due to the scaling issues. For example, if there is a seasonal pattern, which we will discuss later, we cannot see them on the trending data. In such case, it is worth plotting the same data in first differences."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# plot the entire dataset in first differences\n",
+        "fig, ax = plt.subplots(figsize=(6,2), dpi=180)\n",
+        "ax.plot(df.diff().dropna())\n",
+        "ax.title.set_text('Data in first differences')\n",
+        "locs, labels = plt.xticks()\n",
+        "plt.xticks(rotation=45)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "In the previous plot we observe that the data is more volatile towards the end of the series. This period coincides with the Covid-19 period, so we will exclude it from our experiment. Since in this example there are no user-provided features it is hard to make an argument that a model trained on the less volatile pre-covid data will be able to accurately predict the covid period."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# 1. Seasonality\n",
+        "\n",
+        "#### Questions that need to be answered in this section:\n",
+        "1. Is there a seasonality?\n",
+        "2. If it's seasonal, does the data exhibit a trend (up or down)?\n",
+        "\n",
+        "It is hard to visually detect seasonality when the data is trending. The reason being is scale of seasonal fluctuations is dwarfed by the range of the trend in the data. One way to deal with this is to de-trend the data by taking the first differences. We will discuss this in more detail in the next section."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# plot the entire dataset in first differences\n",
+        "fig, ax = plt.subplots(figsize=(6,2), dpi=180)\n",
+        "ax.plot(df.diff().dropna())\n",
+        "ax.title.set_text('Data in first differences')\n",
+        "locs, labels = plt.xticks()\n",
+        "plt.xticks(rotation=45)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "For the  next plot, we will exclude the Covid period again. We will also shorten the length of data because plotting a very long time series may prevent us from seeing seasonal patterns, if there are any, because the plot may look like a random walk."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# remove COVID period\n",
+        "df = df[:COVID_PERIOD_START]\n",
+        "\n",
+        "# plot the entire dataset in first differences\n",
+        "fig, ax = plt.subplots(figsize=(6,2), dpi=180)\n",
+        "ax.plot(df['2015-01-01':].diff().dropna())\n",
+        "ax.title.set_text('Data in first differences')\n",
+        "locs, labels = plt.xticks()\n",
+        "plt.xticks(rotation=45)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<p style=\"font-size:150%; color:blue\"> Conclusion </p>\n",
+        "\n",
+        "Visual examination does not suggest clear seasonal patterns. We will set the STL_TYPE = None, and we will move to the next section that examines stationarity. \n",
+        "\n",
+        "\n",
+        "Say, we are working with a different data set that shows clear patterns of seasonality, we have several options for setting the settings:is hard to say which option will work best in your case, hence you will need to run both options to see which one results in more accurate forecasts. </li>\n",
+        "<ol>\n",
+        "     <li> If the data does not appear to be trending, set DIFFERENCE_SERIES=False, TARGET_LAGS=None and STL_TYPE = \"season\" </li>\n",
+        "     <li> If the data appears to be trending, consider one of the following two settings:\n",
+        "          <ul>\n",
+        "               <ol type=\"a\">\n",
+        "                    <li> DIFFERENCE_SERIES=True, TARGET_LAGS=None and STL_TYPE = \"season\", or </li>\n",
+        "                    <li> DIFFERENCE_SERIES=False, TARGET_LAGS=None and STL_TYPE = \"trend_season\" </li>\n",
+        "               </ol>\n",
+        "               <li> In the first case, by taking first differences we are removing stochastic trend, but we do not remove seasonal patterns. In the second case, we do not remove the stochastic trend and it can be captured by the trend component of the STL decomposition. It is hard to say which option will work best in your case, hence you will need to run both options to see which one results in more accurate forecasts. </li>\n",
+        "          </ul>\n",
+        "</ol>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# 2. Stationarity\n",
+        "If the data does not exhibit seasonal patterns, we would like to see if the data is non-stationary. Particularly, we want to see if there is a clear trending behavior. If such behavior is observed, we would like to first difference the data and examine the plot of an auto-correlation function (ACF) known as correlogram. If the data is seasonal, differencing it will not get rid off the seasonality and this will be shown on the correlogram as well.\n",
+        "\n",
+        "<ul>\n",
+        "    <li> Question: What is stationarity and how to we detect it? </li>\n",
+        "        <ul>\n",
+        "            <li> This is a fairly complex topic. Please read the following <a href=\"https://otexts.com/fpp2/stationarity.html\"> link </a> for a high level discussion on this subject. </li>\n",
+        "            <li> Simply put, we are looking for scenario when examining the time series plots the mean of the series is roughly the same, regardless which time interval you pick to compute it. Thus, trending and seasonal data are examples of non-stationary series. </li>\n",
+        "    </ul>\n",
+        "</ul>\n",
+        "\n",
+        "\n",
+        "<ul>\n",
+        "    <li> Question: Why do want to work with stationary data?</li>\n",
+        "    <ul> \n",
+        "        <li> In the absence of features that capture stochastic trends, the ML models that use (deterministic) time based features (hour of the day, day of the week, month of the year, etc) cannot capture such trends, and will over or under predict depending on the behavior of the time series. By working with stationary data, we eliminate the need to predict such trends, which improves the forecast accuracy. Classical time series models such as Arima and Exponential Smoothing handle non-stationary series by design and do not need such transformations. By differencing the data we are still able to run the same family of models. </li>\n",
+        "    </ul>\n",
+        "</ul>\n",
+        "\n",
+        "#### Questions that need to be answered in this section:\n",
+        "<ol> \n",
+        "    <li> Is the data stationary? </li>\n",
+        "    <li> Does the stationarized data (either the original or the differenced series) exhibit a clear auto-regressive pattern?</li>\n",
+        "</ol>\n",
+        "\n",
+        "To answer the first question, we run a series of tests (we call them unit root tests)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# unit root tests\n",
+        "test = unit_root_test_wrapper(df[TARGET_COLNAME])\n",
+        "print('---------------', '\\n')\n",
+        "print('Summary table', '\\n', test['summary'], '\\n')\n",
+        "print('Is the {} series stationary?: {}'.format(TARGET_COLNAME, test['stationary']))\n",
+        "print('---------------', '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "In the previous cell, we ran a series of unit root tests. The summary table contains the following columns:\n",
+        "<ul> \n",
+        "    <li> test_name is the name of the test.\n",
+        "        <ul> \n",
+        "            <li> ADF: Augmented Dickey-Fuller test </li>\n",
+        "            <li> KPSS: Kwiatkowski-Phillips\u00e2\u20ac\u201cSchmidt\u00e2\u20ac\u201cShin test </li>\n",
+        "            <li> PP: Phillips-Perron test\n",
+        "            <li> ADF GLS: Augmented Dickey-Fuller using generalized least squares method </li>\n",
+        "            <li> AZ: Andrews-Zivot test </li>\n",
+        "        </ul>\n",
+        "    <li> statistic: test statistic </li>\n",
+        "    <li> crit_val: critical value of the test statistic </li>\n",
+        "    <li> p_val: p-value of the test statistic. If the p-val is less than 0.05, the null hypothesis is rejected. </li>\n",
+        "    <li> stationary: is the series stationary based on the test result? </li>\n",
+        "    <li> Null hypothesis: what is being tested. Notice, some test such as ADF and PP assume the process has a unit root and looks for evidence to reject this hypothesis. Other tests, ex.g: KPSS, assumes the process is stationary and looks for evidence to reject such claim.\n",
+        "</ul>\n",
+        "\n",
+        "Each of the tests shows that the original time series is non-stationary. The final decision is based on the majority rule. If, there is a split decision, the algorithm will claim it is stationary. We run a series of tests because each test by itself may not be accurate. In many cases when there are conflicting test results, the user needs to make determination if the series is stationary or not.\n",
+        "\n",
+        "Since we found the series to be non-stationary, we will difference it and then test if the differenced series is stationary."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# unit root tests\n",
+        "test = unit_root_test_wrapper(df[TARGET_COLNAME].diff().dropna())\n",
+        "print('---------------', '\\n')\n",
+        "print('Summary table', '\\n', test['summary'], '\\n')\n",
+        "print('Is the {} series stationary?: {}'.format(TARGET_COLNAME, test['stationary']))\n",
+        "print('---------------', '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Four out of five tests show that the series in first differences is stationary. Notice that this decision is not unanimous. Next, let's plot the original series in first-differences to illustrate the difference between non-stationary (unit root) process vs the stationary one."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# plot original and stationary data\n",
+        "fig = plt.figure(figsize=(10,10))\n",
+        "ax1 = fig.add_subplot(211)\n",
+        "ax1.plot(df[TARGET_COLNAME], '-b')\n",
+        "ax2 = fig.add_subplot(212)\n",
+        "ax2.plot(df[TARGET_COLNAME].diff().dropna(), '-b')\n",
+        "ax1.title.set_text('Original data')\n",
