Merge pull request #459 from datashinobi/yassine/datadrift2

fix link to config nb & settingwithcopywarning

Dockerfiles/1.0.17/Dockerfile

@@ -0,0 +1,29 @@
+FROM continuumio/miniconda:4.5.11
+
+# install git
+RUN apt-get update && apt-get upgrade -y && apt-get install -y git
+
+# create a new conda environment named azureml
+RUN conda create -n azureml -y -q Python=3.6
+
+# install additional packages used by sample notebooks. this is optional
+RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
+
+# install azurmel-sdk components
+RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.17"]
+
+# clone Azure ML GitHub sample notebooks
+RUN cd /home && git clone -b "azureml-sdk-1.0.17" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
+
+# generate jupyter configuration file
+RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
+
+# set an emtpy token for Jupyter to remove authentication. 
+# this is NOT recommended for production environment
+RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
+
+# open up port 8887 on the container
+EXPOSE 8887
+
+# start Jupyter notebook server on port 8887 when the container starts
+CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.18/Dockerfile

@@ -0,0 +1,29 @@
+FROM continuumio/miniconda:4.5.11
+
+# install git
+RUN apt-get update && apt-get upgrade -y && apt-get install -y git
+
+# create a new conda environment named azureml
+RUN conda create -n azureml -y -q Python=3.6
+
+# install additional packages used by sample notebooks. this is optional
+RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
+
+# install azurmel-sdk components
+RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.18"]
+
+# clone Azure ML GitHub sample notebooks
+RUN cd /home && git clone -b "azureml-sdk-1.0.18" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
+
+# generate jupyter configuration file
+RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
+
+# set an emtpy token for Jupyter to remove authentication. 
+# this is NOT recommended for production environment
+RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
+
+# open up port 8887 on the container
+EXPOSE 8887
+
+# start Jupyter notebook server on port 8887 when the container starts
+CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.21/Dockerfile

@@ -0,0 +1,29 @@
+FROM continuumio/miniconda:4.5.11
+
+# install git
+RUN apt-get update && apt-get upgrade -y && apt-get install -y git
+
+# create a new conda environment named azureml
+RUN conda create -n azureml -y -q Python=3.6
+
+# install additional packages used by sample notebooks. this is optional
+RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
+
+# install azurmel-sdk components
+RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.21"]
+
+# clone Azure ML GitHub sample notebooks
+RUN cd /home && git clone -b "azureml-sdk-1.0.21" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
+
+# generate jupyter configuration file
+RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
+
+# set an emtpy token for Jupyter to remove authentication. 
+# this is NOT recommended for production environment
+RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
+
+# open up port 8887 on the container
+EXPOSE 8887
+
+# start Jupyter notebook server on port 8887 when the container starts
+CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.23/Dockerfile

@@ -0,0 +1,29 @@
+FROM continuumio/miniconda:4.5.11
+
+# install git
+RUN apt-get update && apt-get upgrade -y && apt-get install -y git
+
+# create a new conda environment named azureml
+RUN conda create -n azureml -y -q Python=3.6
+
+# install additional packages used by sample notebooks. this is optional
+RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
+
+# install azurmel-sdk components
+RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.23"]
+
+# clone Azure ML GitHub sample notebooks
+RUN cd /home && git clone -b "azureml-sdk-1.0.23" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
+
+# generate jupyter configuration file
+RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
+
+# set an emtpy token for Jupyter to remove authentication. 
+# this is NOT recommended for production environment
+RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
+
+# open up port 8887 on the container
+EXPOSE 8887
+
+# start Jupyter notebook server on port 8887 when the container starts
+CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.30/Dockerfile

@@ -0,0 +1,29 @@
+FROM continuumio/miniconda:4.5.11
+
+# install git
+RUN apt-get update && apt-get upgrade -y && apt-get install -y git
+
+# create a new conda environment named azureml
+RUN conda create -n azureml -y -q Python=3.6
+
+# install additional packages used by sample notebooks. this is optional
+RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
+
+# install azurmel-sdk components
+RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.30"]
+
+# clone Azure ML GitHub sample notebooks
+RUN cd /home && git clone -b "azureml-sdk-1.0.30" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
+
+# generate jupyter configuration file
+RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
+
+# set an emtpy token for Jupyter to remove authentication. 
+# this is NOT recommended for production environment
+RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
+
+# open up port 8887 on the container
+EXPOSE 8887
+
+# start Jupyter notebook server on port 8887 when the container starts
+CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.33/Dockerfile

@@ -0,0 +1,29 @@
+FROM continuumio/miniconda:4.5.11
+
+# install git
+RUN apt-get update && apt-get upgrade -y && apt-get install -y git
+
+# create a new conda environment named azureml
+RUN conda create -n azureml -y -q Python=3.6
+
+# install additional packages used by sample notebooks. this is optional
+RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
+
+# install azurmel-sdk components
+RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.33"]
+
+# clone Azure ML GitHub sample notebooks
+RUN cd /home && git clone -b "azureml-sdk-1.0.33" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
+
+# generate jupyter configuration file
+RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
+
+# set an emtpy token for Jupyter to remove authentication. 
+# this is NOT recommended for production environment
+RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
+
+# open up port 8887 on the container
+EXPOSE 8887
+
+# start Jupyter notebook server on port 8887 when the container starts
+CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.41/Dockerfile

@@ -0,0 +1,29 @@
+FROM continuumio/miniconda:4.5.11
+
+# install git
+RUN apt-get update && apt-get upgrade -y && apt-get install -y git
+
+# create a new conda environment named azureml
+RUN conda create -n azureml -y -q Python=3.6
+
+# install additional packages used by sample notebooks. this is optional
+RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
+
+# install azurmel-sdk components
+RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.41"]
+
+# clone Azure ML GitHub sample notebooks
+RUN cd /home && git clone -b "azureml-sdk-1.0.41" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
+
+# generate jupyter configuration file
+RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
+
+# set an emtpy token for Jupyter to remove authentication. 
+# this is NOT recommended for production environment
+RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
+
+# open up port 8887 on the container
+EXPOSE 8887
+
+# start Jupyter notebook server on port 8887 when the container starts
+CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Dockerfiles/1.0.43/Dockerfile

@@ -0,0 +1,29 @@
+FROM continuumio/miniconda:4.5.11
+
+# install git
+RUN apt-get update && apt-get upgrade -y && apt-get install -y git
+
+# create a new conda environment named azureml
+RUN conda create -n azureml -y -q Python=3.6
+
+# install additional packages used by sample notebooks. this is optional
+RUN ["/bin/bash", "-c", "source activate azureml && conda install -y tqdm cython matplotlib scikit-learn"]
+
+# install azurmel-sdk components
+RUN ["/bin/bash", "-c", "source activate azureml && pip install azureml-sdk[notebooks]==1.0.43"]
+
+# clone Azure ML GitHub sample notebooks
+RUN cd /home && git clone -b "azureml-sdk-1.0.43" --single-branch https://github.com/Azure/MachineLearningNotebooks.git
+
+# generate jupyter configuration file
+RUN ["/bin/bash", "-c", "source activate azureml && mkdir ~/.jupyter && cd ~/.jupyter && jupyter notebook --generate-config"]
+
+# set an emtpy token for Jupyter to remove authentication. 
+# this is NOT recommended for production environment
+RUN echo "c.NotebookApp.token = ''" >> ~/.jupyter/jupyter_notebook_config.py
+
+# open up port 8887 on the container
+EXPOSE 8887
+
+# start Jupyter notebook server on port 8887 when the container starts
+CMD /bin/bash -c "cd /home/MachineLearningNotebooks && source activate azureml && jupyter notebook --port 8887 --no-browser --ip 0.0.0.0 --allow-root"

Licenses/sdk-license/LICENSE

@@ -1,3 +1,4 @@
+    
 This software is made available to you on the condition that you agree to
 [your agreement][1] governing your use of Azure.
 If you do not have an existing agreement governing your use of Azure, you agree that 

NBSETUP.md

@@ -1,6 +1,4 @@
-# Setting up environment
-
----
+# Set up your notebook environment for Azure Machine Learning
 
 To run the notebooks in this repository use one of following options.
 
@@ -12,9 +10,7 @@ Azure Notebooks is a hosted Jupyter-based notebook service in the Azure cloud. A
 1. Follow the instructions in the [Configuration](configuration.ipynb) notebook to create and connect to a workspace
 1. Open one of the sample notebooks
 
-    **Make sure the Azure Notebook kernel is set to `Python 3.6`** when you open a notebook
-
-    ![set kernel to Python 3.6](images/python36.png)
+    **Make sure the Azure Notebook kernel is set to `Python 3.6`** when you open a notebook by choosing Kernel > Change Kernel > Python 3.6 from the menus.
 
 ## **Option 2: Use your own notebook server**
 
@@ -28,11 +24,8 @@ pip install azureml-sdk
 git clone https://github.com/Azure/MachineLearningNotebooks.git
 
 # below steps are optional
-# install the base SDK and a Jupyter notebook server
-pip install azureml-sdk[notebooks]
-
-# install the data prep component
-pip install azureml-dataprep
+# install the base SDK, Jupyter notebook server and tensorboard
+pip install azureml-sdk[notebooks,tensorboard]
 
 # install model explainability component
 pip install azureml-sdk[explain]
@@ -58,8 +51,7 @@ Please make sure you start with the [Configuration](configuration.ipynb) noteboo
 
 ### Video walkthrough:
 
-[![Get Started video](images/yt_cover.png)](https://youtu.be/VIsXeTuW3FU)
-
+[!VIDEO https://youtu.be/VIsXeTuW3FU]
 
