update samples from Release-60 as a part of SDK release

update samples from Release-59 as a part of  SDK release

README.md

@@ -2,7 +2,7 @@
 
 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.
 
-![Azure ML Workflow](https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/master/articles/machine-learning/service/media/concept-azure-machine-learning-architecture/workflow.png)
+![Azure ML Workflow](https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/master/articles/machine-learning/media/concept-azure-machine-learning-architecture/workflow.png)
 
 
 ## Quick installation
@@ -13,15 +13,15 @@ Read more detailed instructions on [how to set up your environment](./NBSETUP.md
 
 ## 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. 
+This [index](./index.md) should assist in navigating the Azure Machine Learning notebook samples and encourage efficient retrieval of topics and content. 
 
 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).
+ * ...try out and explore Azure ML, start with image classification tutorials: [Part 1 (Training)](./tutorials/image-classification-mnist-data/img-classification-part1-training.ipynb) and [Part 2 (Deployment)](./tutorials/image-classification-mnist-data/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).
+ * ...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 [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), 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
@@ -40,6 +40,7 @@ The [How to use Azure ML](./how-to-use-azureml) folder contains specific example
 - [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
+- [Reinforcement Learning](./how-to-use-azureml/reinforcement-learning) - Examples showing how to train reinforcement learning agents
 
 ---
 ## Documentation

configuration.ipynb

@@ -103,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.72 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.11.0 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },

contrib/fairness/fairlearn-azureml-mitigation.ipynb

@@ -0,0 +1,564 @@
+{
+  "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.github.io) 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.github.io/).\n",
+        "\n",
+        "We will apply the [grid search algorithm](https://fairlearn.github.io/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==0.4.6`\n",
+        "* `joblib`\n",
+        "* `shap`\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": [
+        "<a id=\"LoadingData\"></a>\n",
+        "## Loading the Data\n",
+        "We use the well-known `adult` census dataset, which we load using `shap` (for convenience). 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 fairlearn.widget import FairlearnDashboard\n",
+        "from sklearn import svm\n",
+        "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
+        "from sklearn.linear_model import LogisticRegression\n",
+        "import pandas as pd\n",
+        "import shap"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We can now load and inspect the data from the `shap` package:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_raw, Y = shap.datasets.adult()\n",
+        "X_raw[\"Race\"].value_counts().to_dict()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We are going to treat the sex of each individual as a protected attribute (where 0 indicates female and 1 indicates male), and in this particular case we are going separate this attribute out and drop it from the main data (this is not always the best option - see the [Fairlearn website](http://fairlearn.github.io/) for further discussion). We also separate out the Race column, but we will not perform any mitigation based on it. Finally, we perform some standard data preprocessing steps to convert the data into a format suitable for the ML algorithms"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "A = X_raw[['Sex','Race']]\n",
+        "X = X_raw.drop(labels=['Sex', 'Race'],axis = 1)\n",
+        "X = pd.get_dummies(X)\n",
+        "\n",
+        "\n",
+        "le = LabelEncoder()\n",
+        "Y = le.fit_transform(Y)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "With our data prepared, we can make the conventional split in to 'test' and 'train' subsets:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn.model_selection import train_test_split\n",
+        "X_train, X_test, Y_train, Y_test, A_train, A_test = train_test_split(X_raw, \n",
+        "                                                    Y, \n",
+        "                                                    A,\n",
+        "                                                    test_size = 0.2,\n",
+        "                                                    random_state=0,\n",
+        "                                                    stratify=Y)\n",
+        "\n",
+        "# Work around indexing issue\n",
+        "X_train = X_train.reset_index(drop=True)\n",
+        "A_train = A_train.reset_index(drop=True)\n",
+        "X_test = X_test.reset_index(drop=True)\n",
+        "A_test = A_test.reset_index(drop=True)\n",
+        "\n",
+        "# Improve labels\n",
+        "A_test.Sex.loc[(A_test['Sex'] == 0)] = 'female'\n",
+        "A_test.Sex.loc[(A_test['Sex'] == 1)] = 'male'\n",
+        "\n",
+        "\n",
+        "A_test.Race.loc[(A_test['Race'] == 0)] = 'Amer-Indian-Eskimo'\n",
+        "A_test.Race.loc[(A_test['Race'] == 1)] = 'Asian-Pac-Islander'\n",
+        "A_test.Race.loc[(A_test['Race'] == 2)] = 'Black'\n",
+        "A_test.Race.loc[(A_test['Race'] == 3)] = 'Other'\n",
+        "A_test.Race.loc[(A_test['Race'] == 4)] = 'White'"
+      ]
+    },
+    {
+      "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": [
+        "FairlearnDashboard(sensitive_features=A_test, sensitive_feature_names=['Sex', 'Race'],\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",
+        "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 m in predictors:\n",
+        "    classifier = lambda X: m.predict(X)\n",
+        "    \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(classifier)[0])\n",
+        "    disparities.append(disparity.gamma(classifier).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": [
+        "FairlearnDashboard(sensitive_features=A_test, \n",
+        "                   sensitive_feature_names=['Sex', 'Race'],\n",
+        "                   y_true=Y_test.tolist(),\n",
+        "                   y_pred=predictions_dominant)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "When using sex as the sensitive feature, 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 `FairlearnDashboard` 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.github.io/) 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/upload-fairness-dashboard.ipynb

@@ -0,0 +1,507 @@
+{
+  "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 Fairlearn 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==0.4.6`\n",
+        "* `joblib`\n",
+        "* `shap`\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": [
+        "<a id=\"LoadingData\"></a>\n",
+        "## Loading the Data\n",
+        "We use the well-known `adult` census dataset, which we load using `shap` (for convenience). 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.preprocessing import LabelEncoder, StandardScaler\n",
+        "from sklearn.linear_model import LogisticRegression\n",
+        "import pandas as pd\n",
+        "import shap"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Now we can load the data:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_raw, Y = shap.datasets.adult()"
+      ]
+    },
+    {
+      "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 put the rest of the feature data into `X`:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "A = X_raw[['Sex','Race']]\n",
+        "X = X_raw.drop(labels=['Sex', 'Race'],axis = 1)\n",
+        "X = pd.get_dummies(X)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Next, we apply a standard set of scalings:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "sc = StandardScaler()\n",
+        "X_scaled = sc.fit_transform(X)\n",
+        "X_scaled = pd.DataFrame(X_scaled, columns=X.columns)\n",
+        "\n",
+        "le = LabelEncoder()\n",
+        "Y = le.fit_transform(Y)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Finally, we can then split our data into training and test sets, and also make the labels on our test portion of `A` human-readable:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn.model_selection import train_test_split\n",
+        "X_train, X_test, Y_train, Y_test, A_train, A_test = train_test_split(X_scaled, \n",
+        "                                                    Y, \n",
+        "                                                    A,\n",
+        "                                                    test_size = 0.2,\n",
+        "                                                    random_state=0,\n",
+        "                                                    stratify=Y)\n",
+        "\n",
+        "# Work around indexing issue\n",
+        "X_train = X_train.reset_index(drop=True)\n",
+        "A_train = A_train.reset_index(drop=True)\n",
+        "X_test = X_test.reset_index(drop=True)\n",
+        "A_test = A_test.reset_index(drop=True)\n",
+        "\n",
+        "# Improve labels\n",
+        "A_test.Sex.loc[(A_test['Sex'] == 0)] = 'female'\n",
+        "A_test.Sex.loc[(A_test['Sex'] == 1)] = 'male'\n",
+        "\n",
+        "\n",
+        "A_test.Race.loc[(A_test['Race'] == 0)] = 'Amer-Indian-Eskimo'\n",
+        "A_test.Race.loc[(A_test['Race'] == 1)] = 'Asian-Pac-Islander'\n",
+        "A_test.Race.loc[(A_test['Race'] == 2)] = 'Black'\n",
+        "A_test.Race.loc[(A_test['Race'] == 3)] = 'Other'\n",
+        "A_test.Race.loc[(A_test['Race'] == 4)] = 'White'"
+      ]
+    },
+    {
+      "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 fairlearn.widget import FairlearnDashboard\n",
+        "\n",
+        "FairlearnDashboard(sensitive_features=A_test, \n",
+        "                   sensitive_feature_names=['Sex', 'Race'],\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 `FairlearnDashboard` 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": "3.6.8"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 4
+}

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

@@ -9,7 +9,6 @@ As a pre-requisite, run the [configuration Notebook](../configuration.ipynb) not
 * [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>
@@ -117,7 +117,7 @@ jupyter notebook
     - Simple example of using automated ML for regression
     - Uses azure compute for training
 
-- [auto-ml-regression-hardware-performance-explanation-and-featurization.ipynb](regression-hardware-performance-explanation-and-featurization/auto-ml-regression-hardware-performance-explanation-and-featurization.ipynb)
+- [auto-ml-regression-explanation-featurization.ipynb](regression-explanation-featurization/auto-ml-regression-explanation-featurization.ipynb)
     - Dataset: Hardware Performance Dataset
     - Shows featurization and excplanation
     - Uses azure compute for training
@@ -144,7 +144,7 @@ jupyter notebook
     - 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)
+- [auto-ml-forecasting-function.ipynb](forecasting-forecast-function/auto-ml-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)
@@ -152,7 +152,13 @@ jupyter notebook
     - Beer Production Forecasting
 
 - [auto-ml-continuous-retraining.ipynb](continuous-retraining/auto-ml-continuous-retraining.ipynb)
-    - Continous retraining using Pipelines and Time-Series TabularDataset
+    - Continuous 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.
 
 <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.
@@ -191,6 +197,17 @@ 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.
@@ -213,6 +230,15 @@ 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

@@ -2,19 +2,21 @@ name: azure_automl
 dependencies:
   # The python interpreter version.
   # Currently Azure ML only supports 3.5.2 and later.
-- pip
+- pip<=19.3.1
 - python>=3.5.2,<3.6.8
 - nb_conda
 - matplotlib==2.1.0
-- numpy>=1.16.0,<=1.16.2
+- numpy~=1.16.0
 - cython
 - urllib3<1.24
-- scipy>=1.0.0,<=1.1.0
+- scipy==1.4.1
 - scikit-learn>=0.19.0,<=0.20.3
 - pandas>=0.22.0,<=0.23.4
-- py-xgboost<=0.80
-- pyarrow>=0.11.0
+- py-xgboost<=0.90
 - conda-forge::fbprophet==0.5
+- holidays==0.9.11
+- pytorch::pytorch=1.4.0
+- cudatoolkit=10.1.243
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
@@ -22,7 +24,8 @@ dependencies:
   - azureml-train-automl
   - azureml-train
   - azureml-widgets
-  - azureml-explain-model
-  - azureml-contrib-interpret
-  - pandas_ml
-  
+  - azureml-pipeline
+  - pytorch-transformers==1.0.0
+  - spacy==2.1.8
+  - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz
+

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

@@ -2,20 +2,22 @@ name: azure_automl
 dependencies:
   # The python interpreter version.
   # Currently Azure ML only supports 3.5.2 and later.
-- pip
+- pip<=19.3.1
 - nomkl
 - python>=3.5.2,<3.6.8
 - nb_conda
 - matplotlib==2.1.0
-- numpy>=1.16.0,<=1.16.2
+- numpy~=1.16.0
 - cython
 - urllib3<1.24
-- scipy>=1.0.0,<=1.1.0
+- scipy==1.4.1
 - scikit-learn>=0.19.0,<=0.20.3
-- pandas>=0.22.0,<0.23.0
-- py-xgboost<=0.80
-- pyarrow>=0.11.0
+- pandas>=0.22.0,<=0.23.4
+- py-xgboost<=0.90
 - conda-forge::fbprophet==0.5
+- holidays==0.9.11
+- pytorch::pytorch=1.4.0
+- cudatoolkit=9.0
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
@@ -23,7 +25,7 @@ dependencies:
   - azureml-train-automl
   - azureml-train
   - azureml-widgets
-  - azureml-explain-model
-  - azureml-contrib-interpret
-  - pandas_ml
-  
+  - azureml-pipeline
+  - pytorch-transformers==1.0.0
+  - spacy==2.1.8
+  - https://aka.ms/automl-resources/packages/en_core_web_sm-2.1.0.tar.gz  

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

@@ -14,8 +14,9 @@ IF "%CONDA_EXE%"=="" GOTO CondaMissing
 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%

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

@@ -22,8 +22,9 @@ fi
 
 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

@@ -22,8 +22,9 @@ fi
 
 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/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"
       ]
@@ -92,6 +92,49 @@
         "from azureml.explain.model._internal.explanation_client 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 1.11.0 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)"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -106,7 +149,6 @@
         "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",
@@ -134,35 +176,22 @@
       "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",
-        "                                                                max_nodes = 6)\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",
+        "                                                           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 +314,15 @@
         "|**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 +334,7 @@
       "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 +349,11 @@
         "                             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 +362,7 @@
       "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."
       ]
     },
     {
@@ -370,8 +397,6 @@
       "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"
       ]
@@ -382,6 +407,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "# Wait for the remote run to complete\n",
         "remote_run.wait_for_completion()"
       ]
     },
@@ -463,8 +489,31 @@
       "metadata": {},
       "source": [
         "### Retrieve the Best Model's explanation\n",
-        "Retrieve the explanation from the best_run which includes explanations for engineered features and raw features.\n",
+        "Retrieve the explanation from the best_run which includes explanations for engineered features and raw features. Make sure that the run for generating explanations for the best model is completed."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Wait for the best model explanation run to complete\n",
+        "from azureml.core.run import Run\n",
+        "model_explainability_run_id = remote_run.get_properties().get('ModelExplainRunId')\n",
+        "print(model_explainability_run_id)\n",
+        "if model_explainability_run_id is not None:\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",
+        "best_run, fitted_model = remote_run.get_output()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "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 best_run."
       ]
@@ -475,13 +524,32 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "best_run, fitted_model = remote_run.get_output()\n",
         "client = ExplanationClient.from_run(best_run)\n",
         "engineered_explanations = client.download_model_explanation(raw=False)\n",
         "exp_data = engineered_explanations.get_feature_importance_dict()\n",
         "exp_data"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "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 best_run."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "client = ExplanationClient.from_run(best_run)\n",
+        "engineered_explanations = client.download_model_explanation(raw=True)\n",
+        "exp_data = engineered_explanations.get_feature_importance_dict()\n",
+        "exp_data"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -515,7 +583,7 @@
       "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)"
       ]
@@ -527,15 +595,6 @@
         "### Predict with the ONNX model, using onnxruntime package"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "test_df = test_dataset.to_pandas_dataframe()"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -552,12 +611,8 @@
         "else:\n",
         "    python_version_compatible = False\n",
         "\n",
-        "try:\n",
-        "    import onnxruntime\n",
-        "    from azureml.automl.core.onnx_convert import OnnxInferenceHelper    \n",
-        "    onnxrt_present = True\n",
-        "except ImportError:\n",
-        "    onnxrt_present = False\n",
+        "import onnxruntime\n",
+        "from azureml.automl.runtime.onnx_convert import OnnxInferenceHelper\n",
         "\n",
         "def get_onnx_res(run):\n",
         "    res_path = 'onnx_resource.json'\n",
@@ -566,7 +621,8 @@
         "        onnx_res = json.load(f)\n",
         "    return onnx_res\n",
         "\n",
-        "if onnxrt_present and python_version_compatible:    \n",
+        "if python_version_compatible:\n",
+        "    test_df = test_dataset.to_pandas_dataframe()\n",
         "    mdl_bytes = onnx_mdl.SerializeToString()\n",
         "    onnx_res = get_onnx_res(best_run)\n",
         "\n",
@@ -576,10 +632,7 @@
         "    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.')"
       ]
     },
     {
@@ -590,7 +643,7 @@
         "\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*."
       ]
     },
     {
@@ -613,20 +666,6 @@
         "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,
@@ -636,10 +675,8 @@
         "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')"
       ]
     },
     {
@@ -680,10 +717,9 @@
         "from azureml.core.webservice import AciWebservice\n",
         "from azureml.core.webservice import Webservice\n",
         "from azureml.core.model import Model\n",
+        "from azureml.core.environment import Environment\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",
@@ -826,13 +862,6 @@
         "\n",
         "[Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014"
       ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
     }
   ],
   "metadata": {

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
-  - 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 1.11.0 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",
@@ -122,35 +138,22 @@
       "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",
-        "                                                                max_nodes = 6)\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)"
       ]
     },
     {
@@ -210,10 +213,9 @@
         "automl_settings = {\n",
         "    \"n_cross_validations\": 3,\n",
         "    \"primary_metric\": 'average_precision_score_weighted',\n",
-        "    \"preprocess\": True,\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 +232,7 @@
       "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."
       ]
     },
     {
@@ -284,7 +285,11 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "metadata": {},
+      "metadata": {
+        "tags": [
+          "widget-rundetails-sample"
+        ]
+      },
       "outputs": [],
       "source": [
         "from azureml.widgets import RunDetails\n",
@@ -306,7 +311,7 @@
       "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 +322,7 @@
         "\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 +340,7 @@
       "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"
       ]
     },
     {
@@ -452,7 +447,7 @@
       "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

@@ -0,0 +1,587 @@
+{
+  "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/classification-text-dnn/auto-ml-classification-text-dnn.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Text Classification Using Deep Learning**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Evaluate](#Evaluate)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "This notebook demonstrates classification with text data using deep learning in AutoML.\n",
+        "\n",
+        "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, and Bidirectional Long-Short Term neural network (BiLSTM) when a CPU compute is used, thereby optimizing the choice of DNN for the uesr's setup.\n",
+        "\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",
+        "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. Registering the best model for future use\n",
+        "4. Evaluating the final model on a test set"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import logging\n",
+        "import os\n",
+        "import shutil\n",
+        "\n",
+        "import pandas as pd\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.core.compute import AmlCompute\n",
+        "from azureml.core.compute import ComputeTarget\n",
+        "from azureml.core.run import Run\n",
+        "from azureml.widgets import RunDetails\n",
+        "from azureml.core.model import Model \n",
+        "from helper import run_inference, get_result_df\n",
+        "from azureml.train.automl import AutoMLConfig\n",
+        "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 1.11.0 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": [
+        "As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. 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": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose an experiment name.\n",
+        "experiment_name = 'automl-classification-text-dnn'\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace Name'] = 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": [
+        "## Set up a compute cluster\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.  If your goal is to obtain the most accurate model, we recommend you use GPU clusters since BERT featurizers usually outperform BiLSTM featurizers."
+      ]
+    },
+    {
+      "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 cluster.\n",
+        "amlcompute_cluster_name = \"dnntext-cluster\"\n",
+        "\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_D2_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 = 1)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\n",
+        "\n",
+        "compute_target.wait_for_completion(show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Get data\n",
+        "For this notebook we will use 20 Newsgroups data from scikit-learn. We filter the data to contain four classes and take a sample as training data. Please note that for accuracy improvement, more data is needed. For this notebook we provide a small-data example so that you can use this template to use with your larger sized data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data_dir = \"text-dnn-data\" # Local directory to store data\n",
+        "blobstore_datadir = data_dir # Blob store directory to store data in\n",
+        "target_column_name = 'y'\n",
+        "feature_column_name = 'X'\n",
+        "\n",
+        "def get_20newsgroups_data():\n",
+        "    '''Fetches 20 Newsgroups data from scikit-learn\n",
+        "       Returns them in form of pandas dataframes\n",
+        "    '''\n",
+        "    remove = ('headers', 'footers', 'quotes')\n",
+        "    categories = [\n",
+        "        'rec.sport.baseball',\n",
+        "        'rec.sport.hockey',\n",
+        "        'comp.graphics',\n",
+        "        'sci.space',\n",
+        "        ]\n",
+        "\n",
+        "    data = fetch_20newsgroups(subset = 'train', categories = categories,\n",
+        "                                    shuffle = True, random_state = 42,\n",
+        "                                    remove = remove)\n",
+        "    data = pd.DataFrame({feature_column_name: data.data, target_column_name: data.target})\n",
+        "\n",
+        "    data_train = data[:200]\n",
+        "    data_test = data[200:300]    \n",
+        "\n",
+        "    data_train = remove_blanks_20news(data_train, feature_column_name, target_column_name)\n",
+        "    data_test = remove_blanks_20news(data_test, feature_column_name, target_column_name)\n",
+        "    \n",
+        "    return data_train, data_test\n",
+        "    \n",
+        "def remove_blanks_20news(data, feature_column_name, target_column_name):\n",
+        "    \n",
+        "    data[feature_column_name] = data[feature_column_name].replace(r'\\n', ' ', regex=True).apply(lambda x: x.strip())\n",
+        "    data = data[data[feature_column_name] != '']\n",
+        "    \n",
+        "    return data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Fetch data and upload to datastore for use in training"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data_train, data_test = get_20newsgroups_data()\n",
+        "\n",
+        "if not os.path.isdir(data_dir):\n",
+        "    os.mkdir(data_dir)\n",
+        "    \n",
+        "train_data_fname = data_dir + '/train_data.csv'\n",
+        "test_data_fname = data_dir + '/test_data.csv'\n",
+        "\n",
+        "data_train.to_csv(train_data_fname, index=False)\n",
+        "data_test.to_csv(test_data_fname, index=False)\n",
+        "\n",
+        "datastore = ws.get_default_datastore()\n",
+        "datastore.upload(src_dir=data_dir, target_path=blobstore_datadir,\n",
+        "                    overwrite=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "train_dataset = Dataset.Tabular.from_delimited_files(path = [(datastore, blobstore_datadir + '/train_data.csv')])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Prepare AutoML run"
+      ]
+    },
+    {
+      "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)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings = {\n",
+        "    \"experiment_timeout_minutes\": 20,\n",
+        "    \"primary_metric\": 'accuracy',\n",
+        "    \"max_concurrent_iterations\": 4, \n",
+        "    \"max_cores_per_iteration\": -1,\n",
+        "    \"enable_dnn\": True,\n",
+        "    \"enable_early_stopping\": True,\n",
+        "    \"validation_size\": 0.3,\n",
+        "    \"verbosity\": logging.INFO,\n",
+        "    \"enable_voting_ensemble\": False,\n",
+        "    \"enable_stack_ensemble\": False,\n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             compute_target=compute_target,\n",
+        "                             training_data=train_dataset,\n",
+        "                             label_column_name=target_column_name,\n",
+        "                             **automl_settings\n",
+        "                            )"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Submit AutoML Run"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_run = experiment.submit(automl_config, show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Displaying the run objects gives you links to the visual tools in the Azure Portal. Go try them!"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\n",
+        "Below we select the best model pipeline from our iterations, use it to test on test data on the same compute cluster."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "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"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = automl_run.get_output()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "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.  "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Get results stats, extract the best model from AutoML run, download and register the resultant best model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "summary_df = get_result_df(automl_run)\n",
+        "best_dnn_run_id = summary_df['run_id'].iloc[0]\n",
+        "best_dnn_run = Run(experiment, best_dnn_run_id)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model_dir = 'Model' # Local folder where the model will be stored temporarily\n",
+        "if not os.path.isdir(model_dir):\n",
+        "    os.mkdir(model_dir)\n",
+        "    \n",
+        "best_dnn_run.download_file('outputs/model.pkl', model_dir + '/model.pkl')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Register the model in your Azure Machine Learning Workspace. If you previously registered a model, please make sure to delete it so as to replace it with this new model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Register the model\n",
+        "model_name = 'textDNN-20News'\n",
+        "model = Model.register(model_path = model_dir + '/model.pkl',\n",
+        "                       model_name = model_name,\n",
+        "                       tags=None,\n",
+        "                       workspace=ws)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Evaluate on Test Data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We now use the best fitted model from the AutoML Run to make predictions on the test set.  \n",
+        "\n",
+        "Test set schema should match that of the training set."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "test_dataset = Dataset.Tabular.from_delimited_files(path = [(datastore, blobstore_datadir + '/test_data.csv')])\n",
+        "\n",
+        "# preview the first 3 rows of the dataset\n",
+        "test_dataset.take(3).to_pandas_dataframe()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "test_experiment = Experiment(ws, experiment_name + \"_test\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "script_folder = os.path.join(os.getcwd(), 'inference')\n",
+        "os.makedirs(script_folder, exist_ok=True)\n",
+        "shutil.copy('infer.py', script_folder)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "test_run = run_inference(test_experiment, compute_target, script_folder, best_dnn_run,\n",
+        "                         train_dataset, test_dataset, target_column_name, model_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Display computed metrics"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "test_run"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "RunDetails(test_run).show()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "test_run.wait_for_completion()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "pd.Series(test_run.get_metrics())"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "anshirga"
+      }
+    ],
+    "compute": [
+      "AML Compute"
+    ],
+    "datasets": [
+      "None"
+    ],
+    "deployment": [
+      "None"
+    ],
+    "exclude_from_index": false,
+    "framework": [
+      "None"
+    ],
+    "friendly_name": "DNN Text Featurization",
+    "index_order": 2,
+    "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"
+    },
+    "tags": [
+      "None"
+    ],
+    "task": "Text featurization using DNNs for classification"
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

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

@@ -0,0 +1,4 @@
+name: auto-ml-classification-text-dnn
+dependencies:
+- pip:
+  - azureml-sdk

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

@@ -0,0 +1,63 @@
+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
+
+
+def run_inference(test_experiment, compute_target, script_folder, train_run,
+                  train_dataset, 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')
+
+    est = Estimator(source_directory=script_folder,
+                    entry_script='infer.py',
+                    script_params={
+                        '--target_column_name': target_column_name,
+                        '--model_name': model_name
+                    },
+                    inputs=[
+                        train_dataset.as_named_input('train_data'),
+                        test_dataset.as_named_input('test_data')
+                    ],
+                    compute_target=compute_target,
+                    environment_definition=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.log("run_algorithm", run.tags['run_algorithm'])
+    return run
+
+
+def get_result_df(remote_run):
+
+    children = list(remote_run.get_children(recursive=True))
+    summary_df = pd.DataFrame(index=['run_id', 'run_algorithm',
+                                     'primary_metric', 'Score'])
+    goal_minimize = False
+    for run in children:
+        if('run_algorithm' in run.properties and 'score' in run.properties):
+            summary_df[run.id] = [run.id, run.properties['run_algorithm'],
+                                  run.properties['primary_metric'],
+                                  float(run.properties['score'])]
+            if('goal' in run.properties):
+                goal_minimize = run.properties['goal'].split('_')[-1] == 'min'
+
+    summary_df = summary_df.T.sort_values(
+        'Score',
+        ascending=goal_minimize).drop_duplicates(['run_algorithm'])
+    summary_df = summary_df.set_index('run_algorithm')
+
+    return summary_df

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

@@ -0,0 +1,60 @@
+import argparse
+
+import numpy as np
+
+from sklearn.externals import joblib
+
+from azureml.automl.runtime.shared.score import scoring, constants
+from azureml.core import Run
+from azureml.core.model import Model
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument(
+    '--target_column_name', type=str, dest='target_column_name',
+    help='Target Column Name')
+parser.add_argument(
+    '--model_name', type=str, dest='model_name',
+    help='Name of registered model')
+
+args = parser.parse_args()
+target_column_name = args.target_column_name
+model_name = args.model_name
+
+print('args passed are: ')
+print('Target column name: ', target_column_name)
+print('Name of registered model: ', model_name)
+
+model_path = Model.get_model_path(model_name)
+# deserialize the model file back into a sklearn model
+model = joblib.load(model_path)
+
+run = Run.get_context()
+# get input dataset by name
+test_dataset = run.input_datasets['test_data']
+train_dataset = run.input_datasets['train_data']
+
+X_test_df = test_dataset.drop_columns(columns=[target_column_name]) \
+                        .to_pandas_dataframe()
+y_test_df = test_dataset.with_timestamp_columns(None) \
+                        .keep_columns(columns=[target_column_name]) \
+                        .to_pandas_dataframe()
+y_train_df = test_dataset.with_timestamp_columns(None) \
+                         .keep_columns(columns=[target_column_name]) \
+                         .to_pandas_dataframe()
+
+predicted = model.predict_proba(X_test_df)
+
+# Use the AutoML scoring module
+class_labels = np.unique(np.concatenate((y_train_df.values, y_test_df.values)))
+train_labels = model.classes_
+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)
+
+for key, value in scores.items():
+    run.log(key, value)

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",
@@ -75,6 +75,23 @@
         "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 1.11.0 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 +129,6 @@
         "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",
@@ -143,33 +159,22 @@
       "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",
-        "                                                                max_nodes = 4)\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_D2_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)"
       ]
     },
     {
@@ -196,8 +201,8 @@
         "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",
@@ -210,7 +215,24 @@
       "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 +247,6 @@
         "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 +282,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "data_pipeline_run.wait_for_completion()"
+        "data_pipeline_run.wait_for_completion(show_output=False)"
       ]
     },
     {
@@ -272,7 +292,7 @@
         "## 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 +303,8 @@
       "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 +316,23 @@
         "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",
-        "                                                       \"--model_name\", model_name],\n",
-        "                                         outputs=[output_x, output_y], \n",
+        "                                         arguments=[\"--ds_name\", ds_name,\n",
+        "                                                    \"--model_name\", model_name],\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 +347,14 @@
       "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",
         "    \"max_concurrent_iterations\": 3,\n",
         "    \"max_cores_per_iteration\": -1,\n",
         "    \"verbosity\": logging.INFO,\n",
@@ -341,8 +365,8 @@
         "                             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 +382,7 @@
         "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 +401,7 @@
         "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 +454,7 @@
       "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 +463,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "training_pipeline_run.wait_for_completion()"
+        "training_pipeline_run.wait_for_completion(show_output=False)"
       ]
     },
     {
@@ -474,7 +497,7 @@
       "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