+        "ax2.title.set_text('Data in first differences')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "If you were asked a question \"What is the mean of the series before and after 2008?\", for the series titled \"Original data\" the mean values will be significantly different. This implies that the first moment of the series (in this case, it is the mean) is time dependent, i.e., mean changes depending on the interval one is looking at. Thus, the series is deemed to be non-stationary. On the other hand, for the series titled \"Data in first differences\" the means for both periods are roughly the same. Hence, the first moment is time invariant; meaning it does not depend on the interval of time one is looking at. In this example it is easy to visually distinguish between stationary and non-stationary data. Often this distinction is not easy to make, therefore we rely on the statistical tests described above to help us make an informed decision. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<p style=\"font-size:150%; color:blue\"> Conclusion </p>\n",
+        "Since we found the original process to be non-stationary (contains unit root), we will have to model the data in first differences. As a result, we will set the DIFFERENCE_SERIES parameter to True."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# 3 Check if there is a clear autoregressive pattern\n",
+        "We need to determine if we should include lags of the target variable as features in order to improve forecast accuracy. To do this, we will examine the ACF and partial ACF (PACF) plots of the stationary series. In our case, it is a series in first diffrences.\n",
+        "\n",
+        "<ul>\n",
+        "    <li> Question: What is an Auto-regressive pattern? What are we looking for? </li>\n",
+        "    <ul style=\"list-style-type:none;\">\n",
+        "        <li> We are looking for a classical profiles for an AR(p) process such as an exponential decay of an ACF and a the first $p$ significant lags of the PACF. For a more detailed explanation of ACF and PACF please refer to the appendix at the end of this notebook. For illustration purposes, let's examine the ACF/PACF profiles of the simulated data that follows a second order auto-regressive process, abbreviated as an AR(2). <li/>\n",
+        "        <li><img src=\"figures/ACF_PACF_for_AR2.png\" class=\"img_class\">\n",
+        "            <br/>\n",
+        "            The lag order is on the x-axis while the auto- and partial-correlation coefficients are on the y-axis. Vertical lines that are outside the shaded area represent statistically significant lags. Notice, the ACF function decays to zero and the PACF shows 2 significant spikes (we ignore the first spike for lag 0 in both plots since the linear relationship of any series with itself is always 1). <li/>\n",
+        "    </ul>\n",
+        "<ul/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<ul>\n",
+        "    <li> Question: What do I do if I observe an auto-regressive behavior? </li>\n",
+        "    <ul style=\"list-style-type:none;\">\n",
+        "        <li> If such behavior is observed, we might improve the forecast accuracy by enabling the target lags feature in AutoML. There are a few options of doing this </li>\n",
+        "            <ol>\n",
+        "                <li> Set the target lags parameter to 'auto', or </li>\n",
+        "                <li> Specify the list of lags you want to include. Ex.g: target_lags = [1,2,5] </li>\n",
+        "            </ol>\n",
+        "    </ul>\n",
+        "    <br/>\n",
+        "    <li> Next, let's examine the ACF and PACF plots of the stationary target variable (depicted below). Here, we do not see a decay in the ACF, instead we see a decay in PACF. It is hard to make an argument the the target variable exhibits auto-regressive behavior. </li>\n",
+        "    </ul>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Plot the ACF/PACF for the series in differences\n",
+        "fig, ax = plt.subplots(1,2,figsize=(10,5))\n",
+        "plot_acf(df[TARGET_COLNAME].diff().dropna().values.squeeze(), ax=ax[0])\n",
+        "plot_pacf(df[TARGET_COLNAME].diff().dropna().values.squeeze(), ax=ax[1])\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<p style=\"font-size:150%; color:blue\"> Conclusion </p>\n",
+        "Since we do not see a clear indication of an AR(p) process, we will not be using target lags and will set the TARGET_LAGS parameter to None."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<p style=\"font-size:150%; color:blue; font-weight: bold\"> AutoML Experiment Settings </p>\n",
+        "Based on the analysis performed, we should try the following settings for the AutoML experiment and use them in the \"2_run_experiment\" notebook.\n",
+        "<ul>\n",
+        "    <li> STL_TYPE=None </li>\n",
+        "    <li> DIFFERENCE_SERIES=True </li>\n",
+        "    <li> TARGET_LAGS=None </li>\n",
+        "</ul>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Appendix: ACF, PACF and Lag Selection\n",
+        "To do this, we will examine the ACF and partial ACF (PACF) plots of the differenced series. \n",
+        "\n",
+        "<ul>\n",
+        "    <li> Question: What is the ACF? </li>\n",
+        "    <ul style=\"list-style-type:none;\">\n",
+        "        <li> To understand the ACF, first let's look at the correlation coefficient $\\rho_{xz}$\n",
+        "            \\begin{equation}\n",
+        "            \\rho_{xz} = \\frac{\\sigma_{xz}}{\\sigma_{x} \\sigma_{zy}}\n",
+        "            \\end{equation}\n",
+        "        </li>\n",
+        "        where $\\sigma_{xzy}$ is the covariance between two random variables $X$ and $Z$; $\\sigma_x$ and $\\sigma_z$ is the variance for $X$ and $Z$, respectively. The correlation coefficient measures the strength of linear relationship between two random variables. This metric can take any value from -1 to 1. <li/>\n",
+        "        <br/>\n",
+        "        <li> The auto-correlation coefficient $\\rho_{Y_{t} Y_{t-k}}$ is the time series equivalent of the correlation coefficient, except instead of measuring linear association between two random variables $X$ and $Z$, it measures the strength of a linear relationship between a random variable $Y_t$ and its lag $Y_{t-k}$ for any positive interger value of $k$. </li> \n",
+        "    <br />\n",
+        "        <li> To visualize the ACF for a particular lag, say lag 2, plot the second lag of a series $y_{t-2}$ on the x-axis, and plot the series itself $y_t$ on the y-axis. The autocorrelation coefficient is the slope of the best fitted regression line and can be interpreted as follows. A one unit increase in the lag of a variable one period ago leads to a $\\rho_{Y_{t} Y_{t-2}}$ units change in the variable in the current period. This interpreation can be applied to any lag. </li> \n",
+        "    <br />\n",
+        "    <li> In the interpretation posted above we need to be careful not to confuse the word \"leads\" with \"causes\" since these are not the same thing. We do not know the lagged value of the varaible causes it to change. Afterall, there are probably many other features that may explain the movement in $Y_t$. All we are trying to do in this section is to identify situations when the variable contains the strong auto-regressive components that needs to be included in the model to improve forecast accuracy. </li>\n",
+        "    </ul>\n",
+        "</ul>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<ul>\n",
+        "    <li> Question: What is the PACF? </li>\n",
+        "    <ul style=\"list-style-type:none;\">\n",
+        "        <li> When describing the ACF we essentially running a regression between a partigular lag of a series, say, lag 4, and the series itself. What this implies is the regression coefficient for lag 4 captures the impact of everything that happens in lags 1, 2 and 3. In other words, if lag 1 is the most important lag and we exclude it from the regression, naturally, the regression model will assign the importance of the 1st lag to the 4th one. Partial auto-correlation function fixes this problem since it measures the contribution of each lag accounting for the information added by the intermediary lags. If we were to illustrate ACF and PACF for the fourth lag using the regression analogy, the difference is a follows: \n",
+        "        \\begin{align}\n",
+        "            Y_{t} &= a_{0} + a_{4} Y_{t-4} + e_{t} \\\\\n",
+        "            Y_{t} &= b_{0} + b_{1} Y_{t-1} + b_{2} Y_{t-2} + b_{3} Y_{t-3} + b_{4} Y_{t-4} + \\varepsilon_{t} \\\\\n",
+        "        \\end{align}\n",
+        "         </li>\n",
+        "        <br/>\n",
+        "        <li>\n",
+        "            Here, you can think of $a_4$ and $b_{4}$ as the auto- and partial auto-correlation coefficients for lag 4. Notice, in the second equation we explicitely accounting for the intermediate lags by adding them as regrerssors.\n",
+        "        </li>\n",
+        "    </ul>\n",
+        "</ul>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<ul>\n",
+        "    <li> Question: Auto-regressive pattern? What are we looking for? </li>\n",
+        "    <ul style=\"list-style-type:none;\">\n",
+        "        <li> We are looking for a classical profiles for an AR(p) process such as an exponential decay of an ACF and a the first $p$ significant lags of the PACF. Let's examine the ACF/PACF profiles of the same simulated AR(2) shown in Section 3, and check if the ACF/PACF explanation are refelcted in these plots. <li/>\n",
+        "        <li><img src=\"figures/ACF_PACF_for_AR2.png\" class=\"img_class\">\n",
+        "        <li> The autocorrelation coefficient for the 3rd lag is 0.6, which can be interpreted that a one unit increase in the value of the target varaible three periods ago leads to 0.6 units increase in the current period.  However, the PACF plot shows that the partial autocorrealtion coefficient is zero (from a statistical point of view since it lies within the shaded region). This is happening because the 1st and 2nd lags are good predictors of the target variable. Ommiting these two lags from the regression results in the misleading conclusion that the third  lag is a good prediciton. <li/>\n",
+        "        <br/>\n",
+        "        <li> This is why it is important to examine both the ACF and the PACF plots when tring to determine the auto regressive order for the variable in question. <li/>\n",
+        "    </ul>\n",
+        "</ul> "
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "vlbejan"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.9"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 4
+}