 ## **Option 3: Use Docker**
 
@@ -90,9 +82,6 @@ Now you can point your browser to http://localhost:8887. We recommend that you s
 If you need additional Azure ML SDK components, you can either modify the Docker files before you build the Docker images to add additional steps, or install them through command line in the live container after you build the Docker image. For example:
 
 ```sh
-# install dataprep components
-pip install azureml-dataprep
-
 # install the core SDK and automated ml components
 pip install azureml-sdk[automl]
 

README.md

@@ -11,7 +11,7 @@ pip install azureml-sdk
 Read more detailed instructions on [how to set up your environment](./NBSETUP.md) using Azure Notebook service, your own Jupyter notebook server, or Docker.
 
 ## How to navigate and use the example notebooks?
-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. 
+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. 
 
 If you want to...
 
@@ -20,7 +20,7 @@ If you want to...
  * ...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](./how-to-use-azureml/machine-learning-pipelines/pipeline-mpi-batch-prediction.ipynb).
+ * ...deploy models as a batch scoring service, first [train a model within Notebook](./how-to-use-azureml/training/train-within-notebook/train-within-notebook.ipynb), learn how to [register and manage models](./how-to-use-azureml/deployment/register-model-create-image-deploy-service/register-model-create-image-deploy-service.ipynb), then [create Machine Learning Compute for scoring compute](./how-to-use-azureml/training/train-on-amlcompute/train-on-amlcompute.ipynb), and [use Machine Learning Pipelines to deploy your model](https://aka.ms/pl-batch-scoring).
  * ...monitor your deployed models, learn about using [App Insights](./how-to-use-azureml/deployment/enable-app-insights-in-production-service/enable-app-insights-in-production-service.ipynb) and [model data collection](./how-to-use-azureml/deployment/enable-data-collection-for-models-in-aks/enable-data-collection-for-models-in-aks.ipynb).
 
 ## Tutorials
@@ -54,3 +54,15 @@ Visit following repos to see projects contributed by Azure ML users:
 
  - [Fine tune natural language processing models using Azure Machine Learning service](https://github.com/Microsoft/AzureML-BERT)
  - [Fashion MNIST with Azure ML SDK](https://github.com/amynic/azureml-sdk-fashion)
+ 
+## Data/Telemetry 
+This repository collects usage data and sends it to Mircosoft to help improve our products and services. Read Microsoft's [privacy statement to learn more](https://privacy.microsoft.com/en-US/privacystatement)
+
+To opt out of tracking, please go to the raw markdown or .ipynb files and remove the following line of code:
+
+```sh
+    "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/README.png)"
+```
+This URL will be slightly different depending on the file. 
+
+ ![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/README.png)

configuration.ipynb

@@ -9,6 +9,13 @@
         "Licensed under the MIT License."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/configuration.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -96,7 +103,7 @@
       "source": [
         "import azureml.core\n",
         "\n",
-        "print(\"This notebook was created using version 1.0.17 of the Azure ML SDK\")\n",
+        "print(\"This notebook was created using version 1.0.45 of the Azure ML SDK\")\n",
         "print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
       ]
     },
@@ -268,14 +275,14 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your CPU cluster\n",
-        "cpu_cluster_name = \"cpucluster\"\n",
+        "cpu_cluster_name = \"cpu-cluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
         "    cpu_cluster = ComputeTarget(workspace=ws, name=cpu_cluster_name)\n",
-        "    print(\"Found existing cpucluster\")\n",
+        "    print(\"Found existing cpu-cluster\")\n",
         "except ComputeTargetException:\n",
-        "    print(\"Creating new cpucluster\")\n",
+        "    print(\"Creating new cpu-cluster\")\n",
         "    \n",
         "    # Specify the configuration for the new cluster\n",
         "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_D2_V2\",\n",
@@ -306,14 +313,14 @@
         "from azureml.core.compute_target import ComputeTargetException\n",
         "\n",
         "# Choose a name for your GPU cluster\n",
-        "gpu_cluster_name = \"gpucluster\"\n",
+        "gpu_cluster_name = \"gpu-cluster\"\n",
         "\n",
         "# Verify that cluster does not exist already\n",
         "try:\n",
         "    gpu_cluster = ComputeTarget(workspace=ws, name=gpu_cluster_name)\n",
         "    print(\"Found existing gpu cluster\")\n",
         "except ComputeTargetException:\n",
-        "    print(\"Creating new gpucluster\")\n",
+        "    print(\"Creating new gpu-cluster\")\n",
         "    \n",
         "    # Specify the configuration for the new cluster\n",
         "    compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_NC6\",\n",
@@ -336,7 +343,7 @@
         "\n",
         "In this notebook you configured this notebook library to connect easily to an Azure ML workspace.  You can copy this notebook to your own libraries to connect them to you workspace, or use it to bootstrap new workspaces completely.\n",
         "\n",
-        "If you came here from another notebook, you can return there and complete that exercise, or you can try out the [Tutorials](./tutorials) or jump into \"how-to\" notebooks and start creating and deploying models.  A good place to start is the [train in notebook](./how-to-use-azureml/training/train-in-notebook) example that walks through a simplified but complete end to end machine learning process."
+        "If you came here from another notebook, you can return there and complete that exercise, or you can try out the [Tutorials](./tutorials) or jump into \"how-to\" notebooks and start creating and deploying models.  A good place to start is the [train within notebook](./how-to-use-azureml/training/train-within-notebook) example that walks through a simplified but complete end to end machine learning process."
       ]
     },
     {

contrib/RAPIDS/README.md

@@ -0,0 +1,307 @@
+## How to use the RAPIDS on AzureML materials
+### Setting up requirements
+The material requires the use of the Azure ML SDK and of the Jupyter Notebook Server to run the interactive execution. Please refer to instructions to [setup the environment.](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#local "Local Computer Set Up") Follow the instructions under **Local Computer**, make sure to run the last step: <span style="font-family: Courier New;">pip install \<new package\></span> with <span style="font-family: Courier New;">new package = progressbar2  (pip install progressbar2)</span>
+  
+After following the directions, the user should end up setting a conda environment (<span style="font-family: Courier New;">myenv</span>)that can be activated in an Anaconda prompt
+
+The user would also require an Azure Subscription with a Machine Learning Services quota on the desired region for 24 nodes or more (to be able to select a vmSize with 4 GPUs as it is used on the Notebook) on the desired VM family ([NC\_v3](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv3-series),  [NC\_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv2-series), [ND](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#nd-series) or [ND_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ndv2-series-preview)), the specific vmSize to be used within the chosen family would also need to be whitelisted for Machine Learning Services usage.  
+
+&nbsp;  
+### Getting and running the material 
+Clone the AzureML Notebooks repository in GitHub by running the following command on a local_directory: 
+
+* C:\local_directory>git clone https://github.com/Azure/MachineLearningNotebooks.git
+
+On a conda prompt navigate to the local directory, activate the conda environment (<span style="font-family: Courier New;">myenv</span>), where the Azure ML SDK was installed and launch Jupyter Notebook. 
+
+* (<span style="font-family: Courier New;">myenv</span>) C:\local_directory>jupyter notebook
+
+From the resulting browser at http://localhost:8888/tree, navigate to the master notebook: 
+
+* http://localhost:8888/tree/MachineLearningNotebooks/contrib/RAPIDS/azure-ml-with-nvidia-rapids.ipynb
+
+&nbsp;  
+The following notebook will appear:  
+
+![](imgs/NotebookHome.png)
+
+&nbsp;  
+### Master Jupyter Notebook
+The notebook can be executed interactively step by step, by pressing the Run button (In a red circle in the above image.)
+
+The first couple of functional steps import the necessary AzureML libraries.  If you experience any errors please refer back to the [setup the environment.](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#local "Local Computer Set Up") instructions.
+
+&nbsp;  
+#### Setting up a Workspace
+The following step gathers the information necessary to set up a workspace to execute the RAPIDS script. This needs to be done only once, or not at all if you already have a workspace you can use set up on the Azure Portal:
+
+![](imgs/WorkSpaceSetUp.png)
+
+
+It is important to be sure to set the correct values for the subscription\_id, resource\_group, workspace\_name, and region before executing the step. An example is:
+
+    subscription_id = os.environ.get("SUBSCRIPTION_ID", "1358e503-xxxx-4043-xxxx-65b83xxxx32d")
+    resource_group = os.environ.get("RESOURCE_GROUP", "AML-Rapids-Testing")
+    workspace_name = os.environ.get("WORKSPACE_NAME", "AML_Rapids_Tester")
+    workspace_region = os.environ.get("WORKSPACE_REGION", "West US 2")
+
+&nbsp;  
+The resource\_group and workspace_name could take any value, the region should match the region for which the subscription has the required Machine Learning Services node quota.
+
+The first time the code is executed it will redirect to the Azure Portal to validate subscription credentials. After the workspace is created, its related information is stored on a local file so that this step can be subsequently skipped. The immediate step will just load the saved workspace
+
+![](imgs/saved_workspace.png)
+
+Once a workspace has been created the user could skip its creation and just jump to this step. The configuration file resides in:
+
+* C:\local_directory\\MachineLearningNotebooks\contrib\RAPIDS\aml_config\config.json
+
+&nbsp;  
+#### Creating an AML Compute Target 
+Following step, creates an AML Compute Target 
+
+![](imgs/target_creation.png)
+
+Parameter vm\_size on function call AmlCompute.provisioning\_configuration() has to be a member of the VM families ([NC\_v3](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv3-series),  [NC\_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ncv2-series), [ND](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#nd-series) or [ND_v2](https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu#ndv2-series-preview)) that are the ones provided with P40 or V100 GPUs, that are the ones supported by RAPIDS. In this particular case an Standard\_NC24s\_V2 was used.
+
+&nbsp;  
+If the output of running the step has an error of the form:
+
+![](imgs/targeterror1.png)
+
+It is an indication that even though the subscription has a node quota for VMs for that family, it does not have a node quota for Machine Learning Services for that family. 
+You will need to request an increase node quota for that family in that region for **Machine Learning Services**.
+
+&nbsp;  
+Another possible error is the following: 
+
+![](imgs/targeterror2.png)
+
+Which indicates that specified vmSize has not been whitelisted for usage on Machine Learning Services and a request to do so should be filled.
+
+The successful creation of the compute target would have an output like the following:
+
+![](imgs/targetsuccess.png)
+&nbsp;  
+#### RAPIDS script uploading and viewing
+The next step copies the RAPIDS script process_data.py, which is a slightly modified implementation of the [RAPIDS E2E example](https://github.com/rapidsai/notebooks/blob/master/mortgage/E2E.ipynb), into a script processing folder and it presents its contents to the user. (The script is discussed in the next section in detail). 
+If the user wants to use a different RAPIDS script, the references to the  <span style="font-family: Courier New;">process_data.py</span> script have to be changed
+
+![](imgs/scriptuploading.png)
+&nbsp;  
+#### Data Uploading
+The RAPIDS script loads and extracts features from the Fannie Mae’s Mortgage Dataset to train an XGBoost prediction model. The script uses two years of data
+
+The next few steps download and decompress the data and is made available to the  script as an [Azure Machine Learning Datastore](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-access-data).
+
+&nbsp;  
+The following functions are used to download and decompress the input data
+
+
+![](imgs/dcf1.png)
+![](imgs/dcf2.png)
+![](imgs/dcf3.png)
+![](imgs/dcf4.png)
+
+&nbsp;  
+The next step uses those functions to download locally file: 
+http://rapidsai-data.s3-website.us-east-2.amazonaws.com/notebook-mortgage-data/mortgage_2000-2001.tgz'
+And to decompress it, into local folder path = .\mortgage_2000-2001
+The step takes several minutes, the intermediate outputs provide progress indicators.
+
+![](imgs/downamddecom.png)
+
+&nbsp;  
+The decompressed data should have the following structure:
+* .\mortgage_2000-2001\acq\Acquisition_<year>Q<num>.txt 
+* .\mortgage_2000-2001\perf\Performance_<year>Q<num>.txt 
+* .\mortgage_2000-2001\names.csv
+
+The data is divided in partitions that roughly correspond to yearly quarters. RAPIDS includes support for multi-node, multi-GPU deployments, enabling scaling up and out on much larger dataset sizes. The user will be able to verify that the number of partitions that the script is able to process increases with the number of GPUs used. The RAPIDS script is implemented for single-machine scenarios. An example supporting multiple nodes will be published later. 
+
+&nbsp;  
+The next step upload the data into the [Azure Machine Learning Datastore](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-access-data) under reference <span style="font-family: Courier New;">fileroot = mortgage_2000-2001</span>
+
+The step takes several minutes to load the data, the output provides a progress indicator.
+
+![](imgs/datastore.png)
+
+Once the data has been loaded into the Azure Machine LEarning Data Store, in subsequent run, the user can comment out the ds.upload line and just make reference to the <span style="font-family: Courier New;">mortgage_2000-2001</blog> data store reference  
+
+&nbsp;  
+#### Setting up required libraries and environment to run RAPIDS code
+There are two options to setup the environment to run RAPIDS code. The following steps shows how to ues a prebuilt conda environment. A recommended alternative is to specify a base Docker image and package dependencies. You can find sample code for that in the notebook.
+
+![](imgs/install2.png)
+
+&nbsp;  
+#### Wrapper function to submit the RAPIDS script as an Azure Machine Learning experiment
+
+The next step consists of the definition of a wrapper function to be used when the user attempts to run the RAPIDS script with different arguments. It takes as arguments: <span style="font-family: Times New Roman;">*cpu\_training*</span>;  a flag that indicates if the run is meant to be processed with CPU-only, <span style="font-family: Times New Roman;">*gpu\_count*</span>; the number of GPUs to be used if they are meant to be used and part_count: the number of data partitions to be used
+
+![](imgs/wrapper.png)
+
+&nbsp;  
+The core of the function resides in configuring the run by the instantiation of a ScriptRunConfig object, which defines the source_directory for the script to be executed, the name of the script and the arguments to be passed to the script.
+In addition to the wrapper function arguments, two other arguments are passed: <span style="font-family: Times New Roman;">*data\_dir*</span>, the directory where the data is stored and <span style="font-family: Times New Roman;">*end_year*</span> is the largest year to use partition from.
+
+
+As mentioned earlier the size of the data that can be processed increases with the number of gpus, in the function, dictionary <span style="font-family: Times New Roman;">*max\_gpu\_count\_data\_partition_mapping*</span> maps the maximum number of partitions that we empirically found that the system can handle given the number of GPUs used. The function throws a warning when the number of partitions for a given number of gpus exceeds the maximum but the script is still executed, however the user should expect an error as an out of memory situation would be encountered
+If the user wants to use a different RAPIDS script, the reference to the process_data.py script has to be changed
+
+&nbsp;  
+#### Submitting Experiments
+We are ready to submit experiments: launching the RAPIDS script with different sets of parameters.
+
+&nbsp;  
+The following couple of steps submit experiments under different conditions. 
+
+![](imgs/submission1.png)
+
+&nbsp;  
+The user can change variable num\_gpu between one and the number of GPUs supported by the chosen vmSize. Variable part\_count can take any value between 1 and 11, but if it exceeds the maximum for num_gpu, the run would result in an error
+
+&nbsp;  
+If the experiment is successfully submitted, it would be placed on a queue for processing, its status would appeared as Queued and an output like the following would appear 
+
+![](imgs/queue.png)
+
+&nbsp;  
+When the experiment starts running, its status would appeared as Running and the output would change to something like this:
+
+![](imgs/running.png)
+
+&nbsp;  
+#### Reproducing the performance gains plot results on the Blog Post
+When the run has finished successfully, its status would appeared as Completed and the output would change to something like this:
+
+&nbsp; 
+![](imgs/completed.png)
+
+Which is the output for an experiment run with three partitions and one GPU, notice that the reported processing time is 49.16 seconds just as depicted on the performance gains plot on the blog post
+
+&nbsp;  
+
+![](imgs/2GPUs.png)
+
+
+This output corresponds to a run with three partitions and two GPUs, notice that the reported processing time is 37.50 seconds just as depicted on the performance gains plot on the blog post
+
+&nbsp;  
+![](imgs/3GPUs.png)
+
+This output corresponds to an experiment run with three partitions and three GPUs, notice that the reported processing time is 24.40 seconds just as depicted on the performance gains plot on the blog post
+
+&nbsp;  
+![](imgs/4gpus.png)
+
+This output corresponds to an experiment run with three partitions and four GPUs, notice that the reported processing time is 23.33 seconds just as depicted on the performance gains plot on the blogpost
+
+&nbsp;  
+![](imgs/CPUBase.png)
+
+This output corresponds to an experiment run with three partitions and using only CPU, notice that the reported processing time is 9 minutes and 1.21 seconds or 541.21 second just as depicted on the performance gains plot on the blog post
+
+&nbsp;  
+![](imgs/OOM.png)
+
+This output corresponds to an experiment run with nine partitions and four GPUs, notice that the notebook throws a warning signaling that the number of partitions exceed the maximum that the system can handle with those many GPUs and the run ends up failing, hence having and status of Failed. 
+
+&nbsp;  
+##### Freeing Resources
+In the last step the notebook deletes the compute target. (This step is optional especially if the min_nodes in the cluster is set to 0 with which the cluster will scale down to 0 nodes when there is no usage.)
+
+![](imgs/clusterdelete.png)
+
+&nbsp;  
+### RAPIDS Script
+The Master Notebook runs experiments by launching a RAPIDS script with different sets of parameters. In this section, the RAPIDS script, process_data.py in the material, is analyzed
+
+The script first imports all the necessary libraries and parses the arguments passed by the Master Notebook.
+
+The all internal functions to be used by the script are defined.
+
+&nbsp;  
+#### Wrapper Auxiliary Functions:
+The below functions are wrappers for a configuration module for librmm, the RAPIDS Memory Manager python interface:
+
+![](imgs/wap1.png)![](imgs/wap2.png)
+
+&nbsp;  
+A couple of other functions are wrappers for the submission of jobs to the DASK client:
+
+![](imgs/wap3.png)
+![](imgs/wap4.png)
+
+&nbsp;  
+#### Data Loading Functions:
+The data is loaded through the use of the following three functions 
+
+![](imgs/DLF1.png)![](imgs/DLF2.png)![](imgs/DLF3.png)
+
+All three functions use library function cudf.read_csv(), cuDF version for the well known counterpart on Pandas.
+
+&nbsp;  
+#### Data Transformation and Feature Extraction Functions:
+The raw data is transformed and processed to extract features by joining, slicing, grouping, aggregating, factoring, etc, the original dataframes just as is done with Pandas. The following functions in the script are used for that purpose:
+![](imgs/fef1.png)![](imgs/fef2.png)![](imgs/fef3.png)![](imgs/fef4.png)![](imgs/fef5.png)
+
+![](imgs/fef6.png)![](imgs/fef7.png)![](imgs/fef8.png)![](imgs/fef9.png)
+
+&nbsp;  
+#### Main() Function
+The previous functions are used in the Main function to accomplish several steps: Set up the Dask client, do all ETL operations, set up and train an XGBoost model, the function also assigns which data needs to be processed by each Dask client
+
+&nbsp;  
+##### Setting Up DASK client:
+The following lines:
+
+![](imgs/daskini.png)
+
+&nbsp;  
+Initialize and set up a DASK client with a number of workers corresponding to the number of GPUs to be used on the run. A successful execution of the set up will result on the following output:
+
+![](imgs/daskoutput.png)
+
+##### All ETL functions are used on single calls to process\_quarter_gpu, one per data partition
+
+![](imgs/ETL.png)
+
+&nbsp;  
+##### Concentrating the data assigned to each DASK worker
+The partitions assigned to each worker are concatenated and set up for training.
+
+![](imgs/Dask2.png)
+
+&nbsp;  
+##### Setting Training Parameters
+The parameters used for the training of a gradient boosted decision tree model are set up in the following code block:
+![](imgs/PArameters.png)
+
+Notice how the parameters are modified when using the CPU-only mode.
+
+&nbsp;  
+##### Launching the training of a gradient boosted decision tree model using XGBoost.
+
+![](imgs/training.png)
+
+The outputs of the script can be observed in the master notebook as the script is executed
+
+![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/contrib/RAPIDS/README.png)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

contrib/RAPIDS/azure-ml-with-nvidia-rapids.ipynb

@@ -20,7 +20,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "The [RAPIDS](https://www.developer.nvidia.com/rapids) suite of software libraries from NVIDIA enables the execution of end-to-end data science and analytics pipelines entirely on GPUs. In many machine learning projects, a significant portion of the model training time is spent in setting up the data; this stage of the process is known as Extraction, Transformation and Loading, or ETL. By using the DataFrame API for ETL and GPU-capable ML algorithms in RAPIDS, data preparation and training models can be done in GPU-accelerated end-to-end pipelines without incurring serialization costs between the pipeline stages. This notebook demonstrates how to use NVIDIA RAPIDS to prepare data and train model in Azure.\n",
+        "The [RAPIDS](https://www.developer.nvidia.com/rapids) suite of software libraries from NVIDIA enables the execution of end-to-end data science and analytics pipelines entirely on GPUs. In many machine learning projects, a significant portion of the model training time is spent in setting up the data; this stage of the process is known as Extraction, Transformation and Loading, or ETL. By using the DataFrame API for ETL\u00c3\u201a\u00c2\u00a0and GPU-capable ML algorithms in RAPIDS, data preparation and training models can be done in GPU-accelerated end-to-end pipelines without incurring serialization costs between the pipeline stages. This notebook demonstrates how to use NVIDIA RAPIDS to prepare data and train model\u00c2\u00a0in Azure.\n",
         " \n",
         "In this notebook, we will do the following:\n",
         " \n",
@@ -62,6 +62,7 @@
       "source": [
         "import os\n",
         "from azureml.core import Workspace, Experiment\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
         "from azureml.core.compute import AmlCompute, ComputeTarget\n",
         "from azureml.data.data_reference import DataReference\n",
         "from azureml.core.runconfig import RunConfiguration\n",
@@ -210,21 +211,107 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "This sample uses [Fannie Mae\u00e2\u20ac\u2122s Single-Family Loan Performance Data](http://www.fanniemae.com/portal/funding-the-market/data/loan-performance-data.html). Refer to the 'Available mortgage datasets' section in [instructions](https://rapidsai.github.io/demos/datasets/mortgage-data) to get sample data.\n",
-        "\n",
-        "Once you obtain access to the data, you will need to make this data available in an [Azure Machine Learning Datastore](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-access-data), for use in this sample."
+        "This sample uses [Fannie Mae's Single-Family Loan Performance Data](http://www.fanniemae.com/portal/funding-the-market/data/loan-performance-data.html). Once you obtain access to the data, you will need to make this data available in an [Azure Machine Learning Datastore](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-access-data), for use in this sample. The following code shows how to do that."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "<font color='red'>Important</font>: The following step assumes the data is uploaded to the Workspace's default data store under a folder named 'mortgagedata2000_01'. Note that uploading data to the Workspace's default data store is not necessary and the data can be referenced from any datastore, e.g., from Azure Blob or File service, once it is added as a datastore to the workspace. The path_on_datastore parameter needs to be updated, depending on where the data is available.  The directory where the data is available should have the following folder structure, as the process_data.py script expects this directory structure:\n",
-        "* _&lt;data directory>_/acq\n",
-        "* _&lt;data directory>_/perf\n",
-        "* _names.csv_\n",
+        "### Downloading Data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<font color='red'>Important</font>: Python package progressbar2 is necessary to run the following cell. If it is not available in your environment where this notebook is running, please install it."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import tarfile\n",
+        "import hashlib\n",
+        "from urllib.request import urlretrieve\n",
+        "from progressbar import ProgressBar\n",
         "\n",
-        "The 'acq' and 'perf' refer to directories containing data files. The _&lt;data directory>_ is the path specified in _path&#95;on&#95;datastore_ parameter in the step below."
+        "def validate_downloaded_data(path):\n",
+        "    if(os.path.isdir(path) and os.path.exists(path + '//names.csv')) :\n",
+        "        if(os.path.isdir(path + '//acq' ) and len(os.listdir(path + '//acq')) == 8):\n",
+        "            if(os.path.isdir(path + '//perf' ) and len(os.listdir(path + '//perf')) == 11):\n",
+        "                print(\"Data has been downloaded and decompressed at: {0}\".format(path))\n",
+        "                return True\n",
+        "    print(\"Data has not been downloaded and decompressed\")\n",
+        "    return False\n",
+        "\n",
+        "def show_progress(count, block_size, total_size):\n",
+        "    global pbar\n",
+        "    global processed\n",
+        "    \n",
+        "    if count == 0:\n",
+        "        pbar = ProgressBar(maxval=total_size)\n",
+        "        processed = 0\n",
+        "    \n",
+        "    processed += block_size\n",
+        "    processed = min(processed,total_size)\n",
+        "    pbar.update(processed)\n",
+        "\n",
+        "        \n",
+        "def download_file(fileroot):\n",
+        "    filename = fileroot + '.tgz'\n",
+        "    if(not os.path.exists(filename) or hashlib.md5(open(filename, 'rb').read()).hexdigest() != '82dd47135053303e9526c2d5c43befd5' ):\n",
+        "        url_format = 'http://rapidsai-data.s3-website.us-east-2.amazonaws.com/notebook-mortgage-data/{0}.tgz'\n",
+        "        url = url_format.format(fileroot)\n",
+        "        print(\"...Downloading file :{0}\".format(filename))\n",
+        "        urlretrieve(url, filename,show_progress)\n",
+        "        pbar.finish()\n",
+        "        print(\"...File :{0} finished downloading\".format(filename))\n",
+        "    else:\n",
+        "        print(\"...File :{0} has been downloaded already\".format(filename))\n",
+        "    return filename\n",
+        "\n",
+        "def decompress_file(filename,path):\n",
+        "    tar = tarfile.open(filename)\n",
+        "    print(\"...Getting information from {0} about files to decompress\".format(filename))\n",
+        "    members = tar.getmembers()\n",
+        "    numFiles = len(members)\n",
+        "    so_far = 0\n",
+        "    for member_info in members:\n",
+        "        tar.extract(member_info,path=path)\n",
+        "        show_progress(so_far, 1, numFiles)\n",
+        "        so_far += 1\n",
+        "    pbar.finish()\n",
+        "    print(\"...All {0} files have been decompressed\".format(numFiles))\n",
+        "    tar.close()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "fileroot = 'mortgage_2000-2001'\n",
+        "path = '.\\\\{0}'.format(fileroot)\n",
+        "pbar = None\n",
+        "processed = 0\n",
+        "\n",
+        "if(not validate_downloaded_data(path)):\n",
+        "    print(\"Downloading and Decompressing Input Data\")\n",
+        "    filename = download_file(fileroot)\n",
+        "    decompress_file(filename,path)\n",
+        "    print(\"Input Data has been Downloaded and Decompressed\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Uploading Data to Workspace"
       ]
     },
     {
@@ -237,10 +324,10 @@
         "\n",
         "# download and uncompress data in a local directory before uploading to data store\n",
         "# directory specified in src_dir parameter below should have the acq, perf directories with data and names.csv file\n",
-        "# ds.upload(src_dir='<local directory that has data>', target_path='mortgagedata2000_01', overwrite=True, show_progress=True)\n",
+        "ds.upload(src_dir=path, target_path=fileroot, overwrite=True, show_progress=True)\n",
         "\n",
         "# data already uploaded to the datastore\n",
-        "data_ref = DataReference(data_reference_name='data', datastore=ds, path_on_datastore='mortgagedata2000_01')"
+        "data_ref = DataReference(data_reference_name='data', datastore=ds, path_on_datastore=fileroot)"
       ]
     },
     {
@@ -254,7 +341,26 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "AML allows the option of using existing Docker images with prebuilt conda environments. The following step use an existing image from [Docker Hub](https://hub.docker.com/r/rapidsai/rapidsai/)."
+        "RunConfiguration is used to submit jobs to Azure Machine Learning service. When creating RunConfiguration for a job, users can either \n",
+        "1. specify a Docker image with prebuilt conda environment and use it without any modifications to run the job, or \n",
+        "2. specify a Docker image as the base image and conda or pip packages as dependnecies to let AML build a new Docker image with a conda environment containing specified dependencies to use in the job\n",
+        "\n",
+        "The second option is the recommended option in AML. \n",
+        "The following steps have code for both options. You can pick the one that is more appropriate for your requirements. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Specify prebuilt conda environment"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The following code shows how to use an existing image from [Docker Hub](https://hub.docker.com/r/rapidsai/rapidsai/) that has a prebuilt conda environment named 'rapids' when creating a RunConfiguration. Note that this conda environment does not include azureml-defaults package that is required for using AML functionality like metrics tracking, model management etc. This package is automatically installed when you use 'Specify package dependencies' option and that is why it is the recommended option to create RunConfiguraiton in AML."
       ]
     },
     {
@@ -266,18 +372,52 @@
         "run_config = RunConfiguration()\n",
         "run_config.framework = 'python'\n",
         "run_config.environment.python.user_managed_dependencies = True\n",
-        "# use conda environment named 'rapids' available in the Docker image\n",
-        "# this conda environment does not include azureml-defaults package that is required for using AML functionality like metrics tracking, model management etc.\n",
         "run_config.environment.python.interpreter_path = '/conda/envs/rapids/bin/python'\n",
         "run_config.target = gpu_cluster_name\n",
         "run_config.environment.docker.enabled = True\n",
         "run_config.environment.docker.gpu_support = True\n",
-        "# if registry is not mentioned the image is pulled from Docker Hub\n",
-        "run_config.environment.docker.base_image = \"rapidsai/rapidsai:cuda9.2_ubuntu16.04_root\"\n",
+        "run_config.environment.docker.base_image = \"rapidsai/rapidsai:cuda9.2-runtime-ubuntu18.04\"\n",
+        "# run_config.environment.docker.base_image_registry.address = '<registry_url>' # not required if the base_image is in Docker hub\n",
+        "# run_config.environment.docker.base_image_registry.username = '<user_name>' # needed only for private images\n",
+        "# run_config.environment.docker.base_image_registry.password = '<password>' # needed only for private images\n",
         "run_config.environment.spark.precache_packages = False\n",
         "run_config.data_references={'data':data_ref.to_config()}"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Specify package dependencies"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The following code shows how to list package dependencies in a conda environment definition file (rapids.yml) when creating a RunConfiguration"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# cd = CondaDependencies(conda_dependencies_file_path='rapids.yml')\n",
+        "# run_config = RunConfiguration(conda_dependencies=cd)\n",
+        "# run_config.framework = 'python'\n",
+        "# run_config.target = gpu_cluster_name\n",
+        "# run_config.environment.docker.enabled = True\n",
+        "# run_config.environment.docker.gpu_support = True\n",
+        "# run_config.environment.docker.base_image = \"<image>\"\n",
+        "# run_config.environment.docker.base_image_registry.address = '<registry_url>' # not required if the base_image is in Docker hub\n",
+        "# run_config.environment.docker.base_image_registry.username = '<user_name>' # needed only for private images\n",
+        "# run_config.environment.docker.base_image_registry.password = '<password>' # needed only for private images\n",
+        "# run_config.environment.spark.precache_packages = False\n",
+        "# run_config.data_references={'data':data_ref.to_config()}"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -293,17 +433,24 @@
       "source": [
         "# parameter cpu_predictor indicates if training should be done on CPU. If set to true, GPUs are used *only* for ETL and *not* for training\n",
         "# parameter num_gpu indicates number of GPUs to use among the GPUs available in the VM for ETL and if cpu_predictor is false, for training as well \n",
-        "def run_rapids_experiment(cpu_training, gpu_count):\n",
+        "def run_rapids_experiment(cpu_training, gpu_count, part_count):\n",
         "    # any value between 1-4 is allowed here depending the type of VMs available in gpu_cluster\n",
         "    if gpu_count not in [1, 2, 3, 4]:\n",
         "        raise Exception('Value specified for the number of GPUs to use {0} is invalid'.format(gpu_count))\n",
         "\n",
         "    # following data partition mapping is empirical (specific to GPUs used and current data partitioning scheme) and may need to be tweaked\n",
-        "    gpu_count_data_partition_mapping = {1: 2, 2: 4, 3: 5, 4: 7}\n",
-        "    part_count = gpu_count_data_partition_mapping[gpu_count]\n",
-        "\n",
+        "    max_gpu_count_data_partition_mapping = {1: 3, 2: 4, 3: 6, 4: 8}\n",
+        "    \n",
+        "    if part_count > max_gpu_count_data_partition_mapping[gpu_count]:\n",
+        "        print(\"Too many partitions for the number of GPUs, exceeding memory threshold\")\n",
+        "        \n",
+        "    if part_count > 11:\n",
+        "        print(\"Warning: Maximum number of partitions available is 11\")\n",
+        "        part_count = 11\n",
+        "        \n",
         "    end_year = 2000\n",
-        "    if gpu_count > 2:\n",
+        "    \n",
+        "    if part_count > 4:\n",
         "        end_year = 2001 # use more data with more GPUs\n",
         "\n",
         "    src = ScriptRunConfig(source_directory=scripts_folder, \n",
@@ -317,7 +464,8 @@
         "\n",
         "    exp = Experiment(ws, 'rapidstest')\n",
         "    run = exp.submit(config=src)\n",
-        "    RunDetails(run).show()"
+        "    RunDetails(run).show()\n",
+        "    return run"
       ]
     },
     {
@@ -335,9 +483,10 @@
       "source": [
         "cpu_predictor = False\n",
         "# the value for num_gpu should be less than or equal to the number of GPUs available in the VM\n",
-        "num_gpu = 1 \n",
+        "num_gpu = 1\n",
+        "data_part_count = 1\n",
         "# train using CPU, use GPU for both ETL and training\n",
-        "run_rapids_experiment(cpu_predictor, num_gpu)"
+        "run = run_rapids_experiment(cpu_predictor, num_gpu, data_part_count)"
       ]
     },
     {
@@ -358,8 +507,9 @@
         "cpu_predictor = True\n",
         "# the value for num_gpu should be less than or equal to the number of GPUs available in the VM\n",
         "num_gpu = 1\n",
+        "data_part_count = 1\n",
         "# train using CPU, use GPU for ETL\n",
-        "run_rapids_experiment(cpu_predictor, num_gpu)"
+        "run = run_rapids_experiment(cpu_predictor, num_gpu, data_part_count)"
       ]
     },
     {

contrib/RAPIDS/process_data.py

@@ -1,9 +1,9 @@
-# License Info: https://github.com/rapidsai/notebooks/blob/master/LICENSE
 import numpy as np
 import datetime
 import dask_xgboost as dxgb_gpu
 import dask
 import dask_cudf
+from dask_cuda import LocalCUDACluster
 from dask.delayed import delayed
 from dask.distributed import Client, wait
 import xgboost as xgb
@@ -15,53 +15,6 @@ from glob import glob
 import os
 import argparse
 
-parser = argparse.ArgumentParser("rapidssample")
-parser.add_argument("--data_dir", type=str, help="location of data")
-parser.add_argument("--num_gpu", type=int, help="Number of GPUs to use", default=1)
-parser.add_argument("--part_count", type=int, help="Number of data files to train against", default=2)
-parser.add_argument("--end_year", type=int, help="Year to end the data load", default=2000)
-parser.add_argument("--cpu_predictor", type=str, help="Flag to use CPU for prediction", default='False')
-parser.add_argument('-f', type=str, default='') # added for notebook execution scenarios
-args = parser.parse_args()
-data_dir = args.data_dir
-num_gpu = args.num_gpu
-part_count = args.part_count
-end_year = args.end_year
-cpu_predictor = args.cpu_predictor.lower() in ('yes', 'true', 't', 'y', '1')
-
-print('data_dir = {0}'.format(data_dir))
-print('num_gpu = {0}'.format(num_gpu))
-print('part_count = {0}'.format(part_count))
-part_count = part_count + 1 # adding one because the usage below is not inclusive
-print('end_year = {0}'.format(end_year))
-print('cpu_predictor = {0}'.format(cpu_predictor))
-
-import subprocess
-
-cmd = "hostname --all-ip-addresses"
-process = subprocess.Popen(cmd.split(), stdout=subprocess.PIPE)
-output, error = process.communicate()
-IPADDR = str(output.decode()).split()[0]
-print('IPADDR is {0}'.format(IPADDR))
-
-cmd = "/rapids/notebooks/utils/dask-setup.sh 0"
-process = subprocess.Popen(cmd.split(), stdout=subprocess.PIPE)
-output, error = process.communicate()
-
-cmd = "/rapids/notebooks/utils/dask-setup.sh rapids " + str(num_gpu) + " 8786 8787 8790 " + str(IPADDR) + " MASTER"
-process = subprocess.Popen(cmd.split(), stdout=subprocess.PIPE)
-output, error = process.communicate()
-
-print(output.decode())
-
-import dask
-from dask.delayed import delayed
-from dask.distributed import Client, wait
-
-_client = IPADDR + str(":8786")
-
-client = dask.distributed.Client(_client)
-
 def initialize_rmm_pool():
     from librmm_cffi import librmm_config as rmm_cfg
 
@@ -81,15 +34,17 @@ def run_dask_task(func, **kwargs):
     task = func(**kwargs)
     return task
 
-def process_quarter_gpu(year=2000, quarter=1, perf_file=""):
+def process_quarter_gpu(client, col_names_path, acq_data_path, year=2000, quarter=1, perf_file=""):
+    dask_client = client
     ml_arrays = run_dask_task(delayed(run_gpu_workflow),
+                                          col_path=col_names_path,
+                                          acq_path=acq_data_path,
                                           quarter=quarter,
                                           year=year,
                                           perf_file=perf_file)
-    return client.compute(ml_arrays,
+    return dask_client.compute(ml_arrays,
                           optimize_graph=False,
-                          fifo_timeout="0ms"
-                         )
+                          fifo_timeout="0ms")
 
 def null_workaround(df, **kwargs):
     for column, data_type in df.dtypes.items():
@@ -99,9 +54,9 @@ def null_workaround(df, **kwargs):
             df[column] = df[column].fillna(-1)
     return df
 
-def run_gpu_workflow(quarter=1, year=2000, perf_file="", **kwargs):
-    names = gpu_load_names()
-    acq_gdf = gpu_load_acquisition_csv(acquisition_path= acq_data_path + "/Acquisition_"
+def run_gpu_workflow(col_path, acq_path, quarter=1, year=2000, perf_file="", **kwargs):
+    names = gpu_load_names(col_path=col_path)
+    acq_gdf = gpu_load_acquisition_csv(acquisition_path= acq_path + "/Acquisition_"
                                       + str(year) + "Q" + str(quarter) + ".txt")
     acq_gdf = acq_gdf.merge(names, how='left', on=['seller_name'])
     acq_gdf.drop_column('seller_name')
@@ -231,7 +186,7 @@ def gpu_load_acquisition_csv(acquisition_path, **kwargs):
     
     return cudf.read_csv(acquisition_path, names=cols, delimiter='|', dtype=list(dtypes.values()), skiprows=1)
 
-def gpu_load_names(**kwargs):
+def gpu_load_names(col_path):
     """ Loads names used for renaming the banks
     
     Returns
@@ -248,7 +203,7 @@ def gpu_load_names(**kwargs):
         ("new", "category"),
     ])
 
-    return cudf.read_csv(col_names_path, names=cols, delimiter='|', dtype=list(dtypes.values()), skiprows=1)
+    return cudf.read_csv(col_path, names=cols, delimiter='|', dtype=list(dtypes.values()), skiprows=1)
 
 def create_ever_features(gdf, **kwargs):
     everdf = gdf[['loan_id', 'current_loan_delinquency_status']]
@@ -384,32 +339,71 @@ def last_mile_cleaning(df, **kwargs):
     df['delinquency_12'] = df['delinquency_12'].fillna(False).astype('int32')
     for column in df.columns:
         df[column] = df[column].fillna(-1)
-    return df.to_arrow(index=False)
+    return df.to_arrow(preserve_index=False)
 
+def main():
+    #print('XGBOOST_BUILD_DOC is ' + os.environ['XGBOOST_BUILD_DOC'])
+    parser = argparse.ArgumentParser("rapidssample")
+    parser.add_argument("--data_dir", type=str, help="location of data")
+    parser.add_argument("--num_gpu", type=int, help="Number of GPUs to use", default=1)
+    parser.add_argument("--part_count", type=int, help="Number of data files to train against", default=2)
+    parser.add_argument("--end_year", type=int, help="Year to end the data load", default=2000)
+    parser.add_argument("--cpu_predictor", type=str, help="Flag to use CPU for prediction", default='False')
+    parser.add_argument('-f', type=str, default='') # added for notebook execution scenarios
+    args = parser.parse_args()
+    data_dir = args.data_dir
+    num_gpu = args.num_gpu
+    part_count = args.part_count
+    end_year = args.end_year
+    cpu_predictor = args.cpu_predictor.lower() in ('yes', 'true', 't', 'y', '1')
+
+    if cpu_predictor:
+        print('Training with CPUs require num gpu = 1')
+        num_gpu = 1
+
+    print('data_dir = {0}'.format(data_dir))
+    print('num_gpu = {0}'.format(num_gpu))
+    print('part_count = {0}'.format(part_count))
+    #part_count = part_count + 1 # adding one because the usage below is not inclusive
+    print('end_year = {0}'.format(end_year))
+    print('cpu_predictor = {0}'.format(cpu_predictor))
+    
+    import subprocess
+
+    cmd = "hostname --all-ip-addresses"
+    process = subprocess.Popen(cmd.split(), stdout=subprocess.PIPE)
+    output, error = process.communicate()
+    IPADDR = str(output.decode()).split()[0]
+    
+    cluster = LocalCUDACluster(ip=IPADDR,n_workers=num_gpu)
+    client = Client(cluster)
+    client
+    print(client.ncores())
 
 # to download data for this notebook, visit https://rapidsai.github.io/demos/datasets/mortgage-data and update the following paths accordingly
-acq_data_path = "{0}/acq".format(data_dir) #"/rapids/data/mortgage/acq"
-perf_data_path = "{0}/perf".format(data_dir) #"/rapids/data/mortgage/perf"
-col_names_path = "{0}/names.csv".format(data_dir) # "/rapids/data/mortgage/names.csv"
-start_year = 2000
+    acq_data_path = "{0}/acq".format(data_dir) #"/rapids/data/mortgage/acq"
+    perf_data_path = "{0}/perf".format(data_dir) #"/rapids/data/mortgage/perf"
+    col_names_path = "{0}/names.csv".format(data_dir) # "/rapids/data/mortgage/names.csv"
+    start_year = 2000
 #end_year = 2000 # end_year is inclusive -- converted to parameter
 #part_count = 2 # the number of data files to train against -- converted to parameter
 
-client.run(initialize_rmm_pool)
-
+    client.run(initialize_rmm_pool)
+    client
+    print(client.ncores())
 # NOTE: The ETL calculates additional features which are then dropped before creating the XGBoost DMatrix.
 # This can be optimized to avoid calculating the dropped features.
-print("Reading ...")
-t1 = datetime.datetime.now()
-gpu_dfs = []
-gpu_time = 0
-quarter = 1
-year = start_year
-count = 0
-while year <= end_year:
+    print("Reading ...")
+    t1 = datetime.datetime.now()
+    gpu_dfs = []
+    gpu_time = 0
+    quarter = 1
+    year = start_year
+    count = 0
+    while year <= end_year:
         for file in glob(os.path.join(perf_data_path + "/Performance_" + str(year) + "Q" + str(quarter) + "*")):
             if count < part_count:
-            gpu_dfs.append(process_quarter_gpu(year=year, quarter=quarter, perf_file=file))
+                gpu_dfs.append(process_quarter_gpu(client, col_names_path, acq_data_path, year=year, quarter=quarter, perf_file=file))
                 count += 1
                 print('file: {0}'.format(file))
                 print('count: {0}'.format(count))
@@ -418,16 +412,17 @@ while year <= end_year:
             year += 1
             quarter = 1
             
-wait(gpu_dfs)
-t2 = datetime.datetime.now()
-print("Reading time ...")
-print(t2-t1)
-print('len(gpu_dfs) is {0}'.format(len(gpu_dfs)))
+    wait(gpu_dfs)
+    t2 = datetime.datetime.now()
+    print("Reading time ...")
+    print(t2-t1)
+    print('len(gpu_dfs) is {0}'.format(len(gpu_dfs)))
     
-client.run(cudf._gdf.rmm_finalize)
-client.run(initialize_rmm_no_pool)
-
-dxgb_gpu_params = {
+    client.run(cudf._gdf.rmm_finalize)
+    client.run(initialize_rmm_no_pool)
+    client
+    print(client.ncores())
+    dxgb_gpu_params = {
         'nround':            100,
         'max_depth':         8,
         'max_leaves':        2**8,
@@ -448,53 +443,53 @@ dxgb_gpu_params = {
         'criterion':         'friedman_mse',
         'grow_policy':       'lossguide',
         'verbose':           True
-}
+    }
       
-if cpu_predictor:
+    if cpu_predictor:
         print('Training using CPUs')
         dxgb_gpu_params['predictor'] = 'cpu_predictor'
         dxgb_gpu_params['tree_method'] = 'hist'
         dxgb_gpu_params['objective'] = 'reg:linear'
         
-else:
+    else:
         print('Training using GPUs')
     
-print('Training parameters are {0}'.format(dxgb_gpu_params))
+    print('Training parameters are {0}'.format(dxgb_gpu_params))
     
-gpu_dfs = [delayed(DataFrame.from_arrow)(gpu_df) for gpu_df in gpu_dfs[:part_count]]
+    gpu_dfs = [delayed(DataFrame.from_arrow)(gpu_df) for gpu_df in gpu_dfs[:part_count]]
+    gpu_dfs = [gpu_df for gpu_df in gpu_dfs]
+    wait(gpu_dfs)
     
-gpu_dfs = [gpu_df for gpu_df in gpu_dfs]
-
-wait(gpu_dfs)
-tmp_map = [(gpu_df, list(client.who_has(gpu_df).values())[0]) for gpu_df in gpu_dfs]
-new_map = {}
-for key, value in tmp_map:
+    tmp_map = [(gpu_df, list(client.who_has(gpu_df).values())[0]) for gpu_df in gpu_dfs]
+    new_map = {}
+    for key, value in tmp_map:
         if value not in new_map:
             new_map[value] = [key]
         else:
             new_map[value].append(key)
     
-del(tmp_map)
-gpu_dfs = []
-for list_delayed in new_map.values():
+    del(tmp_map)
+    gpu_dfs = []
+    for list_delayed in new_map.values():
         gpu_dfs.append(delayed(cudf.concat)(list_delayed))
     
-del(new_map)
-gpu_dfs = [(gpu_df[['delinquency_12']], gpu_df[delayed(list)(gpu_df.columns.difference(['delinquency_12']))]) for gpu_df in gpu_dfs]
-gpu_dfs = [(gpu_df[0].persist(), gpu_df[1].persist()) for gpu_df in gpu_dfs]
-gpu_dfs = [dask.delayed(xgb.DMatrix)(gpu_df[1], gpu_df[0]) for gpu_df in gpu_dfs]
-gpu_dfs = [gpu_df.persist() for gpu_df in gpu_dfs]
+    del(new_map)
+    gpu_dfs = [(gpu_df[['delinquency_12']], gpu_df[delayed(list)(gpu_df.columns.difference(['delinquency_12']))]) for gpu_df in gpu_dfs]
+    gpu_dfs = [(gpu_df[0].persist(), gpu_df[1].persist()) for gpu_df in gpu_dfs]
     
-gc.collect()
-labels = None
+    gpu_dfs = [dask.delayed(xgb.DMatrix)(gpu_df[1], gpu_df[0]) for gpu_df in gpu_dfs]
+    gpu_dfs = [gpu_df.persist() for gpu_df in gpu_dfs]
+    gc.collect()
+    wait(gpu_dfs)
     
-print('str(gpu_dfs) is {0}'.format(str(gpu_dfs)))
+    labels = None
+    t1 = datetime.datetime.now()
+    bst = dxgb_gpu.train(client, dxgb_gpu_params, gpu_dfs, labels, num_boost_round=dxgb_gpu_params['nround'])
+    t2 = datetime.datetime.now()
+    print("Training time ...")
+    print(t2-t1)
+    print('str(bst) is {0}'.format(str(bst)))
+    print('Exiting script')
 
-wait(gpu_dfs)
-t1 = datetime.datetime.now()
-bst = dxgb_gpu.train(client, dxgb_gpu_params, gpu_dfs, labels, num_boost_round=dxgb_gpu_params['nround'])
-t2 = datetime.datetime.now()
-print("Training time ...")
-print(t2-t1)
-print('str(bst) is {0}'.format(str(bst)))
-print('Exiting script')
+if __name__ == '__main__':
+    main()

contrib/RAPIDS/rapids.yml

@@ -0,0 +1,35 @@
+name: rapids
+channels:
+- nvidia
+- numba
+- conda-forge
+- rapidsai
+- defaults
+- pytorch
+
+dependencies:
+- arrow-cpp=0.12.0
+- bokeh
+- cffi=1.11.5
+- cmake=3.12
+- cuda92
+- cython==0.29
+- dask=1.1.1
+- distributed=1.25.3
+- faiss-gpu=1.5.0
+- numba=0.42
+- numpy=1.15.4
+- nvstrings
+- pandas=0.23.4
+- pyarrow=0.12.0
+- scikit-learn
+- scipy
+- cudf
+- cuml
+- python=3.6.2
+- jupyterlab
+- pip:
+  - file:/rapids/xgboost/python-package/dist/xgboost-0.81-py3-none-any.whl
+  - git+https://github.com/rapidsai/dask-xgboost@dask-cudf
+  - git+https://github.com/rapidsai/dask-cudf@master
+  - git+https://github.com/rapidsai/dask-cuda@master

contrib/datadrift/azure-ml-datadrift.ipynb

@@ -0,0 +1,709 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Track Data Drift between Training and Inference Data in Production \n",
+        "\n",
+        "With this notebook, you will learn how to enable the DataDrift service to automatically track and determine whether your inference data is drifting from the data your model was initially trained on. The DataDrift service provides metrics and visualizations to help stakeholders identify which specific features cause the concept drift to occur.\n",
+        "\n",
+        "Please email driftfeedback@microsoft.com with any issues. A member from the DataDrift team will respond shortly. \n",
+        "\n",
+        "The DataDrift Public Preview API can be found [here](https://docs.microsoft.com/en-us/python/api/azureml-contrib-datadrift/?view=azure-ml-py). "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/contrib/datadrift/azureml-datadrift.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Prerequisites and Setup"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Install the DataDrift package\n",
+        "\n",
+        "Install the azureml-contrib-datadrift, azureml-contrib-opendatasets and lightgbm packages before running this notebook.\n",
+        "```\n",
+        "pip install azureml-contrib-datadrift\n",
+        "pip install azureml-contrib-datasets\n",
+        "pip install lightgbm\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Import Dependencies"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "import os\n",
+        "import time\n",
+        "from datetime import datetime, timedelta\n",
+        "\n",
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "import requests\n",
+        "from azureml.contrib.datadrift import DataDriftDetector, AlertConfiguration\n",
+        "from azureml.contrib.opendatasets import NoaaIsdWeather\n",
+        "from azureml.core import Dataset, Workspace, Run\n",
+        "from azureml.core.compute import AksCompute, ComputeTarget\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.image import ContainerImage\n",
+        "from azureml.core.model import Model\n",
+        "from azureml.core.webservice import Webservice, AksWebservice\n",
+        "from azureml.widgets import RunDetails\n",
+        "from sklearn.externals import joblib\n",
+        "from sklearn.model_selection import train_test_split\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Set up Configuraton and Create Azure ML Workspace\n",
+        "\n",
+        "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) first if you haven't already to establish your connection to the AzureML Workspace."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Please type in your initials/alias. The prefix is prepended to the names of resources created by this notebook. \n",
+        "prefix = \"dd\"\n",
+        "\n",
+        "# NOTE: Please do not change the model_name, as it's required by the score.py file\n",
+        "model_name = \"driftmodel\"\n",
+        "image_name = \"{}driftimage\".format(prefix)\n",
+        "service_name = \"{}driftservice\".format(prefix)\n",
+        "\n",
+        "# optionally, set email address to receive an email alert for DataDrift\n",
+        "email_address = \"\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Generate Train/Testing Data\n",
+        "\n",
+        "For this demo, we will use NOAA weather data from [Azure Open Datasets](https://azure.microsoft.com/services/open-datasets/). You may replace this step with your own dataset. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "usaf_list = ['725724', '722149', '723090', '722159', '723910', '720279',\n",
+        "             '725513', '725254', '726430', '720381', '723074', '726682',\n",
+        "             '725486', '727883', '723177', '722075', '723086', '724053',\n",
+        "             '725070', '722073', '726060', '725224', '725260', '724520',\n",
+        "             '720305', '724020', '726510', '725126', '722523', '703333',\n",
+        "             '722249', '722728', '725483', '722972', '724975', '742079',\n",
+        "             '727468', '722193', '725624', '722030', '726380', '720309',\n",
+        "             '722071', '720326', '725415', '724504', '725665', '725424',\n",
+        "             '725066']\n",
+        "\n",
+        "columns = ['usaf', 'wban', 'datetime', 'latitude', 'longitude', 'elevation', 'windAngle', 'windSpeed', 'temperature', 'stationName', 'p_k']\n",
+        "\n",
+        "\n",
+        "def enrich_weather_noaa_data(noaa_df):\n",
+        "    hours_in_day = 23\n",
+        "    week_in_year = 52\n",
+        "    \n",
+        "    noaa_df[\"hour\"] = noaa_df[\"datetime\"].dt.hour\n",
+        "    noaa_df[\"weekofyear\"] = noaa_df[\"datetime\"].dt.week\n",
+        "    \n",
+        "    noaa_df[\"sine_weekofyear\"] = noaa_df['datetime'].transform(lambda x: np.sin((2*np.pi*x.dt.week-1)/week_in_year))\n",
+        "    noaa_df[\"cosine_weekofyear\"] = noaa_df['datetime'].transform(lambda x: np.cos((2*np.pi*x.dt.week-1)/week_in_year))\n",
+        "\n",
+        "    noaa_df[\"sine_hourofday\"] = noaa_df['datetime'].transform(lambda x: np.sin(2*np.pi*x.dt.hour/hours_in_day))\n",
+        "    noaa_df[\"cosine_hourofday\"] = noaa_df['datetime'].transform(lambda x: np.cos(2*np.pi*x.dt.hour/hours_in_day))\n",
+        "    \n",
+        "    return noaa_df\n",
+        "\n",
+        "def add_window_col(input_df):\n",
+        "    shift_interval = pd.Timedelta('-7 days') # your X days interval\n",
+        "    df_shifted = input_df.copy()\n",
+        "    df_shifted['datetime'] = df_shifted['datetime'] - shift_interval\n",
+        "    df_shifted.drop(list(input_df.columns.difference(['datetime', 'usaf', 'wban', 'sine_hourofday', 'temperature'])), axis=1, inplace=True)\n",
+        "\n",
+        "    # merge, keeping only observations where -1 lag is present\n",
+        "    df2 = pd.merge(input_df,\n",
+        "                   df_shifted,\n",
+        "                   on=['datetime', 'usaf', 'wban', 'sine_hourofday'],\n",
+        "                   how='inner',  # use 'left' to keep observations without lags\n",
+        "                   suffixes=['', '-7'])\n",
+        "    return df2\n",
+        "\n",
+        "def get_noaa_data(start_time, end_time, cols, station_list):\n",
+        "    isd = NoaaIsdWeather(start_time, end_time, cols=cols)\n",
+        "    # Read into Pandas data frame.\n",
+        "    noaa_df = isd.to_pandas_dataframe()\n",
+        "    noaa_df = noaa_df.rename(columns={\"stationName\": \"station_name\"})\n",
+        "    \n",
+        "    df_filtered = noaa_df[noaa_df[\"usaf\"].isin(station_list)]\n",
+        "    df_filtered.reset_index(drop=True)\n",
+        "    \n",
+        "    # Enrich with time features\n",
+        "    df_enriched = enrich_weather_noaa_data(df_filtered)\n",
+        "    \n",
+        "    return df_enriched\n",
+        "\n",
+        "def get_featurized_noaa_df(start_time, end_time, cols, station_list):\n",
+        "    df_1 = get_noaa_data(start_time - timedelta(days=7), start_time - timedelta(seconds=1), cols, station_list)\n",
+        "    df_2 = get_noaa_data(start_time, end_time, cols, station_list)\n",
+        "    noaa_df = pd.concat([df_1, df_2])\n",
+        "    \n",
+        "    print(\"Adding window feature\")\n",
+        "    df_window = add_window_col(noaa_df)\n",
+        "    \n",
+        "    cat_columns = df_window.dtypes == object\n",
+        "    cat_columns = cat_columns[cat_columns == True]\n",
+        "    \n",
+        "    print(\"Encoding categorical columns\")\n",
+        "    df_encoded = pd.get_dummies(df_window, columns=cat_columns.keys().tolist())\n",
+        "    \n",
+        "    print(\"Dropping unnecessary columns\")\n",
+        "    df_featurized = df_encoded.drop(['windAngle', 'windSpeed', 'datetime', 'elevation'], axis=1).dropna().drop_duplicates()\n",
+        "    \n",
+        "    return df_featurized"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Train model on Jan 1 - 14, 2009 data\n",
+        "df = get_featurized_noaa_df(datetime(2009, 1, 1), datetime(2009, 1, 14, 23, 59, 59), columns, usaf_list)\n",
+        "df.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "label = \"temperature\"\n",
+        "x_df = df.drop(label, axis=1)\n",
+        "y_df = df[[label]]\n",
+        "x_train, x_test, y_train, y_test = train_test_split(df, y_df, test_size=0.2, random_state=223)\n",
+        "print(x_train.shape, x_test.shape, y_train.shape, y_test.shape)\n",
+        "\n",
+        "training_dir = 'outputs/training'\n",
+        "training_file = \"training.csv\"\n",
+        "\n",
+        "# Generate training dataframe to register as Training Dataset\n",
+        "os.makedirs(training_dir, exist_ok=True)\n",
+        "training_df = pd.merge(x_train.drop(label, axis=1), y_train, left_index=True, right_index=True)\n",
+        "training_df.to_csv(training_dir + \"/\" + training_file)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create/Register Training Dataset"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "dataset_name = \"dataset\"\n",
+        "name_suffix = datetime.utcnow().strftime(\"%Y-%m-%d-%H-%M-%S\")\n",
+        "snapshot_name = \"snapshot-{}\".format(name_suffix)\n",
+        "\n",
+        "dstore = ws.get_default_datastore()\n",
+        "dstore.upload(training_dir, \"data/training\", show_progress=True)\n",
+        "dpath = dstore.path(\"data/training/training.csv\")\n",
+        "trainingDataset = Dataset.auto_read_files(dpath, include_path=True)\n",
+        "trainingDataset = trainingDataset.register(workspace=ws, name=dataset_name, description=\"dset\", exist_ok=True)\n",
+        "\n",
+        "trainingDataSnapshot = trainingDataset.create_snapshot(snapshot_name=snapshot_name, compute_target=None, create_data_snapshot=True)\n",
+        "datasets = [(Dataset.Scenario.TRAINING, trainingDataSnapshot)]\n",
+        "print(\"dataset registration done.\\n\")\n",
+        "datasets"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train and Save Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import lightgbm as lgb\n",
+        "\n",
+        "train = lgb.Dataset(data=x_train, \n",
+        "                    label=y_train)\n",
+        "\n",
+        "test = lgb.Dataset(data=x_test, \n",
+        "                   label=y_test,\n",
+        "                   reference=train)\n",
+        "\n",
+        "params = {'learning_rate'    : 0.1,\n",
+        "          'boosting'         : 'gbdt',\n",
+        "          'metric'           : 'rmse',\n",
+        "          'feature_fraction' : 1,\n",
+        "          'bagging_fraction' : 1,\n",
+        "          'max_depth': 6,\n",
+        "          'num_leaves'       : 31,\n",
+        "          'objective'        : 'regression',\n",
+        "          'bagging_freq'     : 1,\n",
+        "          \"verbose\": -1,\n",
+        "          'min_data_per_leaf': 100}\n",
+        "\n",
+        "model = lgb.train(params, \n",
+        "                  num_boost_round=500,\n",
+        "                  train_set=train,\n",
+        "                  valid_sets=[train, test],\n",
+        "                  verbose_eval=50,\n",
+        "                  early_stopping_rounds=25)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model_file = 'outputs/{}.pkl'.format(model_name)\n",
+        "\n",
+        "os.makedirs('outputs', exist_ok=True)\n",
+        "joblib.dump(model, model_file)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Register Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model = Model.register(model_path=model_file,\n",
+        "                       model_name=model_name,\n",
+        "                       workspace=ws,\n",
+        "                       datasets=datasets)\n",
+        "\n",
+        "print(model_name, image_name, service_name, model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Deploy Model To AKS"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Prepare Environment"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn', 'joblib', 'lightgbm', 'pandas'],\n",
+        "                                 pip_packages=['azureml-monitoring', 'azureml-sdk[automl]'])\n",
+        "\n",
+        "with open(\"myenv.yml\",\"w\") as f:\n",
+        "    f.write(myenv.serialize_to_string())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create Image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Image creation may take up to 15 minutes.\n",
+        "\n",
+        "image_name = image_name + str(model.version)\n",
+        "\n",
+        "if not image_name in ws.images:\n",
+        "    # Use the score.py defined in this directory as the execution script\n",
+        "    # NOTE: The Model Data Collector must be enabled in the execution script for DataDrift to run correctly\n",
+        "    image_config = ContainerImage.image_configuration(execution_script=\"score.py\",\n",
+        "                                                      runtime=\"python\",\n",
+        "                                                      conda_file=\"myenv.yml\",\n",
+        "                                                      description=\"Image with weather dataset model\")\n",
+        "    image = ContainerImage.create(name=image_name,\n",
+        "                                  models=[model],\n",
+        "                                  image_config=image_config,\n",
+        "                                  workspace=ws)\n",
+        "\n",
+        "    image.wait_for_creation(show_output=True)\n",
+        "else:\n",
+        "    image = ws.images[image_name]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Create Compute Target"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aks_name = 'dd-demo-e2e'\n",
+        "prov_config = AksCompute.provisioning_configuration()\n",
+        "\n",
+        "if not aks_name in ws.compute_targets:\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",
+        "    print(aks_target.provisioning_state)\n",
+        "    print(aks_target.provisioning_errors)\n",
+        "else:\n",
+        "    aks_target=ws.compute_targets[aks_name]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Deploy Service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "aks_service_name = service_name\n",
+        "\n",
+        "if not aks_service_name in ws.webservices:\n",
+        "    aks_config = AksWebservice.deploy_configuration(collect_model_data=True, enable_app_insights=True)\n",
+        "    aks_service = Webservice.deploy_from_image(workspace=ws,\n",
+        "                                               name=aks_service_name,\n",
+        "                                               image=image,\n",
+        "                                               deployment_config=aks_config,\n",
+        "                                               deployment_target=aks_target)\n",
+        "    aks_service.wait_for_deployment(show_output=True)\n",
+        "    print(aks_service.state)\n",
+        "else:\n",
+        "    aks_service = ws.webservices[aks_service_name]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Run DataDrift Analysis"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Send Scoring Data to Service"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Download Scoring Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Score Model on March 15, 2016 data\n",
+        "scoring_df = get_noaa_data(datetime(2016, 3, 15) - timedelta(days=7), datetime(2016, 3, 16),  columns, usaf_list)\n",
+        "# Add the window feature column\n",
+        "scoring_df = add_window_col(scoring_df)\n",
+        "\n",
+        "# Drop features not used by the model\n",
+        "print(\"Dropping unnecessary columns\")\n",
+        "scoring_df = scoring_df.drop(['windAngle', 'windSpeed', 'datetime', 'elevation'], axis=1).dropna()\n",
+        "scoring_df.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# One Hot Encode the scoring dataset to match the training dataset schema\n",
+        "columns_dict = model.datasets[\"training\"][0].get_profile().columns\n",
+        "extra_cols = ('Path', 'Column1')\n",
+        "for k in extra_cols:\n",
+        "    columns_dict.pop(k, None)\n",
+        "training_columns = list(columns_dict.keys())\n",
+        "\n",
+        "categorical_columns = scoring_df.dtypes == object\n",
+        "categorical_columns = categorical_columns[categorical_columns == True]\n",
+        "\n",
+        "test_df = pd.get_dummies(scoring_df[categorical_columns.keys().tolist()])\n",
+        "encoded_df = scoring_df.join(test_df)\n",
+        "\n",
+        "# Populate missing OHE columns with 0 values to match traning dataset schema\n",
+        "difference = list(set(training_columns) - set(encoded_df.columns.tolist()))\n",
+        "for col in difference:\n",
+        "    encoded_df[col] = 0\n",
+        "encoded_df.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Serialize dataframe to list of row dictionaries\n",
+        "encoded_dict = encoded_df.to_dict('records')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Submit Scoring Data to Service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%%time\n",
+        "\n",
+        "# retreive the API keys. AML generates two keys.\n",
+        "key1, key2 = aks_service.get_keys()\n",
+        "\n",
+        "total_count = len(scoring_df)\n",
+        "i = 0\n",
+        "load = []\n",
+        "for row in encoded_dict:\n",
+        "    load.append(row)\n",
+        "    i = i + 1\n",
+        "    if i % 100 == 0:\n",
+        "        payload = json.dumps({\"data\": load})\n",
+        "        \n",
+        "        # construct raw HTTP request and send to the service\n",
+        "        payload_binary = bytes(payload,encoding = 'utf8')\n",
+        "        headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
+        "        resp = requests.post(aks_service.scoring_uri, payload_binary, headers=headers)\n",
+        "        \n",
+        "        print(\"prediction:\", resp.content, \"Progress: {}/{}\".format(i, total_count))   \n",
+        "\n",
+        "        load = []\n",
+        "        time.sleep(3)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Configure DataDrift"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "services = [service_name]\n",
+        "start = datetime.now() - timedelta(days=2)\n",
+        "end = datetime(year=2020, month=1, day=22, hour=15, minute=16)\n",
+        "feature_list = ['usaf', 'wban', 'latitude', 'longitude', 'station_name', 'p_k',  'sine_hourofday', 'cosine_hourofday', 'temperature-7']\n",
+        "alert_config = AlertConfiguration([email_address]) if email_address else None\n",
+        "\n",
+        "# there will be an exception indicating using get() method if DataDrift object already exist\n",
+        "try:\n",
+        "    datadrift = DataDriftDetector.create(ws, model.name, model.version, services, frequency=\"Day\", alert_config=alert_config)\n",
+        "except KeyError:\n",
+        "    datadrift = DataDriftDetector.get(ws, model.name, model.version)\n",
+        "    \n",
+        "print(\"Details of DataDrift Object:\\n{}\".format(datadrift))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Run an Adhoc DataDriftDetector Run"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "target_date = datetime.today()\n",
+        "run = datadrift.run(target_date, services, feature_list=feature_list, create_compute_target=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "exp = Experiment(ws, datadrift._id)\n",
+        "dd_run = Run(experiment=exp, run_id=run)\n",
+        "RunDetails(dd_run).show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Get Drift Analysis Results"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "children = list(dd_run.get_children())\n",
+        "for child in children:\n",
+        "    child.wait_for_completion()\n",
+        "\n",
+        "drift_metrics = datadrift.get_output(start_time=start, end_time=end)\n",
+        "drift_metrics"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Show all drift figures, one per serivice.\n",
+        "# If setting with_details is False (by default), only drift will be shown; if it's True, all details will be shown.\n",
+        "\n",
+        "drift_figures = datadrift.show(with_details=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Enable DataDrift Schedule"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "datadrift.enable_schedule()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "rafarmah"
+      }
+    ],
+    "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"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

contrib/datadrift/score.py

@@ -0,0 +1,58 @@
+import pickle
+import json
+import numpy
+import azureml.train.automl
+from sklearn.externals import joblib
+from sklearn.linear_model import Ridge
+from azureml.core.model import Model
+from azureml.core.run import Run
+from azureml.monitoring import ModelDataCollector
+import time
+import pandas as pd
+
+
+def init():
+    global model, inputs_dc, prediction_dc, feature_names, categorical_features
+
+    print("Model is initialized" + time.strftime("%H:%M:%S"))
+    model_path = Model.get_model_path(model_name="driftmodel")
+    model = joblib.load(model_path)
+
+    feature_names = ["usaf", "wban", "latitude", "longitude", "station_name", "p_k",
+                     "sine_weekofyear", "cosine_weekofyear", "sine_hourofday", "cosine_hourofday",
+                     "temperature-7"]
+
+    categorical_features = ["usaf", "wban", "p_k", "station_name"]
+
+    inputs_dc = ModelDataCollector(model_name="driftmodel",
+                                   identifier="inputs",
+                                   feature_names=feature_names)
+
+    prediction_dc = ModelDataCollector("driftmodel",
+                                       identifier="predictions",
+                                       feature_names=["temperature"])
+
+
+def run(raw_data):
+    global inputs_dc, prediction_dc
+
+    try:
+        data = json.loads(raw_data)["data"]
+        data = pd.DataFrame(data)
+
+        # Remove the categorical features as the model expects OHE values
+        input_data = data.drop(categorical_features, axis=1)
+
+        result = model.predict(input_data)
+
+        # Collect the non-OHE dataframe
+        collected_df = data[feature_names]
+
+        inputs_dc.collect(collected_df.values)
+        prediction_dc.collect(result)
+        return result.tolist()
+    except Exception as e:
+        error = str(e)
+
+        print(error + time.strftime("%H:%M:%S"))
+        return error

googleade5d7141b3f2910.html

@@ -1 +0,0 @@
-google-site-verification: googleade5d7141b3f2910.html

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

@@ -1,8 +1,8 @@
 # Table of Contents
 1. [Automated ML Introduction](#introduction)
-1. [Running samples in Azure Notebooks](#jupyter)
-1. [Running samples in Azure Databricks](#databricks)
-1. [Running samples in a Local Conda environment](#localconda)
+1. [Setup using Azure Notebooks](#jupyter)
+1. [Setup using Azure Databricks](#databricks)
+1. [Setup using a Local Conda environment](#localconda)
 1. [Automated ML SDK Sample Notebooks](#samples)
 1. [Documentation](#documentation)
 1. [Running using python command](#pythoncommand)
@@ -13,15 +13,15 @@
 Automated machine learning (automated ML) builds high quality machine learning models for you by automating model and hyperparameter selection. Bring a labelled dataset that you want to build a model for, automated ML will give you a high quality machine learning model that you can use for predictions.
 
 
-If you are new to Data Science, AutoML will help you get jumpstarted by simplifying machine learning model building. It abstracts you from needing to perform model selection, hyperparameter selection and in one step creates a high quality trained model for you to use.
+If you are new to Data Science, automated ML will help you get jumpstarted by simplifying machine learning model building. It abstracts you from needing to perform model selection, hyperparameter selection and in one step creates a high quality trained model for you to use.
 
-If you are an experienced data scientist, AutoML will help increase your productivity by intelligently performing the model and hyperparameter selection for your training and generates high quality models much quicker than manually specifying several combinations of the parameters and running training jobs. AutoML provides visibility and access to all the training jobs and the performance characteristics of the models to help you further tune the pipeline if you desire.
+If you are an experienced data scientist, automated ML will help increase your productivity by intelligently performing the model and hyperparameter selection for your training and generates high quality models much quicker than manually specifying several combinations of the parameters and running training jobs. Automated ML provides visibility and access to all the training jobs and the performance characteristics of the models to help you further tune the pipeline if you desire.
 
-Below are the three execution environments supported by AutoML.
+Below are the three execution environments supported by automated ML.
 
 
  <a name="jupyter"></a>
-## Running samples in Azure Notebooks - Jupyter based notebooks in the Azure cloud
+## Setup using Azure Notebooks - Jupyter based notebooks in the Azure cloud
 
 1. [![Azure Notebooks](https://notebooks.azure.com/launch.png)](https://aka.ms/aml-clone-azure-notebooks)
 [Import sample notebooks ](https://aka.ms/aml-clone-azure-notebooks) into Azure Notebooks.
@@ -29,7 +29,7 @@ Below are the three execution environments supported by AutoML.
 1. Open one of the sample notebooks.
 
  <a name="databricks"></a>
-## Running samples in Azure Databricks
+## Setup using Azure Databricks
 
 **NOTE**: Please create your Azure Databricks cluster as v4.x (high concurrency preferred) with **Python 3** (dropdown).
 **NOTE**: You should at least have contributor access to your Azure subcription to run the notebook.
@@ -39,35 +39,25 @@ Below are the three execution environments supported by AutoML.
 - Attach the notebook to the cluster.
 
 <a name="localconda"></a>
-## Running samples in a Local Conda environment
+## Setup using a Local Conda environment
 
 To run these notebook on your own notebook server, use these installation instructions.
-
-The instructions below will install everything you need and then start a Jupyter notebook.  To start your Jupyter notebook manually, use:
-
-```
-conda activate azure_automl
-jupyter notebook
-```
-
-or on Mac:
-
-```
-source activate azure_automl
-jupyter notebook
-```
-
+The instructions below will install everything you need and then start a Jupyter notebook.
 
 ### 1. Install mini-conda from [here](https://conda.io/miniconda.html), choose 64-bit Python 3.7 or higher.
 - **Note**: if you already have conda installed, you can keep using it but it should be version 4.4.10 or later (as shown by: conda -V).  If you have a previous version installed, you can update it using the command: conda update conda.
 There's no need to install mini-conda specifically.
 
 ### 2. Downloading the sample notebooks
-- Download the sample notebooks from [GitHub](https://github.com/Azure/MachineLearningNotebooks) as zip and extract the contents to a local directory.  The AutoML sample notebooks are in the "automl" folder.
+- Download the sample notebooks from [GitHub](https://github.com/Azure/MachineLearningNotebooks) as zip and extract the contents to a local directory.  The automated ML sample notebooks are in the "automated-machine-learning" folder.
 
 ### 3. Setup a new conda environment
-The **automl/automl_setup** script creates a new conda environment, installs the necessary packages, configures the widget and starts a jupyter notebook.
-It takes the conda environment name as an optional parameter.  The default conda environment name is azure_automl.  The exact command depends on the operating system.  See the specific sections below for Windows, Mac and Linux.  It can take about 10 minutes to execute.
+The **automl_setup** script creates a new conda environment, installs the necessary packages, configures the widget and starts a jupyter notebook. It takes the conda environment name as an optional parameter.  The default conda environment name is azure_automl.  The exact command depends on the operating system.  See the specific sections below for Windows, Mac and Linux.  It can take about 10 minutes to execute.
+
+Packages installed by the **automl_setup** script:
+    <ul><li>python</li><li>nb_conda</li><li>matplotlib</li><li>numpy</li><li>cython</li><li>urllib3</li><li>scipy</li><li>scikit-learn</li><li>pandas</li><li>tensorflow</li><li>py-xgboost</li><li>azureml-sdk</li><li>azureml-widgets</li><li>pandas-ml</li></ul>
+
+For more details refer to the [automl_env.yml](./automl_env.yml)
 ## Windows
 Start an **Anaconda Prompt** window, cd to the **how-to-use-azureml/automated-machine-learning** folder where the sample notebooks were extracted and then run:
 ```
@@ -95,44 +85,44 @@ bash automl_setup_linux.sh
 