@@ -58,7 +58,7 @@ except Exception as e:
     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_last_slice = datetime.today() - relativedelta(weeks=2)
 
 end_time = datetime.utcnow()
 train_df = get_noaa_data(end_time_last_slice, end_time)
@@ -80,10 +80,10 @@ if train_df.size > 0:
                        target_path=folder_name,
                        overwrite=True,
                        show_progress=True)
-
-    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')
-        ds.register(ws, name=args.ds_name)
 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')
+    ds.register(ws, name=args.ds_name)

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

@@ -101,6 +101,23 @@
         "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 1.11.0 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 +145,6 @@
         "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",
@@ -163,7 +179,7 @@
         "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",
@@ -218,19 +234,18 @@
         "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 +254,8 @@
         "months = DataFrame(months)\n",
         "months.columns = range(1,13)\n",
         "months.boxplot()\n",
-        "pyplot.show()\n"
+        "\n",
+        "plt.show()"
       ]
     },
     {
@@ -301,7 +317,7 @@
       "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).  "
       ]
     },
     {
@@ -336,8 +352,6 @@
         "|**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)."
       ]
     },
@@ -358,12 +372,12 @@
         "\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",
         "                             verbosity=logging.INFO,\n",
-        "                             compute_target = compute_target,\n",
+        "                             compute_target=compute_target,\n",
         "                             max_concurrent_iterations=4,\n",
         "                             max_cores_per_iteration=-1,\n",
         "                            **automl_settings)"
@@ -376,7 +390,7 @@
         "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."
       ]
     },
     {
@@ -538,7 +552,7 @@
       "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\")"
       ]
     },
@@ -555,10 +569,8 @@
         "import shutil\n",
         "\n",
         "script_folder = os.path.join(os.getcwd(), 'inference')\n",
-        "project_folder = './inference'\n",
-        "os.makedirs(project_folder, exist_ok=True)\n",
-        "\n",
-        "!copy infer.py inference"
+        "os.makedirs(script_folder, exist_ok=True)\n",
+        "shutil.copy('infer.py', script_folder)"
       ]
     },
     {

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

@@ -76,9 +76,12 @@ 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 +94,8 @@ 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')],

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

@@ -1,12 +1,14 @@
-import pandas as pd
-import numpy as np
 import argparse
-from azureml.core import Run
+
+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
 
 
 def align_outputs(y_predicted, X_trans, X_test, y_test,
@@ -232,6 +234,9 @@ 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()
@@ -239,6 +244,7 @@ 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: ')
@@ -246,6 +252,7 @@ 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 +274,8 @@ 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')
+fitted_model = joblib.load(model_path)
+
 
 if hasattr(fitted_model, 'get_lookback'):
     lookback = fitted_model.get_lookback()
@@ -294,12 +302,11 @@ 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",
@@ -74,6 +74,23 @@
         "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 1.11.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -95,9 +112,9 @@
         "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",
@@ -123,35 +140,22 @@
       "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-6\"\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",
-        "                                                                max_nodes = 4)\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_D2_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)"
       ]
     },
     {
@@ -160,7 +164,7 @@
       "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."
       ]
     },
     {
@@ -201,7 +205,7 @@
       "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()"
+        "dataset.take(5).to_pandas_dataframe().reset_index(drop=True)"
       ]
     },
     {
@@ -220,8 +224,8 @@
       "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)"
       ]
     },
     {
@@ -230,8 +234,8 @@
       "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)"
       ]
     },
     {
@@ -246,8 +250,8 @@
         "|-|-|\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",
@@ -259,7 +263,7 @@
         "|**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",
         "\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."
       ]
     },
     {
@@ -303,12 +307,12 @@
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',                             \n",
         "                             primary_metric='normalized_root_mean_squared_error',\n",
-        "                             blacklist_models = ['ExtremeRandomTrees'],                             \n",
-        "                             experiment_timeout_minutes=20,\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",
-        "                             enable_early_stopping = True,\n",
+        "                             enable_early_stopping=True,\n",
         "                             n_cross_validations=3, \n",
         "                             max_concurrent_iterations=4,\n",
         "                             max_cores_per_iteration=-1,\n",
@@ -445,20 +449,19 @@
       "outputs": [],
       "source": [
         "import os\n",
+        "import shutil\n",
         "\n",
         "script_folder = os.path.join(os.getcwd(), 'forecast')\n",
-        "project_folder = './forecast'\n",
-        "os.makedirs(project_folder, exist_ok=True)\n",
-        "\n",
-        "!copy forecasting_script.py forecast\n",
-        "!copy forecasting_helper.py forecast"
+        "os.makedirs(script_folder, exist_ok=True)\n",
+        "shutil.copy('forecasting_script.py', script_folder)\n",
+        "shutil.copy('forecasting_helper.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 the function called run_forecast. It submits the test data to the best model and run the estimation on the selected compute target.  Validation errors and current status will be shown when setting `show_output=True` and the execution will be synchronous."
       ]
     },
     {
@@ -507,17 +510,16 @@
       "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",
@@ -586,7 +588,7 @@
     ],
     "category": "tutorial",
     "compute": [
-      "remote"
+      "Remote"
     ],
     "datasets": [
       "BikeShare"
@@ -625,7 +627,7 @@
     "tags": [
       "Forecasting"
     ],
-    "task": "forecasting",
+    "task": "Forecasting",
     "version": 3
   },
   "nbformat": 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_script.py

@@ -1,6 +1,6 @@
 import argparse
 import azureml.train.automl
-from azureml.automl.core._vendor.automl.client.core.runtime import forecasting_models
+from azureml.automl.runtime.shared import forecasting_models
 from azureml.core import Run
 from sklearn.externals import joblib
 import forecasting_helper
@@ -32,18 +32,17 @@ test_dataset = run.input_datasets['test_data']
 
 grain_column_names = []
 
-df = test_dataset.to_pandas_dataframe()
+df = test_dataset.to_pandas_dataframe().reset_index(drop=True)
 
-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],
+    X_test_df,
+    y_test_df.values.T[0],
     target_column_name,
     time_column_name,
     max_horizon,

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

@@ -28,11 +28,10 @@
         "1. [Setup](#Setup)\n",
         "1. [Data and Forecasting Configurations](#Data)\n",
         "1. [Train](#Train)\n",
-        "1. [Results](#Results)\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)"
       ]
     },
     {
@@ -43,7 +42,7 @@
         "\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",
@@ -85,6 +84,23 @@
         "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 1.11.0 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 +125,6 @@
         "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",
@@ -140,35 +155,22 @@
       "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 = \"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",
+        "# 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",
-        "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",
-        "                                                                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)\n",
-        "\n",
-        "# For a more detailed view of current AmlCompute status, use get_status()."
+        "compute_target.wait_for_completion(show_output=True)"
       ]
     },
     {
@@ -211,7 +213,7 @@
       "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 +255,7 @@
       "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 +265,8 @@
       "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)"
       ]
     },
     {
@@ -301,8 +303,8 @@
         "|-|-|\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",
@@ -316,7 +318,7 @@
       "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."
       ]
     },
     {
@@ -332,12 +334,12 @@
         "\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",
+        "                             enable_early_stopping=True,\n",
         "                             n_cross_validations=3,                             \n",
         "                             verbosity=logging.INFO,\n",
         "                            **automl_settings)"
@@ -454,7 +456,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_test = test.to_pandas_dataframe()\n",
+        "X_test = test.to_pandas_dataframe().reset_index(drop=True)\n",
         "y_test = X_test.pop(target_column_name).values"
       ]
     },
@@ -463,11 +465,7 @@
       "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."
+        "For forecasting, we will use the forecast function instead of the predict function. 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. Forecast function also can handle more complicated scenarios, see the [forecast function notebook](../forecasting-forecast-function/auto-ml-forecasting-function.ipynb)."
       ]
     },
     {
@@ -476,15 +474,10 @@
       "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)"
+        "y_predictions, X_trans = fitted_model.forecast(X_test)"
       ]
     },
     {
@@ -514,16 +507,15 @@
       "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=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",
@@ -557,7 +549,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Advanced Training\n",
+        "## 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, 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."
       ]
     },
@@ -568,7 +560,7 @@
         "### 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",
         "\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."
       ]
     },
     {
@@ -586,8 +578,8 @@
         "\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",
@@ -642,7 +634,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Advanced Results\n",
+        "## 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, 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."
       ]
     },
@@ -652,15 +644,10 @@
       "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)"
+        "y_predictions, X_trans = fitted_model_lags.forecast(X_test)"
       ]
     },
     {
@@ -680,16 +667,15 @@
       "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=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",
@@ -730,14 +716,7 @@
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
       "version": "3.6.8"
-    },
-    "star_tag": [
-      "featured"
-    ],
-    "tags": [
-      ""
-    ],
-    "task": "Forecasting"
+    }
   },
   "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-forecast-function/auto-ml-forecasting-function.ipynb

@@ -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 1.11.0 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",
@@ -100,9 +116,9 @@
         "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",
@@ -126,15 +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",
@@ -145,9 +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",
@@ -158,14 +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",
@@ -181,8 +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)"
       ]
     },
     {
@@ -212,7 +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()"
@@ -257,29 +272,22 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "amlcompute_cluster_name = \"cpu-cluster-8\"\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",
+        "from azureml.core.compute import ComputeTarget, AmlCompute\n",
+        "from azureml.core.compute_target import ComputeTargetException\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",
+        "# Choose a name for your CPU cluster\n",
+        "amlcompute_cluster_name = \"fcfn-cluster\"\n",
         "\n",
-        "    # Create the cluster.\\n\",\n",
-        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\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_D2_V2',\n",
+        "                                                           max_nodes=6)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_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)"
       ]
     },
     {
@@ -288,7 +296,7 @@
       "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",
@@ -304,11 +312,11 @@
       "outputs": [],
       "source": [
         "lags = [1,2,3]\n",
-        "max_horizon = n_test_periods\n",
+        "forecast_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",
+        "    'time_series_id_column_names': [ TIME_SERIES_ID_COLUMN_NAME ],\n",
+        "    'forecast_horizon': forecast_horizon ,\n",
         "    'target_lags': lags\n",
         "}"
       ]
@@ -317,7 +325,7 @@
       "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."
       ]
     },
     {
@@ -334,7 +342,7 @@
         "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",
@@ -345,9 +353,24 @@
         "                             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",
-        "\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()"
       ]
@@ -376,9 +399,7 @@
         "\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."
       ]
     },
     {
@@ -407,8 +428,7 @@
       "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",
@@ -436,7 +456,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "quantiles =  fitted_model.forecast_quantiles(X_test, y_query)\n",
+        "quantiles =  fitted_model.forecast_quantiles(X_test)\n",
         "quantiles"
       ]
     },
@@ -447,7 +467,7 @@
         "#### 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."
       ]
     },
     {
@@ -459,10 +479,10 @@
         "# 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"
       ]
     },
     {
@@ -471,7 +491,7 @@
       "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."
       ]
     },
     {
@@ -498,7 +518,7 @@
         "\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`)."
       ]
@@ -515,13 +535,13 @@
         "                                      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())"
       ]
     },
     {
@@ -538,9 +558,7 @@
       "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)"
@@ -550,7 +568,7 @@
       "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."
       ]
@@ -565,7 +583,7 @@
         "\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",
@@ -635,8 +653,8 @@
       "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)"
       ]
     },
@@ -666,7 +684,7 @@
         "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",
@@ -682,7 +700,7 @@
       "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."
       ]
     },
     {
@@ -697,20 +715,105 @@
         "# 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": "erwright"
       }
     ],
     "category": "tutorial",
     "compute": [
-      "remote"
+      "Remote"
     ],
     "datasets": [
       "None"
@@ -739,13 +842,13 @@
       "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-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

@@ -40,7 +40,7 @@
         "## Introduction\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."
       ]
@@ -65,7 +65,25 @@
         "\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 1.11.0 of the Azure ML SDK\")\n",
+        "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
     {
@@ -89,9 +107,9 @@
         "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",
@@ -117,35 +135,22 @@
       "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-7\"\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",
-        "                                                                max_nodes = 4)\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_D2_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)"
       ]
     },
     {
@@ -314,19 +319,60 @@
         "target_column_name = 'Quantity'"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Customization\n",
+        "\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",
+        "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 methods are constant for target data and mean, median, most frequent and constant for training data. 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.\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)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [
+          "sample-featurizationconfig-remarks"
+        ]
+      },
+      "outputs": [],
+      "source": [
+        "featurization_config = FeaturizationConfig()\n",
+        "featurization_config.drop_columns = ['logQuantity']  # 'logQuantity' is a leaky feature, so we remove it.\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\"})"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
         "## Train\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 [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: 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",
+        "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 grain 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 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",
+        "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 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",
-        "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",
+        "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. Note that these models are only available for [Enterprise Edition Workspaces](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-manage-workspace#upgrade).\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",
@@ -334,7 +380,7 @@
         "|-|-|\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",
@@ -345,8 +391,9 @@
         "|**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|"
+        "|**max_horizon**|Maximum desired forecast horizon in units of time-series frequency|\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*.|\n",
+        "|**max_cores_per_iteration**|Maximum number of cores to utilize per iteration. A value of -1 indicates all available cores should be used.|"
       ]
     },
     {
@@ -358,22 +405,21 @@
         "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",
         "\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",
+        "                             enable_early_stopping=True,\n",
+        "                             featurization=featurization_config,\n",
         "                             n_cross_validations=3,\n",
-        "                             max_concurrent_iterations=4,\n",
-        "                             max_cores_per_iteration=-1,\n",
         "                             verbosity=logging.INFO,\n",
+        "                             max_cores_per_iteration=-1,\n",
         "                             **time_series_settings)"
       ]
     },
@@ -382,7 +428,7 @@
       "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."
       ]
     },
     {
@@ -423,6 +469,33 @@
         "model_name = best_run.properties['model_name']"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Transparency\n",
+        "\n",
+        "View updated featurization summary"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "custom_featurizer = fitted_model.named_steps['timeseriestransformer']"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "custom_featurizer.get_featurization_summary()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -455,9 +528,7 @@
       "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",
-        "\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_."
+        "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."
       ]
     },
     {
@@ -466,15 +537,10 @@
       "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)"
+        "y_predictions, X_trans = fitted_model.forecast(X_test)"
       ]
     },
     {
@@ -483,7 +549,7 @@
       "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",
         "\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. "
+        "The [forecast function notebook](../forecasting-forecast-function/auto-ml-forecasting-function.ipynb)."
       ]
     },
     {
@@ -514,16 +580,15 @@
       "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=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",
@@ -570,138 +635,7 @@
       "source": [
         "### Develop the scoring script\n",
         "\n",
-        "Serializing and deserializing complex data frames may be tricky. We first develop the ```run()``` function of the scoring script locally, then write it into a scoring script. It is much easier to debug any quirks of the scoring function without crossing two compute environments. For this exercise, we handle a common quirk of how pandas dataframes serialize time stamp values."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# this is where we test the run function of the scoring script interactively\n",
-        "# before putting it in the scoring script\n",
-        "\n",
-        "timestamp_columns = ['WeekStarting']\n",
-        "\n",
-        "def run(rawdata, test_model = None):\n",
-        "    \"\"\"\n",
-        "    Intended to process 'rawdata' string produced by\n",
-        "    \n",
-        "    {'X': X_test.to_json(), y' : y_test.to_json()}\n",
-        "    \n",
-        "    Don't convert the X payload to numpy.array, use it as pandas.DataFrame\n",
-        "    \"\"\"\n",
-        "    try:\n",
-        "        # unpack the data frame with timestamp        \n",
-        "        rawobj = json.loads(rawdata)                    # rawobj is now a dict of strings        \n",
-        "        X_pred = pd.read_json(rawobj['X'], convert_dates=False)   # load the pandas DF from a json string\n",
-        "        for col in timestamp_columns:                             # fix timestamps\n",
-        "            X_pred[col] = pd.to_datetime(X_pred[col], unit='ms') \n",
-        "        \n",
-        "        y_pred = np.array(rawobj['y'])                    # reconstitute numpy array from serialized list\n",
-        "        \n",
-        "        if test_model is None:\n",
-        "            result = model.forecast(X_pred, y_pred)       # use the global model from init function\n",
-        "        else:\n",
-        "            result = test_model.forecast(X_pred, y_pred)  # use the model on which we are testing\n",
-        "        \n",
-        "    except Exception as e:\n",
-        "        result = str(e)\n",
-        "        return json.dumps({\"error\": result})\n",
-        "    \n",
-        "    forecast_as_list = result[0].tolist()\n",
-        "    index_as_df = result[1].index.to_frame().reset_index(drop=True)\n",
-        "    \n",
-        "    return json.dumps({\"forecast\": forecast_as_list,   # return the minimum over the wire: \n",
-        "                       \"index\": index_as_df.to_json()  # no forecast and its featurized values\n",
-        "                      })"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# test the run function here before putting in the scoring script\n",
-        "import json\n",
-        "\n",
-        "test_sample = json.dumps({'X': X_test.to_json(), 'y' : y_query.tolist()})\n",
-        "response = run(test_sample, fitted_model)\n",
-        "\n",
-        "# unpack the response, dealing with the timestamp serialization again\n",
-        "res_dict = json.loads(response)\n",
-        "y_fcst_all = pd.read_json(res_dict['index'])\n",
-        "y_fcst_all[time_column_name] = pd.to_datetime(y_fcst_all[time_column_name], unit = 'ms')\n",
-        "y_fcst_all['forecast'] = res_dict['forecast']\n",
-        "y_fcst_all.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Now that the function works locally in the notebook, let's write it down into the scoring script. The scoring script is authored by the data scientist. Adjust it to taste, adding inputs, outputs and processing as needed."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%writefile score_fcast.py\n",
-        "import pickle\n",
-        "import json\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "import azureml.train.automl\n",
-        "from sklearn.externals import joblib\n",
-        "from azureml.core.model import Model\n",
-        "\n",
-        "\n",
-        "def init():\n",
-        "    global model\n",
-        "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
-        "    # deserialize the model file back into a sklearn model\n",
-        "    model = joblib.load(model_path)\n",
-        "\n",
-        "timestamp_columns = ['WeekStarting']\n",
-        "\n",
-        "def run(rawdata, test_model = None):\n",
-        "    \"\"\"\n",
-        "    Intended to process 'rawdata' string produced by\n",
-        "    \n",
-        "    {'X': X_test.to_json(), y' : y_test.to_json()}\n",
-        "    \n",
-        "    Don't convert the X payload to numpy.array, use it as pandas.DataFrame\n",
-        "    \"\"\"\n",
-        "    try:\n",
-        "        # unpack the data frame with timestamp        \n",
-        "        rawobj = json.loads(rawdata)                    # rawobj is now a dict of strings        \n",
-        "        X_pred = pd.read_json(rawobj['X'], convert_dates=False)   # load the pandas DF from a json string\n",
-        "        for col in timestamp_columns:                             # fix timestamps\n",
-        "            X_pred[col] = pd.to_datetime(X_pred[col], unit='ms') \n",
-        "        \n",
-        "        y_pred = np.array(rawobj['y'])                    # reconstitute numpy array from serialized list\n",
-        "        \n",
-        "        if test_model is None:\n",
-        "            result = model.forecast(X_pred, y_pred)       # use the global model from init function\n",
-        "        else:\n",
-        "            result = test_model.forecast(X_pred, y_pred)  # use the model on which we are testing\n",
-        "        \n",
-        "    except Exception as e:\n",
-        "        result = str(e)\n",
-        "        return json.dumps({\"error\": result})\n",
-        "    \n",
-        "    # prepare to send over wire as json\n",
-        "    forecast_as_list = result[0].tolist()\n",
-        "    index_as_df = result[1].index.to_frame().reset_index(drop=True)\n",
-        "    \n",
-        "    return json.dumps({\"forecast\": forecast_as_list,   # return the minimum over the wire: \n",
-        "                       \"index\": index_as_df.to_json()  # no forecast and its featurized values\n",
-        "                      })"
+        "For the deployment we need a function which will run the forecast on serialized data. It can be obtained from the best_run."
       ]
     },
     {
@@ -711,11 +645,7 @@
       "outputs": [],
       "source": [
         "script_file_name = 'score_fcast.py'\n",
-        "with open(script_file_name, 'r') as cefr:\n",
-        "    content = cefr.read()\n",
-        "\n",
-        "with open(script_file_name, 'w') as cefw:\n",
-        "    cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
+        "best_run.download_file('outputs/scoring_file_v_1_0_0.py', script_file_name)"
       ]
     },
     {
@@ -773,14 +703,18 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# we send the data to the service serialized into a json string\n",
-        "test_sample = json.dumps({'X':X_test.to_json(), 'y' : y_query.tolist()})\n",
+        "import json\n",
+        "X_query = X_test.copy()\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",
         "response = aci_service.run(input_data = test_sample)\n",
-        "\n",
         "# translate from networkese to datascientese\n",
         "try: \n",
         "    res_dict = json.loads(response)\n",
-        "    y_fcst_all = pd.read_json(res_dict['index'])\n",
+        "    y_fcst_all = pd.DataFrame(res_dict['index'])\n",
         "    y_fcst_all[time_column_name] = pd.to_datetime(y_fcst_all[time_column_name], unit = 'ms')\n",
         "    y_fcst_all['forecast'] = res_dict['forecast']    \n",
         "except:\n",
@@ -823,7 +757,7 @@
     "category": "tutorial",
     "celltoolbar": "Raw Cell Format",
     "compute": [
-      "remote"
+      "Remote"
     ],
     "datasets": [
       "Orange Juice Sales"
@@ -852,8 +786,11 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.7"
+      "version": "3.6.8"
     },
+    "tags": [
+      "None"
+    ],
     "task": "Forecasting"
   },
   "nbformat": 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/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.explain.model._internal.explanation_client 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 1.11.0 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",
@@ -155,8 +174,7 @@
         "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",
+        "    \"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",
@@ -238,9 +256,9 @@
       "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 +278,14 @@
       "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 +349,407 @@
         "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-explain-model 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 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": [
+        "#### 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')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Initialize the Mimic Explainer for feature importance\n",
+        "For explaining the AutoML models, use the MimicWrapper from azureml.explain.model 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.explain.model.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_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": [
+        "#### 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.explain.model.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.explain.model 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 create the conda dependencies comprising of the azureml-explain-model, azureml-train-automl and azureml-defaults packages."
+      ]
+    },
+    {
+      "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 numpy as np\n",
+        "import pandas as pd\n",
+        "import os\n",
+        "import pickle\n",
+        "import azureml.train.automl\n",
+        "import azureml.explain.model\n",
+        "from azureml.train.automl.runtime.automl_explain_utilities import AutoMLExplainerSetupClass, \\\n",
+        "    automl_setup_model_explanations\n",
+        "import joblib\n",
+        "from azureml.core.model import Model\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",
+        "    # 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"
+      ]
+    },
+    {
+      "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']))"
+      ]
+    },
+    {
+      "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 +778,7 @@
   "metadata": {
     "authors": [
       {
-        "name": "tzvikei"
+        "name": "anumamah"
       }
     ],
     "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-concrete-strength/auto-ml-regression-concrete-strength.ipynb

