Compare commits
1 Commits
release_up
...
release_up
| Author | SHA1 | Date | |
|---|---|---|---|
|
584ed9ae74 |
@@ -4,10 +4,6 @@ This repository contains example notebooks demonstrating the [Azure Machine Lear
|
||||
|
||||
|
||||
|
||||
## News
|
||||
|
||||
* [Try Azure Machine Learning with MLflow](./how-to-use-azureml/using-mlflow)
|
||||
|
||||
## Quick installation
|
||||
```sh
|
||||
pip install azureml-sdk
|
||||
@@ -56,7 +52,6 @@ The [How to use Azure ML](./how-to-use-azureml) folder contains specific example
|
||||
|
||||
Visit following repos to see projects contributed by Azure ML users:
|
||||
|
||||
- [AMLSamples](https://github.com/Azure/AMLSamples) Number of end-to-end examples, including face recognition, predictive maintenance, customer churn and sentiment analysis.
|
||||
- [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)
|
||||
|
||||
|
||||
@@ -1,383 +1,383 @@
|
||||
{
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Configuration\n",
|
||||
"\n",
|
||||
"_**Setting up your Azure Machine Learning services workspace and configuring your notebook library**_\n",
|
||||
"\n",
|
||||
"---\n",
|
||||
"---\n",
|
||||
"\n",
|
||||
"## Table of Contents\n",
|
||||
"\n",
|
||||
"1. [Introduction](#Introduction)\n",
|
||||
" 1. What is an Azure Machine Learning workspace\n",
|
||||
"1. [Setup](#Setup)\n",
|
||||
" 1. Azure subscription\n",
|
||||
" 1. Azure ML SDK and other library installation\n",
|
||||
" 1. Azure Container Instance registration\n",
|
||||
"1. [Configure your Azure ML Workspace](#Configure%20your%20Azure%20ML%20workspace)\n",
|
||||
" 1. Workspace parameters\n",
|
||||
" 1. Access your workspace\n",
|
||||
" 1. Create a new workspace\n",
|
||||
" 1. Create compute resources\n",
|
||||
"1. [Next steps](#Next%20steps)\n",
|
||||
"\n",
|
||||
"---\n",
|
||||
"\n",
|
||||
"## Introduction\n",
|
||||
"\n",
|
||||
"This notebook configures your library of notebooks to connect to an Azure Machine Learning (ML) workspace. In this case, a library contains all of the notebooks in the current folder and any nested folders. You can configure this notebook library to use an existing workspace or create a new workspace.\n",
|
||||
"\n",
|
||||
"Typically you will need to run this notebook only once per notebook library as all other notebooks will use connection information that is written here. If you want to redirect your notebook library to work with a different workspace, then you should re-run this notebook.\n",
|
||||
"\n",
|
||||
"In this notebook you will\n",
|
||||
"* Learn about getting an Azure subscription\n",
|
||||
"* Specify your workspace parameters\n",
|
||||
"* Access or create your workspace\n",
|
||||
"* Add a default compute cluster for your workspace\n",
|
||||
"\n",
|
||||
"### What is an Azure Machine Learning workspace\n",
|
||||
"\n",
|
||||
"An Azure ML Workspace is an Azure resource that organizes and coordinates the actions of many other Azure resources to assist in executing and sharing machine learning workflows. In particular, an Azure ML Workspace coordinates storage, databases, and compute resources providing added functionality for machine learning experimentation, deployment, inferencing, and the monitoring of deployed models."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"This section describes activities required before you can access any Azure ML services functionality."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 1. Azure Subscription\n",
|
||||
"\n",
|
||||
"In order to create an Azure ML Workspace, first you need access to an Azure subscription. An Azure subscription allows you to manage storage, compute, and other assets in the Azure cloud. You can [create a new subscription](https://azure.microsoft.com/en-us/free/) or access existing subscription information from the [Azure portal](https://portal.azure.com). Later in this notebook you will need information such as your subscription ID in order to create and access AML workspaces.\n",
|
||||
"\n",
|
||||
"### 2. Azure ML SDK and other library installation\n",
|
||||
"\n",
|
||||
"If you are running in your own environment, follow [SDK installation instructions](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-environment). If you are running in Azure Notebooks or another Microsoft managed environment, the SDK is already installed.\n",
|
||||
"\n",
|
||||
"Also install following libraries to your environment. Many of the example notebooks depend on them\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"(myenv) $ conda install -y matplotlib tqdm scikit-learn\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Once installation is complete, the following cell checks the Azure ML SDK version:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"install"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"This notebook was created using version AZUREML-SDK-VERSION of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you are using an older version of the SDK then this notebook was created using, you should upgrade your SDK.\n",
|
||||
"\n",
|
||||
"### 3. Azure Container Instance registration\n",
|
||||
"Azure Machine Learning uses of [Azure Container Instance (ACI)](https://azure.microsoft.com/services/container-instances) to deploy dev/test web services. An Azure subscription needs to be registered to use ACI. If you or the subscription owner have not yet registered ACI on your subscription, you will need to use the [Azure CLI](https://docs.microsoft.com/en-us/cli/azure/install-azure-cli?view=azure-cli-latest) and execute the following commands. Note that if you ran through the AML [quickstart](https://docs.microsoft.com/en-us/azure/machine-learning/service/quickstart-get-started) you have already registered ACI. \n",