 ### 5. Running Samples
 - Please make sure you use the Python [conda env:azure_automl] kernel when trying the sample Notebooks.
-- Follow the instructions in the individual notebooks to explore various features in AutoML
+- Follow the instructions in the individual notebooks to explore various features in automated ML.
+
+### 6. Starting jupyter notebook manually
+To start your Jupyter notebook manually, use:
+
+```
+conda activate azure_automl
+jupyter notebook
+```
+
+or on Mac or Linux:
+
+```
+source activate azure_automl
+jupyter notebook
+```
 
 <a name="samples"></a>
 # Automated ML SDK Sample Notebooks
 
 - [auto-ml-classification.ipynb](classification/auto-ml-classification.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
-    - Simple example of using Auto ML for classification
+    - Simple example of using automated ML for classification
     - Uses local compute for training
 
 - [auto-ml-regression.ipynb](regression/auto-ml-regression.ipynb)
     - Dataset: scikit learn's [diabetes dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_diabetes.html)
-    - Simple example of using Auto ML for regression
+    - Simple example of using automated ML for regression
     - Uses local compute for training
 
-- [auto-ml-remote-execution.ipynb](remote-execution/auto-ml-remote-execution.ipynb)
-    - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
-    - Example of using Auto ML for classification using a remote linux DSVM for training
-    - Parallel execution of iterations
-    - Async tracking of progress
-    - Cancelling individual iterations or entire run
-    - Retrieving models for any iteration or logged metric
-    - Specify automl settings as kwargs
-
-- [auto-ml-remote-batchai.ipynb](remote-batchai/auto-ml-remote-batchai.ipynb)
+- [auto-ml-remote-amlcompute.ipynb](remote-amlcompute/auto-ml-remote-amlcompute.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
     - Example of using automated ML for classification using remote AmlCompute for training
     - Parallel execution of iterations
     - Async tracking of progress
     - Cancelling individual iterations or entire run
     - Retrieving models for any iteration or logged metric
-    - Specify automl settings as kwargs
-
-- [auto-ml-remote-attach.ipynb](remote-attach/auto-ml-remote-attach.ipynb)
-    - Dataset: Scikit learn's [20newsgroup](http://scikit-learn.org/stable/datasets/twenty_newsgroups.html)
-    - handling text data with preprocess flag
-    - Reading data from a blob store for remote executions
-    - using pandas dataframes for reading data
+    - Specify automated ML settings as kwargs
 
 - [auto-ml-missing-data-blacklist-early-termination.ipynb](missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
@@ -147,17 +137,13 @@ bash automl_setup_linux.sh
 
 - [auto-ml-exploring-previous-runs.ipynb](exploring-previous-runs/auto-ml-exploring-previous-runs.ipynb)
     - List all projects for the workspace
-    - List all AutoML Runs for a given project
-    - Get details for a AutoML Run. (Automl settings, run widget & all metrics)
+    - List all automated ML Runs for a given project
+    - Get details for a automated ML Run. (automated ML settings, run widget & all metrics)
     - Download fitted pipeline for any iteration
 
-- [auto-ml-remote-execution-with-datastore.ipynb](remote-execution-with-datastore/auto-ml-remote-execution-with-datastore.ipynb)
-    - Dataset: Scikit learn's [20newsgroup](http://scikit-learn.org/stable/datasets/twenty_newsgroups.html)
-    - Download the data and store it in DataStore.
-
 - [auto-ml-classification-with-deployment.ipynb](classification-with-deployment/auto-ml-classification-with-deployment.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
-    - Simple example of using Auto ML for classification
+    - Simple example of using automated ML for classification
     - Registering the model
     - Creating Image and creating aci service
     - Testing the aci service
@@ -177,16 +163,41 @@ bash automl_setup_linux.sh
 
 - [auto-ml-classification-with-whitelisting.ipynb](classification-with-whitelisting/auto-ml-classification-with-whitelisting.ipynb)
     - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
-    - Simple example of using Auto ML for classification with whitelisting tensorflow models.
+    - Simple example of using automated ML for classification with whitelisting tensorflow models.
     - Uses local compute for training
 
 - [auto-ml-forecasting-energy-demand.ipynb](forecasting-energy-demand/auto-ml-forecasting-energy-demand.ipynb)
     - Dataset: [NYC energy demand data](forecasting-a/nyc_energy.csv)
-    - Example of using AutoML for training a forecasting model
+    - Example of using automated ML for training a forecasting model
 
 - [auto-ml-forecasting-orange-juice-sales.ipynb](forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.ipynb)
     - Dataset: [Dominick's grocery sales of orange juice](forecasting-b/dominicks_OJ.csv)
-    - Example of training an AutoML forecasting model on multiple time-series
+    - Example of training an automated ML forecasting model on multiple time-series
+
+- [auto-ml-classification-with-onnx.ipynb](classification-with-onnx/auto-ml-classification-with-onnx.ipynb)
+    - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
+    - Simple example of using automated ML for classification with ONNX models
+    - Uses local compute for training
+
+- [auto-ml-bank-marketing-subscribers-with-deployment.ipynb](bank-marketing-subscribers-with-deployment/auto-ml-bank-marketing-with-deployment.ipynb)
+    - Dataset: UCI's [bank marketing dataset](https://www.kaggle.com/janiobachmann/bank-marketing-dataset)
+    - Simple example of using automated ML for classification to predict term deposit subscriptions for a bank
+    - Uses azure compute for training
+
+- [auto-ml-creditcard-with-deployment.ipynb](credit-card-fraud-detection-with-deployment/auto-ml-creditcard-with-deployment.ipynb)
+    - Dataset: Kaggle's [credit card fraud detection dataset](https://www.kaggle.com/mlg-ulb/creditcardfraud)
+    - Simple example of using automated ML for classification to fraudulent credit card transactions
+    - Uses azure compute for training
+
+- [auto-ml-hardware-performance-with-deployment.ipynb](hardware-performance-prediction-with-deployment/auto-ml-hardware-performance-with-deployment.ipynb)
+    - Dataset: UCI's [computer hardware dataset](https://archive.ics.uci.edu/ml/datasets/Computer+Hardware)
+    - Simple example of using automated ML for regression to predict the performance of certain combinations of hardware components
+    - Uses azure compute for training
+
+- [auto-ml-concrete-strength-with-deployment.ipynb](predicting-concrete-strength-with-deployment/auto-ml-concrete-strength-with-deployment.ipynb)
+    - Dataset: UCI's [concrete compressive strength dataset](https://www.kaggle.com/pavanraj159/concrete-compressive-strength-data-set)
+    - Simple example of using automated ML for regression to predict the strength  predict the compressive strength of concrete based off of different ingredient combinations and quantities of those ingredients
+    - Uses azure compute for training
 
 <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.
@@ -205,10 +216,18 @@ The main code of the file must be indented so that it is under this condition.
 <a name="troubleshooting"></a>
 # Troubleshooting
 ## automl_setup fails
-1. On windows, make sure that you are running automl_setup from an Anconda Prompt window rather than a regular cmd window.  You can launch the "Anaconda Prompt" window by hitting the Start button and typing "Anaconda Prompt".  If you don't see the application "Anaconda Prompt", you might not have conda or mini conda installed.  In that case, you can install it [here](https://conda.io/miniconda.html)
+1. On Windows, make sure that you are running automl_setup from an Anconda Prompt window rather than a regular cmd window.  You can launch the "Anaconda Prompt" window by hitting the Start button and typing "Anaconda Prompt".  If you don't see the application "Anaconda Prompt", you might not have conda or mini conda installed.  In that case, you can install it [here](https://conda.io/miniconda.html)
 2. Check that you have conda 64-bit installed rather than 32-bit.  You can check this with the command `conda info`.  The `platform` should be `win-64` for Windows or `osx-64` for Mac.
 3. Check that you have conda 4.4.10 or later.  You can check the version with the command `conda -V`.  If you have a previous version installed, you can update it using the command: `conda update conda`.
-4. Pass a new name as the first parameter to automl_setup so that it creates a new conda environment. You can view existing conda environments using `conda env list` and remove them with `conda env remove -n <environmentname>`. 
+4. On Linux, if the error is `gcc: error trying to exec 'cc1plus': execvp: No such file or directory`, install build essentials using the command `sudo apt-get install build-essential`.
+5. Pass a new name as the first parameter to automl_setup so that it creates a new conda environment. You can view existing conda environments using `conda env list` and remove them with `conda env remove -n <environmentname>`. 
+
+## automl_setup_linux.sh fails
+If automl_setup_linux.sh fails on Ubuntu Linux with the error: `unable to execute 'gcc': No such file or directory`
+1. Make sure that outbound ports 53 and 80 are enabled.  On an Azure VM, you can do this from the Azure Portal by selecting the VM and clicking on Networking.
+2. Run the command: `sudo apt-get update`
+3. Run the command: `sudo apt-get install build-essential --fix-missing`
+4. Run `automl_setup_linux.sh` again.
 
 ## configuration.ipynb fails
 1) For local conda, make sure that you have susccessfully run automl_setup first.
@@ -232,13 +251,20 @@ If a sample notebook fails with an error that property, method or library does n
 ## Numpy import fails on Windows
 Some Windows environments see an error loading numpy with the latest Python version 3.6.8.  If you see this issue, try with Python version 3.6.7.
 
+## Numpy import fails
+Check the tensorflow version in the automated ml conda environment. Supported versions are < 1.13. Uninstall tensorflow from the environment if version is >= 1.13
+You may check the version of tensorflow and uninstall as follows
+1) start a command shell, activate conda environment where automated ml packages are installed
+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. 
+
 ## 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.
 2) `The requested VM size xxxxx is not available in the current region.`  You can select a different region or vm_size. 
 
 ## Remote run: Unable to establish SSH connection
-AutoML uses the SSH protocol to communicate with remote DSVMs.  This defaults to port 22.  Possible causes for this error are:
+Automated ML uses the SSH protocol to communicate with remote DSVMs.  This defaults to port 22.  Possible causes for this error are:
 1) The DSVM is not ready for SSH connections.  When DSVM creation completes, the DSVM might still not be ready to acceept SSH connections.  The sample notebooks have a one minute delay to allow for this.
 2) Your Azure Subscription may restrict the IP address ranges that can access the DSVM on port 22.  You can check this in the Azure Portal by selecting the Virtual Machine and then clicking Networking.  The Virtual Machine name is the name that you provided in the notebook plus 10 alpha numeric characters to make the name unique.  The Inbound Port Rules define what can access the VM on specific ports.  Note that there is a priority priority order.  So, a Deny entry with a low priority number will override a Allow entry with a higher priority number.
 
@@ -249,13 +275,13 @@ This is often an issue with the `get_data` method.
 3) You can get to the error log for the setup iteration by clicking the `Click here to see the run in Azure portal` link, click `Back to Experiment`, click on the highest run number and then click on Logs.
 
 ## Remote run: disk full
-AutoML creates files under /tmp/azureml_runs for each iteration that it runs.  It creates a folder with the iteration id.  For example: AutoML_9a038a18-77cc-48f1-80fb-65abdbc33abe_93.  Under this, there is a azureml-logs folder, which contains logs.  If you run too many iterations on the same DSVM, these files can fill the disk.
+Automated ML creates files under /tmp/azureml_runs for each iteration that it runs.  It creates a folder with the iteration id.  For example: AutoML_9a038a18-77cc-48f1-80fb-65abdbc33abe_93.  Under this, there is a azureml-logs folder, which contains logs.  If you run too many iterations on the same DSVM, these files can fill the disk.
 You can delete the files under /tmp/azureml_runs or just delete the VM and create a new one.
 If your get_data downloads files, make sure the delete them or they can use disk space as well.
 When using DataStore, it is good to specify an absolute path for the files so that they are downloaded just once.  If you specify a relative path, it will download a file for each iteration.
 
 ## Remote run: Iterations fail and the log contains "MemoryError"
-This can be caused by insufficient memory on the DSVM.  AutoML loads all training data into memory.  So, the available memory should be more than the training data size.
+This can be caused by insufficient memory on the DSVM.  Automated ML loads all training data into memory.  So, the available memory should be more than the training data size.
 If you are using a remote DSVM, memory is needed for each concurrent iteration.  The max_concurrent_iterations setting specifies the maximum concurrent iterations.  For example, if the training data size is 8Gb and max_concurrent_iterations is set to 10, the minimum memory required is at least 80Gb.
 To resolve this issue, allocate a DSVM with more memory or reduce the value specified for max_concurrent_iterations.
 

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

@@ -5,17 +5,17 @@ dependencies:
 - python>=3.5.2,<3.6.8
 - nb_conda
 - matplotlib==2.1.0
-- numpy>=1.11.0,<1.15.0
+- numpy>=1.11.0,<=1.16.2
 - cython
 - urllib3<1.24
 - scipy>=1.0.0,<=1.1.0
-- scikit-learn>=0.18.0,<=0.19.1
-- pandas>=0.22.0,<0.23.0
-- tensorflow>=1.12.0
+- scikit-learn>=0.19.0,<=0.20.3
+- pandas>=0.22.0,<=0.23.4
 - py-xgboost<=0.80
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-sdk[automl,notebooks,explain]
+  - azureml-sdk[automl,explain]
+  - azureml-widgets
   - pandas_ml
   

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

@@ -2,21 +2,21 @@ name: azure_automl
 dependencies:
   # The python interpreter version.
   # Currently Azure ML only supports 3.5.2 and later.
+- nomkl
 - python>=3.5.2,<3.6.8
 - nb_conda
 - matplotlib==2.1.0
-- numpy>=1.15.3
+- numpy>=1.11.0,<=1.16.2
 - cython
 - urllib3<1.24
 - scipy>=1.0.0,<=1.1.0
-- scikit-learn>=0.18.0,<=0.19.1
+- scikit-learn>=0.19.0,<=0.20.3
 - pandas>=0.22.0,<0.23.0
-- tensorflow>=1.12.0
 - py-xgboost<=0.80
 
 - pip:
   # Required packages for AzureML execution, history, and data preparation.
-  - azureml-sdk[automl,notebooks,explain]
+  - azureml-sdk[automl,explain]
+  - azureml-widgets
   - pandas_ml
   
-

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

@@ -9,6 +9,8 @@ IF "%automl_env_file%"=="" SET automl_env_file="automl_env.yml"
 
 IF NOT EXIST %automl_env_file% GOTO YmlMissing
 
+IF "%CONDA_EXE%"=="" GOTO CondaMissing
+
 call conda activate %conda_env_name% 2>nul:
 
 if not errorlevel 1 (
@@ -42,6 +44,15 @@ IF NOT "%options%"=="nolaunch" (
 
 goto End
 
+:CondaMissing
+echo Please run this script from an Anaconda Prompt window.
+echo You can start an Anaconda Prompt window by
+echo typing Anaconda Prompt on the Start menu.
+echo If you don't see the Anaconda Prompt app, install Miniconda.
+echo If you are running an older version of Miniconda or Anaconda,
+echo you can upgrade using the command: conda update conda
+goto End
+
 :YmlMissing
 echo File %automl_env_file% not found.
 

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

@@ -31,7 +31,6 @@ else
    conda install lightgbm -c conda-forge -y &&
    python -m ipykernel install --user --name $CONDA_ENV_NAME --display-name "Python ($CONDA_ENV_NAME)" &&
    jupyter nbextension uninstall --user --py azureml.widgets &&
-   pip install numpy==1.15.3 &&
    echo "" &&
    echo "" &&
    echo "***************************************" &&

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

@@ -0,0 +1,729 @@
+{
+ "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-bank-marketing/auto-ml-classification-bank-marketing.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Automated Machine Learning\n",
+    "_**Classification with Deployment using a Bank Marketing Dataset**_\n",
+    "\n",
+    "## Contents\n",
+    "1. [Introduction](#Introduction)\n",
+    "1. [Setup](#Setup)\n",
+    "1. [Train](#Train)\n",
+    "1. [Results](#Results)\n",
+    "1. [Deploy](#Deploy)\n",
+    "1. [Test](#Test)\n",
+    "1. [Acknowledgements](#Acknowledgements)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Introduction\n",
+    "\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",
+    "\n",
+    "In this notebook you will learn how to:\n",
+    "1. Create an experiment using an existing workspace.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model using local compute.\n",
+    "4. Explore the results.\n",
+    "5. Register the model.\n",
+    "6. Create a container image.\n",
+    "7. Create an Azure Container Instance (ACI) service.\n",
+    "8. Test the ACI service."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\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 json\n",
+    "import logging\n",
+    "\n",
+    "from matplotlib import pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "from sklearn import datasets\n",
+    "import azureml.dataprep as dprep\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-classification-bmarketing'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-classification-bankmarketing'\n",
+    "\n",
+    "experiment=Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['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",
+    "    # 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",
+    "Here load the data in the get_data() script to be utilized in azure compute. To do this  first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_Run_config."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isdir('data'):\n",
+    "    os.mkdir('data')\n",
+    "    \n",
+    "if not os.path.exists(project_folder):\n",
+    "    os.makedirs(project_folder)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\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",
+    "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+    "\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], 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",
+    "Here we create the script to be run in azure comput for loading the data, we load the bank marketing dataset into X_train and y_train. Next X_train and y_train is returned for training the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_train.csv\"\n",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X_train = dflow.drop_columns(columns=['y'])\n",
+    "y_train = dflow.keep_columns(columns=['y'], validate_column_exists=True)\n",
+    "dflow.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train\n",
+    "\n",
+    "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+    "|**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, ], Multi-class targets.|\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",
+    "\n",
+    "**_You can find more information about primary metrics_** [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#primary-metric)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "automl_settings = {\n",
+    "    \"iteration_timeout_minutes\": 5,\n",
+    "    \"iterations\": 10,\n",
+    "    \"n_cross_validations\": 2,\n",
+    "    \"primary_metric\": 'AUC_weighted',\n",
+    "    \"preprocess\": True,\n",
+    "    \"max_concurrent_iterations\": 5,\n",
+    "    \"verbosity\": logging.INFO,\n",
+    "}\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors.log',\n",
+    "                             path = project_folder,\n",
+    "                             run_configuration=conda_run_config,\n",
+    "                             X = X_train,\n",
+    "                             y = y_train,\n",
+    "                             **automl_settings\n",
+    "                            )"
+   ]
+  },
+  {
+   "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."
+   ]
+  },
+  {
+   "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"
+   ]
+  },
+  {
+   "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": "markdown",
+   "metadata": {},
+   "source": [
+    "## Deploy\n",
+    "\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*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = remote_run.get_output()"
+   ]
+  },
+  {
+   "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 trained on bank marketing data to predict if a client will subscribe to a term deposit'\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",
+    "\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-sdk', 'azureml-core']:\n",
+    "    print('{}\\t{}'.format(p, dependencies[p]))"
+   ]
+  },
+  {
+   "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','py-xgboost<=0.80'],\n",
+    "                                 pip_packages=['azureml-sdk[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-sdk']))\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": [
+    "### Create a Container Image\n",
+    "\n",
+    "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+    "or when testing a model that is under development."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.image import Image, ContainerImage\n",
+    "\n",
+    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+    "                                 execution_script = script_file_name,\n",
+    "                                 conda_file = conda_env_file_name,\n",
+    "                                 tags = {'area': \"bmData\", 'type': \"automl_classification\"},\n",
+    "                                 description = \"Image for automl classification sample\")\n",
+    "\n",
+    "image = Image.create(name = \"automlsampleimage\",\n",
+    "                     # this is the model object \n",
+    "                     models = [model],\n",
+    "                     image_config = image_config, \n",
+    "                     workspace = ws)\n",
+    "\n",
+    "image.wait_for_creation(show_output = True)\n",
+    "\n",
+    "if image.creation_state == 'Failed':\n",
+    "    print(\"Image build log at: \" + image.image_build_log_uri)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploy the Image as a Web Service on Azure Container Instance\n",
+    "\n",
+    "Deploy an image that contains the model and other assets needed by the service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import AciWebservice\n",
+    "\n",
+    "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+    "                                               memory_gb = 1, \n",
+    "                                               tags = {'area': \"bmData\", 'type': \"automl_classification\"}, \n",
+    "                                               description = 'sample service for Automl Classification')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import Webservice\n",
+    "\n",
+    "aci_service_name = 'automl-sample-bankmarketing'\n",
+    "print(aci_service_name)\n",
+    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+    "                                           image = image,\n",
+    "                                           name = aci_service_name,\n",
+    "                                           workspace = ws)\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 our 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": [
+    "# Load the bank marketing datasets.\n",
+    "from sklearn.datasets import load_diabetes\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from numpy import array"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/bankmarketing_validate.csv\"\n",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X_test = dflow.drop_columns(columns=['y'])\n",
+    "y_test = dflow.keep_columns(columns=['y'], validate_column_exists=True)\n",
+    "dflow.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_test = X_test.to_pandas_dataframe()\n",
+    "y_test = y_test.to_pandas_dataframe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred  = fitted_model.predict(X_test)\n",
+    "actual = array(y_test)\n",
+    "actual = actual[:,0]\n",
+    "print(y_pred.shape, \" \", actual.shape)"
+   ]
+  },
+  {
+   "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 notebook\n",
+    "test_pred = plt.scatter(actual, y_pred, color='b')\n",
+    "test_test = plt.scatter(actual, actual, color='g')\n",
+    "plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Acknowledgements"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This Bank Marketing dataset is made available under the Creative Commons (CCO: Public Domain) License: https://creativecommons.org/publicdomain/zero/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: https://creativecommons.org/publicdomain/zero/1.0/ and is available at: https://www.kaggle.com/janiobachmann/bank-marketing-dataset .\n",
+    "\n",
+    "_**Acknowledgements**_\n",
+    "This data set is originally available within the UCI Machine Learning Database: https://archive.ics.uci.edu/ml/datasets/bank+marketing\n",
+    "\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"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "v-rasav"
+   }
+  ],
+  "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"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -0,0 +1,712 @@
+{
+ "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-credit-card-fraud/auto-ml-classification-credit-card-fraud.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Automated Machine Learning\n",
+    "_**Classification with Deployment using Credit Card Dataset**_\n",
+    "\n",
+    "## Contents\n",
+    "1. [Introduction](#Introduction)\n",
+    "1. [Setup](#Setup)\n",
+    "1. [Train](#Train)\n",
+    "1. [Results](#Results)\n",
+    "1. [Deploy](#Deploy)\n",
+    "1. [Test](#Test)\n",
+    "1. [Acknowledgements](#Acknowledgements)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Introduction\n",
+    "\n",
+    "In this example we use the associated credit card dataset to showcase how you can use AutoML for a simple classification problem and deploy it to an Azure Container Instance (ACI). The classification goal is to predict if a creditcard transaction  is or is not considered a fraudulent charge.\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 using an existing workspace.\n",
+    "2. Configure AutoML using `AutoMLConfig`.\n",
+    "3. Train the model using local compute.\n",
+    "4. Explore the results.\n",
+    "5. Register the model.\n",
+    "6. Create a container image.\n",
+    "7. Create an Azure Container Instance (ACI) service.\n",
+    "8. Test the ACI service."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\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 pandas as pd\n",
+    "import os\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import azureml.dataprep as dprep\n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\n",
+    "from azureml.train.automl import AutoMLConfig\n",
+    "from azureml.train.automl.run import AutoMLRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ws = Workspace.from_config()\n",
+    "\n",
+    "# choose a name for experiment\n",
+    "experiment_name = 'automl-classification-ccard'\n",
+    "# project folder\n",
+    "project_folder = './sample_projects/automl-classification-creditcard'\n",
+    "\n",
+    "experiment=Experiment(ws, experiment_name)\n",
+    "\n",
+    "output = {}\n",
+    "output['SDK version'] = azureml.core.VERSION\n",
+    "output['Subscription ID'] = ws.subscription_id\n",
+    "output['Workspace'] = ws.name\n",
+    "output['Resource Group'] = ws.resource_group\n",
+    "output['Location'] = ws.location\n",
+    "output['Project Directory'] = project_folder\n",
+    "output['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",
+    "    # 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",
+    "Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isdir('data'):\n",
+    "    os.mkdir('data')\n",
+    "    \n",
+    "if not os.path.exists(project_folder):\n",
+    "    os.makedirs(project_folder)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\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",
+    "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+    "\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], 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",
+    "Here create the script to be run in azure compute for loading the data, load the credit card dataset into cards and store the Class column (y) in the y variable and store the remaining data in the x variable. Next split the data  using train_test_split and return X_train and y_train for training the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = \"https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard.csv\"\n",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X = dflow.drop_columns(columns=['Class'])\n",
+    "y = dflow.keep_columns(columns=['Class'], validate_column_exists=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)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train\n",
+    "\n",
+    "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+    "\n",
+    "|Property|Description|\n",
+    "|-|-|\n",
+    "|**task**|classification or regression|\n",
+    "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+    "|**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, ], Multi-class targets.|\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",
+    "\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\": 2,\n",
+    "    \"primary_metric\": 'average_precision_score_weighted',\n",
+    "    \"preprocess\": True,\n",
+    "    \"max_concurrent_iterations\": 5,\n",
+    "    \"verbosity\": logging.INFO,\n",
+    "}\n",
+    "\n",
+    "automl_config = AutoMLConfig(task = 'classification',\n",
+    "                             debug_log = 'automl_errors_20190417.log',\n",
+    "                             path = project_folder,\n",
+    "                             run_configuration=conda_run_config,\n",
+    "                             X = X_train,\n",
+    "                             y = y_train,\n",
+    "                             **automl_settings\n",
+    "                            )"
+   ]
+  },
+  {
+   "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."
+   ]
+  },
+  {
+   "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"
+   ]
+  },
+  {
+   "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": "markdown",
+   "metadata": {},
+   "source": [
+    "## Deploy\n",
+    "\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*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "best_run, fitted_model = remote_run.get_output()"
+   ]
+  },
+  {
+   "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-sdk', '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'],\n",
+    "                                 pip_packages=['azureml-sdk[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-sdk']))\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": [
+    "### Create a Container Image\n",
+    "\n",
+    "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+    "or when testing a model that is under development."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.image import Image, ContainerImage\n",
+    "\n",
+    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+    "                                 execution_script = script_file_name,\n",
+    "                                 conda_file = conda_env_file_name,\n",
+    "                                 tags = {'area': \"cards\", 'type': \"automl_classification\"},\n",
+    "                                 description = \"Image for automl classification sample\")\n",
+    "\n",
+    "image = Image.create(name = \"automlsampleimage\",\n",
+    "                     # this is the model object \n",
+    "                     models = [model],\n",
+    "                     image_config = image_config, \n",
+    "                     workspace = ws)\n",
+    "\n",
+    "image.wait_for_creation(show_output = True)\n",
+    "\n",
+    "if image.creation_state == 'Failed':\n",
+    "    print(\"Image build log at: \" + image.image_build_log_uri)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploy the Image as a Web Service on Azure Container Instance\n",
+    "\n",
+    "Deploy an image that contains the model and other assets needed by the service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import AciWebservice\n",
+    "\n",
+    "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+    "                                               memory_gb = 1, \n",
+    "                                               tags = {'area': \"cards\", 'type': \"automl_classification\"}, \n",
+    "                                               description = 'sample service for Automl Classification')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import Webservice\n",
+    "\n",
+    "aci_service_name = 'automl-sample-creditcard'\n",
+    "print(aci_service_name)\n",
+    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+    "                                           image = image,\n",
+    "                                           name = aci_service_name,\n",
+    "                                           workspace = ws)\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": [
+    "#Randomly select and test\n",
+    "X_test = X_test.to_pandas_dataframe()\n",
+    "y_test = y_test.to_pandas_dataframe()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = fitted_model.predict(X_test)\n",
+    "y_pred"
+   ]
+  },
+  {
+   "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": [
+    "#Randomly select and test\n",
+    "# Plot outputs\n",
+    "%matplotlib notebook\n",
+    "test_pred = plt.scatter(y_test, y_pred, 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()\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Acknowledgements"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This Credit Card fraud Detection dataset is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/ and is available at: https://www.kaggle.com/mlg-ulb/creditcardfraud\n",
+    "\n",
+    "\n",
+    "The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Université Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project\n",
+    "Please cite the following works: \n",
+    "•\tAndrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
+    "•\tDal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
+    "•\tDal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE\n",
+    "o\tDal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
+    "•\tCarcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-Aël; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier\n",
+    "•\tCarcillo, Fabrizio; Le Borgne, Yann-Aël; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing"
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "v-rasav"
+   }
+  ],
+  "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"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/classification-with-deployment/auto-ml-classification-with-deployment.ipynb