@@ -1,756 +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/regression-concrete-strength/auto-ml-regression-concrete-strength.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "_**Regression with Deployment using Hardware Performance Dataset**_\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",
-        "1. [Acknowledgements](#Acknowledgements)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "In this example we use the Predicting Compressive Strength of Concrete Dataset to showcase how you can use AutoML for a regression problem. The regression goal is to predict the compressive strength of concrete based off of different ingredient combinations and the quantities of those ingredients.\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",
-        "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 local compute.\n",
-        "4. Explore the results.\n",
-        "5. Test the best fitted model."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n",
-        "As part of the setup you have already created an Azure ML Workspace object. For AutoML 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",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "import os\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": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# Choose a name for the experiment.\n",
-        "experiment_name = 'automl-regression-concrete'\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 Name'] = 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": [
-        "## 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",
-        "#### 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 = \"automlcl\"\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": [
-        "# Data\n",
-        "\n",
-        "Create a run configuration for the remote run."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "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",
-        "\n",
-        "# Set compute target to AmlCompute\n",
-        "conda_run_config.target = compute_target\n",
-        "conda_run_config.environment.docker.enabled = True\n",
-        "\n",
-        "cd = CondaDependencies.create(conda_packages=['numpy', 'py-xgboost<=0.80'])\n",
-        "conda_run_config.environment.python.conda_dependencies = cd"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load Data\n",
-        "\n",
-        "Load the concrete strength dataset into X and y.  X contains the training features, which are inputs to the model.  y contains the training labels, which are the expected output of the model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/compresive_strength_concrete.csv\"\n",
-        "dataset = Dataset.Tabular.from_delimited_files(data)\n",
-        "X = dataset.drop_columns(columns=['CONCRETE'])\n",
-        "y = dataset.keep_columns(columns=['CONCRETE'], validate=True)\n",
-        "X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
-        "y_train, y_test = y.random_split(percentage=0.8, seed=223) \n",
-        "dataset.take(5).to_pandas_dataframe()"
-      ]
-    },
-    {
-      "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 or regression|\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",
-        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
-        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
-        "|**n_cross_validations**|Number of cross validation splits.|\n",
-        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y**|(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": "markdown",
-      "metadata": {},
-      "source": [
-        "##### If you would like to see even better results increase \"iteration_time_out minutes\" to 10+ mins and increase \"iterations\" to a minimum of 30"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 5,\n",
-        "    \"iterations\": 10,\n",
-        "    \"n_cross_validations\": 5,\n",
-        "    \"primary_metric\": 'spearman_correlation',\n",
-        "    \"preprocess\": True,\n",
-        "    \"max_concurrent_iterations\": 5,\n",
-        "    \"verbosity\": logging.INFO,\n",
-        "}\n",
-        "\n",
-        "automl_config = AutoMLConfig(task = 'regression',\n",
-        "                             debug_log = 'automl.log',\n",
-        "                             run_configuration=conda_run_config,\n",
-        "                             X = X_train,\n",
-        "                             y = y_train,\n",
-        "                             **automl_settings\n",
-        "                            )"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config, show_output = True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Results\n",
-        "Widget for Monitoring Runs\n",
-        "The widget will first report a \u00e2\u20ac\u0153loading status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
-        "Note: The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "RunDetails(remote_run).show() "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "\n",
-        "Retrieve All Child Runs\n",
-        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "children = list(remote_run.get_children())\n",
-        "metricslist = {}\n",
-        "for run in children:\n",
-        "    properties = run.get_properties()\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
-        "    metricslist[int(properties['iteration'])] = metrics\n",
-        "\n",
-        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-        "rundata"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Retrieve the Best Model\n",
-        "Below we select the best pipeline from our iterations. The get_output method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing. Overloads on get_output allow you to retrieve the best run and fitted model for any logged metric or for a particular iteration."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = remote_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Best Model 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, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "iteration = 3\n",
-        "third_run, third_model = remote_run.get_output(iteration = iteration)\n",
-        "print(third_run)\n",
-        "print(third_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Register the Fitted Model for Deployment\n",
-        "If neither metric nor iteration are specified in the register_model call, the iteration with the best primary metric is registered."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "description = 'AutoML Model'\n",
-        "tags = None\n",
-        "model = remote_run.register_model(description = description, tags = tags)\n",
-        "\n",
-        "print(remote_run.model_id) # This will be written to the script file later in the notebook."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create Scoring Script\n",
-        "The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%writefile score.py\n",
-        "import pickle\n",
-        "import json\n",
-        "import numpy\n",
-        "import azureml.train.automl\n",
-        "from sklearn.externals import joblib\n",
-        "from azureml.core.model import Model\n",
-        "\n",
-        "def init():\n",
-        "    global model\n",
-        "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
-        "    # deserialize the model file back into a sklearn model\n",
-        "    model = joblib.load(model_path)\n",
-        "\n",
-        "def run(rawdata):\n",
-        "    try:\n",
-        "        data = json.loads(rawdata)['data']\n",
-        "        data = numpy.array(data)\n",
-        "        result = model.predict(data)\n",
-        "    except Exception as e:\n",
-        "        result = str(e)\n",
-        "        return json.dumps({\"error\": result})\n",
-        "    return json.dumps({\"result\":result.tolist()})"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create a YAML File for the Environment"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "for p in ['azureml-train-automl', 'azureml-core']:\n",
-        "    print('{}\\t{}'.format(p, dependencies[p]))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost==0.80'], pip_packages=['azureml-defaults','azureml-train-automl'])\n",
-        "\n",
-        "conda_env_file_name = 'myenv.yml'\n",
-        "myenv.save_to_file('.', conda_env_file_name)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Substitute the actual version number in the environment file.\n",
-        "# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
-        "# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
-        "\n",
-        "with open(conda_env_file_name, 'r') as cefr:\n",
-        "    content = cefr.read()\n",
-        "\n",
-        "with open(conda_env_file_name, 'w') as cefw:\n",
-        "    cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-train-automl']))\n",
-        "\n",
-        "# Substitute the actual model id in the script file.\n",
-        "\n",
-        "script_file_name = 'score.py'\n",
-        "\n",
-        "with open(script_file_name, 'r') as cefr:\n",
-        "    content = cefr.read()\n",
-        "\n",
-        "with open(script_file_name, 'w') as cefw:\n",
-        "    cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Deploy the model as a Web Service on Azure Container Instance"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "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",
-        "\n",
-        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
-        "                                               memory_gb = 1, \n",
-        "                                               tags = {'area': \"digits\", 'type': \"automl_regression\"}, \n",
-        "                                               description = 'sample service for Automl Regression')\n",
-        "\n",
-        "aci_service_name = 'automl-sample-concrete'\n",
-        "print(aci_service_name)\n",
-        "aci_service = Model.deploy(ws, aci_service_name, [model], inference_config, aciconfig)\n",
-        "aci_service.wait_for_deployment(True)\n",
-        "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": {},
-      "source": [
-        "### Get Logs from a Deployed Web Service\n",
-        "\n",
-        "Gets logs from a deployed web service."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#aci_service.get_logs()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Test\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 = X_test.to_pandas_dataframe()\n",
-        "y_test = y_test.to_pandas_dataframe()\n",
-        "y_test = np.array(y_test)\n",
-        "y_test = y_test[:,0]\n",
-        "X_train = X_train.to_pandas_dataframe()\n",
-        "y_train = y_train.to_pandas_dataframe()\n",
-        "y_train = np.array(y_train)\n",
-        "y_train = y_train[:,0]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "##### Predict on training and test set, and calculate residual values."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_pred_train = fitted_model.predict(X_train)\n",
-        "y_residual_train = y_train - y_pred_train\n",
-        "\n",
-        "y_pred_test = fitted_model.predict(X_test)\n",
-        "y_residual_test = y_test - y_pred_test\n",
-        "\n",
-        "y_residual_train.shape"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%matplotlib inline\n",
-        "from sklearn.metrics import mean_squared_error, r2_score\n",
-        "\n",
-        "# Set up a multi-plot chart.\n",
-        "f, (a0, a1) = plt.subplots(1, 2, gridspec_kw = {'width_ratios':[1, 1], 'wspace':0, 'hspace': 0})\n",
-        "f.suptitle('Regression Residual Values', fontsize = 18)\n",
-        "f.set_figheight(6)\n",
-        "f.set_figwidth(16)\n",
-        "\n",
-        "# Plot residual values of training set.\n",
-        "a0.axis([0, 360, -200, 200])\n",
-        "a0.plot(y_residual_train, 'bo', alpha = 0.5)\n",
-        "a0.plot([-10,360],[0,0], 'r-', lw = 3)\n",
-        "a0.text(16,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_train, y_pred_train))), fontsize = 12)\n",
-        "a0.text(16,140,'R2 score = {0:.2f}'.format(r2_score(y_train, y_pred_train)), fontsize = 12)\n",
-        "a0.set_xlabel('Training samples', fontsize = 12)\n",
-        "a0.set_ylabel('Residual Values', fontsize = 12)\n",
-        "\n",
-        "# Plot a histogram.\n",
-        "#a0.hist(y_residual_train, orientation = 'horizontal', color = ['b']*len(y_residual_train), bins = 10, histtype = 'step')\n",
-        "#a0.hist(y_residual_train, orientation = 'horizontal', color = ['b']*len(y_residual_train), alpha = 0.2, bins = 10)\n",
-        "\n",
-        "# Plot residual values of test set.\n",
-        "a1.axis([0, 90, -200, 200])\n",
-        "a1.plot(y_residual_test, 'bo', alpha = 0.5)\n",
-        "a1.plot([-10,360],[0,0], 'r-', lw = 3)\n",
-        "a1.text(5,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_test, y_pred_test))), fontsize = 12)\n",
-        "a1.text(5,140,'R2 score = {0:.2f}'.format(r2_score(y_test, y_pred_test)), fontsize = 12)\n",
-        "a1.set_xlabel('Test samples', fontsize = 12)\n",
-        "a1.set_yticklabels([])\n",
-        "\n",
-        "# Plot a histogram.\n",
-        "#a1.hist(y_residual_test, orientation = 'horizontal', color = ['b']*len(y_residual_test), bins = 10, histtype = 'step')\n",
-        "#a1.hist(y_residual_test, orientation = 'horizontal', color = ['b']*len(y_residual_test), alpha = 0.2, bins = 10)\n",
-        "\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "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."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Plot outputs\n",
-        "%matplotlib notebook\n",
-        "test_pred = plt.scatter(y_test, y_pred_test, color='b')\n",
-        "test_test = plt.scatter(y_test, y_test, color='g')\n",
-        "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Acknowledgements\n",
-        "\n",
-        "This Predicting Compressive Strength of Concrete Dataset is made available under the CC0 1.0 Universal (CC0 1.0)\n",
-        "Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the CC0 1.0 Universal (CC0 1.0)\n",
-        "Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/ . The dataset itself can be found here: https://www.kaggle.com/pavanraj159/concrete-compressive-strength-data-set and http://archive.ics.uci.edu/ml/datasets/concrete+compressive+strength\n",
-        "\n",
-        "I-Cheng Yeh, \"Modeling of strength of high performance concrete using artificial neural networks,\" Cement and Concrete Research, Vol. 28, No. 12, pp. 1797-1808 (1998). \n",
-        "\n",
-        "Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science."
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "v-rasav"
-      }
-    ],
-    "category": "tutorial",
-    "compute": [
-      "AML Compute"
-    ],
-    "datasets": [
-      "Concrete"
-    ],
-    "deployment": [
-      "Azure Container Instance"
-    ],
-    "exclude_from_index": false,
-    "framework": [
-      "Azure ML AutoML"
-    ],
-    "friendly_name": "Regression with deployment using concrete dataset",
-    "index_order": 1,
-    "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": "3.7.1"
-    },
-    "tags": [
-      ""
-    ],
-    "task": "Regression"
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/regression-concrete-strength/auto-ml-regression-concrete-strength.yml

@@ -1,12 +0,0 @@
-name: auto-ml-regression-concrete-strength
-dependencies:
-- pip:
-  - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-explain-model
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - azureml-dataprep[pandas]

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

@@ -40,7 +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",
+        "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",
         "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",
@@ -51,8 +51,8 @@
         "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"
       ]
     },
     {
@@ -85,6 +85,23 @@
         "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 1.11.0 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 +115,6 @@
         "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",
@@ -127,35 +143,22 @@
       "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",
+        "# 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_D2_V2',\n",
+        "                                                           max_nodes=4)\n",
+        "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, compute_config)\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 = 4)\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 +209,9 @@
         "|-|-|\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.|"
@@ -239,12 +242,16 @@
     {
       "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 +264,16 @@
     {
       "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",
@@ -320,8 +331,6 @@
       "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"
       ]
@@ -514,7 +523,7 @@
         "    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 +541,7 @@
       "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"
       ]
     },
     {
@@ -552,14 +560,9 @@
         "# 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 +607,8 @@
       "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 +616,7 @@
       "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."
       ]
     },
     {
@@ -653,11 +626,10 @@
       "outputs": [],
       "source": [
         "from azureml.explain.model._internal.explanation_client import ExplanationClient\n",
-        "from azureml.contrib.interpret.visualize import ExplanationDashboard\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 +637,7 @@
       "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."
       ]
     },
     {
@@ -674,9 +646,9 @@
       "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())"
       ]
     },
     {
@@ -718,20 +690,10 @@
       "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())"
@@ -772,6 +734,7 @@
         "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",
@@ -779,9 +742,8 @@
         "                                                     \"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 +781,7 @@
       "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",

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

how-to-use-azureml/automated-machine-learning/regression-explanation-featurization/score_explain.py

@@ -5,8 +5,9 @@ import os
 import pickle
 import azureml.train.automl
 import azureml.explain.model
-from azureml.train.automl.automl_explain_utilities import AutoMLExplainerSetupClass, automl_setup_model_explanations
-from sklearn.externals import joblib
+from azureml.train.automl.runtime.automl_explain_utilities import AutoMLExplainerSetupClass, \
+    automl_setup_model_explanations
+import joblib
 from azureml.core.model import Model
 
 

how-to-use-azureml/automated-machine-learning/regression-explanation-featurization/train_explainer.py

@@ -4,14 +4,14 @@ import os
 
 from azureml.core.run import Run
 from azureml.core.experiment import Experiment
-from sklearn.externals import joblib
 from azureml.core.dataset import Dataset
-from azureml.train.automl.automl_explain_utilities import AutoMLExplainerSetupClass, automl_setup_model_explanations
+from azureml.train.automl.runtime.automl_explain_utilities import AutoMLExplainerSetupClass, \
+    automl_setup_model_explanations, automl_check_model_if_explainable
 from azureml.explain.model.mimic.models.lightgbm_model import LGBMExplainableModel
 from azureml.explain.model.mimic_wrapper import MimicWrapper
-from automl.client.core.common.constants import MODEL_PATH
-from azureml.explain.model.scoring.scoring_explainer import TreeScoringExplainer, save
-
+from azureml.automl.core.shared.constants import MODEL_PATH
+from azureml.explain.model.scoring.scoring_explainer import TreeScoringExplainer
+import joblib
 
 OUTPUT_DIR = './outputs/'
 os.makedirs(OUTPUT_DIR, exist_ok=True)
@@ -21,9 +21,14 @@ run = Run.get_context()
 ws = run.experiment.workspace
 
 # Get the AutoML run object from the experiment name and the workspace
-experiment = Experiment(ws, '<<experimnet_name>>')
+experiment = Experiment(ws, '<<experiment_name>>')
 automl_run = Run(experiment=experiment, run_id='<<run_id>>')
 
+# Check if this AutoML model is explainable
+if not automl_check_model_if_explainable(automl_run):
+    raise Exception("Model explanations is currently not supported for " + automl_run.get_properties().get(
+        'run_algorithm'))
+
 # Download the best model from the artifact store
 automl_run.download_file(name=MODEL_PATH, output_file_path='model.pkl')
 
@@ -54,22 +59,22 @@ explainer = MimicWrapper(ws, automl_explainer_setup_obj.automl_estimator, LGBMEx
                          classes=automl_explainer_setup_obj.classes)
 
 # Compute the engineered explanations
-engineered_explanations = explainer.explain(['local', 'global'],
+engineered_explanations = explainer.explain(['local', 'global'], tag='engineered explanations',
                                             eval_dataset=automl_explainer_setup_obj.X_test_transform)
 
 # Compute the raw explanations
-raw_explanations = explainer.explain(['local', 'global'], get_raw=True,
+raw_explanations = explainer.explain(['local', 'global'], get_raw=True, tag='raw explanations',
                                      raw_feature_names=automl_explainer_setup_obj.raw_feature_names,
                                      eval_dataset=automl_explainer_setup_obj.X_test_transform)
 
 print("Engineered and raw explanations computed successfully")
 
-
 # Initialize the ScoringExplainer
 scoring_explainer = TreeScoringExplainer(explainer.explainer, feature_maps=[automl_explainer_setup_obj.feature_map])
 
 # Pickle scoring explainer locally
-save(scoring_explainer, exist_ok=True)
+with open('scoring_explainer.pkl', 'wb') as stream:
+    joblib.dump(scoring_explainer, stream)
 
 # Upload the scoring explainer to the automl run
 automl_run.upload_file('outputs/scoring_explainer.pkl', 'scoring_explainer.pkl')

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

@@ -1,13 +0,0 @@
-name: auto-ml-regression-hardware-performance-explanation-and-featurization
-dependencies:
-- pip:
-  - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-explain-model
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - azureml-explain-model
-  - azureml-contrib-interpret

how-to-use-azureml/automated-machine-learning/regression-hardware-performance/auto-ml-regression-hardware-performance.ipynb

@@ -1,761 +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/regression-hardware-performance/auto-ml-regression-hardware-performance.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Automated Machine Learning\n",
-        "_**Regression with Deployment using Hardware Performance Dataset**_\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",
-        "1. [Acknowledgements](#Acknowledgements)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "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",
-        "\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",
-        "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 local compute.\n",
-        "4. Explore the results.\n",
-        "5. Test the best fitted model."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n",
-        "As part of the setup you have already created an Azure ML Workspace object. For AutoML 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",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "import os\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": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# Choose a name for the experiment.\n",
-        "experiment_name = 'automl-regression-hardware'\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 Name'] = 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": [
-        "## 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",
-        "#### 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 = \"automlcl\"\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": [
-        "# Data\n",
-        "\n",
-        "Create a run configuration for the remote run."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "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",
-        "\n",
-        "# Set compute target to AmlCompute\n",
-        "conda_run_config.target = compute_target\n",
-        "conda_run_config.environment.docker.enabled = True\n",
-        "\n",
-        "cd = CondaDependencies.create(conda_packages=['numpy', 'py-xgboost<=0.80'])\n",
-        "conda_run_config.environment.python.conda_dependencies = cd"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Load Data\n",
-        "\n",
-        "Load the hardware performance dataset into X and y. X contains the training features, which are inputs to the model. y contains the training labels, which are the expected output of 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",
-        "X = dataset.drop_columns(columns=['ERP'])\n",
-        "y = dataset.keep_columns(columns=['ERP'], validate=True)\n",
-        "X_train, X_test = X.random_split(percentage=0.8, seed=223)\n",
-        "y_train, y_test = y.random_split(percentage=0.8, seed=223)\n",
-        "dataset.take(5).to_pandas_dataframe()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "\n",
-        "## 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 or regression|\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",
-        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
-        "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
-        "|**n_cross_validations**|Number of cross validation splits.|\n",
-        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y**|(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": "markdown",
-      "metadata": {},
-      "source": [
-        "##### If you would like to see even better results increase \"iteration_time_out minutes\" to 10+ mins and increase \"iterations\" to a minimum of 30"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 5,\n",
-        "    \"iterations\": 10,\n",
-        "    \"n_cross_validations\": 5,\n",
-        "    \"primary_metric\": 'spearman_correlation',\n",
-        "    \"preprocess\": True,\n",
-        "    \"max_concurrent_iterations\": 5,\n",
-        "    \"verbosity\": logging.INFO,\n",
-        "}\n",
-        "\n",
-        "automl_config = AutoMLConfig(task = 'regression',\n",
-        "                             debug_log = 'automl_errors.log',\n",
-        "                             run_configuration=conda_run_config,\n",
-        "                             X = X_train,\n",
-        "                             y = y_train,\n",
-        "                             **automl_settings\n",
-        "                            )"
-      ]
-    },
-    {
-      "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": [
-        "remote_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Results"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Widget for Monitoring Runs\n",
-        "\n",
-        "The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
-        "\n",
-        "**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.widgets import RunDetails\n",
-        "RunDetails(remote_run).show() "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Wait until the run finishes.\n",
-        "remote_run.wait_for_completion(show_output = True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Retrieve All Child Runs\n",
-        "You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "children = list(remote_run.get_children())\n",
-        "metricslist = {}\n",
-        "for run in children:\n",
-        "    properties = run.get_properties()\n",
-        "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
-        "    metricslist[int(properties['iteration'])] = metrics\n",
-        "\n",
-        "rundata = pd.DataFrame(metricslist).sort_index(1)\n",
-        "rundata"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Retrieve the Best Model\n",
-        "Below we select the best pipeline from our iterations. The get_output method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing. Overloads on get_output allow you to retrieve the best run and fitted model for any logged metric or for a particular iteration."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = remote_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model 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, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "iteration = 3\n",
-        "third_run, third_model = remote_run.get_output(iteration = iteration)\n",
-        "print(third_run)\n",
-        "print(third_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Register the Fitted Model for Deployment\n",
-        "If neither metric nor iteration are specified in the register_model call, the iteration with the best primary metric is registered."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "description = 'AutoML Model'\n",
-        "tags = None\n",
-        "model = remote_run.register_model(description = description, tags = tags)\n",
-        "\n",
-        "print(remote_run.model_id) # This will be written to the script file later in the notebook."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create Scoring Script\n",
-        "The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%writefile score.py\n",
-        "import pickle\n",
-        "import json\n",
-        "import numpy\n",
-        "import azureml.train.automl\n",
-        "from sklearn.externals import joblib\n",
-        "from azureml.core.model import Model\n",
-        "\n",
-        "def init():\n",
-        "    global model\n",
-        "    model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
-        "    # deserialize the model file back into a sklearn model\n",
-        "    model = joblib.load(model_path)\n",
-        "\n",
-        "def run(rawdata):\n",
-        "    try:\n",
-        "        data = json.loads(rawdata)['data']\n",
-        "        data = numpy.array(data)\n",
-        "        result = model.predict(data)\n",
-        "    except Exception as e:\n",
-        "        result = str(e)\n",
-        "        return json.dumps({\"error\": result})\n",
-        "    return json.dumps({\"result\":result.tolist()})"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create a YAML File for the Environment"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "for p in ['azureml-train-automl', 'azureml-core']:\n",
-        "    print('{}\\t{}'.format(p, dependencies[p]))"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost==0.80'], pip_packages=['azureml-defaults','azureml-train-automl'])\n",
-        "\n",
-        "conda_env_file_name = 'myenv.yml'\n",
-        "myenv.save_to_file('.', conda_env_file_name)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Substitute the actual version number in the environment file.\n",
-        "# This is not strictly needed in this notebook because the model should have been generated using the current SDK version.\n",
-        "# However, we include this in case this code is used on an experiment from a previous SDK version.\n",
-        "\n",
-        "with open(conda_env_file_name, 'r') as cefr:\n",
-        "    content = cefr.read()\n",
-        "\n",
-        "with open(conda_env_file_name, 'w') as cefw:\n",
-        "    cefw.write(content.replace(azureml.core.VERSION, dependencies['azureml-train-automl']))\n",
-        "\n",
-        "# Substitute the actual model id in the script file.\n",
-        "\n",
-        "script_file_name = 'score.py'\n",
-        "\n",
-        "with open(script_file_name, 'r') as cefr:\n",
-        "    content = cefr.read()\n",
-        "\n",
-        "with open(script_file_name, 'w') as cefw:\n",
-        "    cefw.write(content.replace('<<modelid>>', remote_run.model_id))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Deploy the model as a Web Service on Azure Container Instance"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "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",
-        "\n",
-        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
-        "                                               memory_gb = 1, \n",
-        "                                               tags = {'area': \"digits\", 'type': \"automl_regression\"}, \n",
-        "                                               description = 'sample service for Automl Regression')\n",
-        "\n",
-        "aci_service_name = 'automl-sample-hardware'\n",
-        "print(aci_service_name)\n",
-        "aci_service = Model.deploy(ws, aci_service_name, [model], inference_config, aciconfig)\n",
-        "aci_service.wait_for_deployment(True)\n",
-        "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": {},
-      "source": [
-        "### Get Logs from a Deployed Web Service\n",
-        "\n",
-        "Gets logs from a deployed web service."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#aci_service.get_logs()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test\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 = X_test.to_pandas_dataframe()\n",
-        "y_test = y_test.to_pandas_dataframe()\n",
-        "y_test = np.array(y_test)\n",
-        "y_test = y_test[:,0]\n",
-        "X_train = X_train.to_pandas_dataframe()\n",
-        "y_train = y_train.to_pandas_dataframe()\n",
-        "y_train = np.array(y_train)\n",
-        "y_train = y_train[:,0]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "##### Predict on training and test set, and calculate residual values."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_pred_train = fitted_model.predict(X_train)\n",
-        "y_residual_train = y_train - y_pred_train\n",
-        "\n",
-        "y_pred_test = fitted_model.predict(X_test)\n",
-        "y_residual_test = y_test - y_pred_test"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "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."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%matplotlib inline\n",
-        "from sklearn.metrics import mean_squared_error, r2_score\n",
-        "\n",
-        "# Set up a multi-plot chart.\n",
-        "f, (a0, a1) = plt.subplots(1, 2, gridspec_kw = {'width_ratios':[1, 1], 'wspace':0, 'hspace': 0})\n",
-        "f.suptitle('Regression Residual Values', fontsize = 18)\n",
-        "f.set_figheight(6)\n",
-        "f.set_figwidth(16)\n",
-        "\n",
-        "# Plot residual values of training set.\n",
-        "a0.axis([0, 360, -200, 200])\n",
-        "a0.plot(y_residual_train, 'bo', alpha = 0.5)\n",
-        "a0.plot([-10,360],[0,0], 'r-', lw = 3)\n",
-        "a0.text(16,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_train, y_pred_train))), fontsize = 12)\n",
-        "a0.text(16,140,'R2 score = {0:.2f}'.format(r2_score(y_train, y_pred_train)),fontsize = 12)\n",
-        "a0.set_xlabel('Training samples', fontsize = 12)\n",
-        "a0.set_ylabel('Residual Values', fontsize = 12)\n",
-        "\n",
-        "# Plot residual values of test set.\n",
-        "a1.axis([0, 90, -200, 200])\n",
-        "a1.plot(y_residual_test, 'bo', alpha = 0.5)\n",
-        "a1.plot([-10,360],[0,0], 'r-', lw = 3)\n",
-        "a1.text(5,170,'RMSE = {0:.2f}'.format(np.sqrt(mean_squared_error(y_test, y_pred_test))), fontsize = 12)\n",
-        "a1.text(5,140,'R2 score = {0:.2f}'.format(r2_score(y_test, y_pred_test)),fontsize = 12)\n",
-        "a1.set_xlabel('Test samples', fontsize = 12)\n",
-        "a1.set_yticklabels([])\n",
-        "\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%matplotlib notebook\n",
-        "test_pred = plt.scatter(y_test, y_pred_test, color='')\n",
-        "test_test = plt.scatter(y_test, y_test, color='g')\n",
-        "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Acknowledgements\n",
-        "This Predicting Hardware Performance Dataset is made available under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication License: https://creativecommons.org/publicdomain/zero/1.0/ . The dataset itself can be found here: https://www.kaggle.com/faizunnabi/comp-hardware-performance and https://archive.ics.uci.edu/ml/datasets/Computer+Hardware\n",
-        "\n",
-        "_**Citation Found Here**_\n"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "v-rasav"
-      }
-    ],
-    "category": "tutorial",
-    "compute": [
-      "AML Compute"
-    ],
-    "datasets": [
-      "Concrete"
-    ],
-    "deployment": [
-      "Azure Container Instance"
-    ],
-    "exclude_from_index": false,
-    "framework": [
-      "Azure ML AutoML"
-    ],
-    "friendly_name": "Regression with deployment using hardware performance dataset",
-    "index_order": 1,
-    "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": "3.7.1"
-    },
-    "star_tag": [
-      "featured"
-    ],
-    "tags": [
-      ""
-    ],
-    "task": "Regression"
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/regression-hardware-performance/auto-ml-regression-hardware-performance.yml

@@ -1,12 +0,0 @@
-name: auto-ml-regression-hardware-performance
-dependencies:
-- pip:
-  - azureml-sdk
-  - interpret
-  - azureml-defaults
-  - azureml-explain-model
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - azureml-dataprep[pandas]

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

@@ -40,7 +40,7 @@
         "## Introduction\n",
         "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",
         "\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",
         "In this notebook you will learn how to:\n",
         "1. Create an `Experiment` in an existing `Workspace`.\n",
@@ -79,6 +79,23 @@
         "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 1.11.0 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,
@@ -93,7 +110,6 @@
         "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",
@@ -122,7 +138,7 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpu-cluster-2\"\n",
+        "cpu_cluster_name = \"reg-cluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
@@ -188,15 +204,18 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "metadata": {},
+      "metadata": {
+        "tags": [
+          "automlconfig-remarks-sample"
+        ]
+      },
       "outputs": [],
       "source": [
         "automl_settings = {\n",
         "    \"n_cross_validations\": 3,\n",
         "    \"primary_metric\": 'r2_score',\n",
-        "    \"preprocess\": True,\n",
         "    \"enable_early_stopping\": True, \n",
-        "    \"experiment_timeout_minutes\": 20, #for real scenarios we reccommend a timeout of at least one hour \n",
+        "    \"experiment_timeout_hours\": 0.3, #for real scenarios we reccommend a timeout of at least one hour \n",
         "    \"max_concurrent_iterations\": 4,\n",
         "    \"max_cores_per_iteration\": -1,\n",
         "    \"verbosity\": logging.INFO,\n",
@@ -214,7 +233,7 @@
       "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."
+        "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."
       ]
     },
     {

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

@@ -2,8 +2,3 @@ name: auto-ml-regression
 dependencies:
 - pip:
   - azureml-sdk
-  - azureml-train-automl
-  - azureml-widgets
-  - matplotlib
-  - pandas_ml
-  - paramiko<2.5.0

how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/ForecastEnergyDemand.sql

@@ -1,23 +0,0 @@
--- This shows using the AutoMLForecast stored procedure to predict using a forecasting model for the nyc_energy dataset.
-
-DECLARE @Model NVARCHAR(MAX) = (SELECT TOP 1 Model FROM dbo.aml_model
-                                WHERE ExperimentName = 'automl-sql-forecast'
-								ORDER BY CreatedDate DESC)
-
-DECLARE @max_horizon INT = 48
-DECLARE @split_time NVARCHAR(22) = (SELECT DATEADD(hour, -@max_horizon, MAX(timeStamp)) FROM nyc_energy WHERE demand IS NOT NULL)
-
-DECLARE @TestDataQuery NVARCHAR(MAX) = '
-SELECT CAST(timeStamp AS NVARCHAR(30)) AS timeStamp,
-       demand,
-	   precip,
-	   temp
-FROM nyc_energy
-WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL
-AND timeStamp > ''' + @split_time + ''''
-
-EXEC dbo.AutoMLForecast @input_query=@TestDataQuery,
-@label_column='demand',
-@time_column_name='timeStamp',
-@model=@model
-WITH RESULT SETS ((timeStamp DATETIME, grain NVARCHAR(255), predicted_demand FLOAT, precip FLOAT, temp FLOAT, actual_demand FLOAT))

how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/GetMetrics.sql

@@ -1,10 +0,0 @@
--- This lists all the metrics for all iterations for the most recent run.
-
-DECLARE @RunId NVARCHAR(43)
-DECLARE @ExperimentName NVARCHAR(255)
-
-SELECT TOP 1 @ExperimentName=ExperimentName, @RunId=SUBSTRING(RunId, 1, 43)
-FROM aml_model
-ORDER BY CreatedDate DESC
-
-EXEC dbo.AutoMLGetMetrics @RunId, @ExperimentName

how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/TrainEnergyDemand.sql

@@ -1,25 +0,0 @@
--- This shows using the AutoMLTrain stored procedure to create a forecasting model for the nyc_energy dataset.
-
-DECLARE @max_horizon INT = 48
-DECLARE @split_time NVARCHAR(22) = (SELECT DATEADD(hour, -@max_horizon, MAX(timeStamp)) FROM nyc_energy WHERE demand IS NOT NULL)
-
-DECLARE @TrainDataQuery NVARCHAR(MAX) = '
-SELECT CAST(timeStamp as NVARCHAR(30)) as timeStamp,
-       demand,
-	   precip,
-	   temp
-FROM nyc_energy
-WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL
-and timeStamp < ''' + @split_time + ''''
-
-INSERT INTO dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
-EXEC dbo.AutoMLTrain @input_query= @TrainDataQuery,
-@label_column='demand',
-@task='forecasting',
-@iterations=10,
-@iteration_timeout_minutes=5,
-@time_column_name='timeStamp',
-@max_horizon=@max_horizon,
-@experiment_name='automl-sql-forecast',
-@primary_metric='normalized_root_mean_squared_error'
-