|
||||
"\n",
|
||||
"```shell\n",
|
||||
"# check to see if ACI is already registered\n",
|
||||
"(myenv) $ az provider show -n Microsoft.ContainerInstance -o table\n",
|
||||
"\n",
|
||||
"# if ACI is not registered, run this command.\n",
|
||||
"# note you need to be the subscription owner in order to execute this command successfully.\n",
|
||||
"(myenv) $ az provider register -n Microsoft.ContainerInstance\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Configure your Azure ML workspace\n",
|
||||
"\n",
|
||||
"### Workspace parameters\n",
|
||||
"\n",
|
||||
"To use an AML Workspace, you will need to import the Azure ML SDK and supply the following information:\n",
|
||||
"* Your subscription id\n",
|
||||
"* A resource group name\n",
|
||||
"* (optional) The region that will host your workspace\n",
|
||||
"* A name for your workspace\n",
|
||||
"\n",
|
||||
"You can get your subscription ID from the [Azure portal](https://portal.azure.com).\n",
|
||||
"\n",
|
||||
"You will also need access to a [_resource group_](https://docs.microsoft.com/en-us/azure/azure-resource-manager/resource-group-overview#resource-groups), which organizes Azure resources and provides a default region for the resources in a group. You can see what resource groups to which you have access, or create a new one in the [Azure portal](https://portal.azure.com). If you don't have a resource group, the create workspace command will create one for you using the name you provide.\n",
|
||||
"\n",
|
||||
"The region to host your workspace will be used if you are creating a new workspace. You do not need to specify this if you are using an existing workspace. You can find the list of supported regions [here](https://azure.microsoft.com/en-us/global-infrastructure/services/?products=machine-learning-service). You should pick a region that is close to your location or that contains your data.\n",
|
||||
"\n",
|
||||
"The name for your workspace is unique within the subscription and should be descriptive enough to discern among other AML Workspaces. The subscription may be used only by you, or it may be used by your department or your entire enterprise, so choose a name that makes sense for your situation.\n",
|
||||
"\n",
|
||||
"The following cell allows you to specify your workspace parameters. This cell uses the python method `os.getenv` to read values from environment variables which is useful for automation. If no environment variable exists, the parameters will be set to the specified default values. \n",
|
||||
"\n",
|
||||
"If you ran the Azure Machine Learning [quickstart](https://docs.microsoft.com/en-us/azure/machine-learning/service/quickstart-get-started) in Azure Notebooks, you already have a configured workspace! You can go to your Azure Machine Learning Getting Started library, view *config.json* file, and copy-paste the values for subscription ID, resource group and workspace name below.\n",
|
||||
"\n",
|
||||
"Replace the default values in the cell below with your workspace parameters"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"subscription_id = os.getenv(\"SUBSCRIPTION_ID\", default=\"<my-subscription-id>\")\n",
|
||||
"resource_group = os.getenv(\"RESOURCE_GROUP\", default=\"<my-resource-group>\")\n",
|
||||
"workspace_name = os.getenv(\"WORKSPACE_NAME\", default=\"<my-workspace-name>\")\n",
|
||||
"workspace_region = os.getenv(\"WORKSPACE_REGION\", default=\"eastus2\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Access your workspace\n",
|
||||
"\n",
|
||||
"The following cell uses the Azure ML SDK to attempt to load the workspace specified by your parameters. If this cell succeeds, your notebook library will be configured to access the workspace from all notebooks using the `Workspace.from_config()` method. The cell can fail if the specified workspace doesn't exist or you don't have permissions to access it. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"try:\n",
|
||||
" ws = Workspace(subscription_id = subscription_id, resource_group = resource_group, workspace_name = workspace_name)\n",
|
||||
" # write the details of the workspace to a configuration file to the notebook library\n",
|
||||
" ws.write_config()\n",
|
||||
" print(\"Workspace configuration succeeded. Skip the workspace creation steps below\")\n",
|
||||
"except:\n",
|
||||
" print(\"Workspace not accessible. Change your parameters or create a new workspace below\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a new workspace\n",
|
||||
"\n",
|
||||
"If you don't have an existing workspace and are the owner of the subscription or resource group, you can create a new workspace. If you don't have a resource group, the create workspace command will create one for you using the name you provide.\n",
|
||||
"\n",
|
||||
"**Note**: As with other Azure services, there are limits on certain resources (for example AmlCompute quota) associated with the Azure ML service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota.\n",
|
||||
"\n",
|
||||
"This cell will create an Azure ML workspace for you in a subscription provided you have the correct permissions.\n",
|
||||
"\n",
|
||||
"This will fail if:\n",
|
||||