@@ -9,6 +9,13 @@
         "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-with-deployment/auto-ml-classification-with-deployment.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -119,7 +126,7 @@
         "|**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, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\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.|"
       ]
     },
@@ -139,7 +146,6 @@
         "                             primary_metric = 'AUC_weighted',\n",
         "                             iteration_timeout_minutes = 20,\n",
         "                             iterations = 10,\n",
-        "                             n_cross_validations = 2,\n",
         "                             verbosity = logging.INFO,\n",
         "                             X = X_train, \n",
         "                             y = y_train,\n",
@@ -263,7 +269,7 @@
       "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)."
+        "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. The following cells create a file, myenv.yml, which specifies the dependencies from the run."
       ]
     },
     {
@@ -303,7 +309,8 @@
       "source": [
         "from azureml.core.conda_dependencies import CondaDependencies\n",
         "\n",
-        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
+        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn','py-xgboost<=0.80'],\n",
+        "                                 pip_packages=['azureml-sdk[automl]'])\n",
         "\n",
         "conda_env_file_name = 'myenv.yml'\n",
         "myenv.save_to_file('.', conda_env_file_name)"

how-to-use-azureml/automated-machine-learning/classification-with-onnx/auto-ml-classification-with-onnx.ipynb

@@ -0,0 +1,381 @@
+{
+  "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-with-onnx/auto-ml-classification-with-onnx.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "_**Classification with Local Compute**_\n",
+        "\n",
+        "## Contents\n",
+        "1. [Introduction](#Introduction)\n",
+        "1. [Setup](#Setup)\n",
+        "1. [Data](#Data)\n",
+        "1. [Train](#Train)\n",
+        "1. [Results](#Results)\n",
+        "1. [Test](#Test)\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Introduction\n",
+        "\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",
+        "\n",
+        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
+        "\n",
+        "Please find the ONNX related documentations [here](https://github.com/onnx/onnx).\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 with ONNX compatible config on.\n",
+        "4. Explore the results and save the ONNX model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n",
+        "\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",
+        "from sklearn import datasets\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "\n",
+        "import azureml.core\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.train.automl import AutoMLConfig, constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# Choose a name for the experiment and specify the project folder.\n",
+        "experiment_name = 'automl-classification-onnx'\n",
+        "project_folder = './sample_projects/automl-classification-onnx'\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['Project Directory'] = project_folder\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": [
+        "## Data\n",
+        "\n",
+        "This uses scikit-learn's [load_iris](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html) method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "iris = datasets.load_iris()\n",
+        "X_train, X_test, y_train, y_test = train_test_split(iris.data, \n",
+        "                                                    iris.target, \n",
+        "                                                    test_size=0.2, \n",
+        "                                                    random_state=0)\n",
+        "\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Ensure the x_train and x_test are pandas DataFrame."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Convert the X_train and X_test to pandas DataFrame and set column names,\n",
+        "# This is needed for initializing the input variable names of ONNX model, \n",
+        "# and the prediction with the ONNX model using the inference helper.\n",
+        "X_train = pd.DataFrame(X_train, columns=['c1', 'c2', 'c3', 'c4'])\n",
+        "X_test = pd.DataFrame(X_test, columns=['c1', 'c2', 'c3', 'c4'])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train with enable ONNX compatible models config on\n",
+        "\n",
+        "Instantiate an `AutoMLConfig` object to specify the settings and data used to run the experiment.\n",
+        "\n",
+        "Set the parameter enable_onnx_compatible_models=True, if you also want to generate the ONNX compatible models. Please note, the forecasting task and TensorFlow models are not ONNX compatible yet.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|classification or regression|\n",
+        "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
+        "|**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",
+        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
+        "|**enable_onnx_compatible_models**|Enable the ONNX compatible models in the experiment.|\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.|"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Set the preprocess=True,  currently the InferenceHelper only supports this mode."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_config = AutoMLConfig(task = 'classification',\n",
+        "                             debug_log = 'automl_errors.log',\n",
+        "                             primary_metric = 'AUC_weighted',\n",
+        "                             iteration_timeout_minutes = 60,\n",
+        "                             iterations = 10,\n",
+        "                             verbosity = logging.INFO,                             \n",
+        "                             X = X_train, \n",
+        "                             y = y_train,\n",
+        "                             preprocess=True,\n",
+        "                             enable_onnx_compatible_models=True,\n",
+        "                             path = project_folder)"
+      ]
+    },
+    {
+      "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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = experiment.submit(automl_config, show_output = True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_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(local_run).show() "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best ONNX Model\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*.\n",
+        "\n",
+        "Set the parameter return_onnx_model=True to retrieve the best ONNX model, instead of the Python model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, onnx_mdl = local_run.get_output(return_onnx_model=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Save the best ONNX model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.automl.core.onnx_convert import OnnxConverter\n",
+        "onnx_fl_path = \"./best_model.onnx\"\n",
+        "OnnxConverter.save_onnx_model(onnx_mdl, onnx_fl_path)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Predict with the ONNX model, using onnxruntime package"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import sys\n",
+        "import json\n",
+        "from azureml.automl.core.onnx_convert import OnnxConvertConstants\n",
+        "\n",
+        "if sys.version_info < OnnxConvertConstants.OnnxIncompatiblePythonVersion:\n",
+        "    python_version_compatible = True\n",
+        "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",
+        "\n",
+        "def get_onnx_res(run):\n",
+        "    res_path = 'onnx_resource.json'\n",
+        "    run.download_file(name=constants.MODEL_RESOURCE_PATH_ONNX, output_file_path=res_path)\n",
+        "    with open(res_path) as f:\n",
+        "        onnx_res = json.load(f)\n",
+        "    return onnx_res\n",
+        "\n",
+        "if onnxrt_present and python_version_compatible:    \n",
+        "    mdl_bytes = onnx_mdl.SerializeToString()\n",
+        "    onnx_res = get_onnx_res(best_run)\n",
+        "\n",
+        "    onnxrt_helper = OnnxInferenceHelper(mdl_bytes, onnx_res)\n",
+        "    pred_onnx, pred_prob_onnx = onnxrt_helper.predict(X_test)\n",
+        "\n",
+        "    print(pred_onnx)\n",
+        "    print(pred_prob_onnx)\n",
+        "else:\n",
+        "    if not python_version_compatible:\n",
+        "        print('Please use Python version 3.6 or 3.7 to run the inference helper.')    \n",
+        "    if not onnxrt_present:\n",
+        "        print('Please install the onnxruntime package to do the prediction with ONNX model.')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "savitam"
+      }
+    ],
+    "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"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/classification-with-whitelisting/auto-ml-classification-with-whitelisting.ipynb

@@ -9,6 +9,13 @@
         "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-with-whitelisting/auto-ml-classification-with-whitelisting.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -60,6 +67,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "#Note: This notebook will install tensorflow if not already installed in the enviornment..\n",
         "import logging\n",
         "\n",
         "from matplotlib import pyplot as plt\n",
@@ -70,6 +78,17 @@
         "import azureml.core\n",
         "from azureml.core.experiment import Experiment\n",
         "from azureml.core.workspace import Workspace\n",
+        "import sys\n",
+        "whitelist_models=[\"LightGBM\"]\n",
+        "if \"3.7\" != sys.version[0:3]:\n",
+        "    try:\n",
+        "        import tensorflow as tf1\n",
+        "    except ImportError:\n",
+        "        from pip._internal import main\n",
+        "        main(['install', 'tensorflow>=1.10.0,<=1.12.0'])\n",
+        "        logging.getLogger().setLevel(logging.ERROR)\n",
+        "    whitelist_models=[\"TensorFlowLinearClassifier\", \"TensorFlowDNN\"]\n",
+        "\n",
         "from azureml.train.automl import AutoMLConfig"
       ]
     },
@@ -138,7 +157,7 @@
         "|**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, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\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",
         "|**whitelist_models**|List of models that AutoML should use.  The possible values are listed [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-auto-train#configure-your-experiment-settings).|"
       ]
@@ -154,12 +173,11 @@
         "                             primary_metric = 'AUC_weighted',\n",
         "                             iteration_timeout_minutes = 60,\n",
         "                             iterations = 10,\n",
-        "                             n_cross_validations = 3,\n",
         "                             verbosity = logging.INFO,\n",
         "                             X = X_train, \n",
         "                             y = y_train,\n",
         "                             enable_tf=True,\n",
-        "                             whitelist_models=[\"TensorFlowLinearClassifier\", \"TensorFlowDNN\"],\n",
+        "                             whitelist_models=whitelist_models,\n",
         "                             path = project_folder)"
       ]
     },

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

@@ -9,6 +9,13 @@
         "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/auto-ml-classification.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -72,6 +79,32 @@
         "from azureml.train.automl import AutoMLConfig"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Accessing the Azure ML workspace requires authentication with Azure.\n",
+        "\n",
+        "The default authentication is interactive authentication using the default tenant.  Executing the `ws = Workspace.from_config()` line in the cell below will prompt for authentication the first time that it is run.\n",
+        "\n",
+        "If you have multiple Azure tenants, you can specify the tenant by replacing the `ws = Workspace.from_config()` line in the cell below with the following:\n",
+        "\n",
+        "```\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,
@@ -133,12 +166,17 @@
         "|-|-|\n",
         "|**task**|classification or regression|\n",
         "|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>average_precision_score_weighted</i><br><i>norm_macro_recall</i><br><i>precision_score_weighted</i>|\n",
-        "|**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, ], [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.|"
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|\n",
+        "\n",
+        "Automated machine learning trains multiple machine learning pipelines.  Each pipelines training is known as an iteration.\n",
+        "* You can specify a maximum number of iterations using the `iterations` parameter.\n",
+        "* You can specify a maximum time for the run using the `experiment_timeout_minutes` parameter.\n",
+        "* If you specify neither the `iterations` nor the `experiment_timeout_minutes`, automated ML keeps running iterations while it continues to see improvements in the scores.\n",
+        "\n",
+        "The following example doesn't specify `iterations` or `experiment_timeout_minutes` and so runs until the scores stop improving.\n"
       ]
     },
     {
@@ -148,15 +186,10 @@
       "outputs": [],
       "source": [
         "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             debug_log = 'automl_errors.log',\n",
         "                             primary_metric = 'AUC_weighted',\n",
-        "                             iteration_timeout_minutes = 60,\n",
-        "                             iterations = 25,\n",
-        "                             n_cross_validations = 3,\n",
-        "                             verbosity = logging.INFO,\n",
         "                             X = X_train, \n",
         "                             y = y_train,\n",
-        "                             path = project_folder)"
+        "                             n_cross_validations = 3)"
       ]
     },
     {
@@ -274,8 +307,45 @@
       "outputs": [],
       "source": [
         "best_run, fitted_model = local_run.get_output()\n",
-        "print(best_run)\n",
-        "print(fitted_model)"
+        "print(best_run)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "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",
+        "The following shows printing hyperparameters for each step in the pipeline."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from pprint import pprint\n",
+        "\n",
+        "def print_model(model, prefix=\"\"):\n",
+        "    for step in model.steps:\n",
+        "        print(prefix + step[0])\n",
+        "        if hasattr(step[1], 'estimators') and hasattr(step[1], 'weights'):\n",
+        "            pprint({'estimators': list(e[0] for e in step[1].estimators), 'weights': step[1].weights})\n",
+        "            print()\n",
+        "            for estimator in step[1].estimators:\n",
+        "                print_model(estimator[1], estimator[0]+ ' - ')\n",
+        "        elif hasattr(step[1], '_base_learners') and hasattr(step[1], '_meta_learner'):\n",
+        "            print(\"\\nMeta Learner\")\n",
+        "            pprint(step[1]._meta_learner)\n",
+        "            print()\n",
+        "            for estimator in step[1]._base_learners:\n",
+        "                print_model(estimator[1], estimator[0]+ ' - ')\n",
+        "        else:\n",
+        "            pprint(step[1].get_params())\n",
+        "            print()\n",
+        "            \n",
+        "print_model(fitted_model)"
       ]
     },
     {
@@ -294,8 +364,16 @@
       "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)"
+        "print(best_run)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print_model(fitted_model)"
       ]
     },
     {
@@ -314,8 +392,16 @@
       "source": [
         "iteration = 3\n",
         "third_run, third_model = local_run.get_output(iteration = iteration)\n",
-        "print(third_run)\n",
-        "print(third_model)"
+        "print(third_run)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print_model(third_model)"
       ]
     },
     {

how-to-use-azureml/automated-machine-learning/dataprep-remote-execution/auto-ml-dataprep-remote-execution.ipynb

@@ -9,12 +9,19 @@
         "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/dataprep-remote-execution/auto-ml-dataprep-remote-execution.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
         "# Automated Machine Learning\n",
-        "_**Prepare Data using `azureml.dataprep` for Remote Execution (DSVM)**_\n",
+        "_**Prepare Data using `azureml.dataprep` for Remote Execution (AmlCompute)**_\n",
         "\n",
         "## Contents\n",
         "1. [Introduction](#Introduction)\n",
@@ -117,21 +124,12 @@
       "outputs": [],
       "source": [
         "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
-        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
-        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
-        "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
-        "\n",
+        "# The data referenced here was a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
         "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
         "# and convert column types manually.\n",
-        "# Here we read a comma delimited file and convert all columns to integers.\n",
-        "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
+        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
+        "dflow = dprep.auto_read_file(example_data).skip(1)  # Remove the header row.\n",
+        "dflow.get_profile()"
       ]
     },
     {
@@ -140,7 +138,30 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X.skip(1).head(5)"
+        "# As `Primary Type` is our y data, we need to drop the values those are null in this column.\n",
+        "dflow = dflow.drop_nulls('Primary Type')\n",
+        "dflow.head(5)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Review the Data Preparation Result\n",
+        "\n",
+        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets.\n",
+        "\n",
+        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X = dflow.drop_columns(columns=['Primary Type', 'FBI Code'])\n",
+        "y = dflow.keep_columns(columns=['Primary Type'], validate_column_exists=True)"
       ]
     },
     {
@@ -162,9 +183,8 @@
         "    \"iteration_timeout_minutes\" : 10,\n",
         "    \"iterations\" : 2,\n",
         "    \"primary_metric\" : 'AUC_weighted',\n",
-        "    \"preprocess\" : False,\n",
-        "    \"verbosity\" : logging.INFO,\n",
-        "    \"n_cross_validations\": 3\n",
+        "    \"preprocess\" : True,\n",
+        "    \"verbosity\" : logging.INFO\n",
         "}"
       ]
     },
@@ -172,7 +192,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Create or Attach a Remote Linux DSVM"
+        "### Create or Attach an AmlCompute cluster"
       ]
     },
     {
@@ -181,21 +201,36 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "dsvm_name = 'mydsvmc'\n",
+        "from azureml.core.compute import AmlCompute\n",
+        "from azureml.core.compute import ComputeTarget\n",
         "\n",
-        "try:\n",
-        "    while ws.compute_targets[dsvm_name].provisioning_state == 'Creating':\n",
-        "        time.sleep(1)\n",
-        "        \n",
-        "    dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
-        "    print('Found existing DVSM.')\n",
-        "except:\n",
-        "    print('Creating a new DSVM.')\n",
-        "    dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
-        "    dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
-        "    dsvm_compute.wait_for_completion(show_output = True)\n",
-        "    print(\"Waiting one minute for ssh to be accessible\")\n",
-        "    time.sleep(60) # Wait for ssh to be accessible"
+        "# Choose a name for your cluster.\n",
+        "amlcompute_cluster_name = \"cpu-cluster\"\n",
+        "\n",
+        "found = False\n",
+        "\n",
+        "# Check if this compute target already exists in the workspace.\n",
+        "\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\",\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 = None, timeout_in_minutes = 20)\n",
+        "\n",
+        "     # For a more detailed view of current AmlCompute status, use get_status()."
       ]
     },
     {
@@ -207,11 +242,15 @@
         "from azureml.core.runconfig import RunConfiguration\n",
         "from azureml.core.conda_dependencies import CondaDependencies\n",
         "\n",
+        "# create a new RunConfig object\n",
         "conda_run_config = RunConfiguration(framework=\"python\")\n",
         "\n",
-        "conda_run_config.target = dsvm_compute\n",
+        "# Set compute target to AmlCompute\n",
+        "conda_run_config.target = compute_target\n",
+        "conda_run_config.environment.docker.enabled = True\n",
+        "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
         "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
+        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
         "conda_run_config.environment.python.conda_dependencies = cd"
       ]
     },
@@ -257,6 +296,44 @@
         "remote_run"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Pre-process cache cleanup\n",
+        "The preprocess data gets cache at user default file store. When the run is completed the cache can be cleaned by running below cell"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "remote_run.clean_preprocessor_cache()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Cancelling Runs\n",
+        "You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Cancel the ongoing experiment and stop scheduling new iterations.\n",
+        "# remote_run.cancel()\n",
+        "\n",
+        "# Cancel iteration 1 and move onto iteration 2.\n",
+        "# remote_run.cancel_iteration(1)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -376,7 +453,8 @@
       "source": [
         "## Test\n",
         "\n",
-        "#### Load Test Data"
+        "#### Load Test Data\n",
+        "For the test data, it should have the same preparation step as the train data. Otherwise it might get failed at the preprocessing step."
       ]
     },
     {
@@ -385,12 +463,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from sklearn import datasets\n",
-        "\n",
-        "digits = datasets.load_digits()\n",
-        "X_test = digits.data[:10, :]\n",
-        "y_test = digits.target[:10]\n",
-        "images = digits.images[:10]"
+        "dflow_test = dprep.auto_read_file(path='https://dprepdata.blob.core.windows.net/demo/crime0-test.csv').skip(1)\n",
+        "dflow_test = dflow_test.drop_nulls('Primary Type')"
       ]
     },
     {
@@ -398,7 +472,7 @@
       "metadata": {},
       "source": [
         "#### Testing Our Best Fitted Model\n",
-        "We will try to predict 2 digits and see how our model works."
+        "We will use confusion matrix to see how our model works."
       ]
     },
     {
@@ -407,65 +481,19 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "#Randomly select digits and test\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
+        "from pandas_ml import ConfusionMatrix\n",
         "\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[index]\n",
-        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
-        "    fig = plt.figure(1, figsize=(3,3))\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",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Appendix"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
+        "y_test = dflow_test.keep_columns(columns=['Primary Type']).to_pandas_dataframe()\n",
+        "X_test = dflow_test.drop_columns(columns=['Primary Type', 'FBI Code']).to_pandas_dataframe()\n",
         "\n",
-        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# sklearn.digits.data + target\n",
-        "digits_complete = dprep.auto_read_file('https://dprepdata.blob.core.windows.net/automl-notebook-data/digits-complete.csv')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "`digits_complete` (sourced from `sklearn.datasets.load_digits()`) is forked into `dflow_X` to capture all the feature columns and `dflow_y` to capture the label column."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(digits_complete.to_pandas_dataframe().shape)\n",
-        "labels_column = 'Column64'\n",
-        "dflow_X = digits_complete.drop_columns(columns = [labels_column])\n",
-        "dflow_y = digits_complete.keep_columns(columns = [labels_column])"
+        "\n",
+        "ypred = fitted_model.predict(X_test)\n",
+        "\n",
+        "cm = ConfusionMatrix(y_test['Primary Type'], ypred)\n",
+        "\n",
+        "print(cm)\n",
+        "\n",
+        "cm.plot()"
       ]
     }
   ],

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

@@ -9,6 +9,13 @@
         "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/dataprep/auto-ml-dataprep.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -115,23 +122,12 @@
       "outputs": [],
       "source": [
         "# You can use `auto_read_file` which intelligently figures out delimiters and datatypes of a file.\n",
-        "# The data referenced here was pulled from `sklearn.datasets.load_digits()`.\n",
-        "simple_example_data_root = 'https://dprepdata.blob.core.windows.net/automl-notebook-data/'\n",
-        "X = dprep.auto_read_file(simple_example_data_root + 'X.csv').skip(1)  # Remove the header row.\n",
-        "\n",
+        "# The data referenced here was a 1MB simple random sample of the Chicago Crime data into a local temporary directory.\n",
         "# You can also use `read_csv` and `to_*` transformations to read (with overridable delimiter)\n",
         "# and convert column types manually.\n",
-        "# Here we read a comma delimited file and convert all columns to integers.\n",
-        "y = dprep.read_csv(simple_example_data_root + 'y.csv').to_long(dprep.ColumnSelector(term='.*', use_regex = True))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Review the Data Preparation Result\n",
-        "\n",
-        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets."
+        "example_data = 'https://dprepdata.blob.core.windows.net/demo/crime0-random.csv'\n",
+        "dflow = dprep.auto_read_file(example_data).skip(1)  # Remove the header row.\n",
+        "dflow.get_profile()"
       ]
     },
     {
@@ -140,7 +136,30 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "X.skip(1).head(5)"
+        "# As `Primary Type` is our y data, we need to drop the values those are null in this column.\n",
+        "dflow = dflow.drop_nulls('Primary Type')\n",
+        "dflow.head(5)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Review the Data Preparation Result\n",
+        "\n",
+        "You can peek the result of a Dataflow at any range using `skip(i)` and `head(j)`. Doing so evaluates only `j` records for all the steps in the Dataflow, which makes it fast even against large datasets.\n",
+        "\n",
+        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X = dflow.drop_columns(columns=['Primary Type', 'FBI Code'])\n",
+        "y = dflow.keep_columns(columns=['Primary Type'], validate_column_exists=True)"
       ]
     },
     {
@@ -162,9 +181,8 @@
         "    \"iteration_timeout_minutes\" : 10,\n",
         "    \"iterations\" : 2,\n",
         "    \"primary_metric\" : 'AUC_weighted',\n",
-        "    \"preprocess\" : False,\n",
-        "    \"verbosity\" : logging.INFO,\n",
-        "    \"n_cross_validations\": 3\n",
+        "    \"preprocess\" : True,\n",
+        "    \"verbosity\" : logging.INFO\n",
         "}"
       ]
     },
@@ -327,7 +345,8 @@
       "source": [
         "## Test\n",
         "\n",
-        "#### Load Test Data"
+        "#### Load Test Data\n",
+        "For the test data, it should have the same preparation step as the train data. Otherwise it might get failed at the preprocessing step."
       ]
     },
     {
@@ -336,12 +355,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from sklearn import datasets\n",
-        "\n",
-        "digits = datasets.load_digits()\n",
-        "X_test = digits.data[:10, :]\n",
-        "y_test = digits.target[:10]\n",
-        "images = digits.images[:10]"
+        "dflow_test = dprep.auto_read_file(path='https://dprepdata.blob.core.windows.net/demo/crime0-test.csv').skip(1)\n",
+        "dflow_test = dflow_test.drop_nulls('Primary Type')"
       ]
     },
     {
@@ -349,7 +364,7 @@
       "metadata": {},
       "source": [
         "#### Testing Our Best Fitted Model\n",
-        "We will try to predict 2 digits and see how our model works."
+        "We will use confusion matrix to see how our model works."
       ]
     },
     {
@@ -358,65 +373,18 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "#Randomly select digits and test\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
+        "from pandas_ml import ConfusionMatrix\n",
         "\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[index]\n",
-        "    title = \"Label value = %d  Predicted value = %d \" % (label, predicted)\n",
-        "    fig = plt.figure(1, figsize=(3,3))\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",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Appendix"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Capture the `Dataflow` Objects for Later Use in AutoML\n",
+        "y_test = dflow_test.keep_columns(columns=['Primary Type']).to_pandas_dataframe()\n",
+        "X_test = dflow_test.drop_columns(columns=['Primary Type', 'FBI Code']).to_pandas_dataframe()\n",
         "\n",
-        "`Dataflow` objects are immutable and are composed of a list of data preparation steps. A `Dataflow` object can be branched at any point for further usage."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# sklearn.digits.data + target\n",
-        "digits_complete = dprep.auto_read_file('https://dprepdata.blob.core.windows.net/automl-notebook-data/digits-complete.csv')"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "`digits_complete` (sourced from `sklearn.datasets.load_digits()`) is forked into `dflow_X` to capture all the feature columns and `dflow_y` to capture the label column."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "print(digits_complete.to_pandas_dataframe().shape)\n",
-        "labels_column = 'Column64'\n",
-        "dflow_X = digits_complete.drop_columns(columns = [labels_column])\n",
-        "dflow_y = digits_complete.keep_columns(columns = [labels_column])"
+        "ypred = fitted_model.predict(X_test)\n",
+        "\n",
+        "cm = ConfusionMatrix(y_test['Primary Type'], ypred)\n",
+        "\n",
+        "print(cm)\n",
+        "\n",
+        "cm.plot()"
       ]
     }
   ],

how-to-use-azureml/automated-machine-learning/exploring-previous-runs/auto-ml-exploring-previous-runs.ipynb

@@ -9,6 +9,13 @@
         "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/exploring-previous-runs/auto-ml-exploring-previous-runs.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -0,0 +1,499 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Copyright (c) Microsoft Corporation. All rights reserved.\n",
+        "\n",
+        "Licensed under the MIT License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-bike-share/auto-ml-forecasting-bike-share.png)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Automated Machine Learning\n",
+        "**BikeShare Demand Forecasting**\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",
+        "In this example, we show how AutoML can be used for bike share forecasting.\n",
+        "\n",
+        "The purpose is to demonstrate how to take advantage of the built-in holiday featurization, access the feature names, and further demonstrate how to work 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",
+        "\n",
+        "In this notebook you would see\n",
+        "1. Creating an Experiment in an existing Workspace\n",
+        "2. Instantiating AutoMLConfig with new task type \"forecasting\" for timeseries data training, and other timeseries related settings: for this dataset we use the basic one: \"time_column_name\" \n",
+        "3. Training the Model using local compute\n",
+        "4. Exploring the results\n",
+        "5. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
+        "6. Testing the fitted model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Setup\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import azureml.core\n",
+        "import pandas as pd\n",
+        "import numpy as np\n",
+        "import logging\n",
+        "import warnings\n",
+        "# Squash warning messages for cleaner output in the notebook\n",
+        "warnings.showwarning = lambda *args, **kwargs: None\n",
+        "\n",
+        "from azureml.core.workspace import Workspace\n",
+        "from azureml.core.experiment import Experiment\n",
+        "from azureml.train.automl import AutoMLConfig\n",
+        "from matplotlib import pyplot as plt\n",
+        "from sklearn.metrics import mean_absolute_error, mean_squared_error"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "ws = Workspace.from_config()\n",
+        "\n",
+        "# choose a name for the run history container in the workspace\n",
+        "experiment_name = 'automl-bikeshareforecasting'\n",
+        "# project folder\n",
+        "project_folder = './sample_projects/automl-local-bikeshareforecasting'\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "\n",
+        "output = {}\n",
+        "output['SDK version'] = azureml.core.VERSION\n",
+        "output['Subscription ID'] = ws.subscription_id\n",
+        "output['Workspace'] = ws.name\n",
+        "output['Resource Group'] = ws.resource_group\n",
+        "output['Location'] = ws.location\n",
+        "output['Project Directory'] = project_folder\n",
+        "output['Run History Name'] = experiment_name\n",
+        "pd.set_option('display.max_colwidth', -1)\n",
+        "outputDf = pd.DataFrame(data = output, index = [''])\n",
+        "outputDf.T"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Data\n",
+        "Read bike share demand data from file, and preview data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "data = pd.read_csv('bike-no.csv', parse_dates=['date'])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Let's set up what we know abou the dataset. \n",
+        "\n",
+        "**Target column** is what we want to forecast.\n",
+        "\n",
+        "**Time column** is the time axis along which to predict.\n",
+        "\n",
+        "**Grain** is another word for an individual time series in your dataset. Grains are identified by values of the columns listed `grain_column_names`, for example \"store\" and \"item\" if your data has multiple time series of sales, one series for each combination of store and item sold.\n",
+        "\n",
+        "This dataset has only one time series. Please see the [orange juice notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales) for an example of a multi-time series dataset."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "target_column_name = 'cnt'\n",
+        "time_column_name = 'date'\n",
+        "grain_column_names = []"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Split the data\n",
+        "\n",
+        "The first split we make is into train and test sets. Note we are splitting on time."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "train = data[data[time_column_name] < '2012-09-01']\n",
+        "test = data[data[time_column_name] >= '2012-09-01']\n",
+        "\n",
+        "X_train = train.copy()\n",
+        "y_train = X_train.pop(target_column_name).values\n",
+        "\n",
+        "X_test = test.copy()\n",
+        "y_test = X_test.pop(target_column_name).values\n",
+        "\n",
+        "print(X_train.shape)\n",
+        "print(y_train.shape)\n",
+        "print(X_test.shape)\n",
+        "print(y_test.shape)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Setting forecaster maximum horizon \n",
+        "\n",
+        "Assuming your test data forms a full and regular time series(regular time intervals and no holes), \n",
+        "the maximum horizon you will need to forecast is the length of the longest grain in your test set."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "if len(grain_column_names) == 0:\n",
+        "    max_horizon = len(X_test)\n",
+        "else:\n",
+        "    max_horizon = X_test.groupby(grain_column_names)[time_column_name].count().max()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Train\n",
+        "\n",
+        "Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
+        "\n",
+        "|Property|Description|\n",
+        "|-|-|\n",
+        "|**task**|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",
+        "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
+        "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\n",
+        "|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\n",
+        "|**country_or_region**|The country/region used to generate holiday features. These should be ISO 3166 two-letter country/region codes (i.e. 'US', 'GB').|\n",
+        "|**path**|Relative path to the project folder.  AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "time_column_name = 'date'\n",
+        "automl_settings = {\n",
+        "    \"time_column_name\": time_column_name,\n",
+        "    # these columns are a breakdown of the total and therefore a leak\n",
+        "    \"drop_column_names\": ['casual', 'registered'],\n",
+        "    # knowing the country/region allows Automated ML to bring in holidays\n",
+        "    \"country_or_region\" : 'US',\n",
+        "    \"max_horizon\" : max_horizon,\n",
+        "    \"target_lags\": 1    \n",
+        "}\n",
+        "\n",
+        "automl_config = AutoMLConfig(task = 'forecasting',                             \n",
+        "                             primary_metric='normalized_root_mean_squared_error',\n",
+        "                             iterations = 10,\n",
+        "                             iteration_timeout_minutes = 5,\n",
+        "                             X = X_train,\n",
+        "                             y = y_train,\n",
+        "                             n_cross_validations = 3,                             \n",
+        "                             path=project_folder,\n",
+        "                             verbosity = logging.INFO,\n",
+        "                            **automl_settings)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "We will now run the experiment, starting with 10 iterations of model search. Experiment can be continued for more iterations if the results are not yet good. You will see the currently running iterations printing to the console."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run = experiment.submit(automl_config, show_output=True)"
+      ]
+    },
+    {
+      "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": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Retrieve the Best Model\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 fit invocation. There are overloads on get_output that allow you to retrieve the best run and fitted model for any logged metric or a particular iteration."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run, fitted_model = local_run.get_output()\n",
+        "fitted_model.steps"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### View the engineered names for featurized data\n",
+        "\n",
+        "You can accees the engineered feature names generated in time-series featurization. Note that a number of named holiday periods are represented. We recommend that you have at least one year of data when using this feature to ensure that all yearly holidays are captured in the training featurization."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "fitted_model.named_steps['timeseriestransformer'].get_engineered_feature_names()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### View the featurization summary\n",
+        "\n",
+        "You can also see what featurization steps were performed on different raw features in the user data. For each raw feature in the user data, the following information is displayed:\n",
+        "\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": [
+        "fitted_model.named_steps['timeseriestransformer'].get_featurization_summary()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Test the Best Fitted Model\n",
+        "\n",
+        "Predict on training and test set, and calculate residual values.\n",
+        "\n",
+        "We always score on the original dataset whose schema matches the scheme of the training dataset."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_test.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "y_query = y_test.copy().astype(np.float)\n",
+        "y_query.fill(np.NaN)\n",
+        "y_fcst, X_trans = fitted_model.forecast(X_test, y_query)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "It is a good practice to always align the output explicitly to the input, as the count and order of the rows may have changed during transformations that span multiple rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name = 'predicted'):\n",
+        "    \"\"\"\n",
+        "    Demonstrates how to get the output aligned to the inputs\n",
+        "    using pandas indexes. Helps understand what happened if\n",
+        "    the output's shape differs from the input shape, or if\n",
+        "    the data got re-sorted by time and grain during forecasting.\n",
+        "    \n",
+        "    Typical causes of misalignment are:\n",
+        "    * we predicted some periods that were missing in actuals -> drop from eval\n",
+        "    * model was asked to predict past max_horizon -> increase max horizon\n",
+        "    * data at start of X_test was needed for lags -> provide previous periods\n",
+        "    \"\"\"\n",
+        "    df_fcst = pd.DataFrame({predicted_column_name : y_predicted})\n",
+        "    # y and X outputs are aligned by forecast() function contract\n",
+        "    df_fcst.index = X_trans.index\n",
+        "    \n",
+        "    # align original X_test to y_test    \n",
+        "    X_test_full = X_test.copy()\n",
+        "    X_test_full[target_column_name] = y_test\n",
+        "\n",
+        "    # X_test_full's index does not include origin, so reset for merge\n",
+        "    df_fcst.reset_index(inplace=True)\n",
+        "    X_test_full = X_test_full.reset_index().drop(columns='index')\n",
+        "    together = df_fcst.merge(X_test_full, how='right')\n",
+        "    \n",
+        "    # drop rows where prediction or actuals are nan \n",
+        "    # happens because of missing actuals \n",
+        "    # or at edges of time due to lags/rolling windows\n",
+        "    clean = together[together[[target_column_name, predicted_column_name]].notnull().all(axis=1)]\n",
+        "    return(clean)\n",
+        "\n",
+        "df_all = align_outputs(y_fcst, X_trans, X_test, y_test)\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def MAPE(actual, pred):\n",
+        "    \"\"\"\n",
+        "    Calculate mean absolute percentage error.\n",
+        "    Remove NA and values where actual is close to zero\n",
+        "    \"\"\"\n",
+        "    not_na = ~(np.isnan(actual) | np.isnan(pred))\n",
+        "    not_zero = ~np.isclose(actual, 0.0)\n",
+        "    actual_safe = actual[not_na & not_zero]\n",
+        "    pred_safe = pred[not_na & not_zero]\n",
+        "    APE = 100*np.abs((actual_safe - pred_safe)/actual_safe)\n",
+        "    return np.mean(APE)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"Simple forecasting model\")\n",
+        "rmse = np.sqrt(mean_squared_error(df_all[target_column_name], df_all['predicted']))\n",
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % rmse)\n",
+        "mae = mean_absolute_error(df_all[target_column_name], df_all['predicted'])\n",
+        "print('mean_absolute_error score: %.2f' % mae)\n",
+        "print('MAPE: %.2f' % MAPE(df_all[target_column_name], df_all['predicted']))\n",
+        "\n",
+        "# Plot outputs\n",
+        "%matplotlib notebook\n",
+        "test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], 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()"
+      ]
+    }
+  ],
+  "metadata": {
+    "authors": [
+      {
+        "name": "xiaga@microsoft.com, tosingli@microsoft.com"
+      }
+    ],
+    "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"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