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

@@ -1,161 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Train a model and use it for prediction\r\n",
-        "\r\n",
-        "Before running this notebook, run the auto-ml-sql-setup.ipynb notebook."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/sql-server/energy-demand/auto-ml-sql-energy-demand.png)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Set the default database"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "USE [automl]\r\n",
-        "GO"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Use the AutoMLTrain stored procedure to create a forecasting model for the nyc_energy dataset."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "INSERT INTO dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n",
-        "EXEC dbo.AutoMLTrain @input_query='\r\n",
-        "SELECT CAST(timeStamp as NVARCHAR(30)) as timeStamp,\r\n",
-        "       demand,\r\n",
-        "\t   precip,\r\n",
-        "\t   temp,\r\n",
-        "\t   CASE WHEN timeStamp < ''2017-01-01'' THEN 0 ELSE 1 END AS is_validate_column\r\n",
-        "FROM nyc_energy\r\n",
-        "WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL\r\n",
-        "and timeStamp < ''2017-02-01''',\r\n",
-        "@label_column='demand',\r\n",
-        "@task='forecasting',\r\n",
-        "@iterations=10,\r\n",
-        "@iteration_timeout_minutes=5,\r\n",
-        "@time_column_name='timeStamp',\r\n",
-        "@is_validate_column='is_validate_column',\r\n",
-        "@experiment_name='automl-sql-forecast',\r\n",
-        "@primary_metric='normalized_root_mean_squared_error'"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Use the AutoMLPredict stored procedure to predict using the forecasting model for the nyc_energy dataset."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "DECLARE @Model NVARCHAR(MAX) = (SELECT TOP 1 Model FROM dbo.aml_model\r\n",
-        "                                WHERE ExperimentName = 'automl-sql-forecast'\r\n",
-        "\t\t\t\t\t\t\t\tORDER BY CreatedDate DESC)\r\n",
-        "\r\n",
-        "EXEC dbo.AutoMLPredict @input_query='\r\n",
-        "SELECT CAST(timeStamp AS NVARCHAR(30)) AS timeStamp,\r\n",
-        "       demand,\r\n",
-        "\t   precip,\r\n",
-        "\t   temp\r\n",
-        "FROM nyc_energy\r\n",
-        "WHERE demand IS NOT NULL AND precip IS NOT NULL AND temp IS NOT NULL\r\n",
-        "AND timeStamp >= ''2017-02-01''',\r\n",
-        "@label_column='demand',\r\n",
-        "@model=@model\r\n",
-        "WITH RESULT SETS ((timeStamp NVARCHAR(30), actual_demand FLOAT, precip FLOAT, temp FLOAT, predicted_demand FLOAT))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## List all the metrics for all iterations for the most recent training run."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "DECLARE @RunId NVARCHAR(43)\r\n",
-        "DECLARE @ExperimentName NVARCHAR(255)\r\n",
-        "\r\n",
-        "SELECT TOP 1 @ExperimentName=ExperimentName, @RunId=SUBSTRING(RunId, 1, 43)\r\n",
-        "FROM aml_model\r\n",
-        "ORDER BY CreatedDate DESC\r\n",
-        "\r\n",
-        "EXEC dbo.AutoMLGetMetrics @RunId, @ExperimentName"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jeffshep"
-      }
-    ],
-    "category": "tutorial",
-    "compute": [
-      "Local"
-    ],
-    "datasets": [
-      "NYC Energy"
-    ],
-    "deployment": [
-      "None"
-    ],
-    "exclude_from_index": false,
-    "framework": [
-      "Azure ML AutoML"
-    ],
-    "friendly_name": "Forecasting with automated ML SQL integration",
-    "index_order": 1,
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "sql",
-      "name": "python36"
-    },
-    "language_info": {
-      "name": "sql",
-      "version": ""
-    },
-    "tags": [
-      ""
-    ],
-    "task": "Forecasting"
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLForecast.sql

@@ -1,92 +0,0 @@
--- This procedure forecast values based on a forecasting model returned by AutoMLTrain.
--- It returns a dataset with the forecasted values.
-SET ANSI_NULLS ON
-GO
-SET QUOTED_IDENTIFIER ON
-GO
-CREATE OR ALTER PROCEDURE [dbo].[AutoMLForecast]
- (
-   @input_query NVARCHAR(MAX),          -- A SQL query returning data to predict on.
-   @model NVARCHAR(MAX),                -- A model returned from AutoMLTrain.
-   @time_column_name  NVARCHAR(255)='', -- The name of the timestamp column for forecasting.
-   @label_column  NVARCHAR(255)='',     -- Optional name of the column from input_query, which should be ignored when predicting
-   @y_query_column NVARCHAR(255)='',    -- Optional value column that can be used for predicting.
-                                        -- If specified, this can contain values for past times (after the model was trained)
-									    -- and contain Nan for future times.
-   @forecast_column_name NVARCHAR(255) = 'predicted'
-                                        -- The name of the output column containing the forecast value.
- ) AS 
-BEGIN 
-  
-    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd 
-import azureml.core  
-import numpy as np 
-from azureml.train.automl import AutoMLConfig  
-import pickle 
-import codecs 
-  
-model_obj = pickle.loads(codecs.decode(model.encode(), "base64")) 
-  
-test_data = input_data.copy() 
-
-if label_column != "" and label_column is not None:
-    y_test = test_data.pop(label_column).values
-else:
-    y_test = None 
-
-if y_query_column != "" and y_query_column is not None:
-    y_query = test_data.pop(y_query_column).values
-else:
-    y_query = np.repeat(np.nan, len(test_data))
-
-X_test = test_data 
-
-if time_column_name != "" and time_column_name is not None:
-    X_test[time_column_name] = pd.to_datetime(X_test[time_column_name])
-
-y_fcst, X_trans = model_obj.forecast(X_test, y_query) 
-
-def align_outputs(y_forecast, X_trans, X_test, y_test, forecast_column_name):
-    # Demonstrates how to get the output aligned to the inputs
-    # using pandas indexes. Helps understand what happened if
-    # the output 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
-
-    df_fcst = pd.DataFrame({forecast_column_name : y_forecast})
-    # 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()
-    if y_test is not None:
-        X_test_full[label_column] = y_test
-
-    # X_test_full 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[[label_column, forecast_column_name]].notnull().all(axis=1)]
-    return(clean)
-
-combined_output = align_outputs(y_fcst, X_trans, X_test, y_test, forecast_column_name)
-  
-' 
-    , @input_data_1 = @input_query 
-    , @input_data_1_name = N'input_data' 
-    , @output_data_1_name = N'combined_output' 
-    , @params = N'@model NVARCHAR(MAX), @time_column_name  NVARCHAR(255), @label_column NVARCHAR(255), @y_query_column NVARCHAR(255), @forecast_column_name NVARCHAR(255)' 
-    , @model = @model 
-	, @time_column_name = @time_column_name
-	, @label_column = @label_column
-	, @y_query_column = @y_query_column
-	, @forecast_column_name = @forecast_column_name
-END

how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLGetMetrics.sql

@@ -1,70 +0,0 @@
--- This procedure returns a list of metrics for each iteration of a run.
-SET ANSI_NULLS ON
-GO
-SET QUOTED_IDENTIFIER ON
-GO
-CREATE OR ALTER PROCEDURE [dbo].[AutoMLGetMetrics]
- (
-	@run_id NVARCHAR(250),                           -- The RunId
-    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.
-    @connection_name NVARCHAR(255)='default'         -- The AML connection to use.
- ) AS
-BEGIN
-    DECLARE @tenantid NVARCHAR(255)
-    DECLARE @appid NVARCHAR(255)
-    DECLARE @password NVARCHAR(255)
-    DECLARE @config_file NVARCHAR(255)
-
-	SELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile
-	FROM aml_connection
-	WHERE ConnectionName = @connection_name;
-
-    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd
-import logging 
-import azureml.core 
-import numpy as np
-from azureml.core.experiment import Experiment 
-from azureml.train.automl.run import AutoMLRun
-from azureml.core.authentication import ServicePrincipalAuthentication 
-from azureml.core.workspace import Workspace 
-
-auth = ServicePrincipalAuthentication(tenantid, appid, password) 
- 
-ws = Workspace.from_config(path=config_file, auth=auth) 
- 
-experiment = Experiment(ws, experiment_name) 
-
-ml_run = AutoMLRun(experiment = experiment, run_id = run_id)
-
-children = list(ml_run.get_children())
-iterationlist = []
-metricnamelist = []
-metricvaluelist = []
-
-for run in children:
-    properties = run.get_properties()
-    if "iteration" in properties:
-        iteration = int(properties["iteration"])
-        for metric_name, metric_value in run.get_metrics().items():
-            if isinstance(metric_value, float):
-                iterationlist.append(iteration)
-                metricnamelist.append(metric_name)
-                metricvaluelist.append(metric_value)
-             
-metrics = pd.DataFrame({"iteration": iterationlist, "metric_name": metricnamelist, "metric_value": metricvaluelist})
-'
-    , @output_data_1_name = N'metrics'
-	, @params = N'@run_id NVARCHAR(250), 
-				  @experiment_name NVARCHAR(32),
-  				  @tenantid NVARCHAR(255),
-				  @appid NVARCHAR(255),
-				  @password NVARCHAR(255),
-				  @config_file NVARCHAR(255)'
-    , @run_id = @run_id
-	, @experiment_name = @experiment_name
-	, @tenantid = @tenantid
-	, @appid = @appid
-	, @password = @password
-	, @config_file = @config_file
-WITH RESULT SETS ((iteration INT, metric_name NVARCHAR(100), metric_value FLOAT))
-END

how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLPredict.sql

@@ -1,41 +0,0 @@
--- This procedure predicts values based on a model returned by AutoMLTrain and a dataset.
--- It returns the dataset with a new column added, which is the predicted value.
-SET ANSI_NULLS ON
-GO
-SET QUOTED_IDENTIFIER ON
-GO
-CREATE OR ALTER PROCEDURE [dbo].[AutoMLPredict]
- (
-   @input_query NVARCHAR(MAX),      -- A SQL query returning data to predict on.
-   @model NVARCHAR(MAX),            -- A model returned from AutoMLTrain.
-   @label_column  NVARCHAR(255)=''  -- Optional name of the column from input_query, which should be ignored when predicting
- ) AS 
-BEGIN 
-  
-    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd 
-import azureml.core  
-import numpy as np 
-from azureml.train.automl import AutoMLConfig  
-import pickle 
-import codecs 
-  
-model_obj = pickle.loads(codecs.decode(model.encode(), "base64")) 
-  
-test_data = input_data.copy() 
-
-if label_column != "" and label_column is not None:
-    y_test = test_data.pop(label_column).values 
-X_test = test_data 
-  
-predicted = model_obj.predict(X_test) 
-  
-combined_output = input_data.assign(predicted=predicted)
-  
-' 
-    , @input_data_1 = @input_query 
-    , @input_data_1_name = N'input_data' 
-    , @output_data_1_name = N'combined_output' 
-    , @params = N'@model NVARCHAR(MAX), @label_column  NVARCHAR(255)' 
-    , @model = @model 
-	, @label_column = @label_column
-END

how-to-use-azureml/automated-machine-learning/sql-server/setup/AutoMLTrain.sql

@@ -1,240 +0,0 @@
--- This stored procedure uses automated machine learning to train several models
--- and returns the best model.
---
--- The result set has several columns:
---   best_run - iteration ID for the best model
---   experiment_name - experiment name pass in with the @experiment_name parameter
---   fitted_model - best model found
---   log_file_text - AutoML debug_log contents
---   workspace - name of the Azure ML workspace where run history is stored
---
--- An example call for a classification problem is:
---    insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
---    exec dbo.AutoMLTrain @input_query='
---    SELECT top 100000 
---          CAST([pickup_datetime] AS NVARCHAR(30)) AS pickup_datetime
---          ,CAST([dropoff_datetime] AS NVARCHAR(30)) AS dropoff_datetime
---          ,[passenger_count]
---          ,[trip_time_in_secs]
---          ,[trip_distance]
---          ,[payment_type]
---          ,[tip_class]
---      FROM [dbo].[nyctaxi_sample] order by [hack_license] ',
---      @label_column = 'tip_class',
---      @iterations=10
--- 
--- An example call for forecasting is:
---      insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)
---      exec dbo.AutoMLTrain @input_query='
---      select cast(timeStamp as nvarchar(30)) as timeStamp,
---             demand,
---      	   precip,
---      	   temp,
---             case when timeStamp < ''2017-01-01'' then 0 else 1 end as is_validate_column
---      from nyc_energy
---      where demand is not null and precip is not null and temp is not null
---      and timeStamp < ''2017-02-01''',
---      @label_column='demand',
---      @task='forecasting',
---      @iterations=10,
---      @iteration_timeout_minutes=5,
---      @time_column_name='timeStamp',
---      @is_validate_column='is_validate_column',
---      @experiment_name='automl-sql-forecast',
---      @primary_metric='normalized_root_mean_squared_error'
-
-SET ANSI_NULLS ON
-GO
-SET QUOTED_IDENTIFIER ON
-GO
-CREATE OR ALTER PROCEDURE [dbo].[AutoMLTrain]
- (
-    @input_query NVARCHAR(MAX),                      -- The SQL Query that will return the data to train and validate the model.
-    @label_column NVARCHAR(255)='Label',             -- The name of the column in the result of @input_query that is the label.
-    @primary_metric NVARCHAR(40)='AUC_weighted',     -- The metric to optimize.
-    @iterations INT=100,                             -- The maximum number of pipelines to train.
-    @task NVARCHAR(40)='classification',             -- The type of task.  Can be classification, regression or forecasting.
-    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.
-    @iteration_timeout_minutes INT = 15,             -- The maximum time in minutes for training a single pipeline. 
-    @experiment_timeout_minutes INT = 60,            -- The maximum time in minutes for training all pipelines.
-    @n_cross_validations INT = 3,                    -- The number of cross validations.
-    @blacklist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that will not be used.
-                                                     -- The list of possible models can be found at:
-                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings
-    @whitelist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that can be used.
-                                                     -- The list of possible models can be found at:
-                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings
-    @experiment_exit_score FLOAT = 0,                -- Stop the experiment if this score is acheived.
-    @sample_weight_column NVARCHAR(255)='',          -- The name of the column in the result of  @input_query that gives a sample weight.
-    @is_validate_column NVARCHAR(255)='',            -- The name of the column in the result of  @input_query that indicates if the row is for training or validation.
-	                                                 -- In the values of the column, 0 means for training and 1 means for validation.
-    @time_column_name  NVARCHAR(255)='',             -- The name of the timestamp column for forecasting.
-    @connection_name NVARCHAR(255)='default',        -- The AML connection to use.
-    @max_horizon INT = 0                             -- A forecast horizon is a time span into the future (or just beyond the latest date in the training data)
-                                                     -- where forecasts of the target quantity are needed.
-                                                     -- For example, if data is recorded daily and max_horizon is 5, we will predict 5 days ahead.
- ) AS
-BEGIN
-
-    DECLARE @tenantid NVARCHAR(255)
-    DECLARE @appid NVARCHAR(255)
-    DECLARE @password NVARCHAR(255)
-    DECLARE @config_file NVARCHAR(255)
-
-	SELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile
-	FROM aml_connection
-	WHERE ConnectionName = @connection_name;
-
-	EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd
-import logging 
-import azureml.core 
-import pandas as pd
-import numpy as np
-from azureml.core.experiment import Experiment 
-from azureml.train.automl import AutoMLConfig 
-from sklearn import datasets 
-import pickle
-import codecs
-from azureml.core.authentication import ServicePrincipalAuthentication 
-from azureml.core.workspace import Workspace 
-
-if __name__.startswith("sqlindb"):
-    auth = ServicePrincipalAuthentication(tenantid, appid, password) 
- 
-    ws = Workspace.from_config(path=config_file, auth=auth) 
- 
-    project_folder = "./sample_projects/" + experiment_name
- 
-    experiment = Experiment(ws, experiment_name) 
-
-    data_train = input_data
-    X_valid = None
-    y_valid = None
-    sample_weight_valid = None
-
-    if is_validate_column != "" and is_validate_column is not None:
-        data_train = input_data[input_data[is_validate_column] <= 0]
-        data_valid = input_data[input_data[is_validate_column] > 0]
-        data_train.pop(is_validate_column)
-        data_valid.pop(is_validate_column)
-        y_valid = data_valid.pop(label_column).values
-        if sample_weight_column != "" and sample_weight_column is not None:
-            sample_weight_valid = data_valid.pop(sample_weight_column).values
-        X_valid = data_valid
-        n_cross_validations = None
-
-    y_train = data_train.pop(label_column).values
-
-    sample_weight = None
-    if sample_weight_column != "" and sample_weight_column is not None:
-        sample_weight = data_train.pop(sample_weight_column).values
-
-    X_train = data_train
-
-    if experiment_timeout_minutes == 0:
-        experiment_timeout_minutes = None
-
-    if experiment_exit_score == 0:
-        experiment_exit_score = None
-
-    if blacklist_models == "":
-        blacklist_models = None
-
-    if blacklist_models is not None:
-        blacklist_models = blacklist_models.replace(" ", "").split(",")
-
-    if whitelist_models == "":
-        whitelist_models = None
-
-    if whitelist_models is not None:
-        whitelist_models = whitelist_models.replace(" ", "").split(",")
-
-    automl_settings = {}
-    preprocess = True
-    if time_column_name != "" and time_column_name is not None:
-        automl_settings = { "time_column_name": time_column_name }
-        preprocess = False
-        if max_horizon > 0:
-            automl_settings["max_horizon"] = max_horizon
-
-    log_file_name = "automl_sqlindb_errors.log"
-	 
-    automl_config = AutoMLConfig(task = task, 
-                                 debug_log = log_file_name, 
-                                 primary_metric = primary_metric, 
-                                 iteration_timeout_minutes = iteration_timeout_minutes, 
-                                 experiment_timeout_minutes = experiment_timeout_minutes,
-                                 iterations = iterations, 
-                                 n_cross_validations = n_cross_validations, 
-                                 preprocess = preprocess,
-                                 verbosity = logging.INFO, 
-                                 X = X_train,  
-                                 y = y_train, 
-                                 path = project_folder,
-                                 blacklist_models = blacklist_models,
-                                 whitelist_models = whitelist_models,
-                                 experiment_exit_score = experiment_exit_score,
-                                 sample_weight = sample_weight,
-                                 X_valid = X_valid,
-                                 y_valid = y_valid,
-                                 sample_weight_valid = sample_weight_valid,
-                                 **automl_settings) 
- 
-    local_run = experiment.submit(automl_config, show_output = True) 
-
-    best_run, fitted_model = local_run.get_output()
-
-    pickled_model = codecs.encode(pickle.dumps(fitted_model), "base64").decode()
-
-    log_file_text = ""
-
-    try:
-        with open(log_file_name, "r") as log_file:
-            log_file_text = log_file.read()
-    except:
-        log_file_text = "Log file not found"
-
-    returned_model = pd.DataFrame({"best_run": [best_run.id], "experiment_name": [experiment_name], "fitted_model": [pickled_model], "log_file_text": [log_file_text], "workspace": [ws.name]}, dtype=np.dtype(np.str))
-'
-	, @input_data_1 = @input_query
-	, @input_data_1_name = N'input_data'
-	, @output_data_1_name = N'returned_model'
-	, @params = N'@label_column NVARCHAR(255), 
-	              @primary_metric NVARCHAR(40),
-				  @iterations INT, @task NVARCHAR(40),
-				  @experiment_name NVARCHAR(32),
-				  @iteration_timeout_minutes INT,
-				  @experiment_timeout_minutes INT,
-				  @n_cross_validations INT,
-				  @blacklist_models NVARCHAR(MAX),
-				  @whitelist_models NVARCHAR(MAX),
-				  @experiment_exit_score FLOAT,
-				  @sample_weight_column NVARCHAR(255),
-				  @is_validate_column NVARCHAR(255),
-				  @time_column_name  NVARCHAR(255),
-				  @tenantid NVARCHAR(255),
-				  @appid NVARCHAR(255),
-				  @password NVARCHAR(255),
-				  @config_file NVARCHAR(255),
-				  @max_horizon INT'
-	, @label_column = @label_column
-	, @primary_metric = @primary_metric
-	, @iterations = @iterations
-	, @task = @task
-	, @experiment_name = @experiment_name
-	, @iteration_timeout_minutes = @iteration_timeout_minutes
-	, @experiment_timeout_minutes = @experiment_timeout_minutes
-	, @n_cross_validations = @n_cross_validations
-	, @blacklist_models = @blacklist_models
-	, @whitelist_models = @whitelist_models
-	, @experiment_exit_score = @experiment_exit_score
-	, @sample_weight_column = @sample_weight_column
-	, @is_validate_column = @is_validate_column
-	, @time_column_name = @time_column_name
-	, @tenantid = @tenantid
-	, @appid = @appid
-	, @password = @password
-	, @config_file = @config_file
-	, @max_horizon = @max_horizon
-WITH RESULT SETS ((best_run NVARCHAR(250), experiment_name NVARCHAR(100), fitted_model VARCHAR(MAX), log_file_text NVARCHAR(MAX), workspace NVARCHAR(100)))
-END

how-to-use-azureml/automated-machine-learning/sql-server/setup/aml_connection.sql

@@ -1,18 +0,0 @@
--- This is a table to store the Azure ML connection information.
-SET ANSI_NULLS ON
-GO
-
-SET QUOTED_IDENTIFIER ON
-GO
-
-CREATE TABLE [dbo].[aml_connection](
-    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,
-	[ConnectionName] [nvarchar](255) NULL,
-	[TenantId] [nvarchar](255) NULL,
-	[AppId] [nvarchar](255) NULL,
-	[Password] [nvarchar](255) NULL,
-	[ConfigFile] [nvarchar](255) NULL
-) ON [PRIMARY]
-GO
-
-

how-to-use-azureml/automated-machine-learning/sql-server/setup/aml_model.sql

@@ -1,22 +0,0 @@
--- This is a table to hold the results from the AutoMLTrain procedure.
-SET ANSI_NULLS ON
-GO
-
-SET QUOTED_IDENTIFIER ON
-GO
-
-CREATE TABLE [dbo].[aml_model](
-    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,
-    [Model] [varchar](max) NOT NULL,        -- The model, which can be passed to AutoMLPredict for testing or prediction.
-    [RunId] [nvarchar](250) NULL,           -- The RunId, which can be used to view the model in the Azure Portal.
-    [CreatedDate] [datetime] NULL,
-    [ExperimentName] [nvarchar](100) NULL,  -- Azure ML Experiment Name
-    [WorkspaceName] [nvarchar](100) NULL,   -- Azure ML Workspace Name
-	[LogFileText] [nvarchar](max) NULL
-) 
-GO
-
-ALTER TABLE [dbo].[aml_model] ADD  DEFAULT (getutcdate()) FOR [CreatedDate]
-GO
-
-

how-to-use-azureml/automated-machine-learning/sql-server/setup/auto-ml-sql-setup.ipynb