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/auto-ml-forecasting-univariate-recipe-experiment-settings.yml

@@ -0,0 +1,4 @@
+name: auto-ml-forecasting-univariate-recipe-experiment-settings
+dependencies:
+- pip:
+  - azureml-sdk

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/auto-ml-forecasting-univariate-recipe-run-experiment.ipynb

@@ -0,0 +1,560 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/2_run_experiment.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Running AutoML experiments\n",
+        "\n",
+        "See the `auto-ml-forecasting-univariate-recipe-experiment-settings` notebook on how to determine settings for seasonal features, target lags and whether the series needs to be differenced or not. To make experimentation user-friendly, the user has to specify several parameters: DIFFERENCE_SERIES, TARGET_LAGS and STL_TYPE. Once these parameters are set, the notebook will generate correct transformations and settings to run experiments, generate forecasts, compute inference set metrics and plot forecast vs actuals. It will also convert the forecast from first differences to levels (original units of measurement) if the DIFFERENCE_SERIES parameter is set to True before calculating inference set metrics.\n",
+        "\n",
+        "<br/>\n",
+        "\n",
+        "The output generated by this notebook is saved in the `experiment_output`folder."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Setup"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import logging\n",
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "\n",
+        "import azureml.automl.runtime\n",
+        "from azureml.core.compute import AmlCompute\n",
+        "from azureml.core.compute import ComputeTarget\n",
+        "import matplotlib.pyplot as plt\n",
+        "from helper_functions import (ts_train_test_split, compute_metrics)\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.train.automl import AutoMLConfig\n",
+        "\n",
+        "\n",
+        "# set printing options\n",
+        "np.set_printoptions(precision=4, suppress=True, linewidth=100)\n",
+        "pd.set_option('display.max_columns', 500)\n",
+        "pd.set_option('display.width', 1000)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "As part of the setup you have already created a **Workspace**. You will also need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute) for your AutoML run. In this tutorial, you create AmlCompute as your training compute resource.\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "amlcompute_cluster_name = \"recipe-cluster\"\n",
+        "        \n",
+        "found = False\n",
+        "# Check if this compute target already exists in the workspace.\n",
+        "cts = ws.compute_targets\n",
+        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
+        "    found = True\n",
+        "    print('Found existing compute target.')\n",
+        "    compute_target = cts[amlcompute_cluster_name]\n",
+        "\n",
+        "if not found:\n",
+        "    print('Creating a new compute target...')\n",
+        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\",\n",
+        "                                                                max_nodes = 6)\n",
+        "\n",
+        "    # Create the cluster.\\n\",\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
+        "\n",
+        "print('Checking cluster status...')\n",
+        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
+        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
+        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Data\n",
+        "\n",
+        "Here, we will load the data from the csv file and drop the Covid period."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "main_data_loc = 'data'\n",
+        "train_file_name = 'S4248SM144SCEN.csv'\n",
+        "\n",
+        "TARGET_COLNAME = \"S4248SM144SCEN\"\n",
+        "TIME_COLNAME = \"observation_date\"\n",
+        "COVID_PERIOD_START = '2020-03-01'  # start of the covid period. To be excluded from evaluation.\n",
+        "\n",
+        "# load data\n",
+        "df = pd.read_csv(os.path.join(main_data_loc, train_file_name))\n",
+        "df[TIME_COLNAME] = pd.to_datetime(df[TIME_COLNAME], format='%Y-%m-%d')\n",
+        "df.sort_values(by=TIME_COLNAME, inplace=True)\n",
+        "\n",
+        "# remove the Covid period\n",
+        "df = df.query('{} <= \"{}\"'.format(TIME_COLNAME, COVID_PERIOD_START))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Set parameters\n",
+        "\n",
+        "The first set of parameters is based on the analysis performed in the `auto-ml-forecasting-univariate-recipe-experiment-settings` notebook. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# set parameters based on the settings notebook analysis\n",
+        "DIFFERENCE_SERIES = True\n",
+        "TARGET_LAGS = None\n",
+        "STL_TYPE = None"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Next, define additional parameters to be used in the <a href=\"https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.automlconfig?view=azure-ml-py\"> AutoML config </a> class.\n",
+        "\n",
+        "<ul> \n",
+        "    <li> FORECAST_HORIZON:  The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 12 periods (i.e. 12 quarters). For more discussion of forecast horizons and guiding principles for setting them, please see the <a href=\"https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand\"> energy demand notebook </a>. \n",
+        "    </li>\n",
+        "    <li> TIME_SERIES_ID_COLNAMES: The names of columns used to group a timeseries. It can be used to create multiple series. If time series identifier is not defined, the data set is assumed to be one time-series. This parameter is used with task type forecasting. Since we are working with a single series, this list is empty.\n",
+        "    </li>\n",
+        "    <li> BLOCKED_MODELS: Optional list of models to be blocked from consideration during model selection stage. At this point we want to consider all ML and Time Series models.\n",
+        "        <ul>\n",
+        "            <li> See the following <a href=\"https://docs.microsoft.com/en-us/python/api/azureml-train-automl-client/azureml.train.automl.constants.supportedmodels.forecasting?view=azure-ml-py\"> link </a> for a list of supported Forecasting models</li>\n",
+        "        </ul>\n",
+        "    </li>\n",
+        "</ul>\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# set other parameters\n",
+        "FORECAST_HORIZON = 12\n",
+        "TIME_SERIES_ID_COLNAMES = []\n",
+        "BLOCKED_MODELS = []"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "To run AutoML, you also need to create an **Experiment**. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# choose a name for the run history container in the workspace\n",
+        "if isinstance(TARGET_LAGS, list):\n",
+        "    TARGET_LAGS_STR = '-'.join(map(str, TARGET_LAGS)) if (len(TARGET_LAGS) > 0) else None\n",
+        "else:\n",
+        "    TARGET_LAGS_STR = TARGET_LAGS\n",
+        "\n",
+        "experiment_desc = 'diff-{}_lags-{}_STL-{}'.format(DIFFERENCE_SERIES, TARGET_LAGS_STR, STL_TYPE)\n",
+        "experiment_name = 'alcohol_{}'.format(experiment_desc)\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['SKU'] = ws.sku\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Run History Name'] = experiment_name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "print(outputDf.T)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# create output directory\n",
+        "output_dir = 'experiment_output/{}'.format(experiment_desc)\n",
+        "if not os.path.exists(output_dir):\n",
+        "    os.makedirs(output_dir)       "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# difference data and test for unit root\n",
+        "if DIFFERENCE_SERIES:\n",
+        "    df_delta = df.copy()\n",
+        "    df_delta[TARGET_COLNAME] = df[TARGET_COLNAME].diff()\n",
+        "    df_delta.dropna(axis=0, inplace=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# split the data into train and test set\n",
+        "if DIFFERENCE_SERIES:    \n",
+        "    # generate train/inference sets using data in first differences\n",
+        "    df_train, df_test = ts_train_test_split(df_input=df_delta,\n",
+        "                                            n=FORECAST_HORIZON,\n",
+        "                                            time_colname=TIME_COLNAME,\n",
+        "                                            ts_id_colnames=TIME_SERIES_ID_COLNAMES)\n",
+        "else:\n",
+        "    df_train, df_test = ts_train_test_split(df_input=df,\n",
+        "                                            n=FORECAST_HORIZON,\n",
+        "                                            time_colname=TIME_COLNAME,\n",
+        "                                            ts_id_colnames=TIME_SERIES_ID_COLNAMES)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Upload files to the Datastore\n",
+        "The [Machine Learning service workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-workspace) is paired with the storage account, which contains the default data store. We will use it to upload the bike share data and create [tabular dataset](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.tabulardataset?view=azure-ml-py) for training. A tabular dataset defines a series of lazily-evaluated, immutable operations to load data from the data source into tabular representation."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "df_train.to_csv(\"train.csv\", index=False)\n",
+        "df_test.to_csv(\"test.csv\", index=False)\n",
+        "\n",
+        "datastore = ws.get_default_datastore()\n",
+        "datastore.upload_files(files = ['./train.csv'], target_path = 'uni-recipe-dataset/tabular/', overwrite = True,show_progress = True)\n",
+        "datastore.upload_files(files = ['./test.csv'], target_path = 'uni-recipe-dataset/tabular/', overwrite = True,show_progress = True)\n",
+        "\n",
+        "from azureml.core import Dataset\n",
+        "train_dataset = Dataset.Tabular.from_delimited_files(path = [(datastore, 'uni-recipe-dataset/tabular/train.csv')])\n",
+        "test_dataset = Dataset.Tabular.from_delimited_files(path = [(datastore, 'uni-recipe-dataset/tabular/test.csv')])\n",
+        "\n",
+        "# print the first 5 rows of the Dataset\n",
+        "train_dataset.to_pandas_dataframe().reset_index(drop=True).head(5)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Config AutoML"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "time_series_settings = {\n",
+        "    'time_column_name': TIME_COLNAME,\n",
+        "    'forecast_horizon': FORECAST_HORIZON,\n",
+        "    'target_lags': TARGET_LAGS,\n",
+        "    'use_stl': STL_TYPE,\n",
+        "    'blocked_models': BLOCKED_MODELS,\n",
+        "    'time_series_id_column_names': TIME_SERIES_ID_COLNAMES\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task='forecasting',\n",
+        "                             debug_log='sample_experiment.log',\n",
+        "                             primary_metric='normalized_root_mean_squared_error',\n",
+        "                             experiment_timeout_minutes=20,\n",
+        "                             iteration_timeout_minutes=5,\n",
+        "                             enable_early_stopping=True,\n",
+        "                             training_data=train_dataset,\n",
+        "                             label_column_name=TARGET_COLNAME,\n",
+        "                             n_cross_validations=5,\n",
+        "                             verbosity=logging.INFO,\n",
+        "                             max_cores_per_iteration=-1,\n",
+        "                             compute_target=compute_target,\n",
+        "                             **time_series_settings)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We will now run the experiment, you can go to Azure ML portal to view the run details."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run = experiment.submit(automl_config, show_output=False)\n",
+        "remote_run.wait_for_completion()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the best model\n",
+        "Below we select the best model from all the training iterations using get_output method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = remote_run.get_output()\n",
+        "fitted_model.steps"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Inference\n",
+        "\n",
+        "We now use the best fitted model from the AutoML Run to make forecasts for the test set. We will do batch scoring on the test dataset which should have the same schema as training dataset.\n",
+        "\n",
+        "The inference will run on a remote compute. In this example, it will re-use the training compute."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "test_experiment = Experiment(ws, experiment_name + \"_inference\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Retreiving forecasts from the model\n",
+        "We have created a function called `run_forecast` that submits the test data to the best model determined during the training run and retrieves forecasts. This function uses a helper script `forecasting_script` which is uploaded and expecuted on the remote compute."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from run_forecast import run_remote_inference\n",
+        "remote_run = run_remote_inference(test_experiment=test_experiment, \n",
+        "                                  compute_target=compute_target,\n",
+        "                                  train_run=best_run,\n",
+        "                                  test_dataset=test_dataset,\n",
+        "                                  target_column_name=TARGET_COLNAME)\n",
+        "remote_run.wait_for_completion(show_output=False)\n",
+        "\n",
+        "remote_run.download_file('outputs/predictions.csv', f'{output_dir}/predictions.csv')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Download the prediction result for metrics calcuation\n",
+        "The test data with predictions are saved in artifact `outputs/predictions.csv`. We will use it to calculate accuracy metrics and vizualize predictions versus actuals."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_trans = pd.read_csv(f'{output_dir}/predictions.csv', parse_dates=[TIME_COLNAME])\n",
+        "X_trans.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# convert forecast in differences to levels\n",
+        "def convert_fcst_diff_to_levels(fcst, yt, df_orig):\n",
+        "    \"\"\" Convert forecast from first differences to levels. \"\"\"\n",
+        "    fcst = fcst.reset_index(drop=False, inplace=False)\n",
+        "    fcst['predicted_level'] = fcst['predicted'].cumsum()\n",
+        "    fcst['predicted_level'] = fcst['predicted_level'].astype(float) + float(yt)\n",
+        "    # merge actuals\n",
+        "    out = pd.merge(fcst,\n",
+        "                   df_orig[[TIME_COLNAME, TARGET_COLNAME]], \n",
+        "                   on=[TIME_COLNAME], how='inner')\n",
+        "    out.rename(columns={TARGET_COLNAME: 'actual_level'}, inplace=True)\n",
+        "    return out"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if DIFFERENCE_SERIES:    \n",
+        "    # convert forecast in differences to the levels\n",
+        "    INFORMATION_SET_DATE = max(df_train[TIME_COLNAME])\n",
+        "    YT = df.query('{} == @INFORMATION_SET_DATE'.format(TIME_COLNAME))[TARGET_COLNAME]\n",
+        "\n",
+        "    fcst_df = convert_fcst_diff_to_levels(fcst=X_trans, yt=YT, df_orig=df)\n",
+        "else:\n",
+        "    fcst_df = X_trans.copy()\n",
+        "    fcst_df['actual_level'] = y_test\n",
+        "    fcst_df['predicted_level'] = y_predictions\n",
+        "\n",
+        "del X_trans"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Calculate metrics and save output"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# compute metrics\n",
+        "metrics_df = compute_metrics(fcst_df=fcst_df,\n",
+        "                             metric_name=None,\n",
+        "                             ts_id_colnames=None)\n",
+        "# save output\n",
+        "metrics_file_name = '{}_metrics.csv'.format(experiment_name)\n",
+        "fcst_file_name = '{}_forecst.csv'.format(experiment_name)\n",
+        "plot_file_name = '{}_plot.pdf'.format(experiment_name)\n",
+        "\n",
+        "metrics_df.to_csv(os.path.join(output_dir, metrics_file_name), index=True)\n",
+        "fcst_df.to_csv(os.path.join(output_dir, fcst_file_name), index=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Generate and save visuals"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "plot_df = df.query('{} > \"2010-01-01\"'.format(TIME_COLNAME))\n",
+        "plot_df.set_index(TIME_COLNAME, inplace=True)\n",
+        "fcst_df.set_index(TIME_COLNAME, inplace=True)\n",
+        "\n",
+        "# generate and save plots\n",
+        "fig, ax = plt.subplots(dpi=180)\n",
+        "ax.plot(plot_df[TARGET_COLNAME], '-g', label='Historical')\n",
+        "ax.plot(fcst_df['actual_level'], '-b', label='Actual')\n",
+        "ax.plot(fcst_df['predicted_level'], '-r', label='Forecast')\n",
+        "ax.legend()\n",
+        "ax.set_title(\"Forecast vs Actuals\")\n",
+        "ax.set_xlabel(TIME_COLNAME)\n",
+        "ax.set_ylabel(TARGET_COLNAME)\n",
+        "locs, labels = plt.xticks()\n",
+        "\n",
+        "plt.setp(labels, rotation=45)\n",
+        "plt.savefig(os.path.join(output_dir, plot_file_name))"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "vlbejan"
+      }
+    ],
+    "kernelspec": {
+      "display_name": "Python 3.6",
+      "language": "python",
+      "name": "python36"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.9"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 4
+}

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/auto-ml-forecasting-univariate-recipe-run-experiment.yml

@@ -0,0 +1,4 @@
+name: auto-ml-forecasting-univariate-recipe-run-experiment
+dependencies:
+- pip:
+  - azureml-sdk