how-to-use-azureml/automated-machine-learning/forecasting-bike-share/bike-no.csv

@@ -0,0 +1,732 @@
+instant,date,season,yr,mnth,weekday,weathersit,temp,atemp,hum,windspeed,casual,registered,cnt
+1,1/1/2011,1,0,1,6,2,0.344167,0.363625,0.805833,0.160446,331,654,985
+2,1/2/2011,1,0,1,0,2,0.363478,0.353739,0.696087,0.248539,131,670,801
+3,1/3/2011,1,0,1,1,1,0.196364,0.189405,0.437273,0.248309,120,1229,1349
+4,1/4/2011,1,0,1,2,1,0.2,0.212122,0.590435,0.160296,108,1454,1562
+5,1/5/2011,1,0,1,3,1,0.226957,0.22927,0.436957,0.1869,82,1518,1600
+6,1/6/2011,1,0,1,4,1,0.204348,0.233209,0.518261,0.0895652,88,1518,1606
+7,1/7/2011,1,0,1,5,2,0.196522,0.208839,0.498696,0.168726,148,1362,1510
+8,1/8/2011,1,0,1,6,2,0.165,0.162254,0.535833,0.266804,68,891,959
+9,1/9/2011,1,0,1,0,1,0.138333,0.116175,0.434167,0.36195,54,768,822
+10,1/10/2011,1,0,1,1,1,0.150833,0.150888,0.482917,0.223267,41,1280,1321
+11,1/11/2011,1,0,1,2,2,0.169091,0.191464,0.686364,0.122132,43,1220,1263
+12,1/12/2011,1,0,1,3,1,0.172727,0.160473,0.599545,0.304627,25,1137,1162
+13,1/13/2011,1,0,1,4,1,0.165,0.150883,0.470417,0.301,38,1368,1406
+14,1/14/2011,1,0,1,5,1,0.16087,0.188413,0.537826,0.126548,54,1367,1421
+15,1/15/2011,1,0,1,6,2,0.233333,0.248112,0.49875,0.157963,222,1026,1248
+16,1/16/2011,1,0,1,0,1,0.231667,0.234217,0.48375,0.188433,251,953,1204
+17,1/17/2011,1,0,1,1,2,0.175833,0.176771,0.5375,0.194017,117,883,1000
+18,1/18/2011,1,0,1,2,2,0.216667,0.232333,0.861667,0.146775,9,674,683
+19,1/19/2011,1,0,1,3,2,0.292174,0.298422,0.741739,0.208317,78,1572,1650
+20,1/20/2011,1,0,1,4,2,0.261667,0.25505,0.538333,0.195904,83,1844,1927
+21,1/21/2011,1,0,1,5,1,0.1775,0.157833,0.457083,0.353242,75,1468,1543
+22,1/22/2011,1,0,1,6,1,0.0591304,0.0790696,0.4,0.17197,93,888,981
+23,1/23/2011,1,0,1,0,1,0.0965217,0.0988391,0.436522,0.2466,150,836,986
+24,1/24/2011,1,0,1,1,1,0.0973913,0.11793,0.491739,0.15833,86,1330,1416
+25,1/25/2011,1,0,1,2,2,0.223478,0.234526,0.616957,0.129796,186,1799,1985
+26,1/26/2011,1,0,1,3,3,0.2175,0.2036,0.8625,0.29385,34,472,506
+27,1/27/2011,1,0,1,4,1,0.195,0.2197,0.6875,0.113837,15,416,431
+28,1/28/2011,1,0,1,5,2,0.203478,0.223317,0.793043,0.1233,38,1129,1167
+29,1/29/2011,1,0,1,6,1,0.196522,0.212126,0.651739,0.145365,123,975,1098
+30,1/30/2011,1,0,1,0,1,0.216522,0.250322,0.722174,0.0739826,140,956,1096
+31,1/31/2011,1,0,1,1,2,0.180833,0.18625,0.60375,0.187192,42,1459,1501
+32,2/1/2011,1,0,2,2,2,0.192174,0.23453,0.829565,0.053213,47,1313,1360
+33,2/2/2011,1,0,2,3,2,0.26,0.254417,0.775417,0.264308,72,1454,1526
+34,2/3/2011,1,0,2,4,1,0.186957,0.177878,0.437826,0.277752,61,1489,1550
+35,2/4/2011,1,0,2,5,2,0.211304,0.228587,0.585217,0.127839,88,1620,1708
+36,2/5/2011,1,0,2,6,2,0.233333,0.243058,0.929167,0.161079,100,905,1005
+37,2/6/2011,1,0,2,0,1,0.285833,0.291671,0.568333,0.1418,354,1269,1623
+38,2/7/2011,1,0,2,1,1,0.271667,0.303658,0.738333,0.0454083,120,1592,1712
+39,2/8/2011,1,0,2,2,1,0.220833,0.198246,0.537917,0.36195,64,1466,1530
+40,2/9/2011,1,0,2,3,2,0.134783,0.144283,0.494783,0.188839,53,1552,1605
+41,2/10/2011,1,0,2,4,1,0.144348,0.149548,0.437391,0.221935,47,1491,1538
+42,2/11/2011,1,0,2,5,1,0.189091,0.213509,0.506364,0.10855,149,1597,1746
+43,2/12/2011,1,0,2,6,1,0.2225,0.232954,0.544167,0.203367,288,1184,1472
+44,2/13/2011,1,0,2,0,1,0.316522,0.324113,0.457391,0.260883,397,1192,1589
+45,2/14/2011,1,0,2,1,1,0.415,0.39835,0.375833,0.417908,208,1705,1913
+46,2/15/2011,1,0,2,2,1,0.266087,0.254274,0.314348,0.291374,140,1675,1815
+47,2/16/2011,1,0,2,3,1,0.318261,0.3162,0.423478,0.251791,218,1897,2115
+48,2/17/2011,1,0,2,4,1,0.435833,0.428658,0.505,0.230104,259,2216,2475
+49,2/18/2011,1,0,2,5,1,0.521667,0.511983,0.516667,0.264925,579,2348,2927
+50,2/19/2011,1,0,2,6,1,0.399167,0.391404,0.187917,0.507463,532,1103,1635
+51,2/20/2011,1,0,2,0,1,0.285217,0.27733,0.407826,0.223235,639,1173,1812
+52,2/21/2011,1,0,2,1,2,0.303333,0.284075,0.605,0.307846,195,912,1107
+53,2/22/2011,1,0,2,2,1,0.182222,0.186033,0.577778,0.195683,74,1376,1450
+54,2/23/2011,1,0,2,3,1,0.221739,0.245717,0.423043,0.094113,139,1778,1917
+55,2/24/2011,1,0,2,4,2,0.295652,0.289191,0.697391,0.250496,100,1707,1807
+56,2/25/2011,1,0,2,5,2,0.364348,0.350461,0.712174,0.346539,120,1341,1461
+57,2/26/2011,1,0,2,6,1,0.2825,0.282192,0.537917,0.186571,424,1545,1969
+58,2/27/2011,1,0,2,0,1,0.343478,0.351109,0.68,0.125248,694,1708,2402
+59,2/28/2011,1,0,2,1,2,0.407273,0.400118,0.876364,0.289686,81,1365,1446
+60,3/1/2011,1,0,3,2,1,0.266667,0.263879,0.535,0.216425,137,1714,1851
+61,3/2/2011,1,0,3,3,1,0.335,0.320071,0.449583,0.307833,231,1903,2134
+62,3/3/2011,1,0,3,4,1,0.198333,0.200133,0.318333,0.225754,123,1562,1685
+63,3/4/2011,1,0,3,5,2,0.261667,0.255679,0.610417,0.203346,214,1730,1944
+64,3/5/2011,1,0,3,6,2,0.384167,0.378779,0.789167,0.251871,640,1437,2077
+65,3/6/2011,1,0,3,0,2,0.376522,0.366252,0.948261,0.343287,114,491,605
+66,3/7/2011,1,0,3,1,1,0.261739,0.238461,0.551304,0.341352,244,1628,1872
+67,3/8/2011,1,0,3,2,1,0.2925,0.3024,0.420833,0.12065,316,1817,2133
+68,3/9/2011,1,0,3,3,2,0.295833,0.286608,0.775417,0.22015,191,1700,1891
+69,3/10/2011,1,0,3,4,3,0.389091,0.385668,0,0.261877,46,577,623
+70,3/11/2011,1,0,3,5,2,0.316522,0.305,0.649565,0.23297,247,1730,1977
+71,3/12/2011,1,0,3,6,1,0.329167,0.32575,0.594583,0.220775,724,1408,2132
+72,3/13/2011,1,0,3,0,1,0.384348,0.380091,0.527391,0.270604,982,1435,2417
+73,3/14/2011,1,0,3,1,1,0.325217,0.332,0.496957,0.136926,359,1687,2046
+74,3/15/2011,1,0,3,2,2,0.317391,0.318178,0.655652,0.184309,289,1767,2056
+75,3/16/2011,1,0,3,3,2,0.365217,0.36693,0.776522,0.203117,321,1871,2192
+76,3/17/2011,1,0,3,4,1,0.415,0.410333,0.602917,0.209579,424,2320,2744
+77,3/18/2011,1,0,3,5,1,0.54,0.527009,0.525217,0.231017,884,2355,3239
+78,3/19/2011,1,0,3,6,1,0.4725,0.466525,0.379167,0.368167,1424,1693,3117
+79,3/20/2011,1,0,3,0,1,0.3325,0.32575,0.47375,0.207721,1047,1424,2471
+80,3/21/2011,2,0,3,1,2,0.430435,0.409735,0.737391,0.288783,401,1676,2077
+81,3/22/2011,2,0,3,2,1,0.441667,0.440642,0.624583,0.22575,460,2243,2703
+82,3/23/2011,2,0,3,3,2,0.346957,0.337939,0.839565,0.234261,203,1918,2121
+83,3/24/2011,2,0,3,4,2,0.285,0.270833,0.805833,0.243787,166,1699,1865
+84,3/25/2011,2,0,3,5,1,0.264167,0.256312,0.495,0.230725,300,1910,2210
+85,3/26/2011,2,0,3,6,1,0.265833,0.257571,0.394167,0.209571,981,1515,2496
+86,3/27/2011,2,0,3,0,2,0.253043,0.250339,0.493913,0.1843,472,1221,1693
+87,3/28/2011,2,0,3,1,1,0.264348,0.257574,0.302174,0.212204,222,1806,2028
+88,3/29/2011,2,0,3,2,1,0.3025,0.292908,0.314167,0.226996,317,2108,2425
+89,3/30/2011,2,0,3,3,2,0.3,0.29735,0.646667,0.172888,168,1368,1536
+90,3/31/2011,2,0,3,4,3,0.268333,0.257575,0.918333,0.217646,179,1506,1685
+91,4/1/2011,2,0,4,5,2,0.3,0.283454,0.68625,0.258708,307,1920,2227
+92,4/2/2011,2,0,4,6,2,0.315,0.315637,0.65375,0.197146,898,1354,2252
+93,4/3/2011,2,0,4,0,1,0.378333,0.378767,0.48,0.182213,1651,1598,3249
+94,4/4/2011,2,0,4,1,1,0.573333,0.542929,0.42625,0.385571,734,2381,3115
+95,4/5/2011,2,0,4,2,2,0.414167,0.39835,0.642083,0.388067,167,1628,1795
+96,4/6/2011,2,0,4,3,1,0.390833,0.387608,0.470833,0.263063,413,2395,2808
+97,4/7/2011,2,0,4,4,1,0.4375,0.433696,0.602917,0.162312,571,2570,3141
+98,4/8/2011,2,0,4,5,2,0.335833,0.324479,0.83625,0.226992,172,1299,1471
+99,4/9/2011,2,0,4,6,2,0.3425,0.341529,0.8775,0.133083,879,1576,2455
+100,4/10/2011,2,0,4,0,2,0.426667,0.426737,0.8575,0.146767,1188,1707,2895
+101,4/11/2011,2,0,4,1,2,0.595652,0.565217,0.716956,0.324474,855,2493,3348
+102,4/12/2011,2,0,4,2,2,0.5025,0.493054,0.739167,0.274879,257,1777,2034
+103,4/13/2011,2,0,4,3,2,0.4125,0.417283,0.819167,0.250617,209,1953,2162
+104,4/14/2011,2,0,4,4,1,0.4675,0.462742,0.540417,0.1107,529,2738,3267
+105,4/15/2011,2,0,4,5,1,0.446667,0.441913,0.67125,0.226375,642,2484,3126
+106,4/16/2011,2,0,4,6,3,0.430833,0.425492,0.888333,0.340808,121,674,795
+107,4/17/2011,2,0,4,0,1,0.456667,0.445696,0.479583,0.303496,1558,2186,3744
+108,4/18/2011,2,0,4,1,1,0.5125,0.503146,0.5425,0.163567,669,2760,3429
+109,4/19/2011,2,0,4,2,2,0.505833,0.489258,0.665833,0.157971,409,2795,3204
+110,4/20/2011,2,0,4,3,1,0.595,0.564392,0.614167,0.241925,613,3331,3944
+111,4/21/2011,2,0,4,4,1,0.459167,0.453892,0.407083,0.325258,745,3444,4189
+112,4/22/2011,2,0,4,5,2,0.336667,0.321954,0.729583,0.219521,177,1506,1683
+113,4/23/2011,2,0,4,6,2,0.46,0.450121,0.887917,0.230725,1462,2574,4036
+114,4/24/2011,2,0,4,0,2,0.581667,0.551763,0.810833,0.192175,1710,2481,4191
+115,4/25/2011,2,0,4,1,1,0.606667,0.5745,0.776667,0.185333,773,3300,4073
+116,4/26/2011,2,0,4,2,1,0.631667,0.594083,0.729167,0.3265,678,3722,4400
+117,4/27/2011,2,0,4,3,2,0.62,0.575142,0.835417,0.3122,547,3325,3872
+118,4/28/2011,2,0,4,4,2,0.6175,0.578929,0.700833,0.320908,569,3489,4058
+119,4/29/2011,2,0,4,5,1,0.51,0.497463,0.457083,0.240063,878,3717,4595
+120,4/30/2011,2,0,4,6,1,0.4725,0.464021,0.503333,0.235075,1965,3347,5312
+121,5/1/2011,2,0,5,0,2,0.451667,0.448204,0.762083,0.106354,1138,2213,3351
+122,5/2/2011,2,0,5,1,2,0.549167,0.532833,0.73,0.183454,847,3554,4401
+123,5/3/2011,2,0,5,2,2,0.616667,0.582079,0.697083,0.342667,603,3848,4451
+124,5/4/2011,2,0,5,3,2,0.414167,0.40465,0.737083,0.328996,255,2378,2633
+125,5/5/2011,2,0,5,4,1,0.459167,0.441917,0.444167,0.295392,614,3819,4433
+126,5/6/2011,2,0,5,5,1,0.479167,0.474117,0.59,0.228246,894,3714,4608
+127,5/7/2011,2,0,5,6,1,0.52,0.512621,0.54125,0.16045,1612,3102,4714
+128,5/8/2011,2,0,5,0,1,0.528333,0.518933,0.631667,0.0746375,1401,2932,4333
+129,5/9/2011,2,0,5,1,1,0.5325,0.525246,0.58875,0.176,664,3698,4362
+130,5/10/2011,2,0,5,2,1,0.5325,0.522721,0.489167,0.115671,694,4109,4803
+131,5/11/2011,2,0,5,3,1,0.5425,0.5284,0.632917,0.120642,550,3632,4182
+132,5/12/2011,2,0,5,4,1,0.535,0.523363,0.7475,0.189667,695,4169,4864
+133,5/13/2011,2,0,5,5,2,0.5125,0.4943,0.863333,0.179725,692,3413,4105
+134,5/14/2011,2,0,5,6,2,0.520833,0.500629,0.9225,0.13495,902,2507,3409
+135,5/15/2011,2,0,5,0,2,0.5625,0.536,0.867083,0.152979,1582,2971,4553
+136,5/16/2011,2,0,5,1,1,0.5775,0.550512,0.787917,0.126871,773,3185,3958
+137,5/17/2011,2,0,5,2,2,0.561667,0.538529,0.837917,0.277354,678,3445,4123
+138,5/18/2011,2,0,5,3,2,0.55,0.527158,0.87,0.201492,536,3319,3855
+139,5/19/2011,2,0,5,4,2,0.530833,0.510742,0.829583,0.108213,735,3840,4575
+140,5/20/2011,2,0,5,5,1,0.536667,0.529042,0.719583,0.125013,909,4008,4917
+141,5/21/2011,2,0,5,6,1,0.6025,0.571975,0.626667,0.12065,2258,3547,5805
+142,5/22/2011,2,0,5,0,1,0.604167,0.5745,0.749583,0.148008,1576,3084,4660
+143,5/23/2011,2,0,5,1,2,0.631667,0.590296,0.81,0.233842,836,3438,4274
+144,5/24/2011,2,0,5,2,2,0.66,0.604813,0.740833,0.207092,659,3833,4492
+145,5/25/2011,2,0,5,3,1,0.660833,0.615542,0.69625,0.154233,740,4238,4978
+146,5/26/2011,2,0,5,4,1,0.708333,0.654688,0.6775,0.199642,758,3919,4677
+147,5/27/2011,2,0,5,5,1,0.681667,0.637008,0.65375,0.240679,871,3808,4679
+148,5/28/2011,2,0,5,6,1,0.655833,0.612379,0.729583,0.230092,2001,2757,4758
+149,5/29/2011,2,0,5,0,1,0.6675,0.61555,0.81875,0.213938,2355,2433,4788
+150,5/30/2011,2,0,5,1,1,0.733333,0.671092,0.685,0.131225,1549,2549,4098
+151,5/31/2011,2,0,5,2,1,0.775,0.725383,0.636667,0.111329,673,3309,3982
+152,6/1/2011,2,0,6,3,2,0.764167,0.720967,0.677083,0.207092,513,3461,3974
+153,6/2/2011,2,0,6,4,1,0.715,0.643942,0.305,0.292287,736,4232,4968
+154,6/3/2011,2,0,6,5,1,0.62,0.587133,0.354167,0.253121,898,4414,5312
+155,6/4/2011,2,0,6,6,1,0.635,0.594696,0.45625,0.123142,1869,3473,5342
+156,6/5/2011,2,0,6,0,2,0.648333,0.616804,0.6525,0.138692,1685,3221,4906
+157,6/6/2011,2,0,6,1,1,0.678333,0.621858,0.6,0.121896,673,3875,4548
+158,6/7/2011,2,0,6,2,1,0.7075,0.65595,0.597917,0.187808,763,4070,4833
+159,6/8/2011,2,0,6,3,1,0.775833,0.727279,0.622083,0.136817,676,3725,4401
+160,6/9/2011,2,0,6,4,2,0.808333,0.757579,0.568333,0.149883,563,3352,3915
+161,6/10/2011,2,0,6,5,1,0.755,0.703292,0.605,0.140554,815,3771,4586
+162,6/11/2011,2,0,6,6,1,0.725,0.678038,0.654583,0.15485,1729,3237,4966
+163,6/12/2011,2,0,6,0,1,0.6925,0.643325,0.747917,0.163567,1467,2993,4460
+164,6/13/2011,2,0,6,1,1,0.635,0.601654,0.494583,0.30535,863,4157,5020
+165,6/14/2011,2,0,6,2,1,0.604167,0.591546,0.507083,0.269283,727,4164,4891
+166,6/15/2011,2,0,6,3,1,0.626667,0.587754,0.471667,0.167912,769,4411,5180
+167,6/16/2011,2,0,6,4,2,0.628333,0.595346,0.688333,0.206471,545,3222,3767
+168,6/17/2011,2,0,6,5,1,0.649167,0.600383,0.735833,0.143029,863,3981,4844
+169,6/18/2011,2,0,6,6,1,0.696667,0.643954,0.670417,0.119408,1807,3312,5119
+170,6/19/2011,2,0,6,0,2,0.699167,0.645846,0.666667,0.102,1639,3105,4744
+171,6/20/2011,2,0,6,1,2,0.635,0.595346,0.74625,0.155475,699,3311,4010
+172,6/21/2011,3,0,6,2,2,0.680833,0.637646,0.770417,0.171025,774,4061,4835
+173,6/22/2011,3,0,6,3,1,0.733333,0.693829,0.7075,0.172262,661,3846,4507
+174,6/23/2011,3,0,6,4,2,0.728333,0.693833,0.703333,0.238804,746,4044,4790
+175,6/24/2011,3,0,6,5,1,0.724167,0.656583,0.573333,0.222025,969,4022,4991
+176,6/25/2011,3,0,6,6,1,0.695,0.643313,0.483333,0.209571,1782,3420,5202
+177,6/26/2011,3,0,6,0,1,0.68,0.637629,0.513333,0.0945333,1920,3385,5305
+178,6/27/2011,3,0,6,1,2,0.6825,0.637004,0.658333,0.107588,854,3854,4708
+179,6/28/2011,3,0,6,2,1,0.744167,0.692558,0.634167,0.144283,732,3916,4648
+180,6/29/2011,3,0,6,3,1,0.728333,0.654688,0.497917,0.261821,848,4377,5225
+181,6/30/2011,3,0,6,4,1,0.696667,0.637008,0.434167,0.185312,1027,4488,5515
+182,7/1/2011,3,0,7,5,1,0.7225,0.652162,0.39625,0.102608,1246,4116,5362
+183,7/2/2011,3,0,7,6,1,0.738333,0.667308,0.444583,0.115062,2204,2915,5119
+184,7/3/2011,3,0,7,0,2,0.716667,0.668575,0.6825,0.228858,2282,2367,4649
+185,7/4/2011,3,0,7,1,2,0.726667,0.665417,0.637917,0.0814792,3065,2978,6043
+186,7/5/2011,3,0,7,2,1,0.746667,0.696338,0.590417,0.126258,1031,3634,4665
+187,7/6/2011,3,0,7,3,1,0.72,0.685633,0.743333,0.149883,784,3845,4629
+188,7/7/2011,3,0,7,4,1,0.75,0.686871,0.65125,0.1592,754,3838,4592
+189,7/8/2011,3,0,7,5,2,0.709167,0.670483,0.757917,0.225129,692,3348,4040
+190,7/9/2011,3,0,7,6,1,0.733333,0.664158,0.609167,0.167912,1988,3348,5336
+191,7/10/2011,3,0,7,0,1,0.7475,0.690025,0.578333,0.183471,1743,3138,4881
+192,7/11/2011,3,0,7,1,1,0.7625,0.729804,0.635833,0.282337,723,3363,4086
+193,7/12/2011,3,0,7,2,1,0.794167,0.739275,0.559167,0.200254,662,3596,4258
+194,7/13/2011,3,0,7,3,1,0.746667,0.689404,0.631667,0.146133,748,3594,4342
+195,7/14/2011,3,0,7,4,1,0.680833,0.635104,0.47625,0.240667,888,4196,5084
+196,7/15/2011,3,0,7,5,1,0.663333,0.624371,0.59125,0.182833,1318,4220,5538
+197,7/16/2011,3,0,7,6,1,0.686667,0.638263,0.585,0.208342,2418,3505,5923
+198,7/17/2011,3,0,7,0,1,0.719167,0.669833,0.604167,0.245033,2006,3296,5302
+199,7/18/2011,3,0,7,1,1,0.746667,0.703925,0.65125,0.215804,841,3617,4458
+200,7/19/2011,3,0,7,2,1,0.776667,0.747479,0.650417,0.1306,752,3789,4541
+201,7/20/2011,3,0,7,3,1,0.768333,0.74685,0.707083,0.113817,644,3688,4332
+202,7/21/2011,3,0,7,4,2,0.815,0.826371,0.69125,0.222021,632,3152,3784
+203,7/22/2011,3,0,7,5,1,0.848333,0.840896,0.580417,0.1331,562,2825,3387
+204,7/23/2011,3,0,7,6,1,0.849167,0.804287,0.5,0.131221,987,2298,3285
+205,7/24/2011,3,0,7,0,1,0.83,0.794829,0.550833,0.169171,1050,2556,3606
+206,7/25/2011,3,0,7,1,1,0.743333,0.720958,0.757083,0.0908083,568,3272,3840
+207,7/26/2011,3,0,7,2,1,0.771667,0.696979,0.540833,0.200258,750,3840,4590
+208,7/27/2011,3,0,7,3,1,0.775,0.690667,0.402917,0.183463,755,3901,4656
+209,7/28/2011,3,0,7,4,1,0.779167,0.7399,0.583333,0.178479,606,3784,4390
+210,7/29/2011,3,0,7,5,1,0.838333,0.785967,0.5425,0.174138,670,3176,3846
+211,7/30/2011,3,0,7,6,1,0.804167,0.728537,0.465833,0.168537,1559,2916,4475
+212,7/31/2011,3,0,7,0,1,0.805833,0.729796,0.480833,0.164813,1524,2778,4302
+213,8/1/2011,3,0,8,1,1,0.771667,0.703292,0.550833,0.156717,729,3537,4266
+214,8/2/2011,3,0,8,2,1,0.783333,0.707071,0.49125,0.20585,801,4044,4845
+215,8/3/2011,3,0,8,3,2,0.731667,0.679937,0.6575,0.135583,467,3107,3574
+216,8/4/2011,3,0,8,4,2,0.71,0.664788,0.7575,0.19715,799,3777,4576
+217,8/5/2011,3,0,8,5,1,0.710833,0.656567,0.630833,0.184696,1023,3843,4866
+218,8/6/2011,3,0,8,6,2,0.716667,0.676154,0.755,0.22825,1521,2773,4294
+219,8/7/2011,3,0,8,0,1,0.7425,0.715292,0.752917,0.201487,1298,2487,3785
+220,8/8/2011,3,0,8,1,1,0.765,0.703283,0.592083,0.192175,846,3480,4326
+221,8/9/2011,3,0,8,2,1,0.775,0.724121,0.570417,0.151121,907,3695,4602
+222,8/10/2011,3,0,8,3,1,0.766667,0.684983,0.424167,0.200258,884,3896,4780
+223,8/11/2011,3,0,8,4,1,0.7175,0.651521,0.42375,0.164796,812,3980,4792
+224,8/12/2011,3,0,8,5,1,0.708333,0.654042,0.415,0.125621,1051,3854,4905
+225,8/13/2011,3,0,8,6,2,0.685833,0.645858,0.729583,0.211454,1504,2646,4150
+226,8/14/2011,3,0,8,0,2,0.676667,0.624388,0.8175,0.222633,1338,2482,3820
+227,8/15/2011,3,0,8,1,1,0.665833,0.616167,0.712083,0.208954,775,3563,4338
+228,8/16/2011,3,0,8,2,1,0.700833,0.645837,0.578333,0.236329,721,4004,4725
+229,8/17/2011,3,0,8,3,1,0.723333,0.666671,0.575417,0.143667,668,4026,4694
+230,8/18/2011,3,0,8,4,1,0.711667,0.662258,0.654583,0.233208,639,3166,3805
+231,8/19/2011,3,0,8,5,2,0.685,0.633221,0.722917,0.139308,797,3356,4153
+232,8/20/2011,3,0,8,6,1,0.6975,0.648996,0.674167,0.104467,1914,3277,5191
+233,8/21/2011,3,0,8,0,1,0.710833,0.675525,0.77,0.248754,1249,2624,3873
+234,8/22/2011,3,0,8,1,1,0.691667,0.638254,0.47,0.27675,833,3925,4758
+235,8/23/2011,3,0,8,2,1,0.640833,0.606067,0.455417,0.146763,1281,4614,5895
+236,8/24/2011,3,0,8,3,1,0.673333,0.630692,0.605,0.253108,949,4181,5130
+237,8/25/2011,3,0,8,4,2,0.684167,0.645854,0.771667,0.210833,435,3107,3542
+238,8/26/2011,3,0,8,5,1,0.7,0.659733,0.76125,0.0839625,768,3893,4661
+239,8/27/2011,3,0,8,6,2,0.68,0.635556,0.85,0.375617,226,889,1115
+240,8/28/2011,3,0,8,0,1,0.707059,0.647959,0.561765,0.304659,1415,2919,4334
+241,8/29/2011,3,0,8,1,1,0.636667,0.607958,0.554583,0.159825,729,3905,4634
+242,8/30/2011,3,0,8,2,1,0.639167,0.594704,0.548333,0.125008,775,4429,5204
+243,8/31/2011,3,0,8,3,1,0.656667,0.611121,0.597917,0.0833333,688,4370,5058
+244,9/1/2011,3,0,9,4,1,0.655,0.614921,0.639167,0.141796,783,4332,5115
+245,9/2/2011,3,0,9,5,2,0.643333,0.604808,0.727083,0.139929,875,3852,4727
+246,9/3/2011,3,0,9,6,1,0.669167,0.633213,0.716667,0.185325,1935,2549,4484
+247,9/4/2011,3,0,9,0,1,0.709167,0.665429,0.742083,0.206467,2521,2419,4940
+248,9/5/2011,3,0,9,1,2,0.673333,0.625646,0.790417,0.212696,1236,2115,3351
+249,9/6/2011,3,0,9,2,3,0.54,0.5152,0.886957,0.343943,204,2506,2710
+250,9/7/2011,3,0,9,3,3,0.599167,0.544229,0.917083,0.0970208,118,1878,1996
+251,9/8/2011,3,0,9,4,3,0.633913,0.555361,0.939565,0.192748,153,1689,1842
+252,9/9/2011,3,0,9,5,2,0.65,0.578946,0.897917,0.124379,417,3127,3544
+253,9/10/2011,3,0,9,6,1,0.66,0.607962,0.75375,0.153608,1750,3595,5345
+254,9/11/2011,3,0,9,0,1,0.653333,0.609229,0.71375,0.115054,1633,3413,5046
+255,9/12/2011,3,0,9,1,1,0.644348,0.60213,0.692174,0.088913,690,4023,4713
+256,9/13/2011,3,0,9,2,1,0.650833,0.603554,0.7125,0.141804,701,4062,4763
+257,9/14/2011,3,0,9,3,1,0.673333,0.6269,0.697083,0.1673,647,4138,4785
+258,9/15/2011,3,0,9,4,2,0.5775,0.553671,0.709167,0.271146,428,3231,3659
+259,9/16/2011,3,0,9,5,2,0.469167,0.461475,0.590417,0.164183,742,4018,4760
+260,9/17/2011,3,0,9,6,2,0.491667,0.478512,0.718333,0.189675,1434,3077,4511
+261,9/18/2011,3,0,9,0,1,0.5075,0.490537,0.695,0.178483,1353,2921,4274
+262,9/19/2011,3,0,9,1,2,0.549167,0.529675,0.69,0.151742,691,3848,4539
+263,9/20/2011,3,0,9,2,2,0.561667,0.532217,0.88125,0.134954,438,3203,3641
+264,9/21/2011,3,0,9,3,2,0.595,0.550533,0.9,0.0964042,539,3813,4352
+265,9/22/2011,3,0,9,4,2,0.628333,0.554963,0.902083,0.128125,555,4240,4795
+266,9/23/2011,4,0,9,5,2,0.609167,0.522125,0.9725,0.0783667,258,2137,2395
+267,9/24/2011,4,0,9,6,2,0.606667,0.564412,0.8625,0.0783833,1776,3647,5423
+268,9/25/2011,4,0,9,0,2,0.634167,0.572637,0.845,0.0503792,1544,3466,5010
+269,9/26/2011,4,0,9,1,2,0.649167,0.589042,0.848333,0.1107,684,3946,4630
+270,9/27/2011,4,0,9,2,2,0.636667,0.574525,0.885417,0.118171,477,3643,4120
+271,9/28/2011,4,0,9,3,2,0.635,0.575158,0.84875,0.148629,480,3427,3907
+272,9/29/2011,4,0,9,4,1,0.616667,0.574512,0.699167,0.172883,653,4186,4839
+273,9/30/2011,4,0,9,5,1,0.564167,0.544829,0.6475,0.206475,830,4372,5202
+274,10/1/2011,4,0,10,6,2,0.41,0.412863,0.75375,0.292296,480,1949,2429
+275,10/2/2011,4,0,10,0,2,0.356667,0.345317,0.791667,0.222013,616,2302,2918
+276,10/3/2011,4,0,10,1,2,0.384167,0.392046,0.760833,0.0833458,330,3240,3570
+277,10/4/2011,4,0,10,2,1,0.484167,0.472858,0.71,0.205854,486,3970,4456
+278,10/5/2011,4,0,10,3,1,0.538333,0.527138,0.647917,0.17725,559,4267,4826
+279,10/6/2011,4,0,10,4,1,0.494167,0.480425,0.620833,0.134954,639,4126,4765
+280,10/7/2011,4,0,10,5,1,0.510833,0.504404,0.684167,0.0223917,949,4036,4985
+281,10/8/2011,4,0,10,6,1,0.521667,0.513242,0.70125,0.0454042,2235,3174,5409
+282,10/9/2011,4,0,10,0,1,0.540833,0.523983,0.7275,0.06345,2397,3114,5511
+283,10/10/2011,4,0,10,1,1,0.570833,0.542925,0.73375,0.0423042,1514,3603,5117
+284,10/11/2011,4,0,10,2,2,0.566667,0.546096,0.80875,0.143042,667,3896,4563
+285,10/12/2011,4,0,10,3,3,0.543333,0.517717,0.90625,0.24815,217,2199,2416
+286,10/13/2011,4,0,10,4,2,0.589167,0.551804,0.896667,0.141787,290,2623,2913
+287,10/14/2011,4,0,10,5,2,0.550833,0.529675,0.71625,0.223883,529,3115,3644
+288,10/15/2011,4,0,10,6,1,0.506667,0.498725,0.483333,0.258083,1899,3318,5217
+289,10/16/2011,4,0,10,0,1,0.511667,0.503154,0.486667,0.281717,1748,3293,5041
+290,10/17/2011,4,0,10,1,1,0.534167,0.510725,0.579583,0.175379,713,3857,4570
+291,10/18/2011,4,0,10,2,2,0.5325,0.522721,0.701667,0.110087,637,4111,4748
+292,10/19/2011,4,0,10,3,3,0.541739,0.513848,0.895217,0.243339,254,2170,2424
+293,10/20/2011,4,0,10,4,1,0.475833,0.466525,0.63625,0.422275,471,3724,4195
+294,10/21/2011,4,0,10,5,1,0.4275,0.423596,0.574167,0.221396,676,3628,4304
+295,10/22/2011,4,0,10,6,1,0.4225,0.425492,0.629167,0.0926667,1499,2809,4308
+296,10/23/2011,4,0,10,0,1,0.421667,0.422333,0.74125,0.0995125,1619,2762,4381
+297,10/24/2011,4,0,10,1,1,0.463333,0.457067,0.772083,0.118792,699,3488,4187
+298,10/25/2011,4,0,10,2,1,0.471667,0.463375,0.622917,0.166658,695,3992,4687
+299,10/26/2011,4,0,10,3,2,0.484167,0.472846,0.720417,0.148642,404,3490,3894
+300,10/27/2011,4,0,10,4,2,0.47,0.457046,0.812917,0.197763,240,2419,2659
+301,10/28/2011,4,0,10,5,2,0.330833,0.318812,0.585833,0.229479,456,3291,3747
+302,10/29/2011,4,0,10,6,3,0.254167,0.227913,0.8825,0.351371,57,570,627
+303,10/30/2011,4,0,10,0,1,0.319167,0.321329,0.62375,0.176617,885,2446,3331
+304,10/31/2011,4,0,10,1,1,0.34,0.356063,0.703333,0.10635,362,3307,3669
+305,11/1/2011,4,0,11,2,1,0.400833,0.397088,0.68375,0.135571,410,3658,4068
+306,11/2/2011,4,0,11,3,1,0.3775,0.390133,0.71875,0.0820917,370,3816,4186
+307,11/3/2011,4,0,11,4,1,0.408333,0.405921,0.702083,0.136817,318,3656,3974
+308,11/4/2011,4,0,11,5,2,0.403333,0.403392,0.6225,0.271779,470,3576,4046
+309,11/5/2011,4,0,11,6,1,0.326667,0.323854,0.519167,0.189062,1156,2770,3926
+310,11/6/2011,4,0,11,0,1,0.348333,0.362358,0.734583,0.0920542,952,2697,3649
+311,11/7/2011,4,0,11,1,1,0.395,0.400871,0.75875,0.057225,373,3662,4035
+312,11/8/2011,4,0,11,2,1,0.408333,0.412246,0.721667,0.0690375,376,3829,4205
+313,11/9/2011,4,0,11,3,1,0.4,0.409079,0.758333,0.0621958,305,3804,4109
+314,11/10/2011,4,0,11,4,2,0.38,0.373721,0.813333,0.189067,190,2743,2933
+315,11/11/2011,4,0,11,5,1,0.324167,0.306817,0.44625,0.314675,440,2928,3368
+316,11/12/2011,4,0,11,6,1,0.356667,0.357942,0.552917,0.212062,1275,2792,4067
+317,11/13/2011,4,0,11,0,1,0.440833,0.43055,0.458333,0.281721,1004,2713,3717
+318,11/14/2011,4,0,11,1,1,0.53,0.524612,0.587083,0.306596,595,3891,4486
+319,11/15/2011,4,0,11,2,2,0.53,0.507579,0.68875,0.199633,449,3746,4195
+320,11/16/2011,4,0,11,3,3,0.456667,0.451988,0.93,0.136829,145,1672,1817
+321,11/17/2011,4,0,11,4,2,0.341667,0.323221,0.575833,0.305362,139,2914,3053
+322,11/18/2011,4,0,11,5,1,0.274167,0.272721,0.41,0.168533,245,3147,3392
+323,11/19/2011,4,0,11,6,1,0.329167,0.324483,0.502083,0.224496,943,2720,3663
+324,11/20/2011,4,0,11,0,2,0.463333,0.457058,0.684583,0.18595,787,2733,3520
+325,11/21/2011,4,0,11,1,3,0.4475,0.445062,0.91,0.138054,220,2545,2765
+326,11/22/2011,4,0,11,2,3,0.416667,0.421696,0.9625,0.118792,69,1538,1607
+327,11/23/2011,4,0,11,3,2,0.440833,0.430537,0.757917,0.335825,112,2454,2566
+328,11/24/2011,4,0,11,4,1,0.373333,0.372471,0.549167,0.167304,560,935,1495
+329,11/25/2011,4,0,11,5,1,0.375,0.380671,0.64375,0.0988958,1095,1697,2792
+330,11/26/2011,4,0,11,6,1,0.375833,0.385087,0.681667,0.0684208,1249,1819,3068
+331,11/27/2011,4,0,11,0,1,0.459167,0.4558,0.698333,0.208954,810,2261,3071
+332,11/28/2011,4,0,11,1,1,0.503478,0.490122,0.743043,0.142122,253,3614,3867
+333,11/29/2011,4,0,11,2,2,0.458333,0.451375,0.830833,0.258092,96,2818,2914
+334,11/30/2011,4,0,11,3,1,0.325,0.311221,0.613333,0.271158,188,3425,3613
+335,12/1/2011,4,0,12,4,1,0.3125,0.305554,0.524583,0.220158,182,3545,3727
+336,12/2/2011,4,0,12,5,1,0.314167,0.331433,0.625833,0.100754,268,3672,3940
+337,12/3/2011,4,0,12,6,1,0.299167,0.310604,0.612917,0.0957833,706,2908,3614
+338,12/4/2011,4,0,12,0,1,0.330833,0.3491,0.775833,0.0839583,634,2851,3485
+339,12/5/2011,4,0,12,1,2,0.385833,0.393925,0.827083,0.0622083,233,3578,3811
+340,12/6/2011,4,0,12,2,3,0.4625,0.4564,0.949583,0.232583,126,2468,2594
+341,12/7/2011,4,0,12,3,3,0.41,0.400246,0.970417,0.266175,50,655,705
+342,12/8/2011,4,0,12,4,1,0.265833,0.256938,0.58,0.240058,150,3172,3322
+343,12/9/2011,4,0,12,5,1,0.290833,0.317542,0.695833,0.0827167,261,3359,3620
+344,12/10/2011,4,0,12,6,1,0.275,0.266412,0.5075,0.233221,502,2688,3190
+345,12/11/2011,4,0,12,0,1,0.220833,0.253154,0.49,0.0665417,377,2366,2743
+346,12/12/2011,4,0,12,1,1,0.238333,0.270196,0.670833,0.06345,143,3167,3310
+347,12/13/2011,4,0,12,2,1,0.2825,0.301138,0.59,0.14055,155,3368,3523
+348,12/14/2011,4,0,12,3,2,0.3175,0.338362,0.66375,0.0609583,178,3562,3740
+349,12/15/2011,4,0,12,4,2,0.4225,0.412237,0.634167,0.268042,181,3528,3709
+350,12/16/2011,4,0,12,5,2,0.375,0.359825,0.500417,0.260575,178,3399,3577
+351,12/17/2011,4,0,12,6,2,0.258333,0.249371,0.560833,0.243167,275,2464,2739
+352,12/18/2011,4,0,12,0,1,0.238333,0.245579,0.58625,0.169779,220,2211,2431
+353,12/19/2011,4,0,12,1,1,0.276667,0.280933,0.6375,0.172896,260,3143,3403
+354,12/20/2011,4,0,12,2,2,0.385833,0.396454,0.595417,0.0615708,216,3534,3750
+355,12/21/2011,1,0,12,3,2,0.428333,0.428017,0.858333,0.2214,107,2553,2660
+356,12/22/2011,1,0,12,4,2,0.423333,0.426121,0.7575,0.047275,227,2841,3068
+357,12/23/2011,1,0,12,5,1,0.373333,0.377513,0.68625,0.274246,163,2046,2209
+358,12/24/2011,1,0,12,6,1,0.3025,0.299242,0.5425,0.190304,155,856,1011
+359,12/25/2011,1,0,12,0,1,0.274783,0.279961,0.681304,0.155091,303,451,754
+360,12/26/2011,1,0,12,1,1,0.321739,0.315535,0.506957,0.239465,430,887,1317
+361,12/27/2011,1,0,12,2,2,0.325,0.327633,0.7625,0.18845,103,1059,1162
+362,12/28/2011,1,0,12,3,1,0.29913,0.279974,0.503913,0.293961,255,2047,2302
+363,12/29/2011,1,0,12,4,1,0.248333,0.263892,0.574167,0.119412,254,2169,2423
+364,12/30/2011,1,0,12,5,1,0.311667,0.318812,0.636667,0.134337,491,2508,2999
+365,12/31/2011,1,0,12,6,1,0.41,0.414121,0.615833,0.220154,665,1820,2485
+366,1/1/2012,1,1,1,0,1,0.37,0.375621,0.6925,0.192167,686,1608,2294