@@ -1,581 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Set up Azure ML Automated Machine Learning on SQL Server 2019 CTP 2.4 big data cluster\r\n",
-        "\r\n",
-        "\\# Prerequisites:  \r\n",
-        "\\# - An Azure subscription and resource group  \r\n",
-        "\\# - An Azure Machine Learning workspace  \r\n",
-        "\\# - A SQL Server 2019 CTP 2.4 big data cluster with Internet access and a database named 'automl'  \r\n",
-        "\\# - Azure CLI  \r\n",
-        "\\# - kubectl command  \r\n",
-        "\\# - The https://github.com/Azure/MachineLearningNotebooks repository downloaded (cloned) to your local machine\r\n",
-        "\r\n",
-        "\\# In the 'automl' database, create a table named 'dbo.nyc_energy' as follows:  \r\n",
-        "\\# - In SQL Server Management Studio, right-click the 'automl' database, select Tasks, then Import Flat File.  \r\n",
-        "\\# - Select the file AzureMlCli\\notebooks\\how-to-use-azureml\\automated-machine-learning\\forecasting-energy-demand\\nyc_energy.csv.  \r\n",
-        "\\# - Using the \"Modify Columns\" page, allow nulls for all columns. \r\n",
-        "\r\n",
-        "\\# Create an Azure Machine Learning Workspace using the instructions at https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace \r\n",
-        "\r\n",
-        "\\# Create an Azure service principal.  You can do this with the following commands: \r\n",
-        "\r\n",
-        "az login  \r\n",
-        "az account set --subscription *subscriptionid*  \r\n",
-        "\r\n",
-        "\\# The following command prints out the **appId** and **tenant**,  \r\n",
-        "\\# which you insert into the indicated cell later in this notebook  \r\n",
-        "\\# to allow AutoML to authenticate with Azure:  \r\n",
-        "\r\n",
-        "az ad sp create-for-rbac --name *principlename* --password *password*\r\n",
-        "\r\n",
-        "\\# Log into the master instance of SQL Server 2019 CTP 2.4:  \r\n",
-        "kubectl exec -it mssql-master-pool-0 -n *clustername* -c mssql-server -- /bin/bash\r\n",
-        "\r\n",
-        "mkdir /tmp/aml\r\n",
-        "\r\n",
-        "cd /tmp/aml\r\n",
-        "\r\n",
-        "\\# **Modify** the following with your subscription_id, resource_group, and workspace_name:  \r\n",
-        "cat > config.json << EOF  \r\n",
-        "{  \r\n",
-        "    \"subscription_id\": \"123456ab-78cd-0123-45ef-abcd12345678\",  \r\n",
-        "    \"resource_group\": \"myrg1\",  \r\n",
-        "    \"workspace_name\": \"myws1\"  \r\n",
-        "}  \r\n",
-        "EOF\r\n",
-        "\r\n",
-        "\\# The directory referenced below is appropriate for the master instance of SQL Server 2019 CTP 2.4.\r\n",
-        "\r\n",
-        "cd /opt/mssql/mlservices/runtime/python/bin\r\n",
-        "\r\n",
-        "./python -m pip install azureml-sdk[automl]\r\n",
-        "\r\n",
-        "./python -m pip install --upgrade numpy \r\n",
-        "\r\n",
-        "./python -m pip install --upgrade sklearn\r\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/sql-server/setup/auto-ml-sql-setup.png)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "-- Enable external scripts to allow invoking Python\r\n",
-        "sp_configure 'external scripts enabled',1 \r\n",
-        "reconfigure with override \r\n",
-        "GO\r\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "-- Use database 'automl'\r\n",
-        "USE [automl]\r\n",
-        "GO"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "-- This is a table to hold the Azure ML connection information.\r\n",
-        "SET ANSI_NULLS ON\r\n",
-        "GO\r\n",
-        "\r\n",
-        "SET QUOTED_IDENTIFIER ON\r\n",
-        "GO\r\n",
-        "\r\n",
-        "CREATE TABLE [dbo].[aml_connection](\r\n",
-        "    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,\r\n",
-        "\t[ConnectionName] [nvarchar](255) NULL,\r\n",
-        "\t[TenantId] [nvarchar](255) NULL,\r\n",
-        "\t[AppId] [nvarchar](255) NULL,\r\n",
-        "\t[Password] [nvarchar](255) NULL,\r\n",
-        "\t[ConfigFile] [nvarchar](255) NULL\r\n",
-        ") ON [PRIMARY]\r\n",
-        "GO"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Copy the values from create-for-rbac above into the cell below"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "-- Use the following values:\r\n",
-        "-- Leave the name as 'Default'\r\n",
-        "-- Insert <tenant> returned by create-for-rbac above\r\n",
-        "-- Insert <AppId> returned by create-for-rbac above\r\n",
-        "-- Insert <password> used in create-for-rbac above\r\n",
-        "-- Leave <path> as '/tmp/aml/config.json'\r\n",
-        "INSERT INTO [dbo].[aml_connection]  \r\n",
-        "VALUES (\r\n",
-        "    N'Default', -- Name\r\n",
-        "    N'11111111-2222-3333-4444-555555555555', -- Tenant\r\n",
-        "    N'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee', -- AppId\r\n",
-        "    N'insertpasswordhere', -- Password\r\n",
-        "    N'/tmp/aml/config.json' -- Path\r\n",
-        "    );\r\n",
-        "GO"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "-- This is a table to hold the results from the AutoMLTrain procedure.\r\n",
-        "SET ANSI_NULLS ON\r\n",
-        "GO\r\n",
-        "\r\n",
-        "SET QUOTED_IDENTIFIER ON\r\n",
-        "GO\r\n",
-        "\r\n",
-        "CREATE TABLE [dbo].[aml_model](\r\n",
-        "    [Id] [int] IDENTITY(1,1) NOT NULL PRIMARY KEY,\r\n",
-        "    [Model] [varchar](max) NOT NULL,        -- The model, which can be passed to AutoMLPredict for testing or prediction.\r\n",
-        "    [RunId] [nvarchar](250) NULL,           -- The RunId, which can be used to view the model in the Azure Portal.\r\n",
-        "    [CreatedDate] [datetime] NULL,\r\n",
-        "    [ExperimentName] [nvarchar](100) NULL,  -- Azure ML Experiment Name\r\n",
-        "    [WorkspaceName] [nvarchar](100) NULL,   -- Azure ML Workspace Name\r\n",
-        "\t[LogFileText] [nvarchar](max) NULL\r\n",
-        ") \r\n",
-        "GO\r\n",
-        "\r\n",
-        "ALTER TABLE [dbo].[aml_model] ADD  DEFAULT (getutcdate()) FOR [CreatedDate]\r\n",
-        "GO\r\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "-- This stored procedure uses automated machine learning to train several models\r\n",
-        "-- and return the best model.\r\n",
-        "--\r\n",
-        "-- The result set has several columns:\r\n",
-        "--   best_run - ID of the best model found\r\n",
-        "--   experiment_name - training run name\r\n",
-        "--   fitted_model - best model found\r\n",
-        "--   log_file_text - console output\r\n",
-        "--   workspace - name of the Azure ML workspace where run history is stored\r\n",
-        "--\r\n",
-        "-- An example call for a classification problem is:\r\n",
-        "--    insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n",
-        "--    exec dbo.AutoMLTrain @input_query='\r\n",
-        "--    SELECT top 100000 \r\n",
-        "--          CAST([pickup_datetime] AS NVARCHAR(30)) AS pickup_datetime\r\n",
-        "--          ,CAST([dropoff_datetime] AS NVARCHAR(30)) AS dropoff_datetime\r\n",
-        "--          ,[passenger_count]\r\n",
-        "--          ,[trip_time_in_secs]\r\n",
-        "--          ,[trip_distance]\r\n",
-        "--          ,[payment_type]\r\n",
-        "--          ,[tip_class]\r\n",
-        "--      FROM [dbo].[nyctaxi_sample] order by [hack_license] ',\r\n",
-        "--      @label_column = 'tip_class',\r\n",
-        "--      @iterations=10\r\n",
-        "-- \r\n",
-        "-- An example call for forecasting is:\r\n",
-        "--      insert into dbo.aml_model(RunId, ExperimentName, Model, LogFileText, WorkspaceName)\r\n",
-        "--      exec dbo.AutoMLTrain @input_query='\r\n",
-        "--      select cast(timeStamp as nvarchar(30)) as timeStamp,\r\n",
-        "--             demand,\r\n",
-        "--      \t   precip,\r\n",
-        "--      \t   temp,\r\n",
-        "--             case when timeStamp < ''2017-01-01'' then 0 else 1 end as is_validate_column\r\n",
-        "--      from nyc_energy\r\n",
-        "--      where demand is not null and precip is not null and temp is not null\r\n",
-        "--      and timeStamp < ''2017-02-01''',\r\n",
-        "--      @label_column='demand',\r\n",
-        "--      @task='forecasting',\r\n",
-        "--      @iterations=10,\r\n",
-        "--      @iteration_timeout_minutes=5,\r\n",
-        "--      @time_column_name='timeStamp',\r\n",
-        "--      @is_validate_column='is_validate_column',\r\n",
-        "--      @experiment_name='automl-sql-forecast',\r\n",
-        "--      @primary_metric='normalized_root_mean_squared_error'\r\n",
-        "\r\n",
-        "SET ANSI_NULLS ON\r\n",
-        "GO\r\n",
-        "SET QUOTED_IDENTIFIER ON\r\n",
-        "GO\r\n",
-        "CREATE OR ALTER PROCEDURE [dbo].[AutoMLTrain]\r\n",
-        " (\r\n",
-        "    @input_query NVARCHAR(MAX),                      -- The SQL Query that will return the data to train and validate the model.\r\n",
-        "    @label_column NVARCHAR(255)='Label',             -- The name of the column in the result of @input_query that is the label.\r\n",
-        "    @primary_metric NVARCHAR(40)='AUC_weighted',     -- The metric to optimize.\r\n",
-        "    @iterations INT=100,                             -- The maximum number of pipelines to train.\r\n",
-        "    @task NVARCHAR(40)='classification',             -- The type of task.  Can be classification, regression or forecasting.\r\n",
-        "    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.\r\n",
-        "    @iteration_timeout_minutes INT = 15,             -- The maximum time in minutes for training a single pipeline. \r\n",
-        "    @experiment_timeout_minutes INT = 60,            -- The maximum time in minutes for training all pipelines.\r\n",
-        "    @n_cross_validations INT = 3,                    -- The number of cross validations.\r\n",
-        "    @blacklist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that will not be used.\r\n",
-        "                                                     -- The list of possible models can be found at:\r\n",
-        "                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings\r\n",
-        "    @whitelist_models NVARCHAR(MAX) = '',            -- A comma separated list of algos that can be used.\r\n",
-        "                                                     -- The list of possible models can be found at:\r\n",
-        "                                                     -- https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings\r\n",
-        "    @experiment_exit_score FLOAT = 0,                -- Stop the experiment if this score is acheived.\r\n",
-        "    @sample_weight_column NVARCHAR(255)='',          -- The name of the column in the result of  @input_query that gives a sample weight.\r\n",
-        "    @is_validate_column NVARCHAR(255)='',            -- The name of the column in the result of  @input_query that indicates if the row is for training or validation.\r\n",
-        "\t                                                 -- In the values of the column, 0 means for training and 1 means for validation.\r\n",
-        "    @time_column_name  NVARCHAR(255)='',             -- The name of the timestamp column for forecasting.\r\n",
-        "\t@connection_name NVARCHAR(255)='default'         -- The AML connection to use.\r\n",
-        " ) AS\r\n",
-        "BEGIN\r\n",
-        "\r\n",
-        "    DECLARE @tenantid NVARCHAR(255)\r\n",
-        "    DECLARE @appid NVARCHAR(255)\r\n",
-        "    DECLARE @password NVARCHAR(255)\r\n",
-        "    DECLARE @config_file NVARCHAR(255)\r\n",
-        "\r\n",
-        "\tSELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile\r\n",
-        "\tFROM aml_connection\r\n",
-        "\tWHERE ConnectionName = @connection_name;\r\n",
-        "\r\n",
-        "\tEXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd\r\n",
-        "import logging \r\n",
-        "import azureml.core \r\n",
-        "import pandas as pd\r\n",
-        "import numpy as np\r\n",
-        "from azureml.core.experiment import Experiment \r\n",
-        "from azureml.train.automl import AutoMLConfig \r\n",
-        "from sklearn import datasets \r\n",
-        "import pickle\r\n",
-        "import codecs\r\n",
-        "from azureml.core.authentication import ServicePrincipalAuthentication \r\n",
-        "from azureml.core.workspace import Workspace \r\n",
-        "\r\n",
-        "if __name__.startswith(\"sqlindb\"):\r\n",
-        "    auth = ServicePrincipalAuthentication(tenantid, appid, password) \r\n",
-        " \r\n",
-        "    ws = Workspace.from_config(path=config_file, auth=auth) \r\n",
-        " \r\n",
-        "    project_folder = \"./sample_projects/\" + experiment_name\r\n",
-        " \r\n",
-        "    experiment = Experiment(ws, experiment_name) \r\n",
-        "\r\n",
-        "    data_train = input_data\r\n",
-        "    X_valid = None\r\n",
-        "    y_valid = None\r\n",
-        "    sample_weight_valid = None\r\n",
-        "\r\n",
-        "    if is_validate_column != \"\" and is_validate_column is not None:\r\n",
-        "        data_train = input_data[input_data[is_validate_column] <= 0]\r\n",
-        "        data_valid = input_data[input_data[is_validate_column] > 0]\r\n",
-        "        data_train.pop(is_validate_column)\r\n",
-        "        data_valid.pop(is_validate_column)\r\n",
-        "        y_valid = data_valid.pop(label_column).values\r\n",
-        "        if sample_weight_column != \"\" and sample_weight_column is not None:\r\n",
-        "            sample_weight_valid = data_valid.pop(sample_weight_column).values\r\n",
-        "        X_valid = data_valid\r\n",
-        "        n_cross_validations = None\r\n",
-        "\r\n",
-        "    y_train = data_train.pop(label_column).values\r\n",
-        "\r\n",
-        "    sample_weight = None\r\n",
-        "    if sample_weight_column != \"\" and sample_weight_column is not None:\r\n",
-        "        sample_weight = data_train.pop(sample_weight_column).values\r\n",
-        "\r\n",
-        "    X_train = data_train\r\n",
-        "\r\n",
-        "    if experiment_timeout_minutes == 0:\r\n",
-        "        experiment_timeout_minutes = None\r\n",
-        "\r\n",
-        "    if experiment_exit_score == 0:\r\n",
-        "        experiment_exit_score = None\r\n",
-        "\r\n",
-        "    if blacklist_models == \"\":\r\n",
-        "        blacklist_models = None\r\n",
-        "\r\n",
-        "    if blacklist_models is not None:\r\n",
-        "        blacklist_models = blacklist_models.replace(\" \", \"\").split(\",\")\r\n",
-        "\r\n",
-        "    if whitelist_models == \"\":\r\n",
-        "        whitelist_models = None\r\n",
-        "\r\n",
-        "    if whitelist_models is not None:\r\n",
-        "        whitelist_models = whitelist_models.replace(\" \", \"\").split(\",\")\r\n",
-        "\r\n",
-        "    automl_settings = {}\r\n",
-        "    preprocess = True\r\n",
-        "    if time_column_name != \"\" and time_column_name is not None:\r\n",
-        "        automl_settings = { \"time_column_name\": time_column_name }\r\n",
-        "        preprocess = False\r\n",
-        "\r\n",
-        "    log_file_name = \"automl_errors.log\"\r\n",
-        "\t \r\n",
-        "    automl_config = AutoMLConfig(task = task, \r\n",
-        "                                 debug_log = log_file_name, \r\n",
-        "                                 primary_metric = primary_metric, \r\n",
-        "                                 iteration_timeout_minutes = iteration_timeout_minutes, \r\n",
-        "                                 experiment_timeout_minutes = experiment_timeout_minutes,\r\n",
-        "                                 iterations = iterations, \r\n",
-        "                                 n_cross_validations = n_cross_validations, \r\n",
-        "                                 preprocess = preprocess,\r\n",
-        "                                 verbosity = logging.INFO, \r\n",
-        "                                 X = X_train,  \r\n",
-        "                                 y = y_train, \r\n",
-        "                                 path = project_folder,\r\n",
-        "                                 blacklist_models = blacklist_models,\r\n",
-        "                                 whitelist_models = whitelist_models,\r\n",
-        "                                 experiment_exit_score = experiment_exit_score,\r\n",
-        "                                 sample_weight = sample_weight,\r\n",
-        "                                 X_valid = X_valid,\r\n",
-        "                                 y_valid = y_valid,\r\n",
-        "                                 sample_weight_valid = sample_weight_valid,\r\n",
-        "                                 **automl_settings) \r\n",
-        " \r\n",
-        "    local_run = experiment.submit(automl_config, show_output = True) \r\n",
-        "\r\n",
-        "    best_run, fitted_model = local_run.get_output()\r\n",
-        "\r\n",
-        "    pickled_model = codecs.encode(pickle.dumps(fitted_model), \"base64\").decode()\r\n",
-        "\r\n",
-        "    log_file_text = \"\"\r\n",
-        "\r\n",
-        "    try:\r\n",
-        "        with open(log_file_name, \"r\") as log_file:\r\n",
-        "            log_file_text = log_file.read()\r\n",
-        "    except:\r\n",
-        "        log_file_text = \"Log file not found\"\r\n",
-        "\r\n",
-        "    returned_model = pd.DataFrame({\"best_run\": [best_run.id], \"experiment_name\": [experiment_name], \"fitted_model\": [pickled_model], \"log_file_text\": [log_file_text], \"workspace\": [ws.name]}, dtype=np.dtype(np.str))\r\n",
-        "'\r\n",
-        "\t, @input_data_1 = @input_query\r\n",
-        "\t, @input_data_1_name = N'input_data'\r\n",
-        "\t, @output_data_1_name = N'returned_model'\r\n",
-        "\t, @params = N'@label_column NVARCHAR(255), \r\n",
-        "\t              @primary_metric NVARCHAR(40),\r\n",
-        "\t\t\t\t  @iterations INT, @task NVARCHAR(40),\r\n",
-        "\t\t\t\t  @experiment_name NVARCHAR(32),\r\n",
-        "\t\t\t\t  @iteration_timeout_minutes INT,\r\n",
-        "\t\t\t\t  @experiment_timeout_minutes INT,\r\n",
-        "\t\t\t\t  @n_cross_validations INT,\r\n",
-        "\t\t\t\t  @blacklist_models NVARCHAR(MAX),\r\n",
-        "\t\t\t\t  @whitelist_models NVARCHAR(MAX),\r\n",
-        "\t\t\t\t  @experiment_exit_score FLOAT,\r\n",
-        "\t\t\t\t  @sample_weight_column NVARCHAR(255),\r\n",
-        "\t\t\t\t  @is_validate_column NVARCHAR(255),\r\n",
-        "\t\t\t\t  @time_column_name  NVARCHAR(255),\r\n",
-        "\t\t\t\t  @tenantid NVARCHAR(255),\r\n",
-        "\t\t\t\t  @appid NVARCHAR(255),\r\n",
-        "\t\t\t\t  @password NVARCHAR(255),\r\n",
-        "\t\t\t\t  @config_file NVARCHAR(255)'\r\n",
-        "\t, @label_column = @label_column\r\n",
-        "\t, @primary_metric = @primary_metric\r\n",
-        "\t, @iterations = @iterations\r\n",
-        "\t, @task = @task\r\n",
-        "\t, @experiment_name = @experiment_name\r\n",
-        "\t, @iteration_timeout_minutes = @iteration_timeout_minutes\r\n",
-        "\t, @experiment_timeout_minutes = @experiment_timeout_minutes\r\n",
-        "\t, @n_cross_validations = @n_cross_validations\r\n",
-        "\t, @blacklist_models = @blacklist_models\r\n",
-        "\t, @whitelist_models = @whitelist_models\r\n",
-        "\t, @experiment_exit_score = @experiment_exit_score\r\n",
-        "\t, @sample_weight_column = @sample_weight_column\r\n",
-        "\t, @is_validate_column = @is_validate_column\r\n",
-        "\t, @time_column_name = @time_column_name\r\n",
-        "\t, @tenantid = @tenantid\r\n",
-        "\t, @appid = @appid\r\n",
-        "\t, @password = @password\r\n",
-        "\t, @config_file = @config_file\r\n",
-        "WITH RESULT SETS ((best_run NVARCHAR(250), experiment_name NVARCHAR(100), fitted_model VARCHAR(MAX), log_file_text NVARCHAR(MAX), workspace NVARCHAR(100)))\r\n",
-        "END"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "-- This procedure returns a list of metrics for each iteration of a training run.\r\n",
-        "SET ANSI_NULLS ON\r\n",
-        "GO\r\n",
-        "SET QUOTED_IDENTIFIER ON\r\n",
-        "GO\r\n",
-        "CREATE OR ALTER PROCEDURE [dbo].[AutoMLGetMetrics]\r\n",
-        " (\r\n",
-        "\t@run_id NVARCHAR(250),                           -- The RunId\r\n",
-        "    @experiment_name NVARCHAR(32)='automl-sql-test', -- This can be used to find the experiment in the Azure Portal.\r\n",
-        "    @connection_name NVARCHAR(255)='default'         -- The AML connection to use.\r\n",
-        " ) AS\r\n",
-        "BEGIN\r\n",
-        "    DECLARE @tenantid NVARCHAR(255)\r\n",
-        "    DECLARE @appid NVARCHAR(255)\r\n",
-        "    DECLARE @password NVARCHAR(255)\r\n",
-        "    DECLARE @config_file NVARCHAR(255)\r\n",
-        "\r\n",
-        "\tSELECT @tenantid=TenantId, @appid=AppId, @password=Password, @config_file=ConfigFile\r\n",
-        "\tFROM aml_connection\r\n",
-        "\tWHERE ConnectionName = @connection_name;\r\n",
-        "\r\n",
-        "    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd\r\n",
-        "import logging \r\n",
-        "import azureml.core \r\n",
-        "import numpy as np\r\n",
-        "from azureml.core.experiment import Experiment \r\n",
-        "from azureml.train.automl.run import AutoMLRun\r\n",
-        "from azureml.core.authentication import ServicePrincipalAuthentication \r\n",
-        "from azureml.core.workspace import Workspace \r\n",
-        "\r\n",
-        "auth = ServicePrincipalAuthentication(tenantid, appid, password) \r\n",
-        " \r\n",
-        "ws = Workspace.from_config(path=config_file, auth=auth) \r\n",
-        " \r\n",
-        "experiment = Experiment(ws, experiment_name) \r\n",
-        "\r\n",
-        "ml_run = AutoMLRun(experiment = experiment, run_id = run_id)\r\n",
-        "\r\n",
-        "children = list(ml_run.get_children())\r\n",
-        "iterationlist = []\r\n",
-        "metricnamelist = []\r\n",
-        "metricvaluelist = []\r\n",
-        "\r\n",
-        "for run in children:\r\n",
-        "    properties = run.get_properties()\r\n",
-        "    if \"iteration\" in properties:\r\n",
-        "        iteration = int(properties[\"iteration\"])\r\n",
-        "        for metric_name, metric_value in run.get_metrics().items():\r\n",
-        "            if isinstance(metric_value, float):\r\n",
-        "                iterationlist.append(iteration)\r\n",
-        "                metricnamelist.append(metric_name)\r\n",
-        "                metricvaluelist.append(metric_value)\r\n",
-        "             \r\n",
-        "metrics = pd.DataFrame({\"iteration\": iterationlist, \"metric_name\": metricnamelist, \"metric_value\": metricvaluelist})\r\n",
-        "'\r\n",
-        "    , @output_data_1_name = N'metrics'\r\n",
-        "\t, @params = N'@run_id NVARCHAR(250), \r\n",
-        "\t\t\t\t  @experiment_name NVARCHAR(32),\r\n",
-        "  \t\t\t\t  @tenantid NVARCHAR(255),\r\n",
-        "\t\t\t\t  @appid NVARCHAR(255),\r\n",
-        "\t\t\t\t  @password NVARCHAR(255),\r\n",
-        "\t\t\t\t  @config_file NVARCHAR(255)'\r\n",
-        "    , @run_id = @run_id\r\n",
-        "\t, @experiment_name = @experiment_name\r\n",
-        "\t, @tenantid = @tenantid\r\n",
-        "\t, @appid = @appid\r\n",
-        "\t, @password = @password\r\n",
-        "\t, @config_file = @config_file\r\n",
-        "WITH RESULT SETS ((iteration INT, metric_name NVARCHAR(100), metric_value FLOAT))\r\n",
-        "END"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "-- This procedure predicts values based on a model returned by AutoMLTrain and a dataset.\r\n",
-        "-- It returns the dataset with a new column added, which is the predicted value.\r\n",
-        "SET ANSI_NULLS ON\r\n",
-        "GO\r\n",
-        "SET QUOTED_IDENTIFIER ON\r\n",
-        "GO\r\n",
-        "CREATE OR ALTER PROCEDURE [dbo].[AutoMLPredict]\r\n",
-        " (\r\n",
-        "   @input_query NVARCHAR(MAX),      -- A SQL query returning data to predict on.\r\n",
-        "   @model NVARCHAR(MAX),            -- A model returned from AutoMLTrain.\r\n",
-        "   @label_column  NVARCHAR(255)=''  -- Optional name of the column from input_query, which should be ignored when predicting\r\n",
-        " ) AS \r\n",
-        "BEGIN \r\n",
-        "  \r\n",
-        "    EXEC sp_execute_external_script @language = N'Python', @script = N'import pandas as pd \r\n",
-        "import azureml.core  \r\n",
-        "import numpy as np \r\n",
-        "from azureml.train.automl import AutoMLConfig  \r\n",
-        "import pickle \r\n",
-        "import codecs \r\n",
-        "  \r\n",
-        "model_obj = pickle.loads(codecs.decode(model.encode(), \"base64\")) \r\n",
-        "  \r\n",
-        "test_data = input_data.copy() \r\n",
-        "\r\n",
-        "if label_column != \"\" and label_column is not None:\r\n",
-        "    y_test = test_data.pop(label_column).values \r\n",
-        "X_test = test_data \r\n",
-        "  \r\n",
-        "predicted = model_obj.predict(X_test) \r\n",
-        "  \r\n",
-        "combined_output = input_data.assign(predicted=predicted)\r\n",
-        "  \r\n",
-        "' \r\n",
-        "    , @input_data_1 = @input_query \r\n",
-        "    , @input_data_1_name = N'input_data' \r\n",
-        "    , @output_data_1_name = N'combined_output' \r\n",
-        "    , @params = N'@model NVARCHAR(MAX), @label_column  NVARCHAR(255)' \r\n",
-        "    , @model = @model \r\n",
-        "\t, @label_column = @label_column\r\n",
-        "END"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "jeffshep"
-      }
-    ],
-    "category": "tutorial",
-    "compute": [
-      "None"
-    ],
-    "datasets": [
-      "None"
-    ],
-    "deployment": [
-      "None"
-    ],
-    "exclude_from_index": false,
-    "framework": [
-      "Azure ML AutoML"
-    ],
-    "friendly_name": "Setup automated ML SQL integration",
-    "index_order": 1,
-    "kernelspec": {
-      "display_name": "Python 3.6",
-      "language": "sql",
-      "name": "python36"
-    },
-    "language_info": {
-      "name": "sql",
-      "version": ""
-    },
-    "tags": [
-      ""
-    ],
-    "task": "None"
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/azure-databricks/amlsdk/deploy-to-aci-04.ipynb

@@ -11,6 +11,13 @@
         "Licensed under the MIT License."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Register Azure Databricks trained model and deploy it to ACI\n"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -161,9 +168,9 @@
       "source": [
         "from azureml.core.conda_dependencies import CondaDependencies \n",
         "\n",
-        "myacienv = CondaDependencies.create(conda_packages=['scikit-learn','numpy','pandas']) #showing how to add libs as an eg. - not needed for this model.\n",
+        "myacienv = CondaDependencies.create(conda_packages=['scikit-learn','numpy','pandas']) # showing how to add libs as an eg. - not needed for this model.\n",
         "\n",
-        "with open(\"mydeployenv.yml\",\"w\") as f:\n",
+        "with open(\"myenv.yml\",\"w\") as f:\n",
         "    f.write(myacienv.serialize_to_string())"
       ]
     },
@@ -175,18 +182,37 @@
       "source": [
         "#deploy to ACI\n",
         "from azureml.core.webservice import AciWebservice, Webservice\n",
+        "from azureml.exceptions import WebserviceException\n",
         "from azureml.core.model import InferenceConfig\n",
+        "from azureml.core.environment import Environment\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "\n",
         "\n",
         "myaci_config = AciWebservice.deploy_configuration(cpu_cores = 2, \n",
         "                                                  memory_gb = 2, \n",
         "                                                  tags = {'name':'Databricks Azure ML ACI'}, \n",
         "                                                  description = 'This is for ADB and AML example.')\n",
         "\n",
-        "inference_config = InferenceConfig(runtime= 'spark-py', \n",
-        "                                   entry_script='score_sparkml.py',\n",
-        "                                   conda_file='mydeployenv.yml')\n",
+        "service_name = 'aciws'\n",
         "\n",
-        "myservice = Model.deploy(ws, 'aciws', [mymodel], inference_config, myaci_config)\n",
+        "# Remove any existing service under the same name.\n",
+        "try:\n",
+        "    Webservice(ws, service_name).delete()\n",
+        "except WebserviceException:\n",
+        "    pass\n",
+        "\n",
+        "myenv = Environment.get(ws, name='AzureML-PySpark-MmlSpark-0.15')\n",
+        "# we need to add extra packages to procured environment\n",
+        "# in order to deploy amended environment we need to rename it\n",
+        "myenv.name = 'myenv'\n",
+        "model_dependencies = CondaDependencies('myenv.yml')\n",
+        "for pip_dep in model_dependencies.pip_packages:\n",
+        "    myenv.python.conda_dependencies.add_pip_package(pip_dep)\n",
+        "for conda_dep in model_dependencies.conda_packages:\n",
+        "    myenv.python.conda_dependencies.add_conda_package(conda_dep)\n",
+        "inference_config = InferenceConfig(entry_script='score_sparkml.py', environment=myenv)\n",
+        "\n",
+        "myservice = Model.deploy(ws, service_name, [mymodel], inference_config, myaci_config)\n",
         "myservice.wait_for_deployment(show_output=True)"
       ]
     },
@@ -199,18 +225,6 @@
         "help(Webservice)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# List images by ws\n",
-        "\n",
-        "for i in ContainerImage.list(workspace = ws):\n",
-        "    print('{}(v.{} [{}]) stored at {} with build log {}'.format(i.name, i.version, i.creation_state, i.image_location, i.image_build_log_uri))"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -258,6 +272,15 @@
         "myservice.delete()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Deploying to other types of computes\n",
+        "\n",
+        "In order to learn how to deploy to other types of compute targets, such as AKS, please take a look at the set of notebooks in the [deployment](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/deployment) folder."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/azure-databricks/amlsdk/deploy-to-aks-05.ipynb

@@ -1,298 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Azure ML & Azure Databricks notebooks by Parashar Shah.\n",
-        "\n",
-        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
-        "\n",
-        "Licensed under the MIT License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "This notebook uses image from ACI notebook for deploying to AKS."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import azureml.core\n",
-        "\n",
-        "# Check core SDK version number\n",
-        "print(\"SDK version:\", azureml.core.VERSION)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Set auth to be used by workspace related APIs.\n",
-        "# For automation or CI/CD ServicePrincipalAuthentication can be used.\n",
-        "# https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.authentication.serviceprincipalauthentication?view=azure-ml-py\n",
-        "auth = None"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Workspace\n",
-        "\n",
-        "ws = Workspace.from_config(auth = auth)\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": [
-        "#Register the model\n",
-        "import os\n",
-        "from azureml.core.model import Model\n",
-        "\n",
-        "model_name = \"AdultCensus_runHistory_aks.mml\" # \n",
-        "model_name_dbfs = os.path.join(\"/dbfs\", model_name)\n",
-        "\n",
-        "print(\"copy model from dbfs to local\")\n",
-        "model_local = \"file:\" + os.getcwd() + \"/\" + model_name\n",
-        "dbutils.fs.cp(model_name, model_local, True)\n",
-        "\n",
-        "mymodel = Model.register(model_path = model_name, # this points to a local file\n",
-        "                       model_name = model_name, # this is the name the model is registered as, am using same name for both path and name.                 \n",
-        "                       description = \"ADB trained model by Parashar\",\n",
-        "                       workspace = ws)\n",
-        "\n",
-        "print(mymodel.name, mymodel.description, mymodel.version)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#%%writefile score_sparkml.py\n",
-        "score_sparkml = \"\"\"\n",
-        " \n",
-        "import json\n",
-        " \n",
-        "def init():\n",
-        "    # One-time initialization of PySpark and predictive model\n",
-        "    import pyspark\n",
-        "    from azureml.core.model import Model\n",
-        "    from pyspark.ml import PipelineModel\n",
-        " \n",
-        "    global trainedModel\n",
-        "    global spark\n",
-        " \n",
-        "    spark = pyspark.sql.SparkSession.builder.appName(\"ADB and AML notebook by Parashar\").getOrCreate()\n",
-        "    model_name = \"{model_name}\" #interpolated\n",
-        "    model_path = Model.get_model_path(model_name)\n",
-        "    trainedModel = PipelineModel.load(model_path)\n",
-        "    \n",
-        "def run(input_json):\n",
-        "    if isinstance(trainedModel, Exception):\n",
-        "        return json.dumps({{\"trainedModel\":str(trainedModel)}})\n",
-        "      \n",
-        "    try:\n",
-        "        sc = spark.sparkContext\n",
-        "        input_list = json.loads(input_json)\n",
-        "        input_rdd = sc.parallelize(input_list)\n",
-        "        input_df = spark.read.json(input_rdd)\n",
-        "    \n",
-        "        # Compute prediction\n",
-        "        prediction = trainedModel.transform(input_df)\n",
-        "        #result = prediction.first().prediction\n",
-        "        predictions = prediction.collect()\n",
-        " \n",
-        "        #Get each scored result\n",
-        "        preds = [str(x['prediction']) for x in predictions]\n",
-        "        result = \",\".join(preds)\n",
-        "        # you can return any data type as long as it is JSON-serializable\n",
-        "        return result.tolist()\n",
-        "    except Exception as e:\n",
-        "        result = str(e)\n",
-        "        return result\n",
-        "    \n",
-        "\"\"\".format(model_name=model_name)\n",
-        " \n",
-        "exec(score_sparkml)\n",
-        " \n",
-        "with open(\"score_sparkml.py\", \"w\") as file:\n",
-        "    file.write(score_sparkml)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.conda_dependencies import CondaDependencies \n",
-        "\n",
-        "myacienv = CondaDependencies.create(conda_packages=['scikit-learn','numpy','pandas']) #showing how to add libs as an eg. - not needed for this model.\n",
-        "\n",
-        "with open(\"mydeployenv.yml\",\"w\") as f:\n",
-        "    f.write(myacienv.serialize_to_string())"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#create AKS compute\n",
-        "#it may take 20-25 minutes to create a new cluster\n",
-        "\n",
-        "from azureml.core.compute import AksCompute, ComputeTarget\n",
-        "\n",
-        "# Use the default configuration (can also provide parameters to customize)\n",
-        "prov_config = AksCompute.provisioning_configuration()\n",
-        "\n",
-        "aks_name = 'ps-aks-demo2' \n",
-        "\n",
-        "# Create the cluster\n",
-        "aks_target = ComputeTarget.create(workspace = ws, \n",
-        "                                  name = aks_name, \n",
-        "                                  provisioning_configuration = prov_config)\n",
-        "\n",
-        "aks_target.wait_for_completion(show_output = True)\n",
-        "\n",
-        "print(aks_target.provisioning_state)\n",
-        "print(aks_target.provisioning_errors)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#deploy to AKS\n",
-        "from azureml.core.webservice import AksWebservice, Webservice\n",
-        "from azureml.core.model import InferenceConfig\n",
-        "\n",
-        "aks_config = AksWebservice.deploy_configuration(enable_app_insights=True)\n",
-        "\n",
-        "inference_config = InferenceConfig(runtime = 'spark-py', \n",
-        "                                   entry_script ='score_sparkml.py',\n",
-        "                                   conda_file ='mydeployenv.yml')\n",
-        "\n",
-        "aks_service = Model.deploy(ws, 'ps-aks-service', [mymodel], inference_config, aks_config, aks_target)\n",
-        "aks_service.wait_for_deployment(show_output=True)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "aks_service.deployment_status"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#for using the Web HTTP API \n",
-        "print(aks_service.scoring_uri)\n",
-        "print(aks_service.get_keys())"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "\n",
-        "#get the some sample data\n",
-        "test_data_path = \"AdultCensusIncomeTest\"\n",
-        "test = spark.read.parquet(test_data_path).limit(5)\n",
-        "\n",
-        "test_json = json.dumps(test.toJSON().collect())\n",
-        "\n",
-        "print(test_json)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#using data defined above predict if income is >50K (1) or <=50K (0)\n",
-        "aks_service.run(input_data=test_json)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#comment to not delete the web service\n",
-        "aks_service.delete()\n",
-        "#model.delete()\n",
-        "aks_target.delete() "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/azure-databricks/amlsdk/deploy-to-aks-existingimage-05.png)"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "pasha"
-      }
-    ],
-    "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"
-    },
-    "name": "deploy-to-aks-existingimage-05",
-    "notebookId": 1030695628045968
-  },
-  "nbformat": 4,
-  "nbformat_minor": 1
-}