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/data/S4248SM144SCEN.csv

@@ -0,0 +1,350 @@
+observation_date,S4248SM144SCEN
+1992-01-01,4302
+1992-02-01,4323
+1992-03-01,4199
+1992-04-01,4397
+1992-05-01,4159
+1992-06-01,4091
+1992-07-01,4109
+1992-08-01,4116
+1992-09-01,4093
+1992-10-01,4095
+1992-11-01,4169
+1992-12-01,4169
+1993-01-01,4124
+1993-02-01,4107
+1993-03-01,4168
+1993-04-01,4254
+1993-05-01,4290
+1993-06-01,4163
+1993-07-01,4274
+1993-08-01,4253
+1993-09-01,4312
+1993-10-01,4296
+1993-11-01,4221
+1993-12-01,4233
+1994-01-01,4218
+1994-02-01,4237
+1994-03-01,4343
+1994-04-01,4357
+1994-05-01,4264
+1994-06-01,4392
+1994-07-01,4381
+1994-08-01,4290
+1994-09-01,4348
+1994-10-01,4357
+1994-11-01,4417
+1994-12-01,4411
+1995-01-01,4417
+1995-02-01,4339
+1995-03-01,4256
+1995-04-01,4276
+1995-05-01,4290
+1995-06-01,4413
+1995-07-01,4305
+1995-08-01,4476
+1995-09-01,4393
+1995-10-01,4447
+1995-11-01,4492
+1995-12-01,4489
+1996-01-01,4635
+1996-02-01,4697
+1996-03-01,4588
+1996-04-01,4633
+1996-05-01,4685
+1996-06-01,4672
+1996-07-01,4666
+1996-08-01,4726
+1996-09-01,4571
+1996-10-01,4624
+1996-11-01,4691
+1996-12-01,4604
+1997-01-01,4657
+1997-02-01,4711
+1997-03-01,4810
+1997-04-01,4626
+1997-05-01,4860
+1997-06-01,4757
+1997-07-01,4916
+1997-08-01,4921
+1997-09-01,4985
+1997-10-01,4905
+1997-11-01,4880
+1997-12-01,5165
+1998-01-01,4885
+1998-02-01,4925
+1998-03-01,5049
+1998-04-01,5090
+1998-05-01,5094
+1998-06-01,4929
+1998-07-01,5132
+1998-08-01,5061
+1998-09-01,5471
+1998-10-01,5327
+1998-11-01,5257
+1998-12-01,5354
+1999-01-01,5427
+1999-02-01,5415
+1999-03-01,5387
+1999-04-01,5483
+1999-05-01,5510
+1999-06-01,5539
+1999-07-01,5532
+1999-08-01,5625
+1999-09-01,5799
+1999-10-01,5843
+1999-11-01,5836
+1999-12-01,5724
+2000-01-01,5757
+2000-02-01,5731
+2000-03-01,5839
+2000-04-01,5825
+2000-05-01,5877
+2000-06-01,5979
+2000-07-01,5828
+2000-08-01,6016
+2000-09-01,6113
+2000-10-01,6150
+2000-11-01,6111
+2000-12-01,6088
+2001-01-01,6360
+2001-02-01,6300
+2001-03-01,5935
+2001-04-01,6204
+2001-05-01,6164
+2001-06-01,6231
+2001-07-01,6336
+2001-08-01,6179
+2001-09-01,6120
+2001-10-01,6134
+2001-11-01,6381
+2001-12-01,6521
+2002-01-01,6333
+2002-02-01,6541
+2002-03-01,6692
+2002-04-01,6591
+2002-05-01,6554
+2002-06-01,6596
+2002-07-01,6620
+2002-08-01,6577
+2002-09-01,6625
+2002-10-01,6441
+2002-11-01,6584
+2002-12-01,6923
+2003-01-01,6600
+2003-02-01,6742
+2003-03-01,6831
+2003-04-01,6782
+2003-05-01,6714
+2003-06-01,6736
+2003-07-01,7146
+2003-08-01,7027
+2003-09-01,6896
+2003-10-01,7107
+2003-11-01,6997
+2003-12-01,7075
+2004-01-01,7235
+2004-02-01,7072
+2004-03-01,6968
+2004-04-01,7144
+2004-05-01,7232
+2004-06-01,7095
+2004-07-01,7181
+2004-08-01,7146
+2004-09-01,7230
+2004-10-01,7327
+2004-11-01,7328
+2004-12-01,7425
+2005-01-01,7520
+2005-02-01,7551
+2005-03-01,7572
+2005-04-01,7701
+2005-05-01,7819
+2005-06-01,7770
+2005-07-01,7627
+2005-08-01,7816
+2005-09-01,7718
+2005-10-01,7772
+2005-11-01,7788
+2005-12-01,7576
+2006-01-01,7940
+2006-02-01,8027
+2006-03-01,7884
+2006-04-01,8043
+2006-05-01,7995
+2006-06-01,8218
+2006-07-01,8159
+2006-08-01,8331
+2006-09-01,8320
+2006-10-01,8397
+2006-11-01,8603
+2006-12-01,8515
+2007-01-01,8336
+2007-02-01,8233
+2007-03-01,8475
+2007-04-01,8310
+2007-05-01,8583
+2007-06-01,8645
+2007-07-01,8713
+2007-08-01,8636
+2007-09-01,8791
+2007-10-01,8984
+2007-11-01,8867
+2007-12-01,9059
+2008-01-01,8911
+2008-02-01,8701
+2008-03-01,8956
+2008-04-01,9095
+2008-05-01,9102
+2008-06-01,9170
+2008-07-01,9194
+2008-08-01,9164
+2008-09-01,9337
+2008-10-01,9186
+2008-11-01,9029
+2008-12-01,9025
+2009-01-01,9486
+2009-02-01,9219
+2009-03-01,9059
+2009-04-01,9171
+2009-05-01,9114
+2009-06-01,8926
+2009-07-01,9150
+2009-08-01,9105
+2009-09-01,9011
+2009-10-01,8743
+2009-11-01,8958
+2009-12-01,8969
+2010-01-01,8984
+2010-02-01,9068
+2010-03-01,9335
+2010-04-01,9481
+2010-05-01,9132
+2010-06-01,9192
+2010-07-01,9123
+2010-08-01,9091
+2010-09-01,9155
+2010-10-01,9556
+2010-11-01,9477
+2010-12-01,9436
+2011-01-01,9519
+2011-02-01,9667
+2011-03-01,9668
+2011-04-01,9628
+2011-05-01,9376
+2011-06-01,9830
+2011-07-01,9626
+2011-08-01,9802
+2011-09-01,9858
+2011-10-01,9838
+2011-11-01,9846
+2011-12-01,9789
+2012-01-01,9955
+2012-02-01,9909
+2012-03-01,9897
+2012-04-01,9909
+2012-05-01,10127
+2012-06-01,10175
+2012-07-01,10129
+2012-08-01,10251
+2012-09-01,10227
+2012-10-01,10174
+2012-11-01,10402
+2012-12-01,10664
+2013-01-01,10585
+2013-02-01,10661
+2013-03-01,10649
+2013-04-01,10676
+2013-05-01,10863
+2013-06-01,10690
+2013-07-01,11007
+2013-08-01,10835
+2013-09-01,10900
+2013-10-01,10749
+2013-11-01,10946
+2013-12-01,10864
+2014-01-01,10726
+2014-02-01,10821
+2014-03-01,10789
+2014-04-01,10892
+2014-05-01,10892
+2014-06-01,10789
+2014-07-01,10662
+2014-08-01,10767
+2014-09-01,10779
+2014-10-01,10922
+2014-11-01,10662
+2014-12-01,10808
+2015-01-01,10865
+2015-02-01,10740
+2015-03-01,10917
+2015-04-01,10933
+2015-05-01,11074
+2015-06-01,11108
+2015-07-01,11493
+2015-08-01,11386
+2015-09-01,11502
+2015-10-01,11487
+2015-11-01,11375
+2015-12-01,11445
+2016-01-01,11787
+2016-02-01,11792
+2016-03-01,11649
+2016-04-01,11810
+2016-05-01,11496
+2016-06-01,11600
+2016-07-01,11503
+2016-08-01,11715
+2016-09-01,11732
+2016-10-01,11885
+2016-11-01,12092
+2016-12-01,11857
+2017-01-01,11881
+2017-02-01,12355
+2017-03-01,12027
+2017-04-01,12183
+2017-05-01,12170
+2017-06-01,12387
+2017-07-01,12041
+2017-08-01,12139
+2017-09-01,11861
+2017-10-01,12202
+2017-11-01,12178
+2017-12-01,12126
+2018-01-01,11942
+2018-02-01,12206
+2018-03-01,12362
+2018-04-01,12287
+2018-05-01,12497
+2018-06-01,12621
+2018-07-01,12729
+2018-08-01,12689
+2018-09-01,12874
+2018-10-01,12776
+2018-11-01,12995
+2018-12-01,13291
+2019-01-01,13364
+2019-02-01,13135
+2019-03-01,13123
+2019-04-01,13110
+2019-05-01,13152
+2019-06-01,13201
+2019-07-01,13354
+2019-08-01,13427
+2019-09-01,13472
+2019-10-01,13436
+2019-11-01,13430
+2019-12-01,13588
+2020-01-01,13533
+2020-02-01,13575
+2020-03-01,13867
+2020-04-01,12319
+2020-05-01,13909
+2020-06-01,13982
+2020-07-01,15384
+2020-08-01,15701
+2020-09-01,15006
+2020-10-01,15741
+2020-11-01,14934
+2020-12-01,13061
+2021-01-01,15743

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/forecasting_script.py

@@ -0,0 +1,46 @@
+"""
+This is the script that is executed on the compute instance. It relies
+on the model.pkl file which is uploaded along with this script to the
+compute instance.
+"""
+
+import argparse
+from azureml.core import Dataset, Run
+from azureml.automl.core.shared.constants import TimeSeriesInternal
+from sklearn.externals import joblib
+
+parser = argparse.ArgumentParser()
+parser.add_argument(
+    '--target_column_name', type=str, dest='target_column_name',
+    help='Target Column Name')
+parser.add_argument(
+    '--test_dataset', type=str, dest='test_dataset',
+    help='Test Dataset')
+
+args = parser.parse_args()
+target_column_name = args.target_column_name
+test_dataset_id = args.test_dataset
+
+run = Run.get_context()
+ws = run.experiment.workspace
+
+# get the input dataset by id
+test_dataset = Dataset.get_by_id(ws, id=test_dataset_id)
+
+X_test_df = test_dataset.drop_columns(columns=[target_column_name]).to_pandas_dataframe().reset_index(drop=True)
+y_test_df = test_dataset.with_timestamp_columns(None).keep_columns(columns=[target_column_name]).to_pandas_dataframe()
+
+# generate forecast
+fitted_model = joblib.load('model.pkl')
+y_pred, X_trans = fitted_model.forecast(X_test_df)
+
+# rename target column
+X_trans.reset_index(drop=False, inplace=True)
+X_trans.rename(columns={TimeSeriesInternal.DUMMY_TARGET_COLUMN: 'predicted'}, inplace=True)
+X_trans['actual'] = y_test_df[target_column_name].values
+
+file_name = 'outputs/predictions.csv'
+export_csv = X_trans.to_csv(file_name, header=True, index=False)  # added Index
+
+# Upload the predictions into artifacts
+run.upload_file(name=file_name, path_or_stream=file_name)