+367,1/2/2012,1,1,1,1,1,0.273043,0.252304,0.381304,0.329665,244,1707,1951
+368,1/3/2012,1,1,1,2,1,0.15,0.126275,0.44125,0.365671,89,2147,2236
+369,1/4/2012,1,1,1,3,2,0.1075,0.119337,0.414583,0.1847,95,2273,2368
+370,1/5/2012,1,1,1,4,1,0.265833,0.278412,0.524167,0.129987,140,3132,3272
+371,1/6/2012,1,1,1,5,1,0.334167,0.340267,0.542083,0.167908,307,3791,4098
+372,1/7/2012,1,1,1,6,1,0.393333,0.390779,0.531667,0.174758,1070,3451,4521
+373,1/8/2012,1,1,1,0,1,0.3375,0.340258,0.465,0.191542,599,2826,3425
+374,1/9/2012,1,1,1,1,2,0.224167,0.247479,0.701667,0.0989,106,2270,2376
+375,1/10/2012,1,1,1,2,1,0.308696,0.318826,0.646522,0.187552,173,3425,3598
+376,1/11/2012,1,1,1,3,2,0.274167,0.282821,0.8475,0.131221,92,2085,2177
+377,1/12/2012,1,1,1,4,2,0.3825,0.381938,0.802917,0.180967,269,3828,4097
+378,1/13/2012,1,1,1,5,1,0.274167,0.249362,0.5075,0.378108,174,3040,3214
+379,1/14/2012,1,1,1,6,1,0.18,0.183087,0.4575,0.187183,333,2160,2493
+380,1/15/2012,1,1,1,0,1,0.166667,0.161625,0.419167,0.251258,284,2027,2311
+381,1/16/2012,1,1,1,1,1,0.19,0.190663,0.5225,0.231358,217,2081,2298
+382,1/17/2012,1,1,1,2,2,0.373043,0.364278,0.716087,0.34913,127,2808,2935
+383,1/18/2012,1,1,1,3,1,0.303333,0.275254,0.443333,0.415429,109,3267,3376
+384,1/19/2012,1,1,1,4,1,0.19,0.190038,0.4975,0.220158,130,3162,3292
+385,1/20/2012,1,1,1,5,2,0.2175,0.220958,0.45,0.20275,115,3048,3163
+386,1/21/2012,1,1,1,6,2,0.173333,0.174875,0.83125,0.222642,67,1234,1301
+387,1/22/2012,1,1,1,0,2,0.1625,0.16225,0.79625,0.199638,196,1781,1977
+388,1/23/2012,1,1,1,1,2,0.218333,0.243058,0.91125,0.110708,145,2287,2432
+389,1/24/2012,1,1,1,2,1,0.3425,0.349108,0.835833,0.123767,439,3900,4339
+390,1/25/2012,1,1,1,3,1,0.294167,0.294821,0.64375,0.161071,467,3803,4270
+391,1/26/2012,1,1,1,4,2,0.341667,0.35605,0.769583,0.0733958,244,3831,4075
+392,1/27/2012,1,1,1,5,2,0.425,0.415383,0.74125,0.342667,269,3187,3456
+393,1/28/2012,1,1,1,6,1,0.315833,0.326379,0.543333,0.210829,775,3248,4023
+394,1/29/2012,1,1,1,0,1,0.2825,0.272721,0.31125,0.24005,558,2685,3243
+395,1/30/2012,1,1,1,1,1,0.269167,0.262625,0.400833,0.215792,126,3498,3624
+396,1/31/2012,1,1,1,2,1,0.39,0.381317,0.416667,0.261817,324,4185,4509
+397,2/1/2012,1,1,2,3,1,0.469167,0.466538,0.507917,0.189067,304,4275,4579
+398,2/2/2012,1,1,2,4,2,0.399167,0.398971,0.672917,0.187187,190,3571,3761
+399,2/3/2012,1,1,2,5,1,0.313333,0.309346,0.526667,0.178496,310,3841,4151
+400,2/4/2012,1,1,2,6,2,0.264167,0.272725,0.779583,0.121896,384,2448,2832
+401,2/5/2012,1,1,2,0,2,0.265833,0.264521,0.687917,0.175996,318,2629,2947
+402,2/6/2012,1,1,2,1,1,0.282609,0.296426,0.622174,0.1538,206,3578,3784
+403,2/7/2012,1,1,2,2,1,0.354167,0.361104,0.49625,0.147379,199,4176,4375
+404,2/8/2012,1,1,2,3,2,0.256667,0.266421,0.722917,0.133721,109,2693,2802
+405,2/9/2012,1,1,2,4,1,0.265,0.261988,0.562083,0.194037,163,3667,3830
+406,2/10/2012,1,1,2,5,2,0.280833,0.293558,0.54,0.116929,227,3604,3831
+407,2/11/2012,1,1,2,6,3,0.224167,0.210867,0.73125,0.289796,192,1977,2169
+408,2/12/2012,1,1,2,0,1,0.1275,0.101658,0.464583,0.409212,73,1456,1529
+409,2/13/2012,1,1,2,1,1,0.2225,0.227913,0.41125,0.167283,94,3328,3422
+410,2/14/2012,1,1,2,2,2,0.319167,0.333946,0.50875,0.141179,135,3787,3922
+411,2/15/2012,1,1,2,3,1,0.348333,0.351629,0.53125,0.1816,141,4028,4169
+412,2/16/2012,1,1,2,4,2,0.316667,0.330162,0.752917,0.091425,74,2931,3005
+413,2/17/2012,1,1,2,5,1,0.343333,0.351629,0.634583,0.205846,349,3805,4154
+414,2/18/2012,1,1,2,6,1,0.346667,0.355425,0.534583,0.190929,1435,2883,4318
+415,2/19/2012,1,1,2,0,2,0.28,0.265788,0.515833,0.253112,618,2071,2689
+416,2/20/2012,1,1,2,1,1,0.28,0.273391,0.507826,0.229083,502,2627,3129
+417,2/21/2012,1,1,2,2,1,0.287826,0.295113,0.594348,0.205717,163,3614,3777
+418,2/22/2012,1,1,2,3,1,0.395833,0.392667,0.567917,0.234471,394,4379,4773
+419,2/23/2012,1,1,2,4,1,0.454167,0.444446,0.554583,0.190913,516,4546,5062
+420,2/24/2012,1,1,2,5,2,0.4075,0.410971,0.7375,0.237567,246,3241,3487
+421,2/25/2012,1,1,2,6,1,0.290833,0.255675,0.395833,0.421642,317,2415,2732
+422,2/26/2012,1,1,2,0,1,0.279167,0.268308,0.41,0.205229,515,2874,3389
+423,2/27/2012,1,1,2,1,1,0.366667,0.357954,0.490833,0.268033,253,4069,4322
+424,2/28/2012,1,1,2,2,1,0.359167,0.353525,0.395833,0.193417,229,4134,4363
+425,2/29/2012,1,1,2,3,2,0.344348,0.34847,0.804783,0.179117,65,1769,1834
+426,3/1/2012,1,1,3,4,1,0.485833,0.475371,0.615417,0.226987,325,4665,4990
+427,3/2/2012,1,1,3,5,2,0.353333,0.359842,0.657083,0.144904,246,2948,3194
+428,3/3/2012,1,1,3,6,2,0.414167,0.413492,0.62125,0.161079,956,3110,4066
+429,3/4/2012,1,1,3,0,1,0.325833,0.303021,0.403333,0.334571,710,2713,3423
+430,3/5/2012,1,1,3,1,1,0.243333,0.241171,0.50625,0.228858,203,3130,3333
+431,3/6/2012,1,1,3,2,1,0.258333,0.255042,0.456667,0.200875,221,3735,3956
+432,3/7/2012,1,1,3,3,1,0.404167,0.3851,0.513333,0.345779,432,4484,4916
+433,3/8/2012,1,1,3,4,1,0.5275,0.524604,0.5675,0.441563,486,4896,5382
+434,3/9/2012,1,1,3,5,2,0.410833,0.397083,0.407083,0.4148,447,4122,4569
+435,3/10/2012,1,1,3,6,1,0.2875,0.277767,0.350417,0.22575,968,3150,4118
+436,3/11/2012,1,1,3,0,1,0.361739,0.35967,0.476957,0.222587,1658,3253,4911
+437,3/12/2012,1,1,3,1,1,0.466667,0.459592,0.489167,0.207713,838,4460,5298
+438,3/13/2012,1,1,3,2,1,0.565,0.542929,0.6175,0.23695,762,5085,5847
+439,3/14/2012,1,1,3,3,1,0.5725,0.548617,0.507083,0.115062,997,5315,6312
+440,3/15/2012,1,1,3,4,1,0.5575,0.532825,0.579583,0.149883,1005,5187,6192
+441,3/16/2012,1,1,3,5,2,0.435833,0.436229,0.842083,0.113192,548,3830,4378
+442,3/17/2012,1,1,3,6,2,0.514167,0.505046,0.755833,0.110704,3155,4681,7836
+443,3/18/2012,1,1,3,0,2,0.4725,0.464,0.81,0.126883,2207,3685,5892
+444,3/19/2012,1,1,3,1,1,0.545,0.532821,0.72875,0.162317,982,5171,6153
+445,3/20/2012,1,1,3,2,1,0.560833,0.538533,0.807917,0.121271,1051,5042,6093
+446,3/21/2012,2,1,3,3,2,0.531667,0.513258,0.82125,0.0895583,1122,5108,6230
+447,3/22/2012,2,1,3,4,1,0.554167,0.531567,0.83125,0.117562,1334,5537,6871
+448,3/23/2012,2,1,3,5,2,0.601667,0.570067,0.694167,0.1163,2469,5893,8362
+449,3/24/2012,2,1,3,6,2,0.5025,0.486733,0.885417,0.192783,1033,2339,3372
+450,3/25/2012,2,1,3,0,2,0.4375,0.437488,0.880833,0.220775,1532,3464,4996
+451,3/26/2012,2,1,3,1,1,0.445833,0.43875,0.477917,0.386821,795,4763,5558
+452,3/27/2012,2,1,3,2,1,0.323333,0.315654,0.29,0.187192,531,4571,5102
+453,3/28/2012,2,1,3,3,1,0.484167,0.47095,0.48125,0.291671,674,5024,5698
+454,3/29/2012,2,1,3,4,1,0.494167,0.482304,0.439167,0.31965,834,5299,6133
+455,3/30/2012,2,1,3,5,2,0.37,0.375621,0.580833,0.138067,796,4663,5459
+456,3/31/2012,2,1,3,6,2,0.424167,0.421708,0.738333,0.250617,2301,3934,6235
+457,4/1/2012,2,1,4,0,2,0.425833,0.417287,0.67625,0.172267,2347,3694,6041
+458,4/2/2012,2,1,4,1,1,0.433913,0.427513,0.504348,0.312139,1208,4728,5936
+459,4/3/2012,2,1,4,2,1,0.466667,0.461483,0.396667,0.100133,1348,5424,6772
+460,4/4/2012,2,1,4,3,1,0.541667,0.53345,0.469583,0.180975,1058,5378,6436
+461,4/5/2012,2,1,4,4,1,0.435,0.431163,0.374167,0.219529,1192,5265,6457
+462,4/6/2012,2,1,4,5,1,0.403333,0.390767,0.377083,0.300388,1807,4653,6460
+463,4/7/2012,2,1,4,6,1,0.4375,0.426129,0.254167,0.274871,3252,3605,6857
+464,4/8/2012,2,1,4,0,1,0.5,0.492425,0.275833,0.232596,2230,2939,5169
+465,4/9/2012,2,1,4,1,1,0.489167,0.476638,0.3175,0.358196,905,4680,5585
+466,4/10/2012,2,1,4,2,1,0.446667,0.436233,0.435,0.249375,819,5099,5918
+467,4/11/2012,2,1,4,3,1,0.348696,0.337274,0.469565,0.295274,482,4380,4862
+468,4/12/2012,2,1,4,4,1,0.3975,0.387604,0.46625,0.290429,663,4746,5409
+469,4/13/2012,2,1,4,5,1,0.4425,0.431808,0.408333,0.155471,1252,5146,6398
+470,4/14/2012,2,1,4,6,1,0.495,0.487996,0.502917,0.190917,2795,4665,7460
+471,4/15/2012,2,1,4,0,1,0.606667,0.573875,0.507917,0.225129,2846,4286,7132
+472,4/16/2012,2,1,4,1,1,0.664167,0.614925,0.561667,0.284829,1198,5172,6370
+473,4/17/2012,2,1,4,2,1,0.608333,0.598487,0.390417,0.273629,989,5702,6691
+474,4/18/2012,2,1,4,3,2,0.463333,0.457038,0.569167,0.167912,347,4020,4367
+475,4/19/2012,2,1,4,4,1,0.498333,0.493046,0.6125,0.0659292,846,5719,6565
+476,4/20/2012,2,1,4,5,1,0.526667,0.515775,0.694583,0.149871,1340,5950,7290
+477,4/21/2012,2,1,4,6,1,0.57,0.542921,0.682917,0.283587,2541,4083,6624
+478,4/22/2012,2,1,4,0,3,0.396667,0.389504,0.835417,0.344546,120,907,1027
+479,4/23/2012,2,1,4,1,2,0.321667,0.301125,0.766667,0.303496,195,3019,3214
+480,4/24/2012,2,1,4,2,1,0.413333,0.405283,0.454167,0.249383,518,5115,5633
+481,4/25/2012,2,1,4,3,1,0.476667,0.470317,0.427917,0.118792,655,5541,6196
+482,4/26/2012,2,1,4,4,2,0.498333,0.483583,0.756667,0.176625,475,4551,5026
+483,4/27/2012,2,1,4,5,1,0.4575,0.452637,0.400833,0.347633,1014,5219,6233
+484,4/28/2012,2,1,4,6,2,0.376667,0.377504,0.489583,0.129975,1120,3100,4220
+485,4/29/2012,2,1,4,0,1,0.458333,0.450121,0.587083,0.116908,2229,4075,6304
+486,4/30/2012,2,1,4,1,2,0.464167,0.457696,0.57,0.171638,665,4907,5572
+487,5/1/2012,2,1,5,2,2,0.613333,0.577021,0.659583,0.156096,653,5087,5740
+488,5/2/2012,2,1,5,3,1,0.564167,0.537896,0.797083,0.138058,667,5502,6169
+489,5/3/2012,2,1,5,4,2,0.56,0.537242,0.768333,0.133696,764,5657,6421
+490,5/4/2012,2,1,5,5,1,0.6275,0.590917,0.735417,0.162938,1069,5227,6296
+491,5/5/2012,2,1,5,6,2,0.621667,0.584608,0.756667,0.152992,2496,4387,6883
+492,5/6/2012,2,1,5,0,2,0.5625,0.546737,0.74,0.149879,2135,4224,6359
+493,5/7/2012,2,1,5,1,2,0.5375,0.527142,0.664167,0.230721,1008,5265,6273
+494,5/8/2012,2,1,5,2,2,0.581667,0.557471,0.685833,0.296029,738,4990,5728
+495,5/9/2012,2,1,5,3,2,0.575,0.553025,0.744167,0.216412,620,4097,4717
+496,5/10/2012,2,1,5,4,1,0.505833,0.491783,0.552083,0.314063,1026,5546,6572
+497,5/11/2012,2,1,5,5,1,0.533333,0.520833,0.360417,0.236937,1319,5711,7030
+498,5/12/2012,2,1,5,6,1,0.564167,0.544817,0.480417,0.123133,2622,4807,7429
+499,5/13/2012,2,1,5,0,1,0.6125,0.585238,0.57625,0.225117,2172,3946,6118
+500,5/14/2012,2,1,5,1,2,0.573333,0.5499,0.789583,0.212692,342,2501,2843
+501,5/15/2012,2,1,5,2,2,0.611667,0.576404,0.794583,0.147392,625,4490,5115
+502,5/16/2012,2,1,5,3,1,0.636667,0.595975,0.697917,0.122512,991,6433,7424
+503,5/17/2012,2,1,5,4,1,0.593333,0.572613,0.52,0.229475,1242,6142,7384
+504,5/18/2012,2,1,5,5,1,0.564167,0.551121,0.523333,0.136817,1521,6118,7639
+505,5/19/2012,2,1,5,6,1,0.6,0.566908,0.45625,0.083975,3410,4884,8294
+506,5/20/2012,2,1,5,0,1,0.620833,0.583967,0.530417,0.254367,2704,4425,7129
+507,5/21/2012,2,1,5,1,2,0.598333,0.565667,0.81125,0.233204,630,3729,4359
+508,5/22/2012,2,1,5,2,2,0.615,0.580825,0.765833,0.118167,819,5254,6073
+509,5/23/2012,2,1,5,3,2,0.621667,0.584612,0.774583,0.102,766,4494,5260
+510,5/24/2012,2,1,5,4,1,0.655,0.6067,0.716667,0.172896,1059,5711,6770
+511,5/25/2012,2,1,5,5,1,0.68,0.627529,0.747083,0.14055,1417,5317,6734
+512,5/26/2012,2,1,5,6,1,0.6925,0.642696,0.7325,0.198992,2855,3681,6536
+513,5/27/2012,2,1,5,0,1,0.69,0.641425,0.697083,0.215171,3283,3308,6591
+514,5/28/2012,2,1,5,1,1,0.7125,0.6793,0.67625,0.196521,2557,3486,6043
+515,5/29/2012,2,1,5,2,1,0.7225,0.672992,0.684583,0.2954,880,4863,5743
+516,5/30/2012,2,1,5,3,2,0.656667,0.611129,0.67,0.134329,745,6110,6855
+517,5/31/2012,2,1,5,4,1,0.68,0.631329,0.492917,0.195279,1100,6238,7338
+518,6/1/2012,2,1,6,5,2,0.654167,0.607962,0.755417,0.237563,533,3594,4127
+519,6/2/2012,2,1,6,6,1,0.583333,0.566288,0.549167,0.186562,2795,5325,8120
+520,6/3/2012,2,1,6,0,1,0.6025,0.575133,0.493333,0.184087,2494,5147,7641
+521,6/4/2012,2,1,6,1,1,0.5975,0.578283,0.487083,0.284833,1071,5927,6998
+522,6/5/2012,2,1,6,2,2,0.540833,0.525892,0.613333,0.209575,968,6033,7001
+523,6/6/2012,2,1,6,3,1,0.554167,0.542292,0.61125,0.077125,1027,6028,7055
+524,6/7/2012,2,1,6,4,1,0.6025,0.569442,0.567083,0.15735,1038,6456,7494
+525,6/8/2012,2,1,6,5,1,0.649167,0.597862,0.467917,0.175383,1488,6248,7736
+526,6/9/2012,2,1,6,6,1,0.710833,0.648367,0.437083,0.144287,2708,4790,7498
+527,6/10/2012,2,1,6,0,1,0.726667,0.663517,0.538333,0.133721,2224,4374,6598
+528,6/11/2012,2,1,6,1,2,0.720833,0.659721,0.587917,0.207713,1017,5647,6664
+529,6/12/2012,2,1,6,2,2,0.653333,0.597875,0.833333,0.214546,477,4495,4972
+530,6/13/2012,2,1,6,3,1,0.655833,0.611117,0.582083,0.343279,1173,6248,7421
+531,6/14/2012,2,1,6,4,1,0.648333,0.624383,0.569583,0.253733,1180,6183,7363
+532,6/15/2012,2,1,6,5,1,0.639167,0.599754,0.589583,0.176617,1563,6102,7665
+533,6/16/2012,2,1,6,6,1,0.631667,0.594708,0.504167,0.166667,2963,4739,7702
+534,6/17/2012,2,1,6,0,1,0.5925,0.571975,0.59875,0.144904,2634,4344,6978
+535,6/18/2012,2,1,6,1,2,0.568333,0.544842,0.777917,0.174746,653,4446,5099
+536,6/19/2012,2,1,6,2,1,0.688333,0.654692,0.69,0.148017,968,5857,6825
+537,6/20/2012,2,1,6,3,1,0.7825,0.720975,0.592083,0.113812,872,5339,6211
+538,6/21/2012,3,1,6,4,1,0.805833,0.752542,0.567917,0.118787,778,5127,5905
+539,6/22/2012,3,1,6,5,1,0.7775,0.724121,0.57375,0.182842,964,4859,5823
+540,6/23/2012,3,1,6,6,1,0.731667,0.652792,0.534583,0.179721,2657,4801,7458
+541,6/24/2012,3,1,6,0,1,0.743333,0.674254,0.479167,0.145525,2551,4340,6891
+542,6/25/2012,3,1,6,1,1,0.715833,0.654042,0.504167,0.300383,1139,5640,6779
+543,6/26/2012,3,1,6,2,1,0.630833,0.594704,0.373333,0.347642,1077,6365,7442
+544,6/27/2012,3,1,6,3,1,0.6975,0.640792,0.36,0.271775,1077,6258,7335
+545,6/28/2012,3,1,6,4,1,0.749167,0.675512,0.4225,0.17165,921,5958,6879
+546,6/29/2012,3,1,6,5,1,0.834167,0.786613,0.48875,0.165417,829,4634,5463
+547,6/30/2012,3,1,6,6,1,0.765,0.687508,0.60125,0.161071,1455,4232,5687
+548,7/1/2012,3,1,7,0,1,0.815833,0.750629,0.51875,0.168529,1421,4110,5531
+549,7/2/2012,3,1,7,1,1,0.781667,0.702038,0.447083,0.195267,904,5323,6227
+550,7/3/2012,3,1,7,2,1,0.780833,0.70265,0.492083,0.126237,1052,5608,6660
+551,7/4/2012,3,1,7,3,1,0.789167,0.732337,0.53875,0.13495,2562,4841,7403
+552,7/5/2012,3,1,7,4,1,0.8275,0.761367,0.457917,0.194029,1405,4836,6241
+553,7/6/2012,3,1,7,5,1,0.828333,0.752533,0.450833,0.146142,1366,4841,6207
+554,7/7/2012,3,1,7,6,1,0.861667,0.804913,0.492083,0.163554,1448,3392,4840
+555,7/8/2012,3,1,7,0,1,0.8225,0.790396,0.57375,0.125629,1203,3469,4672
+556,7/9/2012,3,1,7,1,2,0.710833,0.654054,0.683333,0.180975,998,5571,6569
+557,7/10/2012,3,1,7,2,2,0.720833,0.664796,0.6675,0.151737,954,5336,6290
+558,7/11/2012,3,1,7,3,1,0.716667,0.650271,0.633333,0.151733,975,6289,7264
+559,7/12/2012,3,1,7,4,1,0.715833,0.654683,0.529583,0.146775,1032,6414,7446
+560,7/13/2012,3,1,7,5,2,0.731667,0.667933,0.485833,0.08085,1511,5988,7499
+561,7/14/2012,3,1,7,6,2,0.703333,0.666042,0.699167,0.143679,2355,4614,6969
+562,7/15/2012,3,1,7,0,1,0.745833,0.705196,0.717917,0.166667,1920,4111,6031
+563,7/16/2012,3,1,7,1,1,0.763333,0.724125,0.645,0.164187,1088,5742,6830
+564,7/17/2012,3,1,7,2,1,0.818333,0.755683,0.505833,0.114429,921,5865,6786
+565,7/18/2012,3,1,7,3,1,0.793333,0.745583,0.577083,0.137442,799,4914,5713
+566,7/19/2012,3,1,7,4,1,0.77,0.714642,0.600417,0.165429,888,5703,6591
+567,7/20/2012,3,1,7,5,2,0.665833,0.613025,0.844167,0.208967,747,5123,5870
+568,7/21/2012,3,1,7,6,3,0.595833,0.549912,0.865417,0.2133,1264,3195,4459
+569,7/22/2012,3,1,7,0,2,0.6675,0.623125,0.7625,0.0939208,2544,4866,7410
+570,7/23/2012,3,1,7,1,1,0.741667,0.690017,0.694167,0.138683,1135,5831,6966
+571,7/24/2012,3,1,7,2,1,0.750833,0.70645,0.655,0.211454,1140,6452,7592
+572,7/25/2012,3,1,7,3,1,0.724167,0.654054,0.45,0.1648,1383,6790,8173
+573,7/26/2012,3,1,7,4,1,0.776667,0.739263,0.596667,0.284813,1036,5825,6861
+574,7/27/2012,3,1,7,5,1,0.781667,0.734217,0.594583,0.152992,1259,5645,6904
+575,7/28/2012,3,1,7,6,1,0.755833,0.697604,0.613333,0.15735,2234,4451,6685
+576,7/29/2012,3,1,7,0,1,0.721667,0.667933,0.62375,0.170396,2153,4444,6597
+577,7/30/2012,3,1,7,1,1,0.730833,0.684987,0.66875,0.153617,1040,6065,7105
+578,7/31/2012,3,1,7,2,1,0.713333,0.662896,0.704167,0.165425,968,6248,7216
+579,8/1/2012,3,1,8,3,1,0.7175,0.667308,0.6775,0.141179,1074,6506,7580
+580,8/2/2012,3,1,8,4,1,0.7525,0.707088,0.659583,0.129354,983,6278,7261
+581,8/3/2012,3,1,8,5,2,0.765833,0.722867,0.6425,0.215792,1328,5847,7175
+582,8/4/2012,3,1,8,6,1,0.793333,0.751267,0.613333,0.257458,2345,4479,6824
+583,8/5/2012,3,1,8,0,1,0.769167,0.731079,0.6525,0.290421,1707,3757,5464
+584,8/6/2012,3,1,8,1,2,0.7525,0.710246,0.654167,0.129354,1233,5780,7013
+585,8/7/2012,3,1,8,2,2,0.735833,0.697621,0.70375,0.116908,1278,5995,7273
+586,8/8/2012,3,1,8,3,2,0.75,0.707717,0.672917,0.1107,1263,6271,7534
+587,8/9/2012,3,1,8,4,1,0.755833,0.699508,0.620417,0.1561,1196,6090,7286
+588,8/10/2012,3,1,8,5,2,0.715833,0.667942,0.715833,0.238813,1065,4721,5786
+589,8/11/2012,3,1,8,6,2,0.6925,0.638267,0.732917,0.206479,2247,4052,6299
+590,8/12/2012,3,1,8,0,1,0.700833,0.644579,0.530417,0.122512,2182,4362,6544
+591,8/13/2012,3,1,8,1,1,0.720833,0.662254,0.545417,0.136212,1207,5676,6883
+592,8/14/2012,3,1,8,2,1,0.726667,0.676779,0.686667,0.169158,1128,5656,6784
+593,8/15/2012,3,1,8,3,1,0.706667,0.654037,0.619583,0.169771,1198,6149,7347
+594,8/16/2012,3,1,8,4,1,0.719167,0.654688,0.519167,0.141796,1338,6267,7605
+595,8/17/2012,3,1,8,5,1,0.723333,0.2424,0.570833,0.231354,1483,5665,7148
+596,8/18/2012,3,1,8,6,1,0.678333,0.618071,0.603333,0.177867,2827,5038,7865
+597,8/19/2012,3,1,8,0,2,0.635833,0.603554,0.711667,0.08645,1208,3341,4549
+598,8/20/2012,3,1,8,1,2,0.635833,0.595967,0.734167,0.129979,1026,5504,6530
+599,8/21/2012,3,1,8,2,1,0.649167,0.601025,0.67375,0.0727708,1081,5925,7006
+600,8/22/2012,3,1,8,3,1,0.6675,0.621854,0.677083,0.0702833,1094,6281,7375
+601,8/23/2012,3,1,8,4,1,0.695833,0.637008,0.635833,0.0845958,1363,6402,7765
+602,8/24/2012,3,1,8,5,2,0.7025,0.6471,0.615,0.0721458,1325,6257,7582
+603,8/25/2012,3,1,8,6,2,0.661667,0.618696,0.712917,0.244408,1829,4224,6053
+604,8/26/2012,3,1,8,0,2,0.653333,0.595996,0.845833,0.228858,1483,3772,5255
+605,8/27/2012,3,1,8,1,1,0.703333,0.654688,0.730417,0.128733,989,5928,6917
+606,8/28/2012,3,1,8,2,1,0.728333,0.66605,0.62,0.190925,935,6105,7040
+607,8/29/2012,3,1,8,3,1,0.685,0.635733,0.552083,0.112562,1177,6520,7697
+608,8/30/2012,3,1,8,4,1,0.706667,0.652779,0.590417,0.0771167,1172,6541,7713
+609,8/31/2012,3,1,8,5,1,0.764167,0.6894,0.5875,0.168533,1433,5917,7350
+610,9/1/2012,3,1,9,6,2,0.753333,0.702654,0.638333,0.113187,2352,3788,6140
+611,9/2/2012,3,1,9,0,2,0.696667,0.649,0.815,0.0640708,2613,3197,5810
+612,9/3/2012,3,1,9,1,1,0.7075,0.661629,0.790833,0.151121,1965,4069,6034
+613,9/4/2012,3,1,9,2,1,0.725833,0.686888,0.755,0.236321,867,5997,6864
+614,9/5/2012,3,1,9,3,1,0.736667,0.708983,0.74125,0.187808,832,6280,7112
+615,9/6/2012,3,1,9,4,2,0.696667,0.655329,0.810417,0.142421,611,5592,6203
+616,9/7/2012,3,1,9,5,1,0.703333,0.657204,0.73625,0.171646,1045,6459,7504
+617,9/8/2012,3,1,9,6,2,0.659167,0.611121,0.799167,0.281104,1557,4419,5976
+618,9/9/2012,3,1,9,0,1,0.61,0.578925,0.5475,0.224496,2570,5657,8227
+619,9/10/2012,3,1,9,1,1,0.583333,0.565654,0.50375,0.258713,1118,6407,7525
+620,9/11/2012,3,1,9,2,1,0.5775,0.554292,0.52,0.0920542,1070,6697,7767
+621,9/12/2012,3,1,9,3,1,0.599167,0.570075,0.577083,0.131846,1050,6820,7870
+622,9/13/2012,3,1,9,4,1,0.6125,0.579558,0.637083,0.0827208,1054,6750,7804
+623,9/14/2012,3,1,9,5,1,0.633333,0.594083,0.6725,0.103863,1379,6630,8009
+624,9/15/2012,3,1,9,6,1,0.608333,0.585867,0.501667,0.247521,3160,5554,8714
+625,9/16/2012,3,1,9,0,1,0.58,0.563125,0.57,0.0901833,2166,5167,7333
+626,9/17/2012,3,1,9,1,2,0.580833,0.55305,0.734583,0.151742,1022,5847,6869
+627,9/18/2012,3,1,9,2,2,0.623333,0.565067,0.8725,0.357587,371,3702,4073
+628,9/19/2012,3,1,9,3,1,0.5525,0.540404,0.536667,0.215175,788,6803,7591
+629,9/20/2012,3,1,9,4,1,0.546667,0.532192,0.618333,0.118167,939,6781,7720
+630,9/21/2012,3,1,9,5,1,0.599167,0.571971,0.66875,0.154229,1250,6917,8167
+631,9/22/2012,3,1,9,6,1,0.65,0.610488,0.646667,0.283583,2512,5883,8395
+632,9/23/2012,4,1,9,0,1,0.529167,0.518933,0.467083,0.223258,2454,5453,7907
+633,9/24/2012,4,1,9,1,1,0.514167,0.502513,0.492917,0.142404,1001,6435,7436
+634,9/25/2012,4,1,9,2,1,0.55,0.544179,0.57,0.236321,845,6693,7538
+635,9/26/2012,4,1,9,3,1,0.635,0.596613,0.630833,0.2444,787,6946,7733
+636,9/27/2012,4,1,9,4,2,0.65,0.607975,0.690833,0.134342,751,6642,7393
+637,9/28/2012,4,1,9,5,2,0.619167,0.585863,0.69,0.164179,1045,6370,7415
+638,9/29/2012,4,1,9,6,1,0.5425,0.530296,0.542917,0.227604,2589,5966,8555
+639,9/30/2012,4,1,9,0,1,0.526667,0.517663,0.583333,0.134958,2015,4874,6889
+640,10/1/2012,4,1,10,1,2,0.520833,0.512,0.649167,0.0908042,763,6015,6778
+641,10/2/2012,4,1,10,2,3,0.590833,0.542333,0.871667,0.104475,315,4324,4639
+642,10/3/2012,4,1,10,3,2,0.6575,0.599133,0.79375,0.0665458,728,6844,7572
+643,10/4/2012,4,1,10,4,2,0.6575,0.607975,0.722917,0.117546,891,6437,7328
+644,10/5/2012,4,1,10,5,1,0.615,0.580187,0.6275,0.10635,1516,6640,8156
+645,10/6/2012,4,1,10,6,1,0.554167,0.538521,0.664167,0.268025,3031,4934,7965
+646,10/7/2012,4,1,10,0,2,0.415833,0.419813,0.708333,0.141162,781,2729,3510
+647,10/8/2012,4,1,10,1,2,0.383333,0.387608,0.709583,0.189679,874,4604,5478
+648,10/9/2012,4,1,10,2,2,0.446667,0.438112,0.761667,0.1903,601,5791,6392
+649,10/10/2012,4,1,10,3,1,0.514167,0.503142,0.630833,0.187821,780,6911,7691
+650,10/11/2012,4,1,10,4,1,0.435,0.431167,0.463333,0.181596,834,6736,7570
+651,10/12/2012,4,1,10,5,1,0.4375,0.433071,0.539167,0.235092,1060,6222,7282
+652,10/13/2012,4,1,10,6,1,0.393333,0.391396,0.494583,0.146142,2252,4857,7109
+653,10/14/2012,4,1,10,0,1,0.521667,0.508204,0.640417,0.278612,2080,4559,6639
+654,10/15/2012,4,1,10,1,2,0.561667,0.53915,0.7075,0.296037,760,5115,5875
+655,10/16/2012,4,1,10,2,1,0.468333,0.460846,0.558333,0.182221,922,6612,7534
+656,10/17/2012,4,1,10,3,1,0.455833,0.450108,0.692917,0.101371,979,6482,7461
+657,10/18/2012,4,1,10,4,2,0.5225,0.512625,0.728333,0.236937,1008,6501,7509
+658,10/19/2012,4,1,10,5,2,0.563333,0.537896,0.815,0.134954,753,4671,5424
+659,10/20/2012,4,1,10,6,1,0.484167,0.472842,0.572917,0.117537,2806,5284,8090
+660,10/21/2012,4,1,10,0,1,0.464167,0.456429,0.51,0.166054,2132,4692,6824
+661,10/22/2012,4,1,10,1,1,0.4875,0.482942,0.568333,0.0814833,830,6228,7058
+662,10/23/2012,4,1,10,2,1,0.544167,0.530304,0.641667,0.0945458,841,6625,7466
+663,10/24/2012,4,1,10,3,1,0.5875,0.558721,0.63625,0.0727792,795,6898,7693
+664,10/25/2012,4,1,10,4,2,0.55,0.529688,0.800417,0.124375,875,6484,7359
+665,10/26/2012,4,1,10,5,2,0.545833,0.52275,0.807083,0.132467,1182,6262,7444
+666,10/27/2012,4,1,10,6,2,0.53,0.515133,0.72,0.235692,2643,5209,7852
+667,10/28/2012,4,1,10,0,2,0.4775,0.467771,0.694583,0.398008,998,3461,4459
+668,10/29/2012,4,1,10,1,3,0.44,0.4394,0.88,0.3582,2,20,22
+669,10/30/2012,4,1,10,2,2,0.318182,0.309909,0.825455,0.213009,87,1009,1096
+670,10/31/2012,4,1,10,3,2,0.3575,0.3611,0.666667,0.166667,419,5147,5566
+671,11/1/2012,4,1,11,4,2,0.365833,0.369942,0.581667,0.157346,466,5520,5986
+672,11/2/2012,4,1,11,5,1,0.355,0.356042,0.522083,0.266175,618,5229,5847
+673,11/3/2012,4,1,11,6,2,0.343333,0.323846,0.49125,0.270529,1029,4109,5138
+674,11/4/2012,4,1,11,0,1,0.325833,0.329538,0.532917,0.179108,1201,3906,5107
+675,11/5/2012,4,1,11,1,1,0.319167,0.308075,0.494167,0.236325,378,4881,5259
+676,11/6/2012,4,1,11,2,1,0.280833,0.281567,0.567083,0.173513,466,5220,5686
+677,11/7/2012,4,1,11,3,2,0.295833,0.274621,0.5475,0.304108,326,4709,5035
+678,11/8/2012,4,1,11,4,1,0.352174,0.341891,0.333478,0.347835,340,4975,5315
+679,11/9/2012,4,1,11,5,1,0.361667,0.355413,0.540833,0.214558,709,5283,5992
+680,11/10/2012,4,1,11,6,1,0.389167,0.393937,0.645417,0.0578458,2090,4446,6536
+681,11/11/2012,4,1,11,0,1,0.420833,0.421713,0.659167,0.1275,2290,4562,6852
+682,11/12/2012,4,1,11,1,1,0.485,0.475383,0.741667,0.173517,1097,5172,6269
+683,11/13/2012,4,1,11,2,2,0.343333,0.323225,0.662917,0.342046,327,3767,4094
+684,11/14/2012,4,1,11,3,1,0.289167,0.281563,0.552083,0.199625,373,5122,5495
+685,11/15/2012,4,1,11,4,2,0.321667,0.324492,0.620417,0.152987,320,5125,5445
+686,11/16/2012,4,1,11,5,1,0.345,0.347204,0.524583,0.171025,484,5214,5698
+687,11/17/2012,4,1,11,6,1,0.325,0.326383,0.545417,0.179729,1313,4316,5629
+688,11/18/2012,4,1,11,0,1,0.3425,0.337746,0.692917,0.227612,922,3747,4669
+689,11/19/2012,4,1,11,1,2,0.380833,0.375621,0.623333,0.235067,449,5050,5499
+690,11/20/2012,4,1,11,2,2,0.374167,0.380667,0.685,0.082725,534,5100,5634
+691,11/21/2012,4,1,11,3,1,0.353333,0.364892,0.61375,0.103246,615,4531,5146
+692,11/22/2012,4,1,11,4,1,0.34,0.350371,0.580417,0.0528708,955,1470,2425
+693,11/23/2012,4,1,11,5,1,0.368333,0.378779,0.56875,0.148021,1603,2307,3910
+694,11/24/2012,4,1,11,6,1,0.278333,0.248742,0.404583,0.376871,532,1745,2277
+695,11/25/2012,4,1,11,0,1,0.245833,0.257583,0.468333,0.1505,309,2115,2424
+696,11/26/2012,4,1,11,1,1,0.313333,0.339004,0.535417,0.04665,337,4750,5087
+697,11/27/2012,4,1,11,2,2,0.291667,0.281558,0.786667,0.237562,123,3836,3959
+698,11/28/2012,4,1,11,3,1,0.296667,0.289762,0.50625,0.210821,198,5062,5260
+699,11/29/2012,4,1,11,4,1,0.28087,0.298422,0.555652,0.115522,243,5080,5323
+700,11/30/2012,4,1,11,5,1,0.298333,0.323867,0.649583,0.0584708,362,5306,5668
+701,12/1/2012,4,1,12,6,2,0.298333,0.316904,0.806667,0.0597042,951,4240,5191
+702,12/2/2012,4,1,12,0,2,0.3475,0.359208,0.823333,0.124379,892,3757,4649
+703,12/3/2012,4,1,12,1,1,0.4525,0.455796,0.7675,0.0827208,555,5679,6234
+704,12/4/2012,4,1,12,2,1,0.475833,0.469054,0.73375,0.174129,551,6055,6606
+705,12/5/2012,4,1,12,3,1,0.438333,0.428012,0.485,0.324021,331,5398,5729
+706,12/6/2012,4,1,12,4,1,0.255833,0.258204,0.50875,0.174754,340,5035,5375
+707,12/7/2012,4,1,12,5,2,0.320833,0.321958,0.764167,0.1306,349,4659,5008
+708,12/8/2012,4,1,12,6,2,0.381667,0.389508,0.91125,0.101379,1153,4429,5582
+709,12/9/2012,4,1,12,0,2,0.384167,0.390146,0.905417,0.157975,441,2787,3228
+710,12/10/2012,4,1,12,1,2,0.435833,0.435575,0.925,0.190308,329,4841,5170
+711,12/11/2012,4,1,12,2,2,0.353333,0.338363,0.596667,0.296037,282,5219,5501
+712,12/12/2012,4,1,12,3,2,0.2975,0.297338,0.538333,0.162937,310,5009,5319
+713,12/13/2012,4,1,12,4,1,0.295833,0.294188,0.485833,0.174129,425,5107,5532
+714,12/14/2012,4,1,12,5,1,0.281667,0.294192,0.642917,0.131229,429,5182,5611
+715,12/15/2012,4,1,12,6,1,0.324167,0.338383,0.650417,0.10635,767,4280,5047
+716,12/16/2012,4,1,12,0,2,0.3625,0.369938,0.83875,0.100742,538,3248,3786
+717,12/17/2012,4,1,12,1,2,0.393333,0.4015,0.907083,0.0982583,212,4373,4585
+718,12/18/2012,4,1,12,2,1,0.410833,0.409708,0.66625,0.221404,433,5124,5557
+719,12/19/2012,4,1,12,3,1,0.3325,0.342162,0.625417,0.184092,333,4934,5267
+720,12/20/2012,4,1,12,4,2,0.33,0.335217,0.667917,0.132463,314,3814,4128
+721,12/21/2012,1,1,12,5,2,0.326667,0.301767,0.556667,0.374383,221,3402,3623
+722,12/22/2012,1,1,12,6,1,0.265833,0.236113,0.44125,0.407346,205,1544,1749
+723,12/23/2012,1,1,12,0,1,0.245833,0.259471,0.515417,0.133083,408,1379,1787
+724,12/24/2012,1,1,12,1,2,0.231304,0.2589,0.791304,0.0772304,174,746,920
+725,12/25/2012,1,1,12,2,2,0.291304,0.294465,0.734783,0.168726,440,573,1013
+726,12/26/2012,1,1,12,3,3,0.243333,0.220333,0.823333,0.316546,9,432,441
+727,12/27/2012,1,1,12,4,2,0.254167,0.226642,0.652917,0.350133,247,1867,2114
+728,12/28/2012,1,1,12,5,2,0.253333,0.255046,0.59,0.155471,644,2451,3095
+729,12/29/2012,1,1,12,6,2,0.253333,0.2424,0.752917,0.124383,159,1182,1341
+730,12/30/2012,1,1,12,0,1,0.255833,0.2317,0.483333,0.350754,364,1432,1796
+731,12/31/2012,1,1,12,1,2,0.215833,0.223487,0.5775,0.154846,439,2290,2729