how-to-use-azureml/azure-databricks/automl/automl-databricks-local-01.ipynb

@@ -13,32 +13,45 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "# Automated ML on Azure Databricks\n",
+        "We support installing AML SDK as library from GUI. When attaching a library follow this https://docs.databricks.com/user-guide/libraries.html and add the below string as your PyPi package. You can select the option to attach the library to all clusters or just one cluster.\n",
         "\n",
-        "In this example we use the scikit-learn's <a href=\"http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset\" target=\"_blank\">digit dataset</a> to showcase how you can use AutoML for a simple classification problem.\n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "1. Create Azure Machine Learning Workspace object and initialize your notebook directory to easily reload this object from a configuration file.\n",
-        "2. Create an `Experiment` in an existing `Workspace`.\n",
-        "3. Configure Automated ML using `AutoMLConfig`.\n",
-        "4. Train the model using Azure Databricks.\n",
-        "5. Explore the results.\n",
-        "6. Viewing the engineered names for featurized data and featurization summary for all raw features.\n",
-        "7. Test the best fitted model.\n",
-        "\n",
-        "Before running this notebook, please follow the <a href=\"https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/azure-databricks\" target=\"_blank\">readme for using Automated ML on Azure Databricks</a> for installing necessary libraries to your cluster."
+        "**install azureml-sdk with Automated ML**\n",
+        "* Source: Upload Python Egg or PyPi\n",
+        "* PyPi Name: `azureml-sdk[automl]`\n",
+        "* Select Install Library"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "We support installing AML SDK with Automated ML as library from GUI. When attaching a library follow <a href=\"https://docs.databricks.com/user-guide/libraries.html\" target=\"_blank\">this link</a> and add the below string as your PyPi package. You can select the option to attach the library to all clusters or just one cluster.\n",
+        "# AutoML : Classification with Local Compute on Azure DataBricks\n",
         "\n",
-        "**azureml-sdk with automated ml**\n",
-        "* Source: Upload Python Egg or PyPi\n",
-        "* PyPi Name: `azureml-sdk[automl]`\n",
-        "* Select Install Library"
+        "In this example we use the scikit-learn's to showcase how you can use AutoML for a simple classification problem.\n",
+        "\n",
+        "In this notebook you will learn how to:\n",
+        "1. Create Azure Machine Learning Workspace object and initialize your notebook directory to easily reload this object from a configuration file.\n",
+        "2. Create an `Experiment` in an existing `Workspace`.\n",
+        "3. Configure AutoML using `AutoMLConfig`.\n",
+        "4. Train the model using AzureDataBricks.\n",
+        "5. Explore the results.\n",
+        "6. Test the best fitted model.\n",
+        "\n",
+        "Prerequisites:\n",
+        "Before running this notebook, please follow the readme for installing necessary libraries to your cluster."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Register Machine Learning Services Resource Provider\n",
+        "Microsoft.MachineLearningServices only needs to be registed once in the subscription. To register it:\n",
+        "Start the Azure portal.\n",
+        "Select your All services and then Subscription.\n",
+        "Select the subscription that you want to use.\n",
+        "Click on Resource providers\n",
+        "Click the Register link next to Microsoft.MachineLearningServices"
       ]
     },
     {
@@ -145,31 +158,8 @@
         "               resource_group = resource_group)\n",
         "\n",
         "# Persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
-        "ws.write_config()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create a Folder to Host Sample Projects\n",
-        "Finally, create a folder where all the sample projects will be hosted."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "sample_projects_folder = './sample_projects'\n",
-        "\n",
-        "if not os.path.isdir(sample_projects_folder):\n",
-        "    os.mkdir(sample_projects_folder)\n",
-        "    \n",
-        "print('Sample projects will be created in {}.'.format(sample_projects_folder))"
+        "ws.write_config()\n",
+        "write_config(path=\"/databricks/driver/aml_config/\",file_name=<alias_conf.cfg>)"
       ]
     },
     {
@@ -178,7 +168,7 @@
       "source": [
         "## Create an Experiment\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."
+        "As part of the setup you have already created an Azure ML `Workspace` object. For AutoML you will need to create an `Experiment` object, which is a named object in a `Workspace` used to run experiments."
       ]
     },
     {
@@ -191,6 +181,7 @@
         "import os\n",
         "import random\n",
         "import time\n",
+        "import json\n",
         "\n",
         "from matplotlib import pyplot as plt\n",
         "from matplotlib.pyplot import imshow\n",
@@ -212,7 +203,6 @@
       "source": [
         "# Choose a name for the experiment and specify the project folder.\n",
         "experiment_name = 'automl-local-classification'\n",
-        "project_folder = './sample_projects/automl-local-classification'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
@@ -222,94 +212,11 @@
         "output['Workspace Name'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
         "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
         "output['Experiment Name'] = experiment.name\n",
         "pd.set_option('display.max_colwidth', -1)\n",
         "pd.DataFrame(data = output, index = ['']).T"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Diagnostics\n",
-        "\n",
-        "Opt-in diagnostics for better experience, quality, and security of future releases."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.telemetry import set_diagnostics_collection\n",
-        "set_diagnostics_collection(send_diagnostics = True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Registering Datastore"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Datastore is the way to save connection information to a storage service (e.g. Azure Blob, Azure Data Lake, Azure SQL) information to your workspace so you can access them without exposing credentials in your code. The first thing you will need to do is register a datastore, you can refer to our [python SDK documentation](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.datastore.datastore?view=azure-ml-py) on how to register datastores. __Note: for best security practices, please do not check in code that contains registering datastores with secrets into your source control__\n",
-        "\n",
-        "The code below registers a datastore pointing to a publicly readable blob container."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Datastore\n",
-        "\n",
-        "datastore_name = 'demo_training'\n",
-        "container_name = 'digits' \n",
-        "account_name = 'automlpublicdatasets'\n",
-        "Datastore.register_azure_blob_container(\n",
-        "    workspace = ws, \n",
-        "    datastore_name = datastore_name, \n",
-        "    container_name = container_name, \n",
-        "    account_name = account_name,\n",
-        "    overwrite = True\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Below is an example on how to register a private blob container\n",
-        "```python\n",
-        "datastore = Datastore.register_azure_blob_container(\n",
-        "    workspace = ws, \n",
-        "    datastore_name = 'example_datastore', \n",
-        "    container_name = 'example-container', \n",
-        "    account_name = 'storageaccount',\n",
-        "    account_key = 'accountkey'\n",
-        ")\n",
-        "```\n",
-        "The example below shows how  to register an Azure Data Lake store. Please make sure you have granted the necessary permissions for the service principal to access the data lake.\n",
-        "```python\n",
-        "datastore = Datastore.register_azure_data_lake(\n",
-        "    workspace = ws,\n",
-        "    datastore_name = 'example_datastore',\n",
-        "    store_name = 'adlsstore',\n",
-        "    tenant_id = 'tenant-id-of-service-principal',\n",
-        "    client_id = 'client-id-of-service-principal',\n",
-        "    client_secret = 'client-secret-of-service-principal'\n",
-        ")\n",
-        "```"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -323,9 +230,7 @@
       "source": [
         "Automated ML takes a `TabularDataset` as input.\n",
         "\n",
-        "You are free to use the data preparation libraries/tools of your choice to do the require preparation and once you are done, you can write it to a datastore and create a TabularDataset from it.\n",
-        "\n",
-        "You will get the datastore you registered previously and pass it to Dataset for reading. The data comes from the digits dataset: `sklearn.datasets.load_digits()`. `DataPath` points to a specific location within a datastore. "
+        "You are free to use the data preparation libraries/tools of your choice to do the require preparation and once you are done, you can write it to a datastore and create a TabularDataset from it."
       ]
     },
     {
@@ -334,13 +239,12 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "# The data referenced here was a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
         "from azureml.core.dataset import Dataset\n",
-        "from azureml.data.datapath import DataPath\n",
         "\n",
-        "datastore = Datastore.get(workspace = ws, datastore_name = datastore_name)\n",
-        "\n",
-        "X_train = Dataset.Tabular.from_delimited_files(datastore.path('X.csv'))\n",
-        "y_train = Dataset.Tabular.from_delimited_files(datastore.path('y.csv'))"
+        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
+        "dataset = Dataset.Tabular.from_delimited_files(example_data)\n",
+        "dataset.take(5).to_pandas_dataframe()"
       ]
     },
     {
@@ -357,16 +261,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_train.take(5).to_pandas_dataframe()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_train.take(5).to_pandas_dataframe()"
+        "training_data = dataset.drop_columns(columns=['FBI Code'])\n",
+        "label = 'Primary Type'"
       ]
     },
     {
@@ -384,14 +280,11 @@
         "|**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",
         "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
         "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
-        "|**n_cross_validations**|Number of cross validation splits.|\n",
         "|**spark_context**|Spark Context object. for Databricks, use spark_context=sc|\n",
         "|**max_concurrent_iterations**|Maximum number of iterations to execute in parallel. This should be <= number of worker nodes in your Azure Databricks cluster.|\n",
-        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
-        "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
-        "|**preprocess**|set this to True to enable pre-processing of data eg. string to numeric using one-hot encoding|\n",
-        "|**exit_score**|Target score for experiment. It is associated with the metric. eg. exit_score=0.995 will exit experiment after that|"
+        "|**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.|"
       ]
     },
     {
@@ -404,15 +297,13 @@
         "                             debug_log = 'automl_errors.log',\n",
         "                             primary_metric = 'AUC_weighted',\n",
         "                             iteration_timeout_minutes = 10,\n",
-        "                             iterations = 3,\n",
-        "                             preprocess = True,\n",
+        "                             iterations = 5,\n",
         "                             n_cross_validations = 10,\n",
         "                             max_concurrent_iterations = 2, #change it based on number of worker nodes\n",
         "                             verbosity = logging.INFO,\n",
         "                             spark_context=sc, #databricks/spark related\n",
-        "                             X = X_train, \n",
-        "                             y = y_train,\n",
-        "                             path = project_folder)"
+        "                             training_data=training_data,\n",
+        "                             label_column_name=label)"
       ]
     },
     {
@@ -433,26 +324,6 @@
         "local_run = experiment.submit(automl_config, show_output = True)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Continue experiment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run.continue_experiment(iterations=2,\n",
-        "                              X=X_train, \n",
-        "                              y=y_train,\n",
-        "                              spark_context=sc,\n",
-        "                              show_output=True)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -475,14 +346,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "displayHTML(\"<a href={} target='_blank'>Your experiment in Azure Portal: {}</a>\".format(local_run.get_portal_url(), local_run.id))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The following will show the child runs and waits for the parent run to complete."
+        "displayHTML(\"<a href={} target='_blank'>Azure Portal: {}</a>\".format(local_run.get_portal_url(), local_run.id))"
       ]
     },
     {
@@ -503,6 +367,7 @@
         "metricslist = {}\n",
         "for run in children:\n",
         "    properties = run.get_properties()\n",
+        "    #print(properties)\n",
         "    metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}    \n",
         "    metricslist[int(properties['iteration'])] = metrics\n",
         "\n",
@@ -514,9 +379,11 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Retrieve the Best Model after the above run is complete \n",
+        "## Deploy\n",
         "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+        "### 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*."
       ]
     },
     {
@@ -525,71 +392,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "best_run, fitted_model = local_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model Based on Any Other Metric after the above run is complete based on the child run\n",
-        "Show the run and the model that has the smallest `log_loss` value:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "lookup_metric = \"log_loss\"\n",
-        "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### View the engineered names for featurized data\n",
-        "Below we display the engineered feature names generated for the featurized data using the preprocessing featurization."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "fitted_model.named_steps['datatransformer'].get_engineered_feature_names()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### View the featurization summary\n",
-        "Below we display the featurization that was performed on different raw features in the user data. For each raw feature in the user data, the following information is displayed:-\n",
-        "- Raw feature name\n",
-        "- Number of engineered features formed out of this raw feature\n",
-        "- Type detected\n",
-        "- If feature was dropped\n",
-        "- List of feature transformations for the raw feature"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Get the featurization summary as a list of JSON\n",
-        "featurization_summary = fitted_model.named_steps['datatransformer'].get_featurization_summary()\n",
-        "# View the featurization summary as a pandas dataframe\n",
-        "pd.DataFrame.from_records(featurization_summary)"
+        "best_run, fitted_model = local_run.get_output()"
       ]
     },
     {
@@ -607,11 +410,13 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "blob_location = \"https://{}.blob.core.windows.net/{}\".format(account_name, container_name)\n",
-        "X_test = pd.read_csv(\"{}./X_valid.csv\".format(blob_location), header=0)\n",
-        "y_test = pd.read_csv(\"{}/y_valid.csv\".format(blob_location), header=0)\n",
-        "images  = pd.read_csv(\"{}/images.csv\".format(blob_location), header=None)\n",
-        "images = np.reshape(images.values, (100,8,8))"
+        "dataset_test = Dataset.Tabular.from_delimited_files(path='https://dprepdata.blob.core.windows.net/demo/crime0-test.csv')\n",
+        "\n",
+        "df_test = dataset_test.to_pandas_dataframe()\n",
+        "df_test = df_test[pd.notnull(df_test['Primary Type'])]\n",
+        "\n",
+        "y_test = df_test[['Primary Type']]\n",
+        "X_test = df_test.drop(['Primary Type', 'FBI Code'], axis=1)"
       ]
     },
     {
@@ -628,35 +433,9 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# Randomly select digits and test.\n",
-        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
-        "    print(index)\n",
-        "    predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
-        "    label = y_test.values[index]\n",
-        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
-        "    fig = plt.figure(3, figsize = (5,5))\n",
-        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
-        "    ax1.set_title(title)\n",
-        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
-        "    display(fig)"
+        "fitted_model.predict(X_test)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "When deploying an automated ML trained model, please specify _pippackages=['azureml-sdk[automl]']_ in your CondaDependencies.\n",
-        "\n",
-        "Please refer to only the **Deploy** section in this notebook - <a href=\"https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification-with-deployment\" target=\"_blank\">Deployment of Automated ML trained model</a>"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -689,10 +468,10 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.5"
+      "version": "3.6.8"
     },
     "name": "auto-ml-classification-local-adb",
-    "notebookId": 587284549713154
+    "notebookId": 1275190406842063
   },
   "nbformat": 4,
   "nbformat_minor": 1

how-to-use-azureml/azure-databricks/automl/automl-databricks-local-with-deployment.ipynb

@@ -27,7 +27,7 @@
       "source": [
         "# AutoML : Classification with Local Compute on Azure DataBricks with deployment to ACI\n",
         "\n",
-        "In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/datasets/index.html#optical-recognition-of-handwritten-digits-dataset) to showcase how you can use AutoML for a simple classification problem.\n",
+        "In this example we use the scikit-learn's to showcase how you can use AutoML for a simple classification problem.\n",
         "\n",
         "In this notebook you will learn how to:\n",
         "1. Create Azure Machine Learning Workspace object and initialize your notebook directory to easily reload this object from a configuration file.\n",
@@ -164,30 +164,6 @@
         "write_config(path=\"/databricks/driver/aml_config/\",file_name=<alias_conf.cfg>)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Create a Folder to Host Sample Projects\n",
-        "Finally, create a folder where all the sample projects will be hosted."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "sample_projects_folder = './sample_projects'\n",
-        "\n",
-        "if not os.path.isdir(sample_projects_folder):\n",
-        "    os.mkdir(sample_projects_folder)\n",
-        "    \n",
-        "print('Sample projects will be created in {}.'.format(sample_projects_folder))"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -229,7 +205,6 @@
       "source": [
         "# Choose a name for the experiment and specify the project folder.\n",
         "experiment_name = 'automl-local-classification'\n",
-        "project_folder = './sample_projects/automl-local-classification'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
@@ -239,94 +214,11 @@
         "output['Workspace Name'] = ws.name\n",
         "output['Resource Group'] = ws.resource_group\n",
         "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
         "output['Experiment Name'] = experiment.name\n",
         "pd.set_option('display.max_colwidth', -1)\n",
         "pd.DataFrame(data = output, index = ['']).T"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Diagnostics\n",
-        "\n",
-        "Opt-in diagnostics for better experience, quality, and security of future releases."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.telemetry import set_diagnostics_collection\n",
-        "set_diagnostics_collection(send_diagnostics = True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Registering Datastore"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Datastore is the way to save connection information to a storage service (e.g. Azure Blob, Azure Data Lake, Azure SQL) information to your workspace so you can access them without exposing credentials in your code. The first thing you will need to do is register a datastore, you can refer to our [python SDK documentation](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.datastore.datastore?view=azure-ml-py) on how to register datastores. __Note: for best security practices, please do not check in code that contains registering datastores with secrets into your source control__\n",
-        "\n",
-        "The code below registers a datastore pointing to a publicly readable blob container."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core import Datastore\n",
-        "\n",
-        "datastore_name = 'demo_training'\n",
-        "container_name = 'digits' \n",
-        "account_name = 'automlpublicdatasets'\n",
-        "Datastore.register_azure_blob_container(\n",
-        "    workspace = ws, \n",
-        "    datastore_name = datastore_name, \n",
-        "    container_name = container_name, \n",
-        "    account_name = account_name,\n",
-        "     overwrite = True\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Below is an example on how to register a private blob container\n",
-        "```python\n",
-        "datastore = Datastore.register_azure_blob_container(\n",
-        "    workspace = ws, \n",
-        "    datastore_name = 'example_datastore', \n",
-        "    container_name = 'example-container', \n",
-        "    account_name = 'storageaccount',\n",
-        "    account_key = 'accountkey'\n",
-        ")\n",
-        "```\n",
-        "The example below shows how  to register an Azure Data Lake store. Please make sure you have granted the necessary permissions for the service principal to access the data lake.\n",
-        "```python\n",
-        "datastore = Datastore.register_azure_data_lake(\n",
-        "    workspace = ws,\n",
-        "    datastore_name = 'example_datastore',\n",
-        "    store_name = 'adlsstore',\n",
-        "    tenant_id = 'tenant-id-of-service-principal',\n",
-        "    client_id = 'client-id-of-service-principal',\n",
-        "    client_secret = 'client-secret-of-service-principal'\n",
-        ")\n",
-        "```"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -340,9 +232,7 @@
       "source": [
         "Automated ML takes a `TabularDataset` as input.\n",
         "\n",
-        "You are free to use the data preparation libraries/tools of your choice to do the require preparation and once you are done, you can write it to a datastore and create a TabularDataset from it.\n",
-        "\n",
-        "You will get the datastore you registered previously and pass it to Dataset for reading. The data comes from the digits dataset: `sklearn.datasets.load_digits()`. `DataPath` points to a specific location within a datastore. "
+        "You are free to use the data preparation libraries/tools of your choice to do the require preparation and once you are done, you can write it to a datastore and create a TabularDataset from it."
       ]
     },
     {
@@ -351,13 +241,12 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "# The data referenced here was a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
         "from azureml.core.dataset import Dataset\n",
-        "from azureml.data.datapath import DataPath\n",
         "\n",
-        "datastore = Datastore.get(workspace = ws, datastore_name = datastore_name)\n",
-        "\n",
-        "X_train = Dataset.Tabular.from_delimited_files(datastore.path('X.csv'))\n",
-        "y_train = Dataset.Tabular.from_delimited_files(datastore.path('y.csv'))"
+        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
+        "dataset = Dataset.Tabular.from_delimited_files(example_data)\n",
+        "dataset.take(5).to_pandas_dataframe()"
       ]
     },
     {
@@ -374,16 +263,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X_train.take(5).to_pandas_dataframe()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_train.take(5).to_pandas_dataframe()"
+        "training_data = dataset.drop_columns(columns=['FBI Code'])\n",
+        "label = 'Primary Type'"
       ]
     },
     {
@@ -401,14 +282,11 @@
         "|**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",
         "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
         "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
-        "|**n_cross_validations**|Number of cross validation splits.|\n",
         "|**spark_context**|Spark Context object. for Databricks, use spark_context=sc|\n",
         "|**max_concurrent_iterations**|Maximum number of iterations to execute in parallel. This should be <= number of worker nodes in your Azure Databricks cluster.|\n",
-        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
-        "|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|\n",
-        "|**preprocess**|set this to True to enable pre-processing of data eg. string to numeric using one-hot encoding|\n",
-        "|**exit_score**|Target score for experiment. It is associated with the metric. eg. exit_score=0.995 will exit experiment after that|"
+        "|**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.|"
       ]
     },
     {
@@ -422,14 +300,12 @@
         "                             primary_metric = 'AUC_weighted',\n",
         "                             iteration_timeout_minutes = 10,\n",
         "                             iterations = 5,\n",
-        "                             preprocess = True,\n",
         "                             n_cross_validations = 10,\n",
         "                             max_concurrent_iterations = 2, #change it based on number of worker nodes\n",
         "                             verbosity = logging.INFO,\n",
         "                             spark_context=sc, #databricks/spark related\n",
-        "                             X = X_train, \n",
-        "                             y = y_train,\n",
-        "                             path = project_folder)"
+        "                             training_data=training_data,\n",
+        "                             label_column_name=label)"
       ]
     },
     {
@@ -475,13 +351,6 @@
         "displayHTML(\"<a href={} target='_blank'>Azure Portal: {}</a>\".format(local_run.get_portal_url(), local_run.id))"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "The following will show the child runs and waits for the parent run to complete."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -512,9 +381,11 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Retrieve the Best Model after the above run is complete \n",
+        "## Deploy\n",
         "\n",
-        "Below we select the best pipeline from our iterations. The `get_output` method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing.  Overloads on `get_output` allow you to retrieve the best run and fitted model for *any* logged metric or for a particular *iteration*."
+        "### 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*."
       ]
     },
     {
@@ -523,17 +394,15 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "best_run, fitted_model = local_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
+        "best_run, fitted_model = local_run.get_output()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "#### Best Model Based on Any Other Metric after the above run is complete based on the child run\n",
-        "Show the run and the model that has the smallest `log_loss` value:"
+        "### Download the conda environment file\n",
+        "From the *best_run* download the conda environment file that was used to train the AutoML model."
       ]
     },
     {
@@ -542,10 +411,34 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "lookup_metric = \"log_loss\"\n",
-        "best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
+        "from azureml.automl.core.shared import constants\n",
+        "conda_env_file_name = 'conda_env.yml'\n",
+        "best_run.download_file(name=\"outputs/conda_env_v_1_0_0.yml\", output_file_path=conda_env_file_name)\n",
+        "with open(conda_env_file_name, \"r\") as conda_file:\n",
+        "    conda_file_contents = conda_file.read()\n",
+        "    print(conda_file_contents)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Download the model scoring file\n",
+        "From the *best_run* download the scoring file to get the predictions from the AutoML model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.automl.core.shared import constants\n",
+        "script_file_name = 'scoring_file.py'\n",
+        "best_run.download_file(name=\"outputs/scoring_file_v_1_0_0.py\", output_file_path=script_file_name)\n",
+        "with open(script_file_name, \"r\") as scoring_file:\n",
+        "    scoring_file_contents = scoring_file.read()\n",
+        "    print(scoring_file_contents)"
       ]
     },
     {
@@ -572,8 +465,9 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Create Scoring Script\n",
-        "Replace model_id with name of model from output of above register cell"
+        "### Deploy the model as a Web Service on Azure Container Instance\n",
+        "\n",
+        "Create the configuration needed for deploying the model as a web service service."
       ]
     },
     {
@@ -582,105 +476,17 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "%%writefile score.py\n",
-        "import pickle\n",
-        "import json\n",
-        "import numpy as np\n",
-        "import azureml.train.automl\n",
-        "from sklearn.externals import joblib\n",
-        "from azureml.core.model import Model\n",
-        "import pandas as pd\n",
-        "\n",
-        "def init():\n",
-        "    global model\n",
-        "    model_path = Model.get_model_path(model_name = '<<model_id>>') # this name is model.id of model that we want to deploy\n",
-        "    # deserialize the model file back into a sklearn model\n",
-        "    model = joblib.load(model_path)\n",
-        "\n",
-        "def run(raw_data):\n",
-        "    try:\n",
-        "        data = (pd.DataFrame(np.array(json.loads(raw_data)['data']), columns=[str(i) for i in range(0,64)]))\n",
-        "        result = model.predict(data)\n",
-        "    except Exception as e:\n",
-        "        result = str(e)\n",
-        "        return json.dumps({\"error\": result})\n",
-        "    return json.dumps({\"result\":result.tolist()})"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#Replace <<model_id>>\n",
-        "content = \"\"\n",
-        "with open(\"score.py\", \"r\") as fo:\n",
-        "    content = fo.read()\n",
-        "\n",
-        "new_content = content.replace(\"<<model_id>>\", local_run.model_id)\n",
-        "with open(\"score.py\", \"w\") as fw:\n",
-        "    fw.write(new_content)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Create a YAML File for the Environment"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.conda_dependencies import CondaDependencies\n",
-        "\n",
-        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-defaults', 'azureml-sdk[automl]'])\n",
-        "\n",
-        "conda_env_file_name = 'mydeployenv.yml'\n",
-        "myenv.save_to_file('.', conda_env_file_name)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Deploy the model as a Web Service on Azure Container Instance\n",
-        "Replace servicename with any meaningful name of service"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# this will take 10-15 minutes to finish\n",
-        "\n",
-        "from azureml.core.webservice import AciWebservice, Webservice\n",
         "from azureml.core.model import InferenceConfig\n",
-        "from azureml.core.model import Model\n",
-        "import uuid\n",
+        "from azureml.core.webservice import AciWebservice\n",
+        "from azureml.core.environment import Environment\n",
         "\n",
-        "myaci_config = AciWebservice.deploy_configuration(\n",
-        "    cpu_cores = 2, \n",
-        "    memory_gb = 2, \n",
-        "    tags = {'name':'Databricks Azure ML ACI'}, \n",
-        "    description = 'This is for ADB and AutoML example.')\n",
+        "myenv = Environment.from_conda_specification(name=\"myenv\", file_path=conda_env_file_name)\n",
+        "inference_config = InferenceConfig(entry_script=script_file_name, environment=myenv)\n",
         "\n",
-        "inference_config = InferenceConfig(runtime= 'spark-py', \n",
-        "                                   entry_script='score.py',\n",
-        "                                   conda_file='mydeployenv.yml')\n",
-        "\n",
-        "guid = str(uuid.uuid4()).split(\"-\")[0]\n",
-        "service_name = \"myservice-{}\".format(guid)\n",
-        "print(\"Creating service with name: {}\".format(service_name))\n",
-        "\n",
-        "myservice = Model.deploy(ws, service_name, [model], inference_config, myaci_config)\n",
-        "myservice.wait_for_deployment(show_output=True)"
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 1, \n",
+        "                                               tags = {'area': \"digits\", 'type': \"automl_classification\"}, \n",
+        "                                               description = 'sample service for Automl Classification')"
       ]
     },
     {
@@ -689,8 +495,14 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "#for using the Web HTTP API \n",
-        "print(myservice.scoring_uri)"
+        "from azureml.core.webservice import Webservice\n",
+        "from azureml.core.model import Model\n",
+        "\n",
+        "aci_service_name = 'automl-databricks-local'\n",
+        "print(aci_service_name)\n",
+        "aci_service = Model.deploy(ws, aci_service_name, [model], inference_config, aciconfig)\n",
+        "aci_service.wait_for_deployment(True)\n",
+        "print(aci_service.state)"
       ]
     },
     {
@@ -708,11 +520,13 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "blob_location = \"https://{}.blob.core.windows.net/{}\".format(account_name, container_name)\n",
-        "X_test = pd.read_csv(\"{}./X_valid.csv\".format(blob_location), header=0)\n",
-        "y_test = pd.read_csv(\"{}/y_valid.csv\".format(blob_location), header=0)\n",
-        "images  = pd.read_csv(\"{}/images.csv\".format(blob_location), header=None)\n",
-        "images = np.reshape(images.values, (100,8,8))"
+        "dataset_test = Dataset.Tabular.from_delimited_files(path='https://dprepdata.blob.core.windows.net/demo/crime0-test.csv')\n",
+        "\n",
+        "df_test = dataset_test.to_pandas_dataframe()\n",
+        "df_test = df_test[pd.notnull(df_test['Primary Type'])]\n",
+        "\n",
+        "y_test = df_test[['Primary Type']]\n",
+        "X_test = df_test.drop(['Primary Type', 'FBI Code'], axis=1)"
       ]
     },
     {
@@ -729,20 +543,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "import json\n",
-        "# Randomly select digits and test.\n",
-        "for index in np.random.choice(len(y_test), 2, replace = False):\n",
-        "    print(index)\n",
-        "    test_sample = json.dumps({'data':X_test[index:index + 1].values.tolist()})\n",
-        "    predicted = myservice.run(input_data = test_sample)\n",
-        "    label = y_test.values[index]\n",
-        "    predictedDict = json.loads(predicted)\n",
-        "    title = \"Label value = %d  Predicted value = %s \" % ( label,predictedDict['result'][0])    \n",
-        "    fig = plt.figure(3, figsize = (5,5))\n",
-        "    ax1 = fig.add_axes((0,0,.8,.8))\n",
-        "    ax1.set_title(title)\n",
-        "    plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
-        "    display(fig)"
+        "fitted_model.predict(X_test)"
       ]
     },
     {
@@ -760,7 +561,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "myservice.delete()"
+        "aci_service.delete()"
       ]
     },
     {
@@ -795,10 +596,10 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.5"
+      "version": "3.6.8"
     },
     "name": "auto-ml-classification-local-adb",
-    "notebookId": 2733885892129020
+    "notebookId": 3772036807853791
   },
   "nbformat": 4,
   "nbformat_minor": 1