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/helper_functions.py

@@ -0,0 +1,250 @@
+"""
+Helper functions to determine AutoML experiment settings for forecasting.
+"""
+import pandas as pd
+import statsmodels.tsa.stattools as stattools
+from arch import unitroot
+from azureml.automl.core.shared import constants
+from azureml.automl.runtime.shared.score import scoring
+
+
+def adf_test(series, **kw):
+    """
+    Wrapper for the augmented Dickey-Fuller test. Allows users to set the lag order.
+
+    :param series: series to test
+    :return: dictionary of results
+    """
+    if 'lags' in kw.keys():
+        msg = 'Lag order of {} detected. Running the ADF test...'.format(str(kw['lags']))
+        print(msg)
+        statistic, pval, critval, resstore = stattools.adfuller(series,
+                                                                maxlag=kw['lags'],
+                                                                autolag=kw['autolag'],
+                                                                store=kw['store'])
+    else:
+        statistic, pval, critval, resstore = stattools.adfuller(series,
+                                                                autolag=kw['IC'],
+                                                                store=kw['store'])
+
+    output = {'statistic': statistic,
+              'pval': pval,
+              'critical': critval,
+              'resstore': resstore}
+    return output
+
+
+def kpss_test(series, **kw):
+    """
+    Wrapper for the KPSS test. Allows users to set the lag order.
+
+    :param series: series to test
+    :return: dictionary of results
+    """
+    if kw['store']:
+        statistic, p_value, critical_values, rstore = stattools.kpss(series,
+                                                                     regression=kw['reg_type'],
+                                                                     lags=kw['lags'],
+                                                                     store=kw['store'])
+    else:
+        statistic, p_value, lags, critical_values = stattools.kpss(series,
+                                                                   regression=kw['reg_type'],
+                                                                   lags=kw['lags'])
+    output = {'statistic': statistic,
+              'pval': p_value,
+              'critical': critical_values,
+              'lags': rstore.lags if kw['store'] else lags}
+
+    if kw['store']:
+        output.update({'resstore': rstore})
+    return output
+
+
+def format_test_output(test_name, test_res, H0_unit_root=True):
+    """
+    Helper function to format output. Return a dictionary with specific keys. Will be used to
+    construct the summary data frame for all unit root tests.
+
+    TODO: Add functionality of choosing based on the max lag order specified by user.
+
+    :param test_name: name of the test
+    :param test_res: object that contains corresponding test information. Can be None if test failed.
+    :param H0_unit_root: does the null hypothesis of the test assume a unit root process? Some tests do (ADF),
+                         some don't (KPSS).
+    :return: dictionary of summary table for all tests and final decision on stationary vs non-stationary.
+             If test failed (test_res is None), return empty dictionary.
+    """
+    # Check if the test failed by trying to extract the test statistic
+    if test_name in ('ADF', 'KPSS'):
+        try:
+            test_res['statistic']
+        except BaseException:
+            test_res = None
+    else:
+        try:
+            test_res.stat
+        except BaseException:
+            test_res = None
+
+    if test_res is None:
+        return {}
+
+    # extract necessary information
+    if test_name in ('ADF', 'KPSS'):
+        statistic = test_res['statistic']
+        crit_val = test_res['critical']['5%']
+        p_val = test_res['pval']
+        lags = test_res['resstore'].usedlag if test_name == 'ADF' else test_res['lags']
+    else:
+        statistic = test_res.stat
+        crit_val = test_res.critical_values['5%']
+        p_val = test_res.pvalue
+        lags = test_res.lags
+
+    if H0_unit_root:
+        H0 = 'The process is non-stationary'
+        stationary = "yes" if p_val < 0.05 else "not"
+    else:
+        H0 = 'The process is stationary'
+        stationary = "yes" if p_val > 0.05 else "not"
+
+    out = {
+        'test_name': test_name,
+        'statistic': statistic,
+        'crit_val': crit_val,
+        'p_val': p_val,
+        'lags': int(lags),
+        'stationary': stationary,
+        'Null Hypothesis': H0
+    }
+    return out
+
+
+def unit_root_test_wrapper(series, lags=None):
+    """
+    Main function to run multiple stationarity tests. Runs five tests and returns a summary table + decision
+    based on the majority rule. If the number of tests that determine a series is stationary equals to the
+    number of tests that deem it non-stationary, we assume the series is non-stationary.
+        * Augmented Dickey-Fuller (ADF),
+        * KPSS,
+        * ADF using GLS,
+        * Phillips-Perron (PP),
+        * Zivot-Andrews (ZA)
+
+    :param lags: (optional) parameter that allows user to run a series of tests for a specific lag value.
+    :param series: series to test
+    :return: dictionary of summary table for all tests and final decision on stationary vs nonstaionary
+    """
+    # setting for ADF and KPSS tests
+    adf_settings = {
+        'IC': 'AIC',
+        'store': True
+    }
+
+    kpss_settings = {
+        'reg_type': 'c',
+        'lags': 'auto',
+        'store': True
+    }
+
+    arch_test_settings = {}  # settings for PP, ADF GLS and ZA tests
+    if lags is not None:
+        adf_settings.update({'lags': lags, 'autolag': None})
+        kpss_settings.update({'lags:': lags})
+        arch_test_settings = {'lags': lags}
+    # Run individual tests
+    adf = adf_test(series, **adf_settings)  # ADF test
+    kpss = kpss_test(series, **kpss_settings)  # KPSS test
+    pp = unitroot.PhillipsPerron(series, **arch_test_settings)  # Phillips-Perron test
+    adfgls = unitroot.DFGLS(series, **arch_test_settings)  # ADF using GLS test
+    za = unitroot.ZivotAndrews(series, **arch_test_settings)  # Zivot-Andrews test
+
+    # generate output table
+    adf_dict = format_test_output(test_name='ADF', test_res=adf, H0_unit_root=True)
+    kpss_dict = format_test_output(test_name='KPSS', test_res=kpss, H0_unit_root=False)
+    pp_dict = format_test_output(test_name='Philips Perron', test_res=pp, H0_unit_root=True)
+    adfgls_dict = format_test_output(test_name='ADF GLS', test_res=adfgls, H0_unit_root=True)
+    za_dict = format_test_output(test_name='Zivot-Andrews', test_res=za, H0_unit_root=True)
+
+    test_dict = {'ADF': adf_dict, 'KPSS': kpss_dict, 'PP': pp_dict, 'ADF GLS': adfgls_dict, 'ZA': za_dict}
+    test_sum = pd.DataFrame.from_dict(test_dict, orient='index').reset_index(drop=True)
+
+    # decision based on the majority rule
+    if test_sum.shape[0] > 0:
+        ratio = test_sum[test_sum["stationary"] == "yes"].shape[0] / test_sum.shape[0]
+    else:
+        ratio = 1  # all tests fail, assume the series is stationary
+
+    # Majority rule. If the ratio is exactly 0.5, assume the series in non-stationary.
+    stationary = 'YES' if (ratio > 0.5) else 'NO'
+
+    out = {'summary': test_sum, 'stationary': stationary}
+    return out
+
+
+def ts_train_test_split(df_input, n, time_colname, ts_id_colnames=None):
+    """
+    Group data frame by time series ID and split on last n rows for each group.
+
+    :param df_input: input data frame
+    :param n: number of observations in the test set
+    :param time_colname: time column
+    :param ts_id_colnames: (optional) list of grain column names
+    :return train and test data frames
+    """
+    if ts_id_colnames is None:
+        ts_id_colnames = []
+    ts_id_colnames_original = ts_id_colnames.copy()
+    if len(ts_id_colnames) == 0:
+        ts_id_colnames = ['Grain']
+        df_input[ts_id_colnames[0]] = 'dummy'
+    # Sort by ascending time
+    df_grouped = (df_input.sort_values(time_colname).groupby(ts_id_colnames, group_keys=False))
+    df_head = df_grouped.apply(lambda dfg: dfg.iloc[:-n])
+    df_tail = df_grouped.apply(lambda dfg: dfg.iloc[-n:])
+    # drop group column name if it was not originally provided
+    if len(ts_id_colnames_original) == 0:
+        df_head.drop(ts_id_colnames, axis=1, inplace=True)
+        df_tail.drop(ts_id_colnames, axis=1, inplace=True)
+    return df_head, df_tail
+
+
+def compute_metrics(fcst_df, metric_name=None, ts_id_colnames=None):
+    """
+    Calculate metrics per grain.
+
+    :param fcst_df: forecast data frame. Must contain 2 columns: 'actual_level' and 'predicted_level'
+    :param metric_name: (optional) name of the metric to return
+    :param ts_id_colnames: (optional) list of grain column names
+    :return: dictionary of summary table for all tests and final decision on stationary vs nonstaionary
+    """
+    if ts_id_colnames is None:
+        ts_id_colnames = []
+    if len(ts_id_colnames) == 0:
+        ts_id_colnames = ['TS_ID']
+        fcst_df[ts_id_colnames[0]] = 'dummy'
+    metrics_list = []
+    for grain, df in fcst_df.groupby(ts_id_colnames):
+        try:
+            scores = scoring.score_regression(
+                y_test=df['actual_level'],
+                y_pred=df['predicted_level'],
+                metrics=list(constants.Metric.SCALAR_REGRESSION_SET))
+        except BaseException:
+            msg = '{}: metrics calculation failed.'.format(grain)
+            print(msg)
+            scores = {}
+        one_grain_metrics_df = pd.DataFrame(list(scores.items()), columns=['metric_name', 'metric']).\
+            sort_values(['metric_name'])
+        one_grain_metrics_df.reset_index(inplace=True, drop=True)
+        if len(ts_id_colnames) < 2:
+            one_grain_metrics_df['grain'] = ts_id_colnames[0]
+        else:
+            one_grain_metrics_df['grain'] = "|".join(list(grain))
+
+        metrics_list.append(one_grain_metrics_df)
+    # collect into a data frame
+    grain_metrics = pd.concat(metrics_list)
+    if metric_name is not None:
+        grain_metrics = grain_metrics.query('metric_name == @metric_name')
+    return grain_metrics

how-to-use-azureml/automated-machine-learning/forecasting-recipes-univariate/run_forecast.py

@@ -0,0 +1,38 @@
+import os
+import shutil
+from azureml.core import ScriptRunConfig
+
+
+def run_remote_inference(test_experiment, compute_target, train_run,
+                         test_dataset, target_column_name, inference_folder='./forecast'):
+    # Create local directory to copy the model.pkl and forecsting_script.py files into.
+    # These files will be uploaded to and executed on the compute instance.
+    os.makedirs(inference_folder, exist_ok=True)
+    shutil.copy('forecasting_script.py', inference_folder)
+
+    train_run.download_file('outputs/model.pkl',
+                            os.path.join(inference_folder, 'model.pkl'))
+
+    inference_env = train_run.get_environment()
+
+    config = ScriptRunConfig(source_directory=inference_folder,
+                             script='forecasting_script.py',
+                             arguments=['--target_column_name',
+                                        target_column_name,
+                                        '--test_dataset',
+                                        test_dataset.as_named_input(test_dataset.name)],
+                             compute_target=compute_target,
+                             environment=inference_env)
+
+    run = test_experiment.submit(config,
+                                 tags={'training_run_id':
+                                       train_run.id,
+                                       'run_algorithm':
+                                       train_run.properties['run_algorithm'],
+                                       'valid_score':
+                                       train_run.properties['score'],
+                                       'primary_metric':
+                                       train_run.properties['primary_metric']})
+
+    run.log("run_algorithm", run.tags['run_algorithm'])
+    return run

how-to-use-azureml/automated-machine-learning/local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.ipynb