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

@@ -9,6 +9,13 @@
         "Licensed under the MIT License."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand/auto-ml-forecasting-energy-demand.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -37,7 +44,8 @@
         "2. Instantiating AutoMLConfig with new task type \"forecasting\" for timeseries data training, and other timeseries related settings: for this dataset we use the basic one: \"time_column_name\" \n",
         "3. Training the Model using local compute\n",
         "4. Exploring the results\n",
-        "5. Testing the fitted model"
+        "5. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
+        "6. Testing the fitted model"
       ]
     },
     {
@@ -57,10 +65,6 @@
         "import pandas as pd\n",
         "import numpy as np\n",
         "import logging\n",
-        "import warnings\n",
-        "# Squash warning messages for cleaner output in the notebook\n",
-        "warnings.showwarning = lambda *args, **kwargs: None\n",
-        "\n",
         "\n",
         "from azureml.core.workspace import Workspace\n",
         "from azureml.core.experiment import Experiment\n",
@@ -122,12 +126,22 @@
         "data.head()"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# let's take note of what columns means what in the data\n",
+        "time_column_name = 'timeStamp'\n",
+        "target_column_name = 'demand'"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Split the data to train and test\n",
-        "\n"
+        "### Split the data into train and test sets\n"
       ]
     },
     {
@@ -136,50 +150,10 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "train = data[data['timeStamp'] < '2017-02-01']\n",
-        "test = data[data['timeStamp'] >= '2017-02-01']\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Prepare the test data, we will feed X_test to the fitted model and get prediction"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "y_test = test.pop('demand').values\n",
-        "X_test = test"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Split the train data to train and valid\n",
-        "\n",
-        "Use one month's data as valid data\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "X_train = train[train['timeStamp'] < '2017-01-01']\n",
-        "X_valid = train[train['timeStamp'] >= '2017-01-01']\n",
-        "y_train = X_train.pop('demand').values\n",
-        "y_valid = X_valid.pop('demand').values\n",
-        "print(X_train.shape)\n",
-        "print(y_train.shape)\n",
-        "print(X_valid.shape)\n",
-        "print(y_valid.shape)"
+        "X_train = data[data[time_column_name] < '2017-02-01']\n",
+        "X_test = data[data[time_column_name] >= '2017-02-01']\n",
+        "y_train = X_train.pop(target_column_name).values\n",
+        "y_test = X_test.pop(target_column_name).values"
       ]
     },
     {
@@ -197,9 +171,8 @@
         "|**iterations**|Number of iterations. In each iteration, Auto ML trains a specific pipeline on the given data|\n",
         "|**iteration_timeout_minutes**|Time limit in minutes for each iteration.|\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",
-        "|**X_valid**|Data used to evaluate a model in a iteration. (sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y_valid**|Data used to evaluate a model in a iteration. (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",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\n",
+        "|**n_cross_validations**|Number of cross validation splits.|\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. "
       ]
     },
@@ -209,9 +182,8 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "time_column_name = 'timeStamp'\n",
         "automl_settings = {\n",
-        "    \"time_column_name\": time_column_name,\n",
+        "    \"time_column_name\": time_column_name    \n",
         "}\n",
         "\n",
         "\n",
@@ -222,8 +194,7 @@
         "                             iteration_timeout_minutes = 5,\n",
         "                             X = X_train,\n",
         "                             y = y_train,\n",
-        "                             X_valid = X_valid,\n",
-        "                             y_valid = y_valid,\n",
+        "                             n_cross_validations = 3,\n",
         "                             path=project_folder,\n",
         "                             verbosity = logging.INFO,\n",
         "                            **automl_settings)"
@@ -233,7 +204,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
+        "Submitting the configuration will start a new run in this experiment. For local runs, the execution is synchronous. Depending on the data and number of iterations, this can run for a while. Parameters controlling concurrency may speed up the process, depending on your hardware.\n",
+        "\n",
         "You will see the currently running iterations printing to the console."
       ]
     },
@@ -273,13 +245,34 @@
         "fitted_model.steps"
       ]
     },
+    {
+      "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 time-series featurization."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "fitted_model.named_steps['timeseriestransformer'].get_engineered_feature_names()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
         "### Test the Best Fitted Model\n",
         "\n",
-        "Predict on training and test set, and calculate residual values."
+        "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 `X`. In our case, the test data immediately follows the training data, and we fill the `y` 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."
       ]
     },
     {
@@ -288,15 +281,64 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "y_pred = fitted_model.predict(X_test)\n",
-        "y_pred"
+        "# Replace ALL values in y_pred 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_fcst, X_trans = fitted_model.forecast(X_test, y_query)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# limit the evaluation to data where y_test has actuals\n",
+        "def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name = 'predicted'):\n",
+        "    \"\"\"\n",
+        "    Demonstrates how to get the output aligned to the inputs\n",
+        "    using pandas indexes. Helps understand what happened if\n",
+        "    the output's shape differs from the input shape, or if\n",
+        "    the data got re-sorted by time and grain during forecasting.\n",
+        "    \n",
+        "    Typical causes of misalignment are:\n",
+        "    * we predicted some periods that were missing in actuals -> drop from eval\n",
+        "    * model was asked to predict past max_horizon -> increase max horizon\n",
+        "    * data at start of X_test was needed for lags -> provide previous periods\n",
+        "    \"\"\"\n",
+        "    df_fcst = pd.DataFrame({predicted_column_name : y_predicted})\n",
+        "    # y and X outputs are aligned by forecast() function contract\n",
+        "    df_fcst.index = X_trans.index\n",
+        "    \n",
+        "    # align original X_test to y_test    \n",
+        "    X_test_full = X_test.copy()\n",
+        "    X_test_full[target_column_name] = y_test\n",
+        "\n",
+        "    # X_test_full's does not include origin, so reset for merge\n",
+        "    df_fcst.reset_index(inplace=True)\n",
+        "    X_test_full = X_test_full.reset_index().drop(columns='index')\n",
+        "    together = df_fcst.merge(X_test_full, how='right')\n",
+        "    \n",
+        "    # drop rows where prediction or actuals are nan \n",
+        "    # happens because of missing actuals \n",
+        "    # or at edges of time due to lags/rolling windows\n",
+        "    clean = together[together[[target_column_name, predicted_column_name]].notnull().all(axis=1)]\n",
+        "    return(clean)\n",
+        "\n",
+        "df_all = align_outputs(y_fcst, X_trans, X_test, y_test)\n",
+        "df_all.head()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Use the Check Data Function to remove the nan values from y_test to avoid error when calculate metrics "
+        "Looking at `X_trans` is also useful to see what featurization happened to the data."
       ]
     },
     {
@@ -305,29 +347,14 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "if len(y_test) != len(y_pred):\n",
-        "    raise ValueError(\n",
-        "        'the true values and prediction values do not have equal length.')\n",
-        "elif len(y_test) == 0:\n",
-        "    raise ValueError(\n",
-        "        'y_true and y_pred are empty.')\n",
-        "\n",
-        "# if there is any non-numeric element in the y_true or y_pred,\n",
-        "# the ValueError exception will be thrown.\n",
-        "y_test_f = np.array(y_test).astype(float)\n",
-        "y_pred_f = np.array(y_pred).astype(float)\n",
-        "\n",
-        "# remove entries both in y_true and y_pred where at least\n",
-        "# one element in y_true or y_pred is missing\n",
-        "y_test = y_test_f[~(np.isnan(y_test_f) | np.isnan(y_pred_f))]\n",
-        "y_pred = y_pred_f[~(np.isnan(y_test_f) | np.isnan(y_pred_f))]"
+        "X_trans"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Calculate metrics for the prediction\n"
+        "### Calculate accuracy metrics\n"
       ]
     },
     {
@@ -336,26 +363,180 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
-        "# Explained variance score: 1 is perfect prediction\n",
-        "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
-        "print('R2 score: %.2f' % r2_score(y_test, y_pred))\n",
-        "\n",
-        "\n",
+        "def MAPE(actual, pred):\n",
+        "    \"\"\"\n",
+        "    Calculate mean absolute percentage error.\n",
+        "    Remove NA and values where actual is close to zero\n",
+        "    \"\"\"\n",
+        "    not_na = ~(np.isnan(actual) | np.isnan(pred))\n",
+        "    not_zero = ~np.isclose(actual, 0.0)\n",
+        "    actual_safe = actual[not_na & not_zero]\n",
+        "    pred_safe = pred[not_na & not_zero]\n",
+        "    APE = 100*np.abs((actual_safe - pred_safe)/actual_safe)\n",
+        "    return np.mean(APE)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"Simple forecasting model\")\n",
+        "rmse = np.sqrt(mean_squared_error(df_all[target_column_name], df_all['predicted']))\n",
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % rmse)\n",
+        "mae = mean_absolute_error(df_all[target_column_name], df_all['predicted'])\n",
+        "print('mean_absolute_error score: %.2f' % mae)\n",
+        "print('MAPE: %.2f' % MAPE(df_all[target_column_name], df_all['predicted']))\n",
         "\n",
         "# Plot outputs\n",
         "%matplotlib notebook\n",
-        "test_pred = plt.scatter(y_test, y_pred, color='b')\n",
+        "test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], 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": [
+        "The distribution looks a little heavy tailed: we underestimate the excursions of the extremes. A normal-quantile transform of the target might help, but let's first try using some past data with the lags and rolling window transforms.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Using lags and rolling window features to improve the forecast"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "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.\n",
+        "\n",
+        "Now that we configured target lags, that is the previous values of the target variables, and the prediction is no longer horizon-less. We therefore must 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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "automl_settings_lags = {\n",
+        "    'time_column_name': time_column_name,\n",
+        "    'target_lags': 1,\n",
+        "    'target_rolling_window_size': 5,\n",
+        "    # you MUST set the max_horizon when using lags and rolling windows\n",
+        "    # it is optional when looking-back features are not used \n",
+        "    'max_horizon': len(y_test), # only one grain\n",
+        "}\n",
+        "\n",
+        "\n",
+        "automl_config_lags = AutoMLConfig(task = 'forecasting',\n",
+        "                             debug_log = 'automl_nyc_energy_errors.log',\n",
+        "                             primary_metric='normalized_root_mean_squared_error',\n",
+        "                             iterations = 10,\n",
+        "                             iteration_timeout_minutes = 5,\n",
+        "                             X = X_train,\n",
+        "                             y = y_train,\n",
+        "                             n_cross_validations = 3,\n",
+        "                             path=project_folder,\n",
+        "                             verbosity = logging.INFO,\n",
+        "                            **automl_settings_lags)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "local_run_lags = experiment.submit(automl_config_lags, show_output=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "best_run_lags, fitted_model_lags = local_run_lags.get_output()\n",
+        "y_fcst_lags, X_trans_lags = fitted_model_lags.forecast(X_test, y_query)\n",
+        "df_lags = align_outputs(y_fcst_lags, X_trans_lags, X_test, y_test)\n",
+        "df_lags.head()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "X_trans_lags"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"Forecasting model with lags\")\n",
+        "rmse = np.sqrt(mean_squared_error(df_lags[target_column_name], df_lags['predicted']))\n",
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % rmse)\n",
+        "mae = mean_absolute_error(df_lags[target_column_name], df_lags['predicted'])\n",
+        "print('mean_absolute_error score: %.2f' % mae)\n",
+        "print('MAPE: %.2f' % MAPE(df_lags[target_column_name], df_lags['predicted']))\n",
+        "\n",
+        "# Plot outputs\n",
+        "%matplotlib notebook\n",
+        "test_pred = plt.scatter(df_lags[target_column_name], df_lags['predicted'], 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": [
+        "### What features matter for the forecast?"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.train.automl.automlexplainer import explain_model\n",
+        "\n",
+        "# feature names are everything in the transformed data except the target\n",
+        "features = X_trans.columns[:-1]\n",
+        "expl = explain_model(fitted_model, X_train, X_test, features = features, best_run=best_run_lags, y_train = y_train)\n",
+        "# unpack the tuple\n",
+        "shap_values, expected_values, feat_overall_imp, feat_names, per_class_summary, per_class_imp = expl\n",
+        "best_run_lags"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Please go to the Azure Portal's best run to see the top features chart.\n",
+        "\n",
+        "The informative features make all sorts of intuitive sense. Temperature is a strong driver of heating and cooling demand in NYC. Apart from that, the daily life cycle, expressed by `hour`, and the weekly cycle, expressed by `wday` drives people's energy use habits."
+      ]
     }
   ],
   "metadata": {
     "authors": [
       {
-        "name": "xiaga"
+        "name": "xiaga, tosingli"
       }
     ],
     "kernelspec": {
@@ -373,7 +554,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.8"
+      "version": "3.6.7"
     }
   },
   "nbformat": 4,

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

@@ -9,6 +9,13 @@
         "Licensed under the MIT License."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "![Impressions](https://PixelServer20190423114238.azurewebsites.net/api/impressions/MachineLearningNotebooks/how-to-use-azureml/automated-machine-learning/forecasting-orange-juice-sales/auto-ml-forecasting-orange-juice-sales.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -20,7 +27,9 @@
         "1. [Introduction](#Introduction)\n",
         "1. [Setup](#Setup)\n",
         "1. [Data](#Data)\n",
-        "1. [Train](#Train)"
+        "1. [Train](#Train)\n",
+        "1. [Predict](#Predict)\n",
+        "1. [Operationalize](#Operationalize)"
       ]
     },
     {
@@ -58,10 +67,6 @@
         "import pandas as pd\n",
         "import numpy as np\n",
         "import logging\n",
-        "import warnings\n",
-        "# Squash warning messages for cleaner output in the notebook\n",
-        "warnings.showwarning = lambda *args, **kwargs: None\n",
-        "\n",
         "\n",
         "from azureml.core.workspace import Workspace\n",
         "from azureml.core.experiment import Experiment\n",
@@ -85,9 +90,9 @@
         "ws = Workspace.from_config()\n",
         "\n",
         "# choose a name for the run history container in the workspace\n",
-        "experiment_name = 'automl-ojsalesforecasting'\n",
+        "experiment_name = 'automl-ojforecasting'\n",
         "# project folder\n",
-        "project_folder = './sample_projects/automl-local-ojsalesforecasting'\n",
+        "project_folder = './sample_projects/automl-local-ojforecasting'\n",
         "\n",
         "experiment = Experiment(ws, experiment_name)\n",
         "\n",
@@ -260,12 +265,12 @@
         "    'time_column_name': time_column_name,\n",
         "    'grain_column_names': grain_column_names,\n",
         "    'drop_column_names': ['logQuantity'],\n",
-        "    'max_horizon': n_test_periods\n",
+        "    'max_horizon': n_test_periods # optional\n",
         "}\n",
         "\n",
         "automl_config = AutoMLConfig(task='forecasting',\n",
         "                             debug_log='automl_oj_sales_errors.log',\n",
-        "                             primary_metric='normalized_root_mean_squared_error',\n",
+        "                             primary_metric='normalized_mean_absolute_error',\n",
         "                             iterations=10,\n",
         "                             X=X_train,\n",
         "                             y=y_train,\n",
@@ -293,15 +298,6 @@
         "local_run = experiment.submit(automl_config, show_output=True)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "local_run"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -324,7 +320,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Make Predictions from the Best Fitted Model\n",
+        "# Predict\n",
         "Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. First, we remove the target values from the test set:"
       ]
     },
@@ -352,7 +348,7 @@
       "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",
-        "The target predictions can be retrieved by calling the `predict` method on the best model:"
+        "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_."
       ]
     },
     {
@@ -361,15 +357,76 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "y_pred = fitted_pipeline.predict(X_test)"
+        "# Replace ALL values in y_pred 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_pred, X_trans = fitted_pipeline.forecast(X_test, y_query)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "### Calculate evaluation metrics for the prediction\n",
-        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE)."
+        "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. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Evaluate\n",
+        "\n",
+        "To evaluate the accuracy of the forecast, we'll compare against the actual sales quantities for some select metrics, included the mean absolute percentage error (MAPE). \n",
+        "\n",
+        "It is a good practice to always align the output explicitly to the input, as the count and order of the rows may have changed during transformations that span multiple rows."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name = 'predicted'):\n",
+        "    \"\"\"\n",
+        "    Demonstrates how to get the output aligned to the inputs\n",
+        "    using pandas indexes. Helps understand what happened if\n",
+        "    the output's shape differs from the input shape, or if\n",
+        "    the data got re-sorted by time and grain during forecasting.\n",
+        "    \n",
+        "    Typical causes of misalignment are:\n",
+        "    * we predicted some periods that were missing in actuals -> drop from eval\n",
+        "    * model was asked to predict past max_horizon -> increase max horizon\n",
+        "    * data at start of X_test was needed for lags -> provide previous periods in y\n",
+        "    \"\"\"\n",
+        "    \n",
+        "    df_fcst = pd.DataFrame({predicted_column_name : y_predicted})\n",
+        "    # y and X outputs are aligned by forecast() function contract\n",
+        "    df_fcst.index = X_trans.index\n",
+        "    \n",
+        "    # align original X_test to y_test    \n",
+        "    X_test_full = X_test.copy()\n",
+        "    X_test_full[target_column_name] = y_test\n",
+        "\n",
+        "    # X_test_full's index does not include origin, so reset for merge\n",
+        "    df_fcst.reset_index(inplace=True)\n",
+        "    X_test_full = X_test_full.reset_index().drop(columns='index')\n",
+        "    together = df_fcst.merge(X_test_full, how='right')\n",
+        "    \n",
+        "    # drop rows where prediction or actuals are nan \n",
+        "    # happens because of missing actuals \n",
+        "    # or at edges of time due to lags/rolling windows\n",
+        "    clean = together[together[[target_column_name, predicted_column_name]].notnull().all(axis=1)]\n",
+        "    return(clean)\n",
+        "\n",
+        "df_all = align_outputs(y_pred, X_trans, X_test, y_test)"
       ]
     },
     {
@@ -388,18 +445,392 @@
         "    actual_safe = actual[not_na & not_zero]\n",
         "    pred_safe = pred[not_na & not_zero]\n",
         "    APE = 100*np.abs((actual_safe - pred_safe)/actual_safe)\n",
-        "    return np.mean(APE)\n",
+        "    return np.mean(APE)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"Simple forecasting model\")\n",
+        "rmse = np.sqrt(mean_squared_error(df_all[target_column_name], df_all['predicted']))\n",
+        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % rmse)\n",
+        "mae = mean_absolute_error(df_all[target_column_name], df_all['predicted'])\n",
+        "print('mean_absolute_error score: %.2f' % mae)\n",
+        "print('MAPE: %.2f' % MAPE(df_all[target_column_name], df_all['predicted']))\n",
         "\n",
-        "print(\"[Test Data] \\nRoot Mean squared error: %.2f\" % np.sqrt(mean_squared_error(y_test, y_pred)))\n",
-        "print('mean_absolute_error score: %.2f' % mean_absolute_error(y_test, y_pred))\n",
-        "print('MAPE: %.2f' % MAPE(y_test, y_pred))"
+        "# Plot outputs\n",
+        "import matplotlib.pyplot as plt\n",
+        "\n",
+        "%matplotlib notebook\n",
+        "test_pred = plt.scatter(df_all[target_column_name], df_all['predicted'], 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": [
+        "# Operationalize"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "_Operationalization_ means getting the model into the cloud so that other can run it after you close the notebook. We will create a docker running on Azure Container Instances with the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "description = 'AutoML OJ forecaster'\n",
+        "tags = None\n",
+        "model = local_run.register_model(description = description, tags = tags)\n",
+        "\n",
+        "print(local_run.model_id)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "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_pipeline)\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",
+        "                      })"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# get the model\n",
+        "from azureml.train.automl.run import AutoMLRun\n",
+        "\n",
+        "experiment = Experiment(ws, experiment_name)\n",
+        "ml_run = AutoMLRun(experiment = experiment, run_id = local_run.id)\n",
+        "best_iteration = int(str.split(best_run.id,'_')[-1])      # the iteration number is a postfix of the run ID."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# get the best model's dependencies and write them into this file\n",
+        "from azureml.core.conda_dependencies import CondaDependencies\n",
+        "\n",
+        "conda_env_file_name = 'fcast_env.yml'\n",
+        "\n",
+        "dependencies = ml_run.get_run_sdk_dependencies(iteration = best_iteration)\n",
+        "for p in ['azureml-train-automl', 'azureml-sdk', 'azureml-core']:\n",
+        "    print('{}\\t{}'.format(p, dependencies[p]))\n",
+        "\n",
+        "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'], pip_packages=['azureml-sdk[automl]'])\n",
+        "\n",
+        "myenv.save_to_file('.', conda_env_file_name)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# this is the script file name we wrote a few cells above\n",
+        "script_file_name = 'score_fcast.py'\n",
+        "\n",
+        "# 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-sdk']))\n",
+        "\n",
+        "# Substitute the actual model id in the script file.\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>>', local_run.model_id))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Create a Container Image"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.image import Image, ContainerImage\n",
+        "\n",
+        "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+        "                                 execution_script = script_file_name,\n",
+        "                                 conda_file = conda_env_file_name,\n",
+        "                                 tags = {'type': \"automl-forecasting\"},\n",
+        "                                 description = \"Image for automl forecasting sample\")\n",
+        "\n",
+        "image = Image.create(name = \"automl-fcast-image\",\n",
+        "                     # this is the model object \n",
+        "                     models = [model],\n",
+        "                     image_config = image_config, \n",
+        "                     workspace = ws)\n",
+        "\n",
+        "image.wait_for_creation(show_output = True)\n",
+        "\n",
+        "if image.creation_state == 'Failed':\n",
+        "    print(\"Image build log at: \" + image.image_build_log_uri)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Deploy the Image as a Web Service on Azure Container Instance"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import AciWebservice\n",
+        "\n",
+        "aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
+        "                                               memory_gb = 2, \n",
+        "                                               tags = {'type': \"automl-forecasting\"},\n",
+        "                                               description = \"Automl forecasting sample service\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from azureml.core.webservice import Webservice\n",
+        "\n",
+        "aci_service_name = 'automl-forecast-01'\n",
+        "print(aci_service_name)\n",
+        "\n",
+        "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+        "                                           image = image,\n",
+        "                                           name = aci_service_name,\n",
+        "                                           workspace = ws)\n",
+        "aci_service.wait_for_deployment(True)\n",
+        "print(aci_service.state)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Call the service"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "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",
+        "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[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",
+        "    print(res_dict)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "y_fcst_all.head()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "### Delete the web service if desired"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "serv = Webservice(ws, 'automl-forecast-01')\n",
+        "# serv.delete()     # don't do it accidentally"
       ]
     }
   ],
   "metadata": {
     "authors": [
       {
-        "name": "erwright"
+        "name": "erwright, tosingli"
       }
     ],
     "kernelspec": {
@@ -417,7 +848,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.6.8"
+      "version": "3.6.7"
     }
   },
   "nbformat": 4,

how-to-use-azureml/automated-machine-learning/missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.ipynb

@@ -9,6 +9,13 @@
         "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/missing-data-blacklist-early-termination/auto-ml-missing-data-blacklist-early-termination.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -37,8 +44,9 @@
         "In this notebook you will learn how to:\n",
         "1. Create an `Experiment` in an existing `Workspace`.\n",
         "2. Configure AutoML using `AutoMLConfig`.\n",
-        "4. Train the model.\n",
-        "5. Explore the results.\n",
+        "3. Train the model.\n",
+        "4. Explore the results.\n",
+        "5. Viewing the engineered names for featurized data and featurization summary for all raw features.\n",
         "6. Test the best fitted model.\n",
         "\n",
         "In addition this notebook showcases the following features\n",
@@ -154,12 +162,11 @@
         "|**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",
         "|**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",
         "|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.|\n",
         "|**experiment_exit_score**|*double* value indicating the target for *primary_metric*. <br>Once the target is surpassed the run terminates.|\n",
         "|**blacklist_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>|\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",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\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.|"
       ]
     },
@@ -174,7 +181,6 @@
         "                             primary_metric = 'AUC_weighted',\n",
         "                             iteration_timeout_minutes = 60,\n",
         "                             iterations = 20,\n",
-        "                             n_cross_validations = 5,\n",
         "                             preprocess = True,\n",
         "                             experiment_exit_score = 0.9984,\n",
         "                             blacklist_models = ['KNN','LinearSVM'],\n",
@@ -318,6 +324,45 @@
         "# best_run, fitted_model = local_run.get_output(iteration = iteration)"
       ]
     },
+    {
+      "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": [
+        "fitted_model.named_steps['datatransformer'].get_featurization_summary()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

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

@@ -9,6 +9,13 @@
         "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/model-explanation/auto-ml-model-explanation.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -140,9 +147,9 @@
         "|**max_time_sec**|Time limit in minutes for each iterations|\n",
         "|**iterations**|Number of iterations. In each iteration Auto ML trains the data with a specific pipeline|\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",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
         "|**X_valid**|(sparse) array-like, shape = [n_samples, n_features]|\n",
-        "|**y_valid**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]|\n",
+        "|**y_valid**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
         "|**model_explainability**|Indicate to explain each trained pipeline or not |\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. |"
       ]
@@ -254,7 +261,9 @@
         "3.\toverall_summary: The model level feature importance values sorted in descending order\n",
         "4.\toverall_imp: The feature names sorted in the same order as in overall_summary\n",
         "5.\tper_class_summary: The class level feature importance values sorted in descending order. Only available for the classification case\n",
-        "6.\tper_class_imp: The feature names sorted in the same order as in per_class_summary. Only available for the classification case"
+        "6.\tper_class_imp: The feature names sorted in the same order as in per_class_summary. Only available for the classification case\n",
+        "\n",
+        "Note:- The **retrieve_model_explanation()** API only works in case AutoML has been configured with **'model_explainability'** flag set to **True**. "
       ]
     },
     {
@@ -305,7 +314,7 @@
         "from azureml.train.automl.automlexplainer import explain_model\n",
         "\n",
         "shap_values, expected_values, overall_summary, overall_imp, per_class_summary, per_class_imp = \\\n",
-        "    explain_model(fitted_model, X_train, X_test)"
+        "    explain_model(fitted_model, X_train, X_test, features=features)"
       ]
     },
     {