how-to-use-azureml/azureml-sdk-for-r/README.md

@@ -0,0 +1,36 @@
+## Examples to get started with Azure Machine Learning SDK for R
+
+Learn how to use Azure Machine Learning SDK for R for experimentation and model management.
+
+As a pre-requisite, go through the [Installation](vignettes/installation.Rmd) and [Configuration](vignettes/configuration.Rmd) vignettes to first install the package and set up your Azure Machine Learning Workspace unless you are running these examples on an Azure Machine Learning compute instance. Azure Machine Learning compute instances have the Azure Machine Learning SDK pre-installed and your workspace details pre-configured.
+
+
+Samples
+* Deployment
+	* [deploy-to-aci](./samples/deployment/deploy-to-aci): Deploy a model as a web service to Azure Container Instances (ACI).
+	* [deploy-to-local](./samples/deployment/deploy-to-local): Deploy a model as a web service locally.
+* Training
+	* [train-on-amlcompute](./samples/training/train-on-amlcompute): Train a model on a remote AmlCompute cluster.
+	* [train-on-local](./samples/training/train-on-local): Train a model locally with Docker.
+
+Vignettes
+* [deploy-to-aks](./vignettes/deploy-to-aks): Production deploy a model as a web service to Azure Kubernetes Service (AKS).
+* [hyperparameter-tune-with-keras](./vignettes/hyperparameter-tune-with-keras): Hyperparameter tune a Keras model using HyperDrive, Azure ML's hyperparameter tuning functionality.
+* [train-and-deploy-to-aci](./vignettes/train-and-deploy-to-aci): Train a caret model and deploy as a web service to Azure Container Instances (ACI).
+* [train-with-tensorflow](./vignettes/train-with-tensorflow): Train a deep learning TensorFlow model with Azure ML.
+
+Find more information on the [official documentation site for Azure Machine Learning SDK for R](https://azure.github.io/azureml-sdk-for-r/).
+
+
+### Troubleshooting
+
+- If the following error occurs when submitting an experiment using RStudio:
+   ```R
+    Error in py_call_impl(callable, dots$args, dots$keywords) : 
+     PermissionError: [Errno 13] Permission denied
+   ```
+  Move the files for your project into a subdirectory and reset the working directory to that directory before re-submitting.
+  
+  In order to submit an experiment, the Azure ML SDK must create a .zip file of the project directory to send to the service. However,
+  the SDK does not have permission to write into the .Rproj.user subdirectory that is automatically created during an RStudio
+  session. For this reason, the recommended best practice is to isolate project files into their own directory.

how-to-use-azureml/azureml-sdk-for-r/samples/README.md

@@ -0,0 +1,11 @@
+## Azure Machine Learning samples
+These samples are short code examples for using Azure Machine Learning SDK for R. If you are new to the R SDK, we recommend that you first take a look at the more detailed end-to-end [vignettes](../vignettes).
+
+Before running a sample in RStudio, set the working directory to the folder that contains the sample script in RStudio using `setwd(dirname)` or Session -> Set Working Directory -> To Source File Location. Each vignette assumes that the data and scripts are in the current working directory.
+
+1. [train-on-amlcompute](training/train-on-amlcompute): Train a model on a remote AmlCompute cluster.
+2. [train-on-local](training/train-on-local): Train a model locally with Docker.
+2. [deploy-to-aci](deployment/deploy-to-aci): Deploy a model as a web service to Azure Container Instances (ACI).
+3. [deploy-to-local](deployment/deploy-to-local): Deploy a model as a web service locally.
+
+> Before you run these samples, make sure you have an Azure Machine Learning workspace. You can follow the [configuration vignette](../vignettes/configuration.Rmd) to set up a workspace. (You do not need to do this if you are running these examples on an Azure Machine Learning compute instance).

how-to-use-azureml/azureml-sdk-for-r/samples/deployment/deploy-to-aci/deploy-to-aci.R

@@ -0,0 +1,59 @@
+# Copyright(c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+library(azuremlsdk)
+library(jsonlite)
+
+ws <- load_workspace_from_config()
+
+# Register the model
+model <- register_model(ws, model_path = "project_files/model.rds",
+                        model_name = "model.rds")
+
+# Create environment
+r_env <- r_environment(name = "r_env")
+
+# Create inference config
+inference_config <- inference_config(
+  entry_script = "score.R",
+  source_directory = "project_files",
+  environment = r_env)
+
+# Create ACI deployment config
+deployment_config <- aci_webservice_deployment_config(cpu_cores = 1,
+                                                      memory_gb = 1)
+
+# Deploy the web service
+service <- deploy_model(ws,
+                        'rservice',
+                        list(model),
+                        inference_config,
+                        deployment_config)
+wait_for_deployment(service, show_output = TRUE)
+
+# If you encounter any issue in deploying the webservice, please visit
+# https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-troubleshoot-deployment
+
+# Inferencing
+# versicolor
+plant <- data.frame(Sepal.Length = 6.4,
+                    Sepal.Width = 2.8,
+                    Petal.Length = 4.6,
+                    Petal.Width = 1.8)
+# setosa
+plant <- data.frame(Sepal.Length = 5.1,
+                    Sepal.Width = 3.5,
+                    Petal.Length = 1.4,
+                    Petal.Width = 0.2)
+# virginica
+plant <- data.frame(Sepal.Length = 6.7,
+                    Sepal.Width = 3.3,
+                    Petal.Length = 5.2,
+                    Petal.Width = 2.3)
+
+# Test the web service
+predicted_val <- invoke_webservice(service, toJSON(plant))
+predicted_val
+
+# Delete the web service
+delete_webservice(service)

how-to-use-azureml/azureml-sdk-for-r/samples/deployment/deploy-to-aci/project_files/score.R

@@ -0,0 +1,17 @@
+# Copyright(c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+library(jsonlite)
+
+init <- function() {
+    model_path <- Sys.getenv("AZUREML_MODEL_DIR")
+    model <- readRDS(file.path(model_path, "model.rds"))
+    message("model is loaded")
+
+    function(data) {
+        plant <- as.data.frame(fromJSON(data))
+        prediction <- predict(model, plant)
+        result <- as.character(prediction)
+        toJSON(result)
+    }
+}

how-to-use-azureml/azureml-sdk-for-r/samples/deployment/deploy-to-local/deploy-to-local.R

@@ -0,0 +1,112 @@
+# Copyright(c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+# Register model and deploy locally
+# This example shows how to deploy a web service in step-by-step fashion:
+#   
+# 1) Register model
+# 2) Deploy the model as a web service in a local Docker container.
+# 3) Invoke web service with SDK or call web service with raw HTTP call.
+# 4) Quickly test changes to your entry script by reloading the local service.
+# 5) Optionally, you can also make changes to model and update the local service.
+
+library(azuremlsdk)
+library(jsonlite)
+
+ws <- load_workspace_from_config()
+
+# Register the model
+model <- register_model(ws, model_path = "project_files/model.rds",
+                        model_name = "model.rds")
+
+# Create environment
+r_env <- r_environment(name = "r_env")
+
+# Create inference config
+inference_config <- inference_config(
+  entry_script = "score.R",
+  source_directory = "project_files",
+  environment = r_env)
+
+# Create local deployment config
+local_deployment_config <- local_webservice_deployment_config()
+
+# Deploy the web service
+# NOTE:
+# The Docker image runs as a Linux container. If you are running Docker for Windows, you need to ensure the Linux Engine is running:
+# # PowerShell command to switch to Linux engine
+# & 'C:\Program Files\Docker\Docker\DockerCli.exe' -SwitchLinuxEngine
+service <- deploy_model(ws,
+                        'rservice-local',
+                        list(model),
+                        inference_config,
+                        local_deployment_config)
+# Wait for deployment
+wait_for_deployment(service, show_output = TRUE)
+
+# Show the port of local service
+message(service$port)
+
+# If you encounter any issue in deploying the webservice, please visit
+# https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-troubleshoot-deployment
+
+# Inferencing
+# versicolor
+# plant <- data.frame(Sepal.Length = 6.4,
+#                     Sepal.Width = 2.8,
+#                     Petal.Length = 4.6,
+#                     Petal.Width = 1.8)
+# setosa
+plant <- data.frame(Sepal.Length = 5.1,
+                    Sepal.Width = 3.5,
+                    Petal.Length = 1.4,
+                    Petal.Width = 0.2)
+# # virginica
+# plant <- data.frame(Sepal.Length = 6.7,
+#                     Sepal.Width = 3.3,
+#                     Petal.Length = 5.2,
+#                     Petal.Width = 2.3)
+
+#Test the web service
+invoke_webservice(service, toJSON(plant))
+
+## The last few lines of the logs should have the correct prediction and should display -> R[write to console]: "setosa" 
+cat(gsub(pattern = "\n", replacement = " \n", x = get_webservice_logs(service)))
+
+## Test the web service with a HTTP Raw request
+# 
+# NOTE:
+# To test the service locally use the https://localhost:<local_service$port> URL
+
+# Import the request library
+library(httr)
+# Get the service scoring URL from the service object, its URL is for testing locally
+local_service_url <- service$scoring_uri #Same as https://localhost:<local_service$port>
+
+#POST request to web service
+resp <- POST(local_service_url, body = plant, encode = "json", verbose())
+
+## The last few lines of the logs should have the correct prediction and should display -> R[write to console]: "setosa" 
+cat(gsub(pattern = "\n", replacement = " \n", x = get_webservice_logs(service)))
+
+
+# Optional, use a new scoring script
+inference_config <- inference_config(
+  entry_script = "score_new.R",
+  source_directory = "project_files",
+  environment = r_env)
+
+## Then reload the service to see the changes made
+reload_local_webservice_assets(service)
+
+## Check reloaded service, you will see the last line will say "this is a new scoring script! I was reloaded"
+invoke_webservice(service, toJSON(plant))
+cat(gsub(pattern = "\n", replacement = " \n", x = get_webservice_logs(service)))
+
+# Update service
+# If you want to change your model(s), environment, or deployment configuration, call update() to rebuild the Docker image.
+
+# update_local_webservice(service, models = [NewModelObject], deployment_config = deployment_config, wait = FALSE, inference_config = inference_config)
+
+# Delete service
+delete_local_webservice(service)

how-to-use-azureml/azureml-sdk-for-r/samples/deployment/deploy-to-local/project_files/score.R

@@ -0,0 +1,18 @@
+# Copyright(c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+library(jsonlite)
+
+init <- function() {
+    model_path <- Sys.getenv("AZUREML_MODEL_DIR")
+    model <- readRDS(file.path(model_path, "model.rds"))
+    message("model is loaded")
+
+    function(data) {
+        plant <- as.data.frame(fromJSON(data))
+        prediction <- predict(model, plant)
+        result <- as.character(prediction)
+        message(result)
+        toJSON(result)
+    }
+}

how-to-use-azureml/azureml-sdk-for-r/samples/deployment/deploy-to-local/project_files/score_new.R

@@ -0,0 +1,19 @@
+# Copyright(c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+library(jsonlite)
+
+init <- function() {
+    model_path <- Sys.getenv("AZUREML_MODEL_DIR")
+    model <- readRDS(file.path(model_path, "model.rds"))
+    message("model is loaded")
+
+    function(data) {
+        plant <- as.data.frame(fromJSON(data))
+        prediction <- predict(model, plant)
+        result <- as.character(prediction)
+        message(result)
+        message("this is a new scoring script! I was reloaded")
+        toJSON(result)
+    }
+}

how-to-use-azureml/azureml-sdk-for-r/samples/training/train-on-amlcompute/scripts/train.R

@@ -0,0 +1,34 @@
+# This script loads a dataset of which the last column is supposed to be the
+# class and logs the accuracy
+
+library(azuremlsdk)
+library(caret)
+library(optparse)
+library(datasets)
+
+
+iris_data <- data(iris)
+summary(iris_data)
+
+in_train <- createDataPartition(y = iris_data$Species, p = .8, list = FALSE)
+train_data <- iris_data[in_train,]
+test_data <- iris_data[-in_train,]
+
+# Run algorithms using 10-fold cross validation
+control <- trainControl(method = "cv", number = 10)
+metric <- "Accuracy"
+
+set.seed(7)
+model <- train(Species ~ .,
+               data = train_data,
+               method = "lda",
+               metric = metric,
+               trControl = control)
+predictions <- predict(model, test_data)
+conf_matrix <- confusionMatrix(predictions, test_data$Species)
+message(conf_matrix)
+
+log_metric_to_run(metric, conf_matrix$overall["Accuracy"])
+
+saveRDS(model, file = "./outputs/model.rds")
+message("Model saved")

how-to-use-azureml/azureml-sdk-for-r/samples/training/train-on-amlcompute/train-on-amlcompute.R

@@ -0,0 +1,41 @@
+# Copyright(c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+# Reminder: set working directory to current file location prior to running this script
+
+library(azuremlsdk)
+
+ws <- load_workspace_from_config()
+
+# Create AmlCompute cluster
+cluster_name <- "r-cluster"
+compute_target <- get_compute(ws, cluster_name = cluster_name)
+if (is.null(compute_target)) {
+    vm_size <- "STANDARD_D2_V2"
+    compute_target <- create_aml_compute(workspace = ws,
+                                       cluster_name = cluster_name,
+                                       vm_size = vm_size,
+                                       max_nodes = 1)
+
+    wait_for_provisioning_completion(compute_target, show_output = TRUE)
+}
+
+# Define estimator
+est <- estimator(source_directory = "scripts",
+                 entry_script = "train.R",
+                 compute_target = compute_target)
+
+experiment_name <- "train-r-script-on-amlcompute"
+exp <- experiment(ws, experiment_name)
+
+# Submit job and display the run details
+run <- submit_experiment(exp, est)
+view_run_details(run)
+wait_for_run_completion(run, show_output = TRUE)
+
+# Get the run metrics
+metrics <- get_run_metrics(run)
+metrics
+
+# Delete cluster
+delete_compute(compute_target)

how-to-use-azureml/azureml-sdk-for-r/samples/training/train-on-local/scripts/train.R

@@ -0,0 +1,28 @@
+# This script loads a dataset of which the last column is supposed to be the
+# class and logs the accuracy
+
+library(azuremlsdk)
+library(caret)
+library(datasets)
+
+iris_data <- data(iris)
+summary(iris_data)
+
+in_train <- createDataPartition(y = iris_data$Species, p = .8, list = FALSE)
+train_data <- iris_data[in_train,]
+test_data <- iris_data[-in_train,]
+# Run algorithms using 10-fold cross validation
+control <- trainControl(method = "cv", number = 10)
+metric <- "Accuracy"
+
+set.seed(7)
+model <- train(Species ~ .,
+               data = train_data,
+               method = "lda",
+               metric = metric,
+               trControl = control)
+predictions <- predict(model, test_data)
+conf_matrix <- confusionMatrix(predictions, test_data$Species)
+message(conf_matrix)
+
+log_metric_to_run(metric, conf_matrix$overall["Accuracy"])

how-to-use-azureml/azureml-sdk-for-r/samples/training/train-on-local/train-on-local.R

@@ -0,0 +1,26 @@
+# Copyright(c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+# Reminder: set working directory to current file location prior to running this script
+
+library(azuremlsdk)
+
+ws <- load_workspace_from_config()
+
+# Define estimator
+est <- estimator(source_directory = "scripts",
+                 entry_script = "train.R",
+                 compute_target = "local")
+
+# Initialize experiment
+experiment_name <- "train-r-script-on-local"
+exp <- experiment(ws, experiment_name)
+
+# Submit job and display the run details
+run <- submit_experiment(exp, est)
+view_run_details(run)
+wait_for_run_completion(run, show_output = TRUE)
+
+# Get the run metrics
+metrics <- get_run_metrics(run)
+metrics

how-to-use-azureml/azureml-sdk-for-r/vignettes/README.md

@@ -0,0 +1,17 @@
+## Azure Machine Learning vignettes
+
+These vignettes are end-to-end tutorials for using Azure Machine Learning SDK for R.
+
+Before running a vignette in RStudio, set the working directory to the folder that contains the vignette file (.Rmd file) in RStudio using `setwd(dirname)` or Session -> Set Working Directory -> To Source File Location. Each vignette assumes that the data and scripts are in the current working directory.
+
+The following vignettes are included:
+1. [installation](installation.Rmd): Install the Azure ML SDK for R.
+2. [configuration](configuration.Rmd): Set up an Azure ML workspace.
+3. [train-and-deploy-to-aci](train-and-deploy-to-aci): Train a caret model and deploy as a web service to Azure Container Instances (ACI).
+4. [train-with-tensorflow](train-with-tensorflow/): Train a deep learning TensorFlow model with Azure ML.
+5. [hyperparameter-tune-with-keras](hyperparameter-tune-with-keras/): Hyperparameter tune a Keras model using HyperDrive, Azure ML's hyperparameter tuning functionality.
+6. [deploy-to-aks](deploy-to-aks/): Production deploy a model as a web service to Azure Kubernetes Service (AKS).
+
+> Before you run these samples, make sure you have an Azure Machine Learning workspace. You can follow the [configuration vignette](../vignettes/configuration.Rmd) to set up a workspace. (You do not need to do this if you are running these examples on an Azure Machine Learning compute instance).
+
+For additional examples on using the R SDK, see the [samples](../samples) folder.

how-to-use-azureml/azureml-sdk-for-r/vignettes/configuration.Rmd

@@ -0,0 +1,108 @@
+---
+title: "Set up an Azure ML workspace"
+date: "`r Sys.Date()`"
+output: rmarkdown::html_vignette
+vignette: >
+  %\VignetteIndexEntry{Set up an Azure ML workspace}
+  %\VignetteEngine{knitr::rmarkdown}
+  \use_package{UTF-8}
+---
+
+This tutorial gets you started with the Azure Machine Learning service by walking through the requirements and instructions for setting up a workspace, the top-level resource for Azure ML.
+
+You do not need run this if you are working on an Azure Machine Learning Compute Instance, as the compute instance is already associated with an existing workspace.
+
+## What is an Azure ML workspace?
+The workspace is the top-level resource for Azure ML, providing a centralized place to work with all the artifacts you create when you use Azure ML. The workspace keeps a history of all training runs, including logs, metrics, output, and a snapshot of your scripts.
+
+When you create a new workspace, it automatically creates several Azure resources that are used by the workspace:
+
+* Azure Container Registry: Registers docker containers that you use during training and when you deploy a model. To minimize costs, ACR is lazy-loaded until deployment images are created.
+* Azure Storage account: Used as the default datastore for the workspace.
+* Azure Application Insights: Stores monitoring information about your models.
+* Azure Key Vault: Stores secrets that are used by compute targets and other sensitive information that's needed by the workspace.
+
+## Setup
+This section describes the steps required before you can access any Azure ML service functionality.
+
+### Azure subscription
+In order to create an Azure ML workspace, first you need access to an Azure subscription. An Azure subscription allows you to manage storage, compute, and other assets in the Azure cloud. You can [create a new subscription](https://azure.microsoft.com/en-us/free/) or access existing subscription information from the [Azure portal](https://portal.azure.com/). Later in this tutorial you will need information such as your subscription ID in order to create and access workspaces.
+
+### Azure ML SDK installation
+Follow the [installation guide](https://azure.github.io/azureml-sdk-for-r/articles/installation.html) to install **azuremlsdk** on your machine.
+
+## Configure your workspace
+### Workspace parameters
+To use an Azure ML workspace, you will need to supply the following information:
+
+* Your subscription ID
+* A resource group name
+* (Optional) The region that will host your workspace
+* A name for your workspace
+
+You can get your subscription ID from the [Azure portal](https://portal.azure.com/).
+
+You will also need access to a [resource group](https://docs.microsoft.com/en-us/azure/azure-resource-manager/resource-group-overview#resource-groups), which organizes Azure resources and provides a default region for the resources in a group. You can see what resource groups to which you have access, or create a new one in the Azure portal. If you don't have a resource group, the `create_workspace()` method will create one for you using the name you provide.
+
+The region to host your workspace will be used if you are creating a new workspace. You do not need to specify this if you are using an existing workspace. You can find the list of supported regions [here](https://azure.microsoft.com/en-us/global-infrastructure/services/?products=machine-learning-service). You should pick a region that is close to your location or that contains your data.
+
+The name for your workspace is unique within the subscription and should be descriptive enough to discern among other workspaces. The subscription may be used only by you, or it may be used by your department or your entire enterprise, so choose a name that makes sense for your situation.
+
+The following code chunk allows you to specify your workspace parameters. It uses `Sys.getenv` to read values from environment variables, which is useful for automation. If no environment variable exists, the parameters will be set to the specified default values. Replace the default values in the code below with your default parameter values.
+
+``` {r configure_parameters, eval=FALSE}
+subscription_id <- Sys.getenv("SUBSCRIPTION_ID", unset = "<my-subscription-id>")
+resource_group <- Sys.getenv("RESOURCE_GROUP", default="<my-resource-group>")
+workspace_name <- Sys.getenv("WORKSPACE_NAME", default="<my-workspace-name>")
+workspace_region <- Sys.getenv("WORKSPACE_REGION", default="eastus2")
+``` 
+
+### Create a new workspace
+If you don't have an existing workspace and are the owner of the subscription or resource group, you can create a new workspace. If you don't have a resource group, `create_workspace()` will create one for you using the name you provide. If you don't want it to do so, set the `create_resource_group = FALSE` parameter.
+
+Note: As with other Azure services, there are limits on certain resources (e.g. AmlCompute quota) associated with the Azure ML 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.
+
+This cell will create an Azure ML workspace for you in a subscription, provided you have the correct permissions.
+
+This will fail if:
+
+* You do not have permission to create a workspace in the resource group.
+* You do not have permission to create a resource group if it does not exist.
+* You are not a subscription owner or contributor and no Azure ML workspaces have ever been created in this subscription.
+
+If workspace creation fails, please work with your IT admin to provide you with the appropriate permissions or to provision the required resources.
+
+There are additional parameters that are not shown below that can be configured when creating a workspace. Please see [`create_workspace()`](https://azure.github.io/azureml-sdk-for-r/reference/create_workspace.html) for more details.
+
+``` {r create_workspace, eval=FALSE}
+library(azuremlsdk)
+
+ws <- create_workspace(name = workspace_name,
+                       subscription_id = subscription_id,
+                       resource_group = resource_group,
+                       location = workspace_region,
+                       exist_ok = TRUE)
+```
+
+You can out write out the workspace ARM properties to a config file with [`write_workspace_config()`](https://azure.github.io/azureml-sdk-for-r/reference/write_workspace_config.html). The method provides a simple way of reusing the same workspace across multiple files or projects. Users can save the workspace details with `write_workspace_config()`, and use [`load_workspace_from_config()`](https://azure.github.io/azureml-sdk-for-r/reference/load_workspace_from_config.html) to load the same workspace in different files or projects without retyping the workspace ARM properties. The method defaults to writing out the config file to the current working directory with "config.json" as the file name. To specify a different path or file name, set the `path` and `file_name` parameters.
+
+``` {r write_config, eval=FALSE}
+write_workspace_config(ws)
+```
+
+### Access an existing workspace
+You can access an existing workspace in a couple of ways. If your workspace properties were previously saved to a config file, you can load the workspace as follows:
+
+``` {r load_config, eval=FALSE}
+ws <- load_workspace_from_config()
+```
+
+If Azure ML cannot find the config file, specify the path to the config file with the `path` parameter. The method defaults to starting the search in the current directory.
+
+You can also initialize a workspace using the [`get_workspace()`](https://azure.github.io/azureml-sdk-for-r/reference/get_workspace.html) method.
+
+``` {r get_workspace, eval=FALSE}
+ws <- get_workspace(name = workspace_name,
+                    subscription_id = subscription_id,
+                    resource_group = resource_group)
+```