@@ -28,7 +28,8 @@
         "1. [Setup](#Setup)\n",
         "1. [Train](#Train)\n",
         "1. [Results](#Results)\n",
-        "1. [Test](#Test)\n",
+        "1. [Test](#Tests)\n",
+        "1. [Explanation](#Explanation)\n",
         "1. [Acknowledgements](#Acknowledgements)"
       ]
     },
@@ -42,14 +43,16 @@
         "\n",
         "This notebook is using the local machine compute to train the model.\n",
         "\n",
-        "If you are using an Azure Machine Learning [Notebook VM](https://docs.microsoft.com/en-us/azure/machine-learning/service/tutorial-1st-experiment-sdk-setup), you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
+        "If you are using an Azure Machine Learning Compute Instance, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
         "\n",
         "In this notebook you will learn how to:\n",
         "1. Create an experiment using an existing workspace.\n",
         "2. Configure AutoML using `AutoMLConfig`.\n",
         "3. Train the model.\n",
         "4. Explore the results.\n",
-        "5. Test the fitted model."
+        "5. Test the fitted model.\n",
+        "6. Explore any model's explanation and explore feature importance in azure portal.\n",
+        "7. Create an AKS cluster, deploy the webservice of AutoML scoring model and the explainer model to the AKS and consume the web service."
       ]
     },
     {
@@ -71,13 +74,30 @@
         "\n",
         "from matplotlib import pyplot as plt\n",
         "import pandas as pd\n",
-        "import os\n",
         "\n",
         "import azureml.core\n",
         "from azureml.core.experiment import Experiment\n",
         "from azureml.core.workspace import Workspace\n",
         "from azureml.core.dataset import Dataset\n",
-        "from azureml.train.automl import AutoMLConfig"
+        "from azureml.train.automl import AutoMLConfig\n",
+        "from azureml.interpret import ExplanationClient"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
     {
@@ -94,7 +114,6 @@
         "experiment=Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
@@ -154,9 +173,8 @@
       "source": [
         "automl_settings = {\n",
         "    \"n_cross_validations\": 3,\n",
-        "    \"primary_metric\": 'average_precision_score_weighted',\n",
-        "    \"preprocess\": True,\n",
-        "    \"experiment_timeout_minutes\": 10, # This is a time limit for testing purposes, remove it for real use cases, this will drastically limit ablity to find the best model possible\n",
+        "    \"primary_metric\": 'AUC_weighted',\n",
+        "    \"experiment_timeout_hours\": 0.25, # This is a time limit for testing purposes, remove it for real use cases, this will drastically limit ability to find the best model possible\n",
         "    \"verbosity\": logging.INFO,\n",
         "    \"enable_stack_ensemble\": False\n",
         "}\n",
@@ -197,15 +215,6 @@
         "#local_run = AutoMLRun(experiment = experiment, run_id = '<replace with your run id>')"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -238,9 +247,9 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Analyze results\n",
+        "### Analyze results\n",
         "\n",
-        "### Retrieve the Best Model\n",
+        "#### Retrieve the Best Model\n",
         "\n",
         "Below we select the best pipeline from our iterations. The `get_output` method on `automl_classifier` returns the best run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
       ]
@@ -260,24 +269,14 @@
       "metadata": {},
       "source": [
         "#### Print the properties of the model\n",
-        "The fitted_model is a python object and you can read the different properties of the object.\n",
-        "See *Print the properties of the model* section in [this sample notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification/auto-ml-classification.ipynb)."
+        "The fitted_model is a python object and you can read the different properties of the object.\n"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Deploy\n",
-        "\n",
-        "To deploy the model into a web service endpoint, see _Deploy_ section in [this sample notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification-with-deployment/auto-ml-classification-with-deployment.ipynb)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test the fitted model\n",
+        "## Tests\n",
         "\n",
         "Now that the model is trained, split the data in the same way the data was split for training (The difference here is the data is being split locally) and then run the test data through the trained model to get the predicted values."
       ]
@@ -341,6 +340,449 @@
         "plt.show()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Explanation\n",
+        "In this section, we will show how to compute model explanations and visualize the explanations using azureml-interpret package. We will also show how to run the automl model and the explainer model through deploying an AKS web service.\n",
+        "\n",
+        "Besides retrieving an existing model explanation for an AutoML model, you can also explain your AutoML model with different test data. The following steps will allow you to compute and visualize engineered feature importance based on your test data.\n",
+        "\n",
+        "### Run the explanation\n",
+        "#### Download the engineered feature importance from artifact store\n",
+        "You can use ExplanationClient to download the engineered feature explanations from the artifact store of the best_run. You can also use azure portal url to view the dash board visualization of the feature importance values of the engineered features."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "client = ExplanationClient.from_run(best_run)\n",
+        "engineered_explanations = client.download_model_explanation(raw=False)\n",
+        "print(engineered_explanations.get_feature_importance_dict())\n",
+        "print(\"You can visualize the engineered explanations under the 'Explanations (preview)' tab in the AutoML run at:-\\n\" + best_run.get_portal_url())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Download the raw feature importance from artifact store\n",
+        "You can use ExplanationClient to download the raw feature explanations from the artifact store of the best_run. You can also use azure portal url to view the dash board visualization of the feature importance values of the raw features."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "raw_explanations = client.download_model_explanation(raw=True)\n",
+        "print(raw_explanations.get_feature_importance_dict())\n",
+        "print(\"You can visualize the raw explanations under the 'Explanations (preview)' tab in the AutoML run at:-\\n\" + best_run.get_portal_url())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Retrieve any other AutoML model from training"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_run, fitted_model = local_run.get_output(metric='accuracy')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Setup the model explanations for AutoML models\n",
+        "The fitted_model can generate the following which will be used for getting the engineered explanations using automl_setup_model_explanations:-\n",
+        "\n",
+        "1. Featurized data from train samples/test samples\n",
+        "2. Gather engineered name lists\n",
+        "3. Find the classes in your labeled column in classification scenarios\n",
+        "\n",
+        "The automl_explainer_setup_obj contains all the structures from above list."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_train = training_data.drop_columns(columns=[label_column_name])\n",
+        "y_train = training_data.keep_columns(columns=[label_column_name], validate=True)\n",
+        "X_test = validation_data.drop_columns(columns=[label_column_name])"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.automl.runtime.automl_explain_utilities import automl_setup_model_explanations\n",
+        "\n",
+        "automl_explainer_setup_obj = automl_setup_model_explanations(fitted_model, X=X_train, \n",
+        "                                                             X_test=X_test, y=y_train, \n",
+        "                                                             task='classification',\n",
+        "                                                             automl_run=automl_run)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Initialize the Mimic Explainer for feature importance\n",
+        "For explaining the AutoML models, use the MimicWrapper from azureml-interpret package. The MimicWrapper can be initialized with fields in automl_explainer_setup_obj, your workspace and a surrogate model to explain the AutoML model (fitted_model here). The MimicWrapper also takes the automl_run object where engineered explanations will be uploaded."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.interpret.mimic_wrapper import MimicWrapper\n",
+        "explainer = MimicWrapper(ws, automl_explainer_setup_obj.automl_estimator,\n",
+        "                         explainable_model=automl_explainer_setup_obj.surrogate_model, \n",
+        "                         init_dataset=automl_explainer_setup_obj.X_transform, run=automl_explainer_setup_obj.automl_run,\n",
+        "                         features=automl_explainer_setup_obj.engineered_feature_names, \n",
+        "                         feature_maps=[automl_explainer_setup_obj.feature_map],\n",
+        "                         classes=automl_explainer_setup_obj.classes,\n",
+        "                         explainer_kwargs=automl_explainer_setup_obj.surrogate_model_params)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Use Mimic Explainer for computing and visualizing engineered feature importance\n",
+        "The explain() method in MimicWrapper can be called with the transformed test samples to get the feature importance for the generated engineered features. You can also use azure portal url to view the dash board visualization of the feature importance values of the engineered features."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Compute the engineered explanations\n",
+        "engineered_explanations = explainer.explain(['local', 'global'], eval_dataset=automl_explainer_setup_obj.X_test_transform)\n",
+        "print(engineered_explanations.get_feature_importance_dict())\n",
+        "print(\"You can visualize the engineered explanations under the 'Explanations (preview)' tab in the AutoML run at:-\\n\" + automl_run.get_portal_url())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Use Mimic Explainer for computing and visualizing raw feature importance\n",
+        "The explain() method in MimicWrapper can be called with the transformed test samples to get the feature importance for the original features in your data. You can also use azure portal url to view the dash board visualization of the feature importance values of the original/raw features."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Compute the raw explanations\n",
+        "raw_explanations = explainer.explain(['local', 'global'], get_raw=True,\n",
+        "                                     raw_feature_names=automl_explainer_setup_obj.raw_feature_names,\n",
+        "                                     eval_dataset=automl_explainer_setup_obj.X_test_transform,\n",
+        "                                     raw_eval_dataset=automl_explainer_setup_obj.X_test_raw)\n",
+        "print(raw_explanations.get_feature_importance_dict())\n",
+        "print(\"You can visualize the raw explanations under the 'Explanations (preview)' tab in the AutoML run at:-\\n\" + automl_run.get_portal_url())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Initialize the scoring Explainer, save and upload it for later use in scoring explanation"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.interpret.scoring.scoring_explainer import TreeScoringExplainer\n",
+        "import joblib\n",
+        "\n",
+        "# Initialize the ScoringExplainer\n",
+        "scoring_explainer = TreeScoringExplainer(explainer.explainer, feature_maps=[automl_explainer_setup_obj.feature_map])\n",
+        "\n",
+        "# Pickle scoring explainer locally to './scoring_explainer.pkl'\n",
+        "scoring_explainer_file_name = 'scoring_explainer.pkl'\n",
+        "with open(scoring_explainer_file_name, 'wb') as stream:\n",
+        "    joblib.dump(scoring_explainer, stream)\n",
+        "\n",
+        "# Upload the scoring explainer to the automl run\n",
+        "automl_run.upload_file('outputs/scoring_explainer.pkl', scoring_explainer_file_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Deploying the scoring and explainer models to a web service to Azure Kubernetes Service (AKS)\n",
+        "\n",
+        "We use the TreeScoringExplainer from azureml.interpret package to create the scoring explainer which will be used to compute the raw and engineered feature importances at the inference time. In the cell below, we register the AutoML model and the scoring explainer with the Model Management Service."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Register trained automl model present in the 'outputs' folder in the artifacts\n",
+        "original_model = automl_run.register_model(model_name='automl_model', \n",
+        "                                           model_path='outputs/model.pkl')\n",
+        "scoring_explainer_model = automl_run.register_model(model_name='scoring_explainer',\n",
+        "                                                    model_path='outputs/scoring_explainer.pkl')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Create the conda dependencies for setting up the service\n",
+        "\n",
+        "We need to download the conda dependencies using the automl_run object."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.automl.core.shared import constants\n",
+        "from azureml.core.environment import Environment\n",
+        "\n",
+        "automl_run.download_file(constants.CONDA_ENV_FILE_PATH, 'myenv.yml')\n",
+        "myenv = Environment.from_conda_specification(name=\"myenv\", file_path=\"myenv.yml\")\n",
+        "myenv"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Write the Entry Script\n",
+        "Write the script that will be used to predict on your model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%writefile score.py\n",
+        "import joblib\n",
+        "import pandas as pd\n",
+        "from azureml.core.model import Model\n",
+        "from azureml.train.automl.runtime.automl_explain_utilities import automl_setup_model_explanations\n",
+        "\n",
+        "\n",
+        "def init():\n",
+        "    global automl_model\n",
+        "    global scoring_explainer\n",
+        "\n",
+        "    # Retrieve the path to the model file using the model name\n",
+        "    # Assume original model is named original_prediction_model\n",
+        "    automl_model_path = Model.get_model_path('automl_model')\n",
+        "    scoring_explainer_path = Model.get_model_path('scoring_explainer')\n",
+        "\n",
+        "    automl_model = joblib.load(automl_model_path)\n",
+        "    scoring_explainer = joblib.load(scoring_explainer_path)\n",
+        "\n",
+        "\n",
+        "def run(raw_data):\n",
+        "    data = pd.read_json(raw_data, orient='records')    \n",
+        "    # Make prediction\n",
+        "    predictions = automl_model.predict(data)\n",
+        "    # Setup for inferencing explanations\n",
+        "    automl_explainer_setup_obj = automl_setup_model_explanations(automl_model,\n",
+        "                                                                 X_test=data, task='classification')\n",
+        "    # Retrieve model explanations for engineered explanations\n",
+        "    engineered_local_importance_values = scoring_explainer.explain(automl_explainer_setup_obj.X_test_transform)\n",
+        "    # Retrieve model explanations for raw explanations\n",
+        "    raw_local_importance_values = scoring_explainer.explain(automl_explainer_setup_obj.X_test_transform, get_raw=True)\n",
+        "    # You can return any data type as long as it is JSON-serializable\n",
+        "    return {'predictions': predictions.tolist(),\n",
+        "            'engineered_local_importance_values': engineered_local_importance_values,\n",
+        "            'raw_local_importance_values': raw_local_importance_values}\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Create the InferenceConfig \n",
+        "Create the inference config that will be used when deploying the model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.model import InferenceConfig\n",
+        "\n",
+        "inf_config = InferenceConfig(entry_script='score.py', environment=myenv)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Provision the AKS Cluster\n",
+        "This is a one time setup. You can reuse this cluster for multiple deployments after it has been created. If you delete the cluster or the resource group that contains it, then you would have to recreate it."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.compute import ComputeTarget, AksCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
+        "\n",
+        "# Choose a name for your cluster.\n",
+        "aks_name = 'scoring-explain'\n",
+        "\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    aks_target = ComputeTarget(workspace=ws, name=aks_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    prov_config = AksCompute.provisioning_configuration(vm_size='STANDARD_D3_V2')\n",
+        "    aks_target = ComputeTarget.create(workspace=ws, \n",
+        "                                      name=aks_name,\n",
+        "                                      provisioning_configuration=prov_config)\n",
+        "aks_target.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Deploy web service to AKS"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Set the web service configuration (using default here)\n",
+        "from azureml.core.webservice import AksWebservice\n",
+        "from azureml.core.model import Model\n",
+        "\n",
+        "aks_config = AksWebservice.deploy_configuration()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aks_service_name ='model-scoring-local-aks'\n",
+        "\n",
+        "aks_service = Model.deploy(workspace=ws,\n",
+        "                           name=aks_service_name,\n",
+        "                           models=[scoring_explainer_model, original_model],\n",
+        "                           inference_config=inf_config,\n",
+        "                           deployment_config=aks_config,\n",
+        "                           deployment_target=aks_target)\n",
+        "\n",
+        "aks_service.wait_for_deployment(show_output = True)\n",
+        "print(aks_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### View the service logs"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aks_service.get_logs()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Consume the web service using run method to do the scoring and explanation of scoring.\n",
+        "We test the web sevice by passing data. Run() method retrieves API keys behind the scenes to make sure that call is authenticated."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Serialize the first row of the test data into json\n",
+        "X_test_json = X_test_df[:1].to_json(orient='records')\n",
+        "print(X_test_json)\n",
+        "\n",
+        "# Call the service to get the predictions and the engineered and raw explanations\n",
+        "output = aks_service.run(X_test_json)\n",
+        "\n",
+        "# Print the predicted value\n",
+        "print('predictions:\\n{}\\n'.format(output['predictions']))\n",
+        "# Print the engineered feature importances for the predicted value\n",
+        "print('engineered_local_importance_values:\\n{}\\n'.format(output['engineered_local_importance_values']))\n",
+        "# Print the raw feature importances for the predicted value\n",
+        "print('raw_local_importance_values:\\n{}\\n'.format(output['raw_local_importance_values']))\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Clean up\n",
+        "Delete the service."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aks_service.delete()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -369,7 +811,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "tzvikei"
+        "name": "ratanase"
       }
     ],
     "category": "tutorial",