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

@@ -0,0 +1,800 @@
+{
+ "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",
+    "from sklearn.model_selection import train_test_split\n",
+    "import azureml.dataprep as dprep\n",
+    " \n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\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 and specify the project folder.\n",
+    "experiment_name = 'automl-regression-concrete'\n",
+    "project_folder = './sample_projects/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['Project Directory'] = project_folder\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",
+    "    # 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",
+    "Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isdir('data'):\n",
+    "    os.mkdir('data')\n",
+    "    \n",
+    "if not os.path.exists(project_folder):\n",
+    "    os.makedirs(project_folder)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\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",
+    "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+    "\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
+    "conda_run_config.environment.python.conda_dependencies = cd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load Data\n",
+    "\n",
+    "Here create the script to be run in azure compute for loading the data, load the concrete strength dataset into the X and y  variables. Next, split the data  using train_test_split and return X_train and y_train for training the model. Finally, return X_train and y_train for training 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",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X = dflow.drop_columns(columns=['CONCRETE'])\n",
+    "y = dflow.keep_columns(columns=['CONCRETE'], validate_column_exists=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",
+    "dflow.head()"
+   ]
+  },
+  {
+   "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",
+    "|**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",
+    "\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",
+    "                             path = project_folder,\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 “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",
+    "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-sdk', 'azureml-core']:\n",
+    "    print('{}\\t{}'.format(p, dependencies[p]))"
+   ]
+  },
+  {
+   "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-sdk[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-sdk']))\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": [
+    "### Create a Container Image\n",
+    "\n",
+    "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+    "or when testing a model that is under development."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.image import Image, ContainerImage\n",
+    "\n",
+    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+    "                                 execution_script = script_file_name,\n",
+    "                                 conda_file = conda_env_file_name,\n",
+    "                                 tags = {'area': \"digits\", 'type': \"automl_regression\"},\n",
+    "                                 description = \"Image for automl regression sample\")\n",
+    "\n",
+    "image = Image.create(name = \"automlsampleimage\",\n",
+    "                     # this is the model object \n",
+    "                     models = [model],\n",
+    "                     image_config = image_config, \n",
+    "                     workspace = ws)\n",
+    "\n",
+    "image.wait_for_creation(show_output = True)\n",
+    "\n",
+    "if image.creation_state == 'Failed':\n",
+    "    print(\"Image build log at: \" + image.image_build_log_uri)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploy the Image as a Web Service on Azure Container Instance\n",
+    "\n",
+    "Deploy an image that contains the model and other assets needed by the service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import AciWebservice\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')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import Webservice\n",
+    "\n",
+    "aci_service_name = 'automl-sample-concrete'\n",
+    "print(aci_service_name)\n",
+    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+    "                                           image = image,\n",
+    "                                           name = aci_service_name,\n",
+    "                                           workspace = ws)\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"
+   }
+  ],
+  "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"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -0,0 +1,800 @@
+{
+ "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",
+    "from sklearn.model_selection import train_test_split\n",
+    "import azureml.dataprep as dprep\n",
+    " \n",
+    "\n",
+    "import azureml.core\n",
+    "from azureml.core.experiment import Experiment\n",
+    "from azureml.core.workspace import Workspace\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 and specify the project folder.\n",
+    "experiment_name = 'automl-regression-hardware'\n",
+    "project_folder = './sample_projects/automl-remote-regression'\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['Project Directory'] = project_folder\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",
+    "    # 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",
+    "Here load the data in the get_data script to be utilized in azure compute. To do this, first load all the necessary libraries and dependencies to set up paths for the data and to create the conda_run_config."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isdir('data'):\n",
+    "    os.mkdir('data')\n",
+    "    \n",
+    "if not os.path.exists(project_folder):\n",
+    "    os.makedirs(project_folder)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.runconfig import RunConfiguration\n",
+    "from azureml.core.conda_dependencies import CondaDependencies\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",
+    "conda_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
+    "\n",
+    "\n",
+    "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
+    "conda_run_config.environment.python.conda_dependencies = cd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load Data\n",
+    "\n",
+    "Here create the script to be run in azure compute for loading the data, load the hardware dataset into the X and y variables. Next split the data  using train_test_split and return X_train and y_train for training 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",
+    "dflow = dprep.auto_read_file(data)\n",
+    "dflow.get_profile()\n",
+    "X = dflow.drop_columns(columns=['ERP'])\n",
+    "y = dflow.keep_columns(columns=['ERP'], validate_column_exists=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",
+    "dflow.head()"
+   ]
+  },
+  {
+   "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",
+    "|**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",
+    "\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_20190417.log',\n",
+    "                             path = project_folder,\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-sdk', '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'], pip_packages=['azureml-sdk[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-sdk']))\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": [
+    "### Create a Container Image\n",
+    "\n",
+    "Next use Azure Container Instances for deploying models as a web service for quickly deploying and validating your model\n",
+    "or when testing a model that is under development."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.image import Image, ContainerImage\n",
+    "\n",
+    "image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
+    "                                 execution_script = script_file_name,\n",
+    "                                 conda_file = conda_env_file_name,\n",
+    "                                 tags = {'area': \"digits\", 'type': \"automl_regression\"},\n",
+    "                                 description = \"Image for automl regression sample\")\n",
+    "\n",
+    "image = Image.create(name = \"automlsampleimage\",\n",
+    "                     # this is the model object \n",
+    "                     models = [model],\n",
+    "                     image_config = image_config, \n",
+    "                     workspace = ws)\n",
+    "\n",
+    "image.wait_for_creation(show_output = True)\n",
+    "\n",
+    "if image.creation_state == 'Failed':\n",
+    "    print(\"Image build log at: \" + image.image_build_log_uri)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploy the Image as a Web Service on Azure Container Instance\n",
+    "\n",
+    "Deploy an image that contains the model and other assets needed by the service."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import AciWebservice\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')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azureml.core.webservice import Webservice\n",
+    "\n",
+    "aci_service_name = 'automl-sample-hardware'\n",
+    "print(aci_service_name)\n",
+    "aci_service = Webservice.deploy_from_image(deployment_config = aciconfig,\n",
+    "                                           image = image,\n",
+    "                                           name = aci_service_name,\n",
+    "                                           workspace = ws)\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"
+   }
+  ],
+  "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"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

@@ -9,6 +9,13 @@
         "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/auto-ml-regression.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -137,7 +144,7 @@
         "|**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, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], targets values.|\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.|"
       ]
     },

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

@@ -9,6 +9,13 @@
         "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/remote-amlcompute/auto-ml-remote-amlcompute.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -129,7 +136,7 @@
         "from azureml.core.compute import ComputeTarget\n",
         "\n",
         "# Choose a name for your cluster.\n",
-        "amlcompute_cluster_name = \"automlcl\"\n",
+        "amlcompute_cluster_name = \"cpu-cluster\"\n",
         "\n",
         "found = False\n",
         "# Check if this compute target already exists in the workspace.\n",
@@ -138,30 +145,23 @@
         "    found = True\n",
         "    print('Found existing compute target.')\n",
         "    compute_target = cts[amlcompute_cluster_name]\n",
-        "    \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",
+        "    # Create the cluster.\\n\",\n",
         "    compute_target = ComputeTarget.create(ws, amlcompute_cluster_name, provisioning_config)\n",
-        "    \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 = None, timeout_in_minutes = 20)\n",
-        "    \n",
+        "\n",
         "     # For a more detailed view of current AmlCompute status, use get_status()."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": []
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -220,7 +220,7 @@
         "# set the data reference of the run coonfiguration\n",
         "conda_run_config.data_references = {ds.name: dr}\n",
         "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
+        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy','py-xgboost<=0.80'])\n",
         "conda_run_config.environment.python.conda_dependencies = cd"
       ]
     },
@@ -267,7 +267,7 @@
       "outputs": [],
       "source": [
         "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 2,\n",
+        "    \"iteration_timeout_minutes\": 10,\n",
         "    \"iterations\": 20,\n",
         "    \"n_cross_validations\": 5,\n",
         "    \"primary_metric\": 'AUC_weighted',\n",

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

@@ -1,515 +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": [
-        "# Automated Machine Learning\n",
-        "_**Remote Execution using attach**_\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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "In this example we use the scikit-learn's [20newsgroup](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_20newsgroups.html) to showcase how you can use AutoML to handle text data with remote attach.\n",
-        "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
-        "\n",
-        "In this notebook you will learn how to:\n",
-        "1. Create an `Experiment` in an existing `Workspace`.\n",
-        "2. Attach an existing DSVM to a workspace.\n",
-        "3. Configure AutoML using `AutoMLConfig`.\n",
-        "4. Train the model using the DSVM.\n",
-        "5. Explore the results.\n",
-        "6. Test the best fitted model.\n",
-        "\n",
-        "In addition this notebook showcases the following features\n",
-        "- **Parallel** executions for iterations\n",
-        "- **Asynchronous** tracking of progress\n",
-        "- **Cancellation** of individual iterations or the entire run\n",
-        "- Retrieving models for any iteration or logged metric\n",
-        "- Specifying AutoML settings as `**kwargs`\n",
-        "- Handling **text** data using the `preprocess` flag"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n",
-        "\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 os\n",
-        "\n",
-        "import numpy as np\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.train.automl import AutoMLConfig"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "ws = Workspace.from_config()\n",
-        "\n",
-        "# Choose a name for the run history container in the workspace.\n",
-        "experiment_name = 'automl-remote-attach'\n",
-        "project_folder = './sample_projects/automl-remote-attach'\n",
-        "\n",
-        "experiment = Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
-        "output['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": [
-        "### Attach a Remote Linux DSVM\n",
-        "To use a remote Docker compute target:\n",
-        "1. Create a Linux DSVM in Azure, following these [quick instructions](https://docs.microsoft.com/en-us/azure/machine-learning/desktop-workbench/how-to-create-dsvm-hdi). Make sure you use the Ubuntu flavor (not CentOS). Make sure that disk space is available under `/tmp` because AutoML creates files under `/tmp/azureml_run`s. The DSVM should have more cores than the number of parallel runs that you plan to enable. It should also have at least 4GB per core.\n",
-        "2. Enter the IP address, user name and password below.\n",
-        "\n",
-        "**Note:** By default, SSH runs on port 22 and you don't need to change the port number below. If you've configured SSH to use a different port, change `dsvm_ssh_port` accordinglyaddress. [Read more](https://docs.microsoft.com/en-us/azure/virtual-machines/troubleshooting/detailed-troubleshoot-ssh-connection) on changing SSH ports for security reasons."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.compute import ComputeTarget, RemoteCompute\n",
-        "import time\n",
-        "\n",
-        "# Add your VM information below\n",
-        "# If a compute with the specified compute_name already exists, it will be used and the dsvm_ip_addr, dsvm_ssh_port, \n",
-        "# dsvm_username and dsvm_password will be ignored.\n",
-        "compute_name  = 'mydsvmb'\n",
-        "dsvm_ip_addr  = '<<ip_addr>>'\n",
-        "dsvm_ssh_port = 22\n",
-        "dsvm_username = '<<username>>'\n",
-        "dsvm_password = '<<password>>'\n",
-        "\n",
-        "if compute_name in ws.compute_targets:\n",
-        "    print('Using existing compute.')\n",
-        "    dsvm_compute = ws.compute_targets[compute_name]\n",
-        "else:\n",
-        "    attach_config = RemoteCompute.attach_configuration(address=dsvm_ip_addr, username=dsvm_username, password=dsvm_password, ssh_port=dsvm_ssh_port)\n",
-        "    ComputeTarget.attach(workspace=ws, name=compute_name, attach_configuration=attach_config)\n",
-        "\n",
-        "    while ws.compute_targets[compute_name].provisioning_state == 'Creating':\n",
-        "        time.sleep(1)\n",
-        "\n",
-        "    dsvm_compute = ws.compute_targets[compute_name]\n",
-        "    \n",
-        "    if dsvm_compute.provisioning_state == 'Failed':\n",
-        "        print('Attached failed.')\n",
-        "        print(dsvm_compute.provisioning_errors)\n",
-        "        dsvm_compute.detach()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.runconfig import RunConfiguration\n",
-        "from azureml.core.conda_dependencies import CondaDependencies\n",
-        "\n",
-        "# create a new RunConfig object\n",
-        "conda_run_config = RunConfiguration(framework=\"python\")\n",
-        "\n",
-        "# Set compute target to the Linux DSVM\n",
-        "conda_run_config.target = dsvm_compute\n",
-        "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
-        "conda_run_config.environment.python.conda_dependencies = cd"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "For remote executions you should author a `get_data.py` file containing a `get_data()` function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
-        "In this example, the `get_data()` function returns a [dictionary](README.md#getdata)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "if not os.path.exists(project_folder):\n",
-        "    os.makedirs(project_folder)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%writefile $project_folder/get_data.py\n",
-        "\n",
-        "import numpy as np\n",
-        "from sklearn.datasets import fetch_20newsgroups\n",
-        "\n",
-        "def get_data():\n",
-        "    remove = ('headers', 'footers', 'quotes')\n",
-        "    categories = [\n",
-        "        'alt.atheism',\n",
-        "        'talk.religion.misc',\n",
-        "        'comp.graphics',\n",
-        "        'sci.space',\n",
-        "    ]\n",
-        "    data_train = fetch_20newsgroups(subset = 'train', categories = categories,\n",
-        "                                    shuffle = True, random_state = 42,\n",
-        "                                    remove = remove)\n",
-        "    \n",
-        "    X_train = np.array(data_train.data).reshape((len(data_train.data),1))\n",
-        "    y_train = np.array(data_train.target)\n",
-        "    \n",
-        "    return { \"X\" : X_train, \"y\" : y_train }"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "You can specify `automl_settings` as `**kwargs` as well. Also note that you can use a `get_data()` function for local excutions too.\n",
-        "\n",
-        "**Note:** When using Remote DSVM, you can't pass Numpy arrays directly to the fit method.\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\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",
-        "|**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",
-        "|**max_concurrent_iterations**|Maximum number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM.|\n",
-        "|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.|\n",
-        "|**enable_cache**|Setting this to *True* enables preprocess done once and reuse the same preprocessed data for all the iterations. Default value is True.\n",
-        "|**max_cores_per_iteration**|Indicates how many cores on the compute target would be used to train a single pipeline.<br>Default is *1*; you can set it to *-1* to use all cores.|"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 60,\n",
-        "    \"iterations\": 4,\n",
-        "    \"n_cross_validations\": 5,\n",
-        "    \"primary_metric\": 'AUC_weighted',\n",
-        "    \"preprocess\": True,\n",
-        "    \"max_cores_per_iteration\": 2\n",
-        "}\n",
-        "\n",
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             path = project_folder,\n",
-        "                             run_configuration=conda_run_config,\n",
-        "                             data_script = project_folder + \"/get_data.py\",\n",
-        "                             **automl_settings\n",
-        "                            )\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Call the `submit` method on the experiment object and pass the run configuration. For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets and models even when the experiment is running to retrieve the best model up to that point. Once you are satisfied with the model, you can cancel a particular iteration or the whole run."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run = experiment.submit(automl_config)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Results\n",
-        "#### 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",
-        "You can click on a pipeline to see run properties and output logs.  Logs are also available on the DSVM under `/tmp/azureml_run/{iterationid}/azureml-logs`\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": [
-        "### Pre-process cache cleanup\n",
-        "The preprocess data gets cache at user default file store. When the run is completed the cache can be cleaned by running below cell"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.clean_preprocessor_cache()"
-      ]
-    },
-    {
-      "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": [
-        "### Cancelling Runs\n",
-        "You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Cancel the ongoing experiment and stop scheduling new iterations.\n",
-        "# remote_run.cancel()\n",
-        "\n",
-        "# Cancel iteration 1 and move onto iteration 2.\n",
-        "# remote_run.cancel_iteration(1)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Model\n",
-        "\n",
-        "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*."
-      ]
-    },
-    {
-      "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 which has the smallest `accuracy` value:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# lookup_metric = \"accuracy\"\n",
-        "# best_run, fitted_model = remote_run.get_output(metric = lookup_metric)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Model from a Specific Iteration"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "iteration = 0\n",
-        "zero_run, zero_model = remote_run.get_output(iteration = iteration)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Load test data.\n",
-        "from pandas_ml import ConfusionMatrix\n",
-        "from sklearn.datasets import fetch_20newsgroups\n",
-        "\n",
-        "remove = ('headers', 'footers', 'quotes')\n",
-        "categories = [\n",
-        "        'alt.atheism',\n",
-        "        'talk.religion.misc',\n",
-        "        'comp.graphics',\n",
-        "        'sci.space',\n",
-        "    ]\n",
-        "\n",
-        "data_test = fetch_20newsgroups(subset = 'test', categories = categories,\n",
-        "                               shuffle = True, random_state = 42,\n",
-        "                               remove = remove)\n",
-        "\n",
-        "X_test = np.array(data_test.data).reshape((len(data_test.data),1))\n",
-        "y_test = data_test.target\n",
-        "\n",
-        "# Test our best pipeline.\n",
-        "\n",
-        "y_pred = fitted_model.predict(X_test)\n",
-        "y_pred_strings = [data_test.target_names[i] for i in y_pred]\n",
-        "y_test_strings = [data_test.target_names[i] for i in y_test]\n",
-        "\n",
-        "cm = ConfusionMatrix(y_test_strings, y_pred_strings)\n",
-        "print(cm)\n",
-        "cm.plot()"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "savitam"
-      }
-    ],
-    "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"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

how-to-use-azureml/automated-machine-learning/remote-execution-with-datastore/auto-ml-remote-execution-with-datastore.ipynb

@@ -1,583 +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": [
-        "# Automated Machine Learning\n",
-        "_**Remote Execution with DataStore**_\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)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Introduction\n",
-        "This sample accesses a data file on a remote DSVM through DataStore. Advantages of using data store are:\n",
-        "1. DataStore secures the access details.\n",
-        "2. DataStore supports read, write to blob and file store\n",
-        "3. AutoML natively supports copying data from DataStore to DSVM\n",
-        "\n",
-        "Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
-        "\n",
-        "In this notebook you would see\n",
-        "1. Storing data in DataStore.\n",
-        "2. get_data returning data from DataStore."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Setup\n",
-        "\n",
-        "As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import logging\n",
-        "import os\n",
-        "import time\n",
-        "\n",
-        "import numpy as np\n",
-        "import pandas as pd\n",
-        "\n",
-        "import azureml.core\n",
-        "from azureml.core.compute import DsvmCompute\n",
-        "from azureml.core.experiment import Experiment\n",
-        "from azureml.core.workspace import Workspace\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 experiment\n",
-        "experiment_name = 'automl-remote-datastore-file'\n",
-        "# project folder\n",
-        "project_folder = './sample_projects/automl-remote-datastore-file'\n",
-        "\n",
-        "experiment=Experiment(ws, experiment_name)\n",
-        "\n",
-        "output = {}\n",
-        "output['SDK version'] = azureml.core.VERSION\n",
-        "output['Subscription ID'] = ws.subscription_id\n",
-        "output['Workspace'] = ws.name\n",
-        "output['Resource Group'] = ws.resource_group\n",
-        "output['Location'] = ws.location\n",
-        "output['Project Directory'] = project_folder\n",
-        "output['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 a Remote Linux DSVM\n",
-        "Note: If creation fails with a message about Marketplace purchase eligibilty, go to portal.azure.com, start creating DSVM there, and select \"Want to create programmatically\" to enable programmatic creation. Once you've enabled it, you can exit without actually creating VM.\n",
-        "\n",
-        "**Note**: By default SSH runs on port 22 and you don't need to specify it. But if for security reasons you can switch to a different port (such as 5022), you can append the port number to the address. [Read more](https://docs.microsoft.com/en-us/azure/virtual-machines/troubleshooting/detailed-troubleshoot-ssh-connection) on this."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "compute_target_name = 'mydsvmc'\n",
-        "\n",
-        "try:\n",
-        "    while ws.compute_targets[compute_target_name].provisioning_state == 'Creating':\n",
-        "        time.sleep(1)\n",
-        "        \n",
-        "    dsvm_compute = DsvmCompute(workspace=ws, name=compute_target_name)\n",
-        "    print('found existing:', dsvm_compute.name)\n",
-        "except:\n",
-        "    dsvm_config = DsvmCompute.provisioning_configuration(vm_size=\"Standard_D2_v2\")\n",
-        "    dsvm_compute = DsvmCompute.create(ws, name=compute_target_name, provisioning_configuration=dsvm_config)\n",
-        "    dsvm_compute.wait_for_completion(show_output=True)\n",
-        "    print(\"Waiting one minute for ssh to be accessible\")\n",
-        "    time.sleep(60) # Wait for ssh to be accessible"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Data\n",
-        "\n",
-        "### Copy data file to local\n",
-        "\n",
-        "Download the data file.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "if not os.path.isdir('data'):\n",
-        "    os.mkdir('data')    "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from sklearn.datasets import fetch_20newsgroups\n",
-        "import csv\n",
-        "\n",
-        "remove = ('headers', 'footers', 'quotes')\n",
-        "categories = [\n",
-        "        'alt.atheism',\n",
-        "        'talk.religion.misc',\n",
-        "        'comp.graphics',\n",
-        "        'sci.space',\n",
-        "    ]\n",
-        "data_train = fetch_20newsgroups(subset = 'train', categories = categories,\n",
-        "                                    shuffle = True, random_state = 42,\n",
-        "                                    remove = remove)\n",
-        "    \n",
-        "pd.DataFrame(data_train.data).to_csv(\"data/X_train.tsv\", index=False, header=False, quoting=csv.QUOTE_ALL, sep=\"\\t\")\n",
-        "pd.DataFrame(data_train.target).to_csv(\"data/y_train.tsv\", index=False, header=False, sep=\"\\t\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Upload data to the cloud"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "Now make the data accessible remotely by uploading that data from your local machine into Azure so it can be accessed for remote training. The datastore is a convenient construct associated with your workspace for you to upload/download data, and interact with it from your remote compute targets. It is backed by Azure blob storage account.\n",
-        "\n",
-        "The data.tsv files are uploaded into a directory named data at the root of the datastore."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#blob_datastore = Datastore(ws, blob_datastore_name)\n",
-        "ds = ws.get_default_datastore()\n",
-        "print(ds.datastore_type, ds.account_name, ds.container_name)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# ds.upload_files(\"data.tsv\")\n",
-        "ds.upload(src_dir='./data', target_path='data', overwrite=True, show_progress=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Configure & Run\n",
-        "\n",
-        "First let's create a DataReferenceConfigruation object to inform the system what data folder to download to the compute target.\n",
-        "The path_on_compute should be an absolute path to ensure that the data files are downloaded only once.   The get_data method should use this same path to access the data files."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.runconfig import DataReferenceConfiguration\n",
-        "dr = DataReferenceConfiguration(datastore_name=ds.name, \n",
-        "                   path_on_datastore='data', \n",
-        "                   path_on_compute='/tmp/azureml_runs',\n",
-        "                   mode='download', # download files from datastore to compute target\n",
-        "                   overwrite=False)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "from azureml.core.runconfig import RunConfiguration\n",
-        "from azureml.core.conda_dependencies import CondaDependencies\n",
-        "\n",
-        "# create a new RunConfig object\n",
-        "conda_run_config = RunConfiguration(framework=\"python\")\n",
-        "\n",
-        "# Set compute target to the Linux DSVM\n",
-        "conda_run_config.target = dsvm_compute\n",
-        "# set the data reference of the run coonfiguration\n",
-        "conda_run_config.data_references = {ds.name: dr}\n",
-        "\n",
-        "cd = CondaDependencies.create(pip_packages=['azureml-sdk[automl]'], conda_packages=['numpy'])\n",
-        "conda_run_config.environment.python.conda_dependencies = cd"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Create Get Data File\n",
-        "For remote executions you should author a get_data.py file containing a get_data() function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
-        "\n",
-        "The *get_data()* function returns a [dictionary](README.md#getdata).\n",
-        "\n",
-        "The read_csv uses the path_on_compute value specified in the DataReferenceConfiguration call plus the path_on_datastore folder and then the actual file name."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "if not os.path.exists(project_folder):\n",
-        "    os.makedirs(project_folder)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%%writefile $project_folder/get_data.py\n",
-        "\n",
-        "import pandas as pd\n",
-        "\n",
-        "def get_data():\n",
-        "    X_train = pd.read_csv(\"/tmp/azureml_runs/data/X_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "    y_train = pd.read_csv(\"/tmp/azureml_runs/data/y_train.tsv\", delimiter=\"\\t\", header=None, quotechar='\"')\n",
-        "\n",
-        "    return { \"X\" : X_train.values, \"y\" : y_train[0].values }"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Train\n",
-        "\n",
-        "You can specify automl_settings as **kwargs** as well. Also note that you can use the get_data() symantic for local excutions too. \n",
-        "\n",
-        "<i>Note: For Remote DSVM and Batch AI you cannot pass Numpy arrays directly to AutoMLConfig.</i>\n",
-        "\n",
-        "|Property|Description|\n",
-        "|-|-|\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",
-        "|**iterations**|Number of iterations. In each iteration Auto ML trains a specific pipeline with the data|\n",
-        "|**n_cross_validations**|Number of cross validation splits|\n",
-        "|**max_concurrent_iterations**|Max number of iterations that would be executed in parallel.  This should be less than the number of cores on the DSVM\n",
-        "|**preprocess**| *True/False* <br>Setting this to *True* enables Auto ML to perform preprocessing <br>on the input to handle *missing data*, and perform some common *feature extraction*|\n",
-        "|**enable_cache**|Setting this to *True* enables preprocess done once and reuse the same preprocessed data for all the iterations. Default value is True.|\n",
-        "|**max_cores_per_iteration**| Indicates how many cores on the compute target would be used to train a single pipeline.<br> Default is *1*, you can set it to *-1* to use all cores|"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "automl_settings = {\n",
-        "    \"iteration_timeout_minutes\": 60,\n",
-        "    \"iterations\": 4,\n",
-        "    \"n_cross_validations\": 5,\n",
-        "    \"primary_metric\": 'AUC_weighted',\n",
-        "    \"preprocess\": True,\n",
-        "    \"max_cores_per_iteration\": 1,\n",
-        "    \"verbosity\": logging.INFO\n",
-        "}\n",
-        "automl_config = AutoMLConfig(task = 'classification',\n",
-        "                             debug_log = 'automl_errors.log',\n",
-        "                             path=project_folder,\n",
-        "                             run_configuration=conda_run_config,\n",
-        "                             #compute_target = dsvm_compute,\n",
-        "                             data_script = project_folder + \"/get_data.py\",\n",
-        "                             **automl_settings\n",
-        "                            )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets/models even when the experiment is running to retreive the best model up to that point. Once you are satisfied with the model you can cancel a particular iteration or the whole run."
-      ]
-    },
-    {
-      "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\n",
-        "#### Widget for monitoring runs\n",
-        "\n",
-        "The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
-        "\n",
-        "You can click on a pipeline to see run properties and output logs. Logs are also available on the DSVM under /tmp/azureml_run/{iterationid}/azureml-logs\n",
-        "\n",
-        "NOTE: The widget displays a link at the bottom. This links to a web-ui 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": [
-        "\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": [
-        "### Canceling Runs\n",
-        "You can cancel ongoing remote runs using the *cancel()* and *cancel_iteration()* functions"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Cancel the ongoing experiment and stop scheduling new iterations\n",
-        "# remote_run.cancel()\n",
-        "\n",
-        "# Cancel iteration 1 and move onto iteration 2\n",
-        "# remote_run.cancel_iteration(1)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Pre-process cache cleanup\n",
-        "The preprocess data gets cache at user default file store. When the run is completed the cache can be cleaned by running below cell"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "remote_run.clean_preprocessor_cache()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "### Retrieve the Best Model\n",
-        "\n",
-        "Below we select the best pipeline from our iterations. The *get_output* method returns the best run and the fitted model. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "best_run, fitted_model = remote_run.get_output()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Best Model based on any other metric"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# lookup_metric = \"accuracy\"\n",
-        "# best_run, fitted_model = remote_run.get_output(metric=lookup_metric)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "#### Model from a specific iteration"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# iteration = 1\n",
-        "# best_run, fitted_model = remote_run.get_output(iteration=iteration)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Test\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# Load test data.\n",
-        "from pandas_ml import ConfusionMatrix\n",
-        "\n",
-        "data_test = fetch_20newsgroups(subset = 'test', categories = categories,\n",
-        "                               shuffle = True, random_state = 42,\n",
-        "                               remove = remove)\n",
-        "\n",
-        "X_test = np.array(data_test.data).reshape((len(data_test.data),1))\n",
-        "y_test = data_test.target\n",
-        "\n",
-        "# Test our best pipeline.\n",
-        "\n",
-        "y_pred = fitted_model.predict(X_test)\n",
-        "y_pred_strings = [data_test.target_names[i] for i in y_pred]\n",
-        "y_test_strings = [data_test.target_names[i] for i in y_test]\n",
-        "\n",
-        "cm = ConfusionMatrix(y_test_strings, y_pred_strings)\n",
-        "print(cm)\n",
-        "cm.plot()"
-      ]
-    }
-  ],
-  "metadata": {
-    "authors": [
-      {
-        "name": "savitam"
-      }
-    ],
-    "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"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 2
-}

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

@@ -9,6 +9,13 @@
         "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/sample-weight/auto-ml-sample-weight.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},

how-to-use-azureml/automated-machine-learning/sparse-data-train-test-split/auto-ml-sparse-data-train-test-split.ipynb

@@ -9,6 +9,13 @@
         "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/sparse-data-train-test-split/auto-ml-sparse-data-train-test-split.png)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -156,9 +163,9 @@
         "|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
         "|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.<br>**Note:** If input data is sparse, you cannot use *True*.|\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",
+        "|**y**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\n",
         "|**X_valid**|(sparse) array-like, shape = [n_samples, n_features] for the custom validation set.|\n",
-        "|**y_valid**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification for the custom validation set.|\n",
+        "|**y_valid**|(sparse) array-like, shape = [n_samples, ], Multi-class targets.|\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.|"
       ]
     },

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

@@ -0,0 +1,113 @@
+# Table of Contents
+1. [Introduction](#introduction)
+1. [Setup using Azure Data Studio](#azuredatastudiosetup)
+1. [Energy demand example using Azure Data Studio](#azuredatastudioenergydemand)
+1. [Set using SQL Server Management Studio for SQL Server 2017 on Windows](#ssms2017)
+1. [Set using SQL Server Management Studio for SQL Server 2019 on Linux](#ssms2019)
+1. [Energy demand example using SQL Server Management Studio](#ssmsenergydemand)
+
+
+<a name="introduction"></a>
+# Introduction
+SQL Server 2017 or 2019 can call Azure ML automated machine learning to create models trained on data from SQL Server.
+This uses the sp_execute_external_script stored procedure, which can call Python scripts.
+SQL Server 2017 and SQL Server 2019 can both run on Windows or Linux.
+However, this integration is not available for SQL Server 2017 on Linux. 
+
+This folder shows how to setup the integration and has a sample that uses the integration to train and predict based on an energy demand dataset.
+
+This integration is part of SQL Server and so can be used from any SQL client. 
+These instructions show using it from Azure Data Studio or SQL Server Managment Studio.
+
+<a name="azuredatastudiosetup"></a>
+## Setup using Azure Data Studio
+
+These step show setting up the integration using Azure Data Studio.
+
+1. If you don't already have SQL Server, you can install it from [https://www.microsoft.com/en-us/sql-server/sql-server-downloads](https://www.microsoft.com/en-us/sql-server/sql-server-downloads)
+1. Install Azure Data Studio from [https://docs.microsoft.com/en-us/sql/azure-data-studio/download?view=sql-server-2017](https://docs.microsoft.com/en-us/sql/azure-data-studio/download?view=sql-server-2017)
+1. Start Azure Data Studio and connect to SQL Server. [https://docs.microsoft.com/en-us/sql/azure-data-studio/sql-notebooks?view=sql-server-2017](https://docs.microsoft.com/en-us/sql/azure-data-studio/sql-notebooks?view=sql-server-2017)
+1. Create a database named "automl".
+1. Open the notebook how-to-use-azureml\automated-machine-learning\sql-server\setup\auto-ml-sql-setup.ipynb and follow the instructions in it.
+
+ <a name="azuredatastudioenergydemand"></a>
+## Energy demand example using Azure Data Studio
+
+Once you have completed the setup, you can try the energy demand sample in the notebook energy-demand\auto-ml-sql-energy-demand.ipynb.
+This has cells to train a model, predict based on the model and show metrics for each pipeline run in training the model.
+
+<a name="ssms2017"></a>
+## Setup using SQL Server Management Studio for SQL Server 2017 on Windows
+
+These instruction setup the integration for SQL Server 2017 on Windows.
+
+1. If you don't already have SQL Server, you can install it from [https://www.microsoft.com/en-us/sql-server/sql-server-downloads](https://www.microsoft.com/en-us/sql-server/sql-server-downloads)
+2. Enable external scripts with the following commands: 
+```sh
+   sp_configure 'external scripts enabled',1 
+   reconfigure with override
+```
+3. Stop SQL Server. 
+4. Install the automated machine learning libraries using the following commands from Administrator command prompt (If you are using a non-default SQL Server instance name, replace MSSQLSERVER in the second command with the instance name)
+```sh
+   cd "C:\Program Files\Microsoft SQL Server"
+   cd "MSSQL14.MSSQLSERVER\PYTHON_SERVICES"
+   python.exe -m pip install azureml-sdk[automl]
+   python.exe -m pip install --upgrade numpy
+   python.exe -m pip install --upgrade sklearn
+```
+5. Start SQL Server and the service "SQL Server Launchpad service". 
+6. In Windows Firewall, click on advanced settings and in Outbound Rules, disable "Block network access for R local user accounts in SQL Server instance xxxx". 
+7. Execute the files in the setup folder in SQL Server Management Studio: aml_model.sql, aml_connection.sql, AutoMLGetMetrics.sql, AutoMLPredict.sql and AutoMLTrain.sql 
+8. Create an Azure Machine Learning Workspace.  You can use the instructions at: [https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace ](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace)
+9. Create a config.json file file using the subscription id, resource group name and workspace name that you used to create the workspace.  The file is described at: [https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#workspace)
+10. Create an Azure service principal.  You can do this with the commands: 
+```sh
+   az login 
+   az account set --subscription subscriptionid 
+   az ad sp create-for-rbac --name principlename --password password 
+```
+11. Insert the values \<tenant\>, \<AppId\> and \<password\> returned by create-for-rbac above into the aml_connection table.  Set \<path\> as the absolute path to your config.json file. Set the name to <20>Default<6C>. 
+ 
+<a name="ssms2019"></a>
+## Setup using SQL Server Management Studio for SQL Server 2019 on Linux
+1. Install SQL Server 2019 from: [https://www.microsoft.com/en-us/sql-server/sql-server-downloads](https://www.microsoft.com/en-us/sql-server/sql-server-downloads)
+2. Install machine learning support from: [https://docs.microsoft.com/en-us/sql/linux/sql-server-linux-setup-machine-learning?view=sqlallproducts-allversions#ubuntu](https://docs.microsoft.com/en-us/sql/linux/sql-server-linux-setup-machine-learning?view=sqlallproducts-allversions#ubuntu)
+3. Then install SQL Server management Studio from [https://docs.microsoft.com/en-us/sql/ssms/download-sql-server-management-studio-ssms?view=sql-server-2017](https://docs.microsoft.com/en-us/sql/ssms/download-sql-server-management-studio-ssms?view=sql-server-2017)
+4. Enable external scripts with the following commands: 
+```sh
+   sp_configure 'external scripts enabled',1 
+   reconfigure with override 
+```
+5. Stop SQL Server. 
+6. Install the automated machine learning libraries using the following commands from Administrator command (If you are using a non-default SQL Server instance name, replace MSSQLSERVER in the second command with the instance name): 
+```sh
+   sudo /opt/mssql/mlservices/bin/python/python -m pip install azureml-sdk[automl] 
+   sudo /opt/mssql/mlservices/bin/python/python -m pip install --upgrade numpy 
+   sudo /opt/mssql/mlservices/bin/python/python -m pip install --upgrade sklearn
+```
+7. Start SQL Server. 
+8. Execute the files aml_model.sql, aml_connection.sql, AutoMLGetMetrics.sql, AutoMLPredict.sql and AutoMLTrain.sql in SQL Server Management Studio. 
+9. Create an Azure Machine Learning Workspace.  You can use the instructions at: [https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-workspace)
+10. Create a config.json file file using the subscription id, resource group name and workspace name that you use to create the workspace.  The file is described at: [https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#workspace](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-configure-environment#workspace)
+11. Create an Azure service principal.  You can do this with the commands: 
+```sh
+   az login 
+   az account set --subscription subscriptionid 
+   az ad sp create-for-rbac --name principlename --password password 
+``` 
+12. Insert the values \<tenant\>, \<AppId\> and \<password\> returned by create-for-rbac above into the aml_connection table.  Set \<path\> as the absolute path to your config.json file. Set the name to <20>Default<6C>. 
+ 
+<a name="ssmsenergydemand"></a>
+## Energy demand example using SQL Server Management Studio
+
+Once you have completed the setup, you can try the energy demand sample queries.
+First you need to load the sample data in the database.
+1. In SQL Server Management Studio, you can right-click the database, select Tasks, then Import Flat file. 
+1. Select the file MachineLearningNotebooks\notebooks\how-to-use-azureml\automated-machine-learning\forecasting-energy-demand\nyc_energy.csv. 
+1. When you get to the column definition page, allow nulls for all columns. 
+
+You can then run the queries in the energy-demand folder:
+* TrainEnergyDemand.sql runs AutoML, trains multiple models on data and selects the best model.
+* PredictEnergyDemand.sql predicts based on the most recent training run.
+* GetMetrics.sql returns all the metrics for each model in the most recent training run.

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

@@ -0,0 +1,10 @@
+-- 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/PredictEnergyDemand.sql

@@ -0,0 +1,17 @@
+-- This shows using the AutoMLPredict 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)
+
+EXEC dbo.AutoMLPredict @input_query='
+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 >= ''2017-02-01''',
+@label_column='demand',
+@model=@model
+WITH RESULT SETS ((timeStamp NVARCHAR(30), actual_demand FLOAT, precip FLOAT, temp FLOAT, predicted_demand FLOAT))