how-to-use-azureml/azureml-sdk-for-r/vignettes/deploy-to-aks/deploy-to-aks.Rmd

@@ -0,0 +1,188 @@
+---
+title: "Deploy a web service to Azure Kubernetes Service"
+date: "`r Sys.Date()`"
+output: rmarkdown::html_vignette
+vignette: >
+  %\VignetteIndexEntry{Deploy a web service to Azure Kubernetes Service}
+  %\VignetteEngine{knitr::rmarkdown}
+  \use_package{UTF-8}
+---
+
+This tutorial demonstrates how to deploy a model as a web service on [Azure Kubernetes Service](https://azure.microsoft.com/en-us/services/kubernetes-service/) (AKS). AKS is good for high-scale production deployments; use it if you need one or more of the following capabilities:
+
+* Fast response time
+* Autoscaling of the deployed service
+* Hardware acceleration options such as GPU
+
+You will learn to:
+
+* Set up your testing environment
+* Register a model
+* Provision an AKS cluster
+* Deploy the model to AKS
+* Test the deployed service
+
+## Prerequisites
+If you don<6F>t have access to an Azure ML workspace, follow the [setup tutorial](https://azure.github.io/azureml-sdk-for-r/articles/configuration.html) to configure and create a workspace.
+
+## Set up your testing environment
+Start by setting up your environment. This includes importing the **azuremlsdk** package and connecting to your workspace.
+
+### Import package
+```{r import_package, eval=FALSE}
+library(azuremlsdk)
+```
+
+### Load your workspace
+Instantiate a workspace object from your existing workspace. The following code will load the workspace details from a **config.json** file if you previously wrote one out with `write_workspace_config()`. 
+```{r load_workspace, eval=FALSE}
+ws <- load_workspace_from_config()
+```
+
+Or, you can retrieve a workspace by directly specifying your workspace details:
+```{r get_workspace, eval=FALSE}
+ws <- get_workspace("<your workspace name>", "<your subscription ID>", "<your resource group>")
+```
+
+## Register the model
+In this tutorial we will deploy a model that was trained in one of the [samples](https://github.com/Azure/azureml-sdk-for-r/blob/master/samples/training/train-on-amlcompute/train-on-amlcompute.R). The model was trained with the Iris dataset and can be used to determine if a flower is one of three Iris flower species (setosa, versicolor, virginica). We have provided the model file (`model.rds`) for the tutorial; it is located in the "project_files" directory of this vignette.
+
+First, register the model to your workspace with [`register_model()`](https://azure.github.io/azureml-sdk-for-r/reference/register_model.html). A registered model can be any collection of files, but in this case the R model file is sufficient. Azure ML will use the registered model for deployment.
+
+```{r register_model, eval=FALSE}
+model <- register_model(ws, 
+                        model_path = "project_files/model.rds", 
+                        model_name = "iris_model",
+                        description = "Predict an Iris flower type")
+```
+
+## Provision an AKS cluster
+When deploying a web service to AKS, you deploy to an AKS cluster that is connected to your workspace. There are two ways to connect an AKS cluster to your workspace:
+
+* Create the AKS cluster. The process automatically connects the cluster to the workspace. 
+* Attach an existing AKS cluster to your workspace. You can attach a cluster with the [`attach_aks_compute()`](https://azure.github.io/azureml-sdk-for-r/reference/attach_aks_compute.html) method.
+
+Creating or attaching an AKS cluster is a one-time process for your workspace. You can reuse this cluster for multiple deployments. If you delete the cluster or the resource group that contains it, you must create a new cluster the next time you need to deploy.
+
+In this tutorial, we will go with the first method of provisioning a new cluster. See the [`create_aks_compute()`](https://azure.github.io/azureml-sdk-for-r/reference/create_aks_compute.html) reference for the full set of configurable parameters. If you pick custom values for the `agent_count` and `vm_size` parameters, you need to make sure `agent_count` multiplied by `vm_size` is greater than or equal to `12` virtual CPUs.
+
+``` {r provision_cluster, eval=FALSE}
+aks_target <- create_aks_compute(ws, cluster_name = 'myakscluster')
+
+wait_for_provisioning_completion(aks_target, show_output = TRUE)
+```
+
+The Azure ML SDK does not provide support for scaling an AKS cluster. To scale the nodes in the cluster, use the UI for your AKS cluster in the Azure portal. You can only change the node count, not the VM size of the cluster.
+
+## Deploy as a web service
+### Define the inference dependencies
+To deploy a model, you need an **inference configuration**, which describes the environment needed to host the model and web service. To create an inference config, you will first need a scoring script and an Azure ML environment.
+
+The scoring script (`entry_script`) is an R script that will take as input variable values (in JSON format) and output a prediction from your model. For this tutorial, use the provided scoring file `score.R`. The scoring script must contain an `init()` method that loads your model and returns a function that uses the model to make a prediction based on the input data. See the [documentation](https://azure.github.io/azureml-sdk-for-r/reference/inference_config.html#details) for more details.
+
+Next, define an Azure ML **environment** for your script<70>s package dependencies. With an environment, you specify R packages (from CRAN or elsewhere) that are needed for your script to run. You can also provide the values of environment variables that your script can reference to modify its behavior. 
+
+By default Azure ML will build a default Docker image that includes R, the Azure ML SDK, and additional required dependencies for deployment. See the documentation here for the full list of dependencies that will be installed in the default container. You can also specify additional packages to be installed at runtime, or even a custom Docker image to be used instead of the base image that will be built, using the other available parameters to [`r_environment()`](https://azure.github.io/azureml-sdk-for-r/reference/r_environment.html).
+
+```{r create_env, eval=FALSE}
+r_env <- r_environment(name = "deploy_env")
+```
+
+Now you have everything you need to create an inference config for encapsulating your scoring script and environment dependencies.
+
+``` {r create_inference_config, eval=FALSE}
+inference_config <- inference_config(
+  entry_script = "score.R",
+  source_directory = "project_files",
+  environment = r_env)
+```
+
+### Deploy to AKS
+Now, define the deployment configuration that describes the compute resources needed, for example, the number of cores and memory. See the [`aks_webservice_deployment_config()`](https://azure.github.io/azureml-sdk-for-r/reference/aks_webservice_deployment_config.html) for the full set of configurable parameters.
+
+``` {r deploy_config, eval=FALSE}
+aks_config <- aks_webservice_deployment_config(cpu_cores = 1, memory_gb = 1)
+```
+
+Now, deploy your model as a web service to the AKS cluster you created earlier.
+
+```{r deploy_service, eval=FALSE}
+aks_service <- deploy_model(ws, 
+                            'my-new-aksservice', 
+                            models = list(model), 
+                            inference_config = inference_config, 
+                            deployment_config = aks_config,
+                            deployment_target = aks_target)
+
+wait_for_deployment(aks_service, show_output = TRUE)
+```
+
+To inspect the logs from the deployment:
+```{r get_logs, eval=FALSE}
+get_webservice_logs(aks_service)
+```
+
+If you encounter any issue in deploying the web service, please visit the [troubleshooting guide](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-troubleshoot-deployment).
+
+## Test the deployed service
+Now that your model is deployed as a service, you can test the service from R using [`invoke_webservice()`](https://azure.github.io/azureml-sdk-for-r/reference/invoke_webservice.html). Provide a new set of data to predict from, convert it to JSON, and send it to the service.
+
+``` {r test_service, eval=FALSE}
+library(jsonlite)
+# versicolor
+plant <- data.frame(Sepal.Length = 6.4,
+                    Sepal.Width = 2.8,
+                    Petal.Length = 4.6,
+                    Petal.Width = 1.8)
+
+# setosa
+# plant <- data.frame(Sepal.Length = 5.1,
+#                    Sepal.Width = 3.5,
+#                    Petal.Length = 1.4,
+#                    Petal.Width = 0.2)
+
+# virginica
+# plant <- data.frame(Sepal.Length = 6.7,
+#                    Sepal.Width = 3.3,
+#                    Petal.Length = 5.2,
+#                    Petal.Width = 2.3)
+
+predicted_val <- invoke_webservice(aks_service, toJSON(plant))
+message(predicted_val)
+```
+
+You can also get the web service<63>s HTTP endpoint, which accepts REST client calls. You can share this endpoint with anyone who wants to test the web service or integrate it into an application.
+
+``` {r eval=FALSE}
+aks_service$scoring_uri
+```
+
+## Web service authentication
+When deploying to AKS, key-based authentication is enabled by default. You can also enable token-based authentication. Token-based authentication requires clients to use an Azure Active Directory account to request an authentication token, which is used to make requests to the deployed service.
+
+To disable key-based auth, set the `auth_enabled = FALSE` parameter when creating the deployment configuration with [`aks_webservice_deployment_config()`](https://azure.github.io/azureml-sdk-for-r/reference/aks_webservice_deployment_config.html). 
+To enable token-based auth, set `token_auth_enabled = TRUE` when creating the deployment config.
+
+### Key-based authentication
+If key authentication is enabled, you can use the [`get_webservice_keys()`](https://azure.github.io/azureml-sdk-for-r/reference/get_webservice_keys.html) method to retrieve a primary and secondary authentication key. To generate a new key, use [`generate_new_webservice_key()`](https://azure.github.io/azureml-sdk-for-r/reference/generate_new_webservice_key.html).
+
+### Token-based authentication
+If token authentication is enabled, you can use the [`get_webservice_token()`](https://azure.github.io/azureml-sdk-for-r/reference/get_webservice_token.html) method to retrieve a JWT token and that token's expiration time. Make sure to request a new token after the token's expiration time.
+
+## Clean up resources
+Delete the resources once you no longer need them. Do not delete any resource you plan on still using.
+
+Delete the web service:
+```{r delete_service, eval=FALSE}
+delete_webservice(aks_service)
+```
+
+Delete the registered model:
+```{r delete_model, eval=FALSE}
+delete_model(model)
+```
+
+Delete the AKS cluster:
+```{r delete_cluster, eval=FALSE}
+delete_compute(aks_target)
+```

how-to-use-azureml/azureml-sdk-for-r/vignettes/deploy-to-aks/project_files/score.R

@@ -0,0 +1,17 @@
+#' Copyright(c) Microsoft Corporation.
+#' Licensed under the MIT license.
+
+library(jsonlite)
+
+init <- function() {
+    model_path <- Sys.getenv("AZUREML_MODEL_DIR")
+    model <- readRDS(file.path(model_path, "model.rds"))
+    message("model is loaded")
+
+    function(data) {
+        plant <- as.data.frame(fromJSON(data))
+        prediction <- predict(model, plant)
+        result <- as.character(prediction)
+        toJSON(result)
+    }
+}

how-to-use-azureml/azureml-sdk-for-r/vignettes/hyperparameter-tune-with-keras/hyperparameter-tune-with-keras.Rmd

@@ -0,0 +1,242 @@
+---
+title: "Hyperparameter tune a Keras model"
+date: "`r Sys.Date()`"
+output: rmarkdown::html_vignette
+vignette: >
+  %\VignetteIndexEntry{Hyperparameter tune a Keras model}
+  %\VignetteEngine{knitr::rmarkdown}
+  \use_package{UTF-8}
+---
+
+This tutorial demonstrates how you can efficiently tune hyperparameters for a model using HyperDrive, Azure ML's hyperparameter tuning functionality. You will train a Keras model on the CIFAR10 dataset, automate hyperparameter exploration, launch parallel jobs, log your results, and find the best run.
+
+### What are hyperparameters?
+
+Hyperparameters are variable parameters chosen to train a model. Learning rate, number of epochs, and batch size are all examples of hyperparameters.
+
+Using brute-force methods to find the optimal values for parameters can be time-consuming, and poor-performing runs can result in wasted money. To avoid this, HyperDrive automates hyperparameter exploration in a time-saving and cost-effective manner by launching several parallel runs with different configurations and finding the configuration that results in best performance on your primary metric.
+
+Let's get started with the example to see how it works!
+
+## Prerequisites
+
+If you don<6F>t have access to an Azure ML workspace, follow the [setup tutorial](https://azure.github.io/azureml-sdk-for-r/articles/configuration.html) to configure and create a workspace.
+
+## Set up development environment
+The setup for your development work in this tutorial includes the following actions:
+
+* Import required packages
+* Connect to a workspace
+* Create an experiment to track your runs
+* Create a remote compute target to use for training
+
+### Import **azuremlsdk** package
+```{r eval=FALSE}
+library(azuremlsdk)
+```
+
+### Load your workspace
+Instantiate a workspace object from your existing workspace. The following code will load the workspace details from a **config.json** file if you previously wrote one out with [`write_workspace_config()`](https://azure.github.io/azureml-sdk-for-r/reference/write_workspace_config.html).
+```{r load_workpace, eval=FALSE}
+ws <- load_workspace_from_config()
+```
+
+Or, you can retrieve a workspace by directly specifying your workspace details:
+```{r get_workpace, eval=FALSE}
+ws <- get_workspace("<your workspace name>", "<your subscription ID>", "<your resource group>")
+```
+
+### Create an experiment
+An Azure ML **experiment** tracks a grouping of runs, typically from the same training script. Create an experiment to track hyperparameter tuning runs for the Keras model.
+
+```{r create_experiment, eval=FALSE}
+exp <- experiment(workspace = ws, name = 'hyperdrive-cifar10')
+```
+
+If you would like to track your runs in an existing experiment, simply specify that experiment's name to the `name` parameter of `experiment()`.
+
+### Create a compute target
+By using Azure Machine Learning Compute (AmlCompute), a managed service, data scientists can train machine learning models on clusters of Azure virtual machines. In this tutorial, you create a GPU-enabled cluster as your training environment. The code below creates the compute cluster for you if it doesn't already exist in your workspace.
+
+You may need to wait a few minutes for your compute cluster to be provisioned if it doesn't already exist.
+
+```{r create_cluster, eval=FALSE}
+cluster_name <- "gpucluster"
+
+compute_target <- get_compute(ws, cluster_name = cluster_name)
+if (is.null(compute_target))
+{
+  vm_size <- "STANDARD_NC6"
+  compute_target <- create_aml_compute(workspace = ws, 
+                                       cluster_name = cluster_name,
+                                       vm_size = vm_size, 
+                                       max_nodes = 4)
+  
+  wait_for_provisioning_completion(compute_target, show_output = TRUE)
+}
+```
+
+## Prepare the training script
+A training script called `cifar10_cnn.R` has been provided for you in the "project_files" directory of this tutorial.
+
+In order to leverage HyperDrive, the training script for your model must log the relevant metrics during model training. When you configure the hyperparameter tuning run, you specify the primary metric to use for evaluating run performance. You must log this metric so it is available to the hyperparameter tuning process.
+
+In order to log the required metrics, you need to do the following **inside the training script**:
+
+* Import the **azuremlsdk** package
+```
+library(azuremlsdk)
+```
+
+* Take the hyperparameters as command-line arguments to the script. This is necessary so that when HyperDrive carries out the hyperparameter sweep, it can run the training script with different values to the hyperparameters as defined by the search space.
+
+* Use the [`log_metric_to_run()`](https://azure.github.io/azureml-sdk-for-r/reference/log_metric_to_run.html) function to log the hyperparameters and the primary metric.
+```
+log_metric_to_run("batch_size", batch_size)
+...
+log_metric_to_run("epochs", epochs)
+...
+log_metric_to_run("lr", lr)
+...
+log_metric_to_run("decay", decay)
+...
+log_metric_to_run("Loss", results[[1]])
+```
+
+## Create an estimator
+
+An Azure ML **estimator** encapsulates the run configuration information needed for executing a training script on the compute target. Azure ML runs are run as containerized jobs on the specified compute target. By default, the Docker image built for your training job will include R, the Azure ML SDK, and a set of commonly used R packages. See the full list of default packages included [here](https://azure.github.io/azureml-sdk-for-r/reference/r_environment.html). The estimator is used to define the configuration for each of the child runs that the parent HyperDrive run will kick off.
+
+To create the estimator, define the following:
+
+* The directory that contains your scripts needed for training (`source_directory`). All the files in this directory are uploaded to the cluster node(s) for execution. The directory must contain your training script and any additional scripts required.
+* The training script that will be executed (`entry_script`).
+* The compute target (`compute_target`), in this case the AmlCompute cluster you created earlier.
+* Any environment dependencies required for training. Since the training script requires the Keras package, which is not included in the image by default, pass the package name to the `cran_packages` parameter to have it installed in the Docker container where the job will run. See the [`estimator()`](https://azure.github.io/azureml-sdk-for-r/reference/estimator.html) reference for the full set of configurable options.
+* Set the `use_gpu = TRUE` flag so the default base GPU Docker image will be built, since the job will be run on a GPU cluster.
+
+```{r create_estimator, eval=FALSE}
+est <- estimator(source_directory = "project_files",
+                 entry_script = "cifar10_cnn.R",
+                 compute_target = compute_target,
+                 cran_packages = c("keras"),
+                 use_gpu = TRUE)
+```
+
+## Configure the HyperDrive run
+To kick off hyperparameter tuning in Azure ML, you will need to configure a HyperDrive run, which will in turn launch individual children runs of the training scripts with the corresponding hyperparameter values.
+
+### Define search space
+
+In this experiment, we will use four hyperparameters: batch size, number of epochs, learning rate, and decay. In order to begin tuning, we must define the range of values we would like to explore from and how they will be distributed. This is called a parameter space definition and can be created with discrete or continuous ranges.
+
+__Discrete hyperparameters__ are specified as a choice among discrete values represented as a list.
+
+Advanced discrete hyperparameters can also be specified using a distribution. The following distributions are supported:
+
+ * `quniform(low, high, q)`
+ * `qloguniform(low, high, q)`
+ * `qnormal(mu, sigma, q)`
+ * `qlognormal(mu, sigma, q)`
+
+__Continuous hyperparameters__ are specified as a distribution over a continuous range of values. The following distributions are supported:
+
+ * `uniform(low, high)`
+ * `loguniform(low, high)`
+ * `normal(mu, sigma)`
+ * `lognormal(mu, sigma)`
+
+Here, we will use the [`random_parameter_sampling()`](https://azure.github.io/azureml-sdk-for-r/reference/random_parameter_sampling.html) function to define the search space for each hyperparameter. `batch_size` and `epochs` will be chosen from discrete sets while `lr` and `decay` will be drawn from continuous distributions.
+
+Other available sampling function options are:
+
+ * [`grid_parameter_sampling()`](https://azure.github.io/azureml-sdk-for-r/reference/grid_parameter_sampling.html)
+ * [`bayesian_parameter_sampling()`](https://azure.github.io/azureml-sdk-for-r/reference/bayesian_parameter_sampling.html)
+
+```{r search_space, eval=FALSE}
+sampling <- random_parameter_sampling(list(batch_size = choice(c(16, 32, 64)),
+                                           epochs = choice(c(200, 350, 500)),
+                                           lr = normal(0.0001, 0.005),
+                                           decay = uniform(1e-6, 3e-6)))
+```
+
+### Define termination policy
+
+To prevent resource waste, Azure ML can detect and terminate poorly performing runs. HyperDrive will do this automatically if you specify an early termination policy.
+
+Here, you will use the [`bandit_policy()`](https://azure.github.io/azureml-sdk-for-r/reference/bandit_policy.html), which terminates any runs where the primary metric is not within the specified slack factor with respect to the best performing training run.
+
+```{r termination_policy, eval=FALSE}
+policy <- bandit_policy(slack_factor = 0.15)
+```
+
+Other termination policy options are:
+
+ * [`median_stopping_policy()`](https://azure.github.io/azureml-sdk-for-r/reference/median_stopping_policy.html)
+ * [`truncation_selection_policy()`](https://azure.github.io/azureml-sdk-for-r/reference/truncation_selection_policy.html)
+ 
+If no policy is provided, all runs will continue to completion regardless of performance.
+
+### Finalize configuration
+
+Now, you can create a `HyperDriveConfig` object to define your HyperDrive run. Along with the sampling and policy definitions, you need to specify the name of the primary metric that you want to track and whether we want to maximize it or minimize it. The `primary_metric_name` must correspond with the name of the primary metric you logged in your training script. `max_total_runs` specifies the total number of child runs to launch. See the [hyperdrive_config()](https://azure.github.io/azureml-sdk-for-r/reference/hyperdrive_config.html) reference for the full set of configurable parameters.
+
+```{r create_config, eval=FALSE}
+hyperdrive_config <- hyperdrive_config(hyperparameter_sampling = sampling,
+                                       primary_metric_goal("MINIMIZE"),
+                                       primary_metric_name = "Loss",
+                                       max_total_runs = 4,
+                                       policy = policy,
+                                       estimator = est)
+```
+
+## Submit the HyperDrive run
+
+Finally submit the experiment to run on your cluster. The parent HyperDrive run will launch the individual child runs. `submit_experiment()` will return a `HyperDriveRun` object that you will use to interface with the run. In this tutorial, since the cluster we created scales to a max of `4` nodes, all 4 child runs will be launched in parallel.
+
+```{r submit_run, eval=FALSE}
+hyperdrive_run <- submit_experiment(exp, hyperdrive_config)
+```
+
+You can view the HyperDrive run<75>s details as a table. Clicking the <20>Web View<65> link provided will bring you to Azure Machine Learning studio, where you can monitor the run in the UI.
+
+```{r eval=FALSE}
+view_run_details(hyperdrive_run)
+```
+
+Wait until hyperparameter tuning is complete before you run more code.
+
+```{r eval=FALSE}
+wait_for_run_completion(hyperdrive_run, show_output = TRUE)
+```
+
+## Analyse runs by performance
+
+Finally, you can view and compare the metrics collected during all of the child runs!
+
+```{r analyse_runs, eval=FALSE}
+# Get the metrics of all the child runs
+child_run_metrics <- get_child_run_metrics(hyperdrive_run)
+child_run_metrics
+
+# Get the child run objects sorted in descending order by the best primary metric
+child_runs <- get_child_runs_sorted_by_primary_metric(hyperdrive_run)
+child_runs
+
+# Directly get the run object of the best performing run
+best_run <- get_best_run_by_primary_metric(hyperdrive_run)
+
+# Get the metrics of the best performing run
+metrics <- get_run_metrics(best_run)
+metrics
+```
+
+The `metrics` variable will include the values of the hyperparameters that resulted in the best performing run.
+
+## Clean up resources
+Delete the resources once you no longer need them. Don't delete any resource you plan to still use. 
+
+Delete the compute cluster:
+```{r delete_compute, eval=FALSE}
+delete_compute(compute_target)
+```

how-to-use-azureml/azureml-sdk-for-r/vignettes/hyperparameter-tune-with-keras/project_files/cifar10_cnn.R

@@ -0,0 +1,124 @@
+#' Modified from: "https://github.com/rstudio/keras/blob/master/vignettes/
+#' examples/cifar10_cnn.R"
+#' 
+#' Train a simple deep CNN on the CIFAR10 small images dataset.
+#'  
+#' It gets down to 0.65 test logloss in 25 epochs, and down to 0.55 after 50
+#' epochs, though it is still underfitting at that point.
+
+library(keras)
+install_keras()
+
+library(azuremlsdk)
+
+# Parameters --------------------------------------------------------------
+
+args <- commandArgs(trailingOnly = TRUE)
+
+batch_size <- as.numeric(args[2])
+log_metric_to_run("batch_size", batch_size)
+
+epochs <- as.numeric(args[4])
+log_metric_to_run("epochs", epochs)
+
+lr <- as.numeric(args[6])
+log_metric_to_run("lr", lr)
+
+decay <- as.numeric(args[8])
+log_metric_to_run("decay", decay)
+
+data_augmentation <- TRUE
+
+
+# Data Preparation --------------------------------------------------------
+
+# See ?dataset_cifar10 for more info
+cifar10 <- dataset_cifar10()
+
+# Feature scale RGB values in test and train inputs  
+x_train <- cifar10$train$x / 255
+x_test <- cifar10$test$x / 255
+y_train <- to_categorical(cifar10$train$y, num_classes = 10)
+y_test <- to_categorical(cifar10$test$y, num_classes = 10)
+
+
+# Defining Model ----------------------------------------------------------
+
+# Initialize sequential model
+model <- keras_model_sequential()
+
+model %>%
+
+# Start with hidden 2D convolutional layer being fed 32x32 pixel images
+layer_conv_2d(
+    filter = 32, kernel_size = c(3, 3), padding = "same",
+    input_shape = c(32, 32, 3)
+  ) %>%
+  layer_activation("relu") %>%
+
+  # Second hidden layer
+  layer_conv_2d(filter = 32, kernel_size = c(3, 3)) %>%
+  layer_activation("relu") %>%
+
+  # Use max pooling
+  layer_max_pooling_2d(pool_size = c(2, 2)) %>%
+  layer_dropout(0.25) %>%
+
+  # 2 additional hidden 2D convolutional layers
+  layer_conv_2d(filter = 32, kernel_size = c(3, 3), padding = "same") %>%
+  layer_activation("relu") %>%
+  layer_conv_2d(filter = 32, kernel_size = c(3, 3)) %>%
+  layer_activation("relu") %>%
+
+  # Use max pooling once more
+  layer_max_pooling_2d(pool_size = c(2, 2)) %>%
+  layer_dropout(0.25) %>%
+
+  # Flatten max filtered output into feature vector 
+  # and feed into dense layer
+  layer_flatten() %>%
+  layer_dense(512) %>%
+  layer_activation("relu") %>%
+  layer_dropout(0.5) %>%
+
+  # Outputs from dense layer are projected onto 10 unit output layer
+  layer_dense(10) %>%
+  layer_activation("softmax")
+
+opt <- optimizer_rmsprop(lr, decay)
+
+model %>%
+    compile(loss = "categorical_crossentropy",
+          optimizer = opt,
+          metrics = "accuracy"
+)
+
+
+# Training ----------------------------------------------------------------
+
+if (!data_augmentation) {
+
+    model %>%
+    fit(x_train,
+        y_train,
+        batch_size = batch_size,
+        epochs = epochs,
+        validation_data = list(x_test, y_test),
+        shuffle = TRUE
+  )
+
+} else {
+
+    datagen <- image_data_generator(rotation_range = 20,
+                                  width_shift_range = 0.2,
+                                  height_shift_range = 0.2,
+                                  horizontal_flip = TRUE
+  )
+
+    datagen %>% fit_image_data_generator(x_train)
+
+    results <- evaluate(model, x_train, y_train, batch_size)
+    log_metric_to_run("Loss", results[[1]])
+    cat("Loss: ", results[[1]], "\n")
+    cat("Accuracy: ", results[[2]], "\n")
+}

how-to-use-azureml/azureml-sdk-for-r/vignettes/installation.Rmd

@@ -0,0 +1,100 @@
+---
+title: "Install the Azure ML SDK for R"
+date: "`r Sys.Date()`"
+output: rmarkdown::html_vignette
+vignette: >
+  %\VignetteIndexEntry{Install the Azure ML SDK for R}
+  %\VignetteEngine{knitr::rmarkdown}
+  \use_package{UTF-8}
+---
+
+This article covers the step-by-step instructions for installing the Azure ML SDK for R.
+
+You do not need run this if you are working on an Azure Machine Learning Compute Instance, as the compute instance already has the Azure ML SDK preinstalled.
+
+## Install Conda
+
+If you do not have Conda already installed on your machine, you will first need to install it, since the Azure ML R SDK uses **reticulate** to bind to the Python SDK. We recommend installing [Miniconda](https://docs.conda.io/en/latest/miniconda.html), which is a smaller, lightweight version of Anaconda. Choose the 64-bit binary for Python 3.5 or later.
+
+## Install the **azuremlsdk** R package
+You will need **remotes** to install **azuremlsdk** from the GitHub repo.
+``` {r install_remotes, eval=FALSE}
+install.packages('remotes')
+``` 
+
+Then, you can use the `install_github` function to install the package.
+``` {r install_azuremlsdk, eval=FALSE}
+remotes::install_cran('azuremlsdk', repos = 'https://cloud.r-project.org/')
+```
+
+If you are using R installed from CRAN, which comes with 32-bit and 64-bit binaries, you may need to specify the parameter `INSTALL_opts=c("--no-multiarch")` to only build for the current 64-bit architecture.
+``` {r eval=FALSE}
+remotes::install_cran('azuremlsdk', repos = 'https://cloud.r-project.org/', INSTALL_opts=c("--no-multiarch"))
+```
+
+## Install the Azure ML Python SDK
+Lastly, use the **azuremlsdk** R library to install the Python SDK. By default, `azuremlsdk::install_azureml()` will install the [latest version of the Python SDK](https://pypi.org/project/azureml-sdk/) in a conda environment called `r-azureml` if reticulate < 1.14 or `r-reticulate` if reticulate ≥ 1.14.
+``` {r install_pythonsdk, eval=FALSE}
+azuremlsdk::install_azureml()
+```
+
+If you would like to override the default version, environment name, or Python version, you can pass in those arguments. If you would like to restart the R session after installation or delete the conda environment if it already exists and create a new environment, you can also do so: 
+``` {r eval=FALSE}
+azuremlsdk::install_azureml(version = NULL, 
+                            custom_envname = "<your conda environment name>",
+                            conda_python_version = "<desired python version>",
+                            restart_session = TRUE,
+                            remove_existing_env = TRUE)
+```
+
+## Test installation
+You can confirm your installation worked by loading the library and successfully retrieving a run.
+``` {r test_installation, eval=FALSE}
+library(azuremlsdk)
+get_current_run()
+```
+
+## Troubleshooting
+-   In step 3 of the installation, if you get ssl errors on windows, it is due to an
+outdated openssl binary. Install the latest openssl binaries from
+[here](https://wiki.openssl.org/index.php/Binaries).
+
+- If installation fails due to this error:
+
+  ```R
+  Error in strptime(xx, f, tz = tz) : 
+    (converted from warning) unable to identify current timezone 'C':
+  please set environment variable 'TZ'
+  In R CMD INSTALL
+  Error in i.p(...) : 
+    (converted from warning) installation of package ‘C:/.../azureml_0.4.0.tar.gz’ had non-zero exit
+    status
+  ```
+  
+  You will need to set your time zone environment variable to GMT and restart the installation process.
+  
+  ```R
+  Sys.setenv(TZ='GMT')
+  ```
+
+- If the following permission error occurs while installing in RStudio,
+  change your RStudio session to administrator mode, and re-run the installation command.
+
+  ```R
+  Downloading GitHub repo Azure/azureml-sdk-for-r@master
+  Skipping 2 packages ahead of CRAN: reticulate, rlang
+  Running `R CMD build`...
+  
+  Error: (converted from warning) invalid package
+  'C:/.../file2b441bf23631'
+  In R CMD INSTALL
+  Error in i.p(...) : 
+    (converted from warning) installation of package
+    ‘C:/.../file2b441bf23631’ had non-zero exit status
+  In addition: Warning messages:
+  1: In file(con, "r") :
+    cannot open file 'C:...\file2b44144a540f': Permission denied
+  2: In file(con, "r") :
+    cannot open file 'C:...\file2b4463c21577': Permission denied
+  ```
+  

how-to-use-azureml/azureml-sdk-for-r/vignettes/train-and-deploy-to-aci/project_files/accident_predict.R

@@ -0,0 +1,16 @@
+#' Copyright(c) Microsoft Corporation.
+#' Licensed under the MIT license.
+
+library(jsonlite)
+
+init <- function() {
+    model_path <- Sys.getenv("AZUREML_MODEL_DIR")
+    model <- readRDS(file.path(model_path, "model.rds"))
+    message("logistic regression model loaded")
+
+    function(data) {
+        vars <- as.data.frame(fromJSON(data))
+        prediction <- as.numeric(predict(model, vars, type = "response") * 100)
+        toJSON(prediction)
+    }
+}