how-to-use-azureml/automated-machine-learning/local-run-classification-credit-card-fraud/auto-ml-classification-credit-card-fraud-local.yml

@@ -2,10 +2,3 @@ name: auto-ml-classification-credit-card-fraud-local
 dependencies:
 - pip:
   - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-explain-model
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml

how-to-use-azureml/automated-machine-learning/regression-explanation-featurization/auto-ml-regression-explanation-featurization.ipynb

@@ -40,9 +40,7 @@
         "In this example we use the Hardware Performance Dataset to showcase how you can use AutoML for a simple regression problem. The Regression goal is to predict the performance of certain combinations of hardware parts.\n",
         "After training AutoML models for this regression data set, we show how you can compute model explanations on your remote compute using a sample explainer script.\n",
         "\n",
-        "If you are using an Azure Machine Learning Notebook VM, you are all set.  Otherwise, go through the [configuration](../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
-        "\n",
-        "An Enterprise workspace is required for this notebook. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page.](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade) \n",
+        "If you are using an Azure Machine Learning Compute Instance, you are all set.  Otherwise, go through the [configuration](../../../configuration.ipynb)  notebook first if you haven't already to establish your connection to the AzureML Workspace. \n",
         "\n",
         "In this notebook you will learn how to:\n",
         "1. Create an `Experiment` in an existing `Workspace`.\n",
@@ -51,8 +49,8 @@
         "4. Explore the results and featurization transparency options\n",
         "5. Setup remote compute for computing the model explanations for a given AutoML model.\n",
         "6. Start an AzureML experiment on your remote compute to compute explanations for an AutoML model.\n",
-        "7. Download the feature importance for engineered features and visualize the explanations for engineered features. \n",
-        "8. Download the feature importance for raw features and visualize the explanations for raw features. \n"
+        "7. Download the feature importance for engineered features and visualize the explanations for engineered features on azure portal. \n",
+        "8. Download the feature importance for raw features and visualize the explanations for raw features on azure portal. \n"
       ]
     },
     {
@@ -79,12 +77,28 @@
         "import azureml.core\n",
         "from azureml.core.experiment import Experiment\n",
         "from azureml.core.workspace import Workspace\n",
-        "import azureml.dataprep as dprep\n",
         "from azureml.automl.core.featurization import FeaturizationConfig\n",
         "from azureml.train.automl import AutoMLConfig\n",
         "from azureml.core.dataset import Dataset"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "This sample notebook may use features that are not available in previous versions of the Azure ML SDK."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"This notebook was created using version 1.34.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -98,7 +112,6 @@
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
         "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
         "output['Subscription ID'] = ws.subscription_id\n",
         "output['Workspace Name'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
@@ -116,6 +129,8 @@
         "### Create or Attach existing AmlCompute\n",
         "You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for your AutoML run. In this tutorial, you create `AmlCompute` as your training compute resource.\n",
         "\n",
+        "> Note that if you have an AzureML Data Scientist role, you will not have permission to create compute resources. Talk to your workspace or IT admin to create the compute targets described in this section, if they do not already exist.\n",
+        "\n",
         "**Creation of AmlCompute takes approximately 5 minutes.** If the AmlCompute with that name is already in your workspace this code will skip the creation process.\n",
         "\n",
         "As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
@@ -127,35 +142,22 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.compute import AmlCompute\n",
-        "from azureml.core.compute import ComputeTarget\n",
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"cpu-cluster-5\"\n",
+        "amlcompute_cluster_name = \"hardware-cluster\"\n",
         "\n",
-        "found = False\n",
-        "# Check if this compute target already exists in the workspace.\n",
-        "cts = ws.compute_targets\n",
-        "if amlcompute_cluster_name in cts and cts[amlcompute_cluster_name].type == 'AmlCompute':\n",
-        "    found = True\n",
-        "    print('Found existing compute target.')\n",
-        "    compute_target = cts[amlcompute_cluster_name]\n",
-        "\n",
-        "if not found:\n",
-        "    print('Creating a new compute target...')\n",
-        "    provisioning_config = AmlCompute.provisioning_configuration(vm_size = \"STANDARD_D2_V2\", # for GPU, use \"STANDARD_NC6\"\n",
-        "                                                                #vm_priority = 'lowpriority', # optional\n",
+        "# Verify that cluster does not exist already\n",
+        "try:\n",
+        "    compute_target = ComputeTarget(workspace=ws, name=amlcompute_cluster_name)\n",
+        "    print('Found existing cluster, use it.')\n",
+        "except ComputeTargetException:\n",
+        "    compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS12_V2',\n",
         "                                                           max_nodes=4)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
         "\n",
-        "    # Create the cluster.\\n\",\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "\n",
-        "print('Checking cluster status...')\n",
-        "# Can poll for a minimum number of nodes and for a specific timeout.\n",
-        "# If no min_node_count is provided, it will use the scale settings for the cluster.\n",
-        "compute_target.wait_for_completion(show_output = True, min_node_count = None, timeout_in_minutes = 20)\n",
-        "\n",
-        "# For a more detailed view of current AmlCompute status, use get_status()."
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
@@ -206,9 +208,9 @@
         "|-|-|\n",
         "|**task**|classification, regression or forecasting|\n",
         "|**primary_metric**|This is the metric that you want to optimize. Regression supports the following primary metrics: <br><i>spearman_correlation</i><br><i>normalized_root_mean_squared_error</i><br><i>r2_score</i><br><i>normalized_mean_absolute_error</i>|\n",
-        "|**experiment_timeout_minutes**| Maximum amount of time in minutes that all iterations combined can take before the experiment terminates.|\n",
+        "|**experiment_timeout_hours**| Maximum amount of time in hours that all iterations combined can take before the experiment terminates.|\n",
         "|**enable_early_stopping**| Flag to enble early termination if the score is not improving in the short term.|\n",
-        "|**featurization**| 'auto' / 'off' / FeaturizationConfig Indicator for whether featurization step should be done automatically or not, or whether customized featurization should be used. Note: If the input data is sparse, featurization cannot be turned on.|\n",
+        "|**featurization**| 'auto' / 'off' / FeaturizationConfig Indicator for whether featurization step should be done automatically or not, or whether customized featurization should be used. Setting this enables AutoML to perform featurization on the input to handle *missing data*, and to perform some common *feature extraction*. Note: If the input data is sparse, featurization cannot be turned on.|\n",
         "|**n_cross_validations**|Number of cross validation splits.|\n",
         "|**training_data**|(sparse) array-like, shape = [n_samples, n_features]|\n",
         "|**label_column_name**|(sparse) array-like, shape = [n_samples, ], targets values.|"
@@ -220,9 +222,8 @@
       "source": [
         "## Customization\n",
         "\n",
-        "This step requires an Enterprise workspace to gain access to this feature. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page.](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade). \n",
-        "\n",
         "Supported customization includes:\n",
+        "\n",
         "1. Column purpose update: Override feature type for the specified column.\n",
         "2. Transformer parameter update: Update parameters for the specified transformer. Currently supports Imputer and HashOneHotEncoder.\n",
         "3. Drop columns: Columns to drop from being featurized.\n",
@@ -239,12 +240,16 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "metadata": {},
+      "metadata": {
+        "tags": [
+          "sample-featurizationconfig-remarks2"
+        ]
+      },
       "outputs": [],
       "source": [
         "featurization_config = FeaturizationConfig()\n",
         "featurization_config.blocked_transformers = ['LabelEncoder']\n",
-        "#featurization_config.drop_columns = ['ERP', 'MMIN']\n",
+        "#featurization_config.drop_columns = ['MMIN']\n",
         "featurization_config.add_column_purpose('MYCT', 'Numeric')\n",
         "featurization_config.add_column_purpose('VendorName', 'CategoricalHash')\n",
         "#default strategy mean, add transformer param for for 3 columns\n",
@@ -257,12 +262,16 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "metadata": {},
+      "metadata": {
+        "tags": [
+          "sample-featurizationconfig-remarks3"
+        ]
+      },
       "outputs": [],
       "source": [
         "automl_settings = {\n",
         "    \"enable_early_stopping\": True, \n",
-        "    \"experiment_timeout_minutes\" : 10,\n",
+        "    \"experiment_timeout_hours\" : 0.25,\n",
         "    \"max_concurrent_iterations\": 4,\n",
         "    \"max_cores_per_iteration\": -1,\n",
         "    \"n_cross_validations\": 5,\n",
@@ -297,15 +306,6 @@
         "remote_run = experiment.submit(automl_config, show_output = False)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -320,8 +320,6 @@
       "outputs": [],
       "source": [
         "#from azureml.train.automl.run import AutoMLRun\n",
-        "#experiment_name = 'automl-regression-hardware'\n",
-        "#experiment = Experiment(ws, experiment_name)\n",
         "#remote_run = AutoMLRun(experiment=experiment, run_id='<run_ID_goes_here')\n",
         "#remote_run"
       ]
@@ -438,12 +436,11 @@
       "metadata": {},
       "source": [
         "## Explanations\n",
-        "This step requires an Enterprise workspace to gain access to this feature. To learn more about creating an Enterprise workspace or upgrading to an Enterprise workspace from the Azure portal, please visit our [Workspace page.](https://docs.microsoft.com/azure/machine-learning/service/concept-workspace#upgrade). \n",
         "This section will walk you through the workflow to compute model explanations for an AutoML model on your remote compute.\n",
         "\n",
         "### Retrieve any AutoML Model for explanations\n",
         "\n",
-        "Below we select the some AutoML pipeline from our iterations. The `get_output` method returns the a AutoML run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+        "Below we select an AutoML pipeline from our iterations. The `get_output` method returns the a AutoML run and the fitted model for the last invocation. Overloads on `get_output` allow you to retrieve the best run and fitted model for any logged `metric` or for a particular `iteration`."
       ]
     },
     {
@@ -452,7 +449,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "automl_run, fitted_model = remote_run.get_output(metric='r2_score')"
+        "#automl_run, fitted_model = remote_run.get_output(metric='r2_score')\n",
+        "automl_run, fitted_model = remote_run.get_output(iteration=2)"
       ]
     },
     {
@@ -514,7 +512,7 @@
         "    content = cefr.read()\n",
         "\n",
         "# Replace the values in train_explainer.py file with the appropriate values\n",
-        "content = content.replace('<<experimnet_name>>', automl_run.experiment.name) # your experiment name.\n",
+        "content = content.replace('<<experiment_name>>', automl_run.experiment.name) # your experiment name.\n",
         "content = content.replace('<<run_id>>', automl_run.id) # Run-id of the AutoML run for which you want to explain the model.\n",
         "content = content.replace('<<target_column_name>>', 'ERP') # Your target column name\n",
         "content = content.replace('<<task>>', 'regression') # Training task type\n",
@@ -532,8 +530,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "#### Create conda configuration for model explanations experiment\n",
-        "We need `azureml-explain-model`, `azureml-train-automl` and `azureml-core` packages for computing model explanations for your AutoML model on remote compute."
+        "#### Create conda configuration for model explanations experiment from automl_run object"
       ]
     },
     {
@@ -543,8 +540,6 @@
       "outputs": [],
       "source": [
         "from azureml.core.runconfig import RunConfiguration\n",
-        "from azureml.core.conda_dependencies import CondaDependencies\n",
-        "import pkg_resources\n",
         "\n",
         "# create a new RunConfig object\n",
         "conda_run_config = RunConfiguration(framework=\"python\")\n",
@@ -552,14 +547,9 @@
         "# Set compute target to AmlCompute\n",
         "conda_run_config.target = compute_target\n",
         "conda_run_config.environment.docker.enabled = True\n",
-        "azureml_pip_packages = [\n",
-        "    'azureml-train-automl', 'azureml-core', 'azureml-explain-model'\n",
-        "]\n",
         "\n",
         "# specify CondaDependencies obj\n",
-        "conda_run_config.environment.python.conda_dependencies = CondaDependencies.create(\n",
-        "    conda_packages=['scikit-learn', 'numpy','py-xgboost<=0.80'],\n",
-        "    pip_packages=azureml_pip_packages)"
+        "conda_run_config.environment.python.conda_dependencies = automl_run.get_environment().python.conda_dependencies"
       ]
     },
     {
@@ -604,38 +594,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Feature importance  and  explanation dashboard\n",
-        "In this section we describe how you can download the explanation results from the explanations experiment and visualize the feature importance for your AutoML model. "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Setup for visualizing the model explanation results\n",
-        "For visualizing the explanation results for the *fitted_model* we need to perform the following steps:-\n",
-        "1. Featurize test data samples.\n",
-        "\n",
-        "The *automl_explainer_setup_obj* contains all the structures from above list. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_test = test_data.drop_columns([label]).to_pandas_dataframe()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.train.automl.automl_explain_utilities import AutoMLExplainerSetupClass, automl_setup_model_explanations\n",
-        "explainer_setup_class = automl_setup_model_explanations(fitted_model, 'regression', X_test=X_test)"
+        "### Feature importance  and  visualizing explanation dashboard\n",
+        "In this section we describe how you can download the explanation results from the explanations experiment and visualize the feature importance for your AutoML model on the azure portal."
       ]
     },
     {
@@ -643,7 +603,7 @@
       "metadata": {},
       "source": [
         "#### Download engineered feature importance from artifact store\n",
-        "You can use *ExplanationClient* to download the engineered feature explanations from the artifact store of the *automl_run*. You can also use ExplanationDashboard to view the dash board visualization of the feature importance values of the engineered features."
+        "You can use *ExplanationClient* to download the engineered feature explanations from the artifact store of the *automl_run*. You can also use azure portal url to view the dash board visualization of the feature importance values of the engineered features."
       ]
     },
     {
@@ -652,12 +612,11 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.explain.model._internal.explanation_client import ExplanationClient\n",
-        "from azureml.contrib.interpret.visualize import ExplanationDashboard\n",
+        "from azureml.interpret import ExplanationClient\n",
         "client = ExplanationClient.from_run(automl_run)\n",
-        "engineered_explanations = client.download_model_explanation(raw=False)\n",
+        "engineered_explanations = client.download_model_explanation(raw=False, comment='engineered explanations')\n",
         "print(engineered_explanations.get_feature_importance_dict())\n",
-        "ExplanationDashboard(engineered_explanations, explainer_setup_class.automl_estimator, explainer_setup_class.X_test_transform)"
+        "print(\"You can visualize the engineered explanations under the 'Explanations (preview)' tab in the AutoML run at:-\\n\" + automl_run.get_portal_url())"
       ]
     },
     {
@@ -665,7 +624,7 @@
       "metadata": {},
       "source": [
         "#### Download raw feature importance from artifact store\n",
-        "You can use *ExplanationClient* to download the raw feature explanations from the artifact store of the *automl_run*. You can also use ExplanationDashboard to view the dash board visualization of the feature importance values of the raw features."
+        "You can use *ExplanationClient* to download the raw feature explanations from the artifact store of the *automl_run*. You can also use azure portal url to view the dash board visualization of the feature importance values of the raw features."
       ]
     },
     {
@@ -674,20 +633,20 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "raw_explanations = client.download_model_explanation(raw=True)\n",
+        "raw_explanations = client.download_model_explanation(raw=True, comment='raw explanations')\n",
         "print(raw_explanations.get_feature_importance_dict())\n",
-        "ExplanationDashboard(raw_explanations, explainer_setup_class.automl_pipeline, explainer_setup_class.X_test_raw)"
+        "print(\"You can visualize the raw explanations under the 'Explanations (preview)' tab in the AutoML run at:-\\n\" + automl_run.get_portal_url())"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Operationailze\n",
+        "## Operationalize\n",
         "In this section we will show how you can operationalize an AutoML model and the explainer which was used to compute the explanations in the previous section.\n",
         "\n",
         "### Register the AutoML model and the scoring explainer\n",
-        "We use the *TreeScoringExplainer* from *azureml.explain.model* package to create the scoring explainer which will be used to compute the raw and engineered feature importances at the inference time. \n",
+        "We use the *TreeScoringExplainer* from *azureml-interpret* package to create the scoring explainer which will be used to compute the raw and engineered feature importances at the inference time. \n",
         "In the cell below, we register the AutoML model and the scoring explainer with the Model Management Service."
       ]
     },
@@ -709,7 +668,7 @@
       "metadata": {},
       "source": [
         "### Create the conda dependencies for setting up the service\n",
-        "We need to create the conda dependencies comprising of the *azureml-explain-model*, *azureml-train-automl* and *azureml-defaults* packages. "
+        "We need to create the conda dependencies comprising of the *azureml* packages using the training environment from the *automl_run*."
       ]
     },
     {
@@ -718,20 +677,10 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.conda_dependencies import CondaDependencies \n",
-        "\n",
-        "azureml_pip_packages = [\n",
-        "    'azureml-explain-model', 'azureml-train-automl', 'azureml-defaults'\n",
-        "]\n",
-        " \n",
-        "\n",
-        "# specify CondaDependencies obj\n",
-        "myenv = CondaDependencies.create(conda_packages=['scikit-learn', 'pandas', 'numpy', 'py-xgboost<=0.80'],\n",
-        "                                 pip_packages=azureml_pip_packages,\n",
-        "                                 pin_sdk_version=True)\n",
+        "conda_dep = automl_run.get_environment().python.conda_dependencies\n",
         "\n",
         "with open(\"myenv.yml\",\"w\") as f:\n",
-        "    f.write(myenv.serialize_to_string())\n",
+        "    f.write(conda_dep.serialize_to_string())\n",
         "\n",
         "with open(\"myenv.yml\",\"r\") as f:\n",
         "    print(f.read())"
@@ -768,20 +717,19 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from azureml.core.webservice import Webservice\n",
         "from azureml.core.model import InferenceConfig\n",
         "from azureml.core.webservice import AciWebservice\n",
         "from azureml.core.model import Model\n",
+        "from azureml.core.environment import Environment\n",
         "\n",
-        "aciconfig = AciWebservice.deploy_configuration(cpu_cores=1, \n",
-        "                                               memory_gb=1, \n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores=2, \n",
+        "                                               memory_gb=2, \n",
         "                                               tags={\"data\": \"Machine Data\",  \n",
         "                                                     \"method\" : \"local_explanation\"}, \n",
         "                                               description='Get local explanations for Machine test data')\n",
         "\n",
-        "inference_config = InferenceConfig(runtime= \"python\", \n",
-        "                                   entry_script=\"score_explain.py\",\n",
-        "                                   conda_file=\"myenv.yml\")\n",
+        "myenv = Environment.from_conda_specification(name=\"myenv\", file_path=\"myenv.yml\")\n",
+        "inference_config = InferenceConfig(entry_script=\"score_explain.py\", environment=myenv)\n",
         "\n",
         "# Use configs and models generated above\n",
         "service = Model.deploy(ws, 'model-scoring', [scoring_explainer_model, original_model], inference_config, aciconfig)\n",
@@ -819,6 +767,7 @@
       "outputs": [],
       "source": [
         "if service.state == 'Healthy':\n",
+        "    X_test = test_data.drop_columns([label]).to_pandas_dataframe()\n",
         "    # Serialize the first row of the test data into json\n",
         "    X_test_json = X_test[:1].to_json(orient='records')\n",
         "    print(X_test_json)\n",
@@ -942,7 +891,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "anumamah"
+        "name": "anshirga"
       }
     ],
     "categories": [

how-to-use-azureml/automated-machine-learning/regression-explanation-featurization/auto-ml-regression-explanation-featurization.yml

@@ -0,0 +1,4 @@
+name: auto-ml-regression-explanation-featurization
+dependencies:
+- pip:
+  - azureml-sdk