"* You do not have permission to create a workspace in the resource group\n",
|
||||
"* You do not have permission to create a resource group if it's non-existing.\n",
|
||||
"* You are not a subscription owner or contributor and no Azure ML workspaces have ever been created in this subscription\n",
|
||||
"\n",
|
||||
"If workspace creation fails, please work with your IT admin to provide you with the appropriate permissions or to provision the required resources."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create workspace"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"# Create the workspace using the specified parameters\n",
|
||||
"ws = Workspace.create(name = workspace_name,\n",
|
||||
" subscription_id = subscription_id,\n",
|
||||
" resource_group = resource_group, \n",
|
||||
" location = workspace_region,\n",
|
||||
" create_resource_group = True,\n",
|
||||
" exist_ok = True)\n",
|
||||
"ws.get_details()\n",
|
||||
"\n",
|
||||
"# write the details of the workspace to a configuration file to the notebook library\n",
|
||||
"ws.write_config()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create compute resources for your training experiments\n",
|
||||
"\n",
|
||||
"Many of the sample notebooks use Azure ML managed compute (AmlCompute) to train models using a dynamically scalable pool of compute. In this section you will create default compute clusters for use by the other notebooks and any other operations you choose.\n",
|
||||
"\n",
|
||||
"To create a cluster, you need to specify a compute configuration that specifies the type of machine to be used and the scalability behaviors. Then you choose a name for the cluster that is unique within the workspace that can be used to address the cluster later.\n",
|
||||
"\n",
|
||||
"The cluster parameters are:\n",
|
||||
"* vm_size - this describes the virtual machine type and size used in the cluster. All machines in the cluster are the same type. You can get the list of vm sizes available in your region by using the CLI command\n",
|
||||
"\n",
|
||||
"```shell\n",
|
||||
"az vm list-skus -o tsv\n",
|
||||
"```\n",
|
||||
"* min_nodes - this sets the minimum size of the cluster. If you set the minimum to 0 the cluster will shut down all nodes while not in use. Setting this number to a value higher than 0 will allow for faster start-up times, but you will also be billed when the cluster is not in use.\n",
|
||||
"* max_nodes - this sets the maximum size of the cluster. Setting this to a larger number allows for more concurrency and a greater distributed processing of scale-out jobs.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"To create a **CPU** cluster now, run the cell below. The autoscale settings mean that the cluster will scale down to 0 nodes when inactive and up to 4 nodes when busy."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
|
||||
"from azureml.core.compute_target import ComputeTargetException\n",
|
||||
"\n",
|
||||
"# Choose a name for your CPU cluster\n",
|
||||
"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 cpu-cluster\")\n",
|
||||
"except ComputeTargetException:\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",
|
||||
" min_nodes=0,\n",
|
||||
" max_nodes=4)\n",
|
||||
"\n",
|
||||
" # Create the cluster with the specified name and configuration\n",
|
||||
" cpu_cluster = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
|
||||
" \n",
|
||||
" # Wait for the cluster to complete, show the output log\n",
|
||||
" cpu_cluster.wait_for_completion(show_output=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To create a **GPU** cluster, run the cell below. Note that your subscription must have sufficient quota for GPU VMs or the command will fail. To increase quota, see [these instructions](https://docs.microsoft.com/en-us/azure/azure-supportability/resource-manager-core-quotas-request). "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
|
||||
"from azureml.core.compute_target import ComputeTargetException\n",
|
||||
"\n",
|
||||
"# Choose a name for your GPU cluster\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 gpu-cluster\")\n",
|
||||
" \n",
|
||||
" # Specify the configuration for the new cluster\n",
|
||||
" compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_NC6\",\n",
|
||||
" min_nodes=0,\n",
|
||||
" max_nodes=4)\n",
|
||||
" # Create the cluster with the specified name and configuration\n",
|
||||
" gpu_cluster = ComputeTarget.create(ws, gpu_cluster_name, compute_config)\n",
|
||||
"\n",
|
||||
" # Wait for the cluster to complete, show the output log\n",
|
||||
" gpu_cluster.wait_for_completion(show_output=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"---\n",
|
||||
"\n",
|
||||
"## Next steps\n",
|
||||
"\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 within notebook](./how-to-use-azureml/training/train-within-notebook) example that walks through a simplified but complete end to end machine learning process."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "roastala"
|
||||
}
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Configuration\n",
|
||||
"\n",
|
||||
"_**Setting up your Azure Machine Learning services workspace and configuring your notebook library**_\n",
|
||||
"\n",
|
||||
"---\n",
|
||||
"---\n",
|
||||
"\n",
|
||||
"## Table of Contents\n",
|
||||
"\n",
|
||||
"1. [Introduction](#Introduction)\n",
|
||||
" 1. What is an Azure Machine Learning workspace\n",
|
||||
"1. [Setup](#Setup)\n",
|
||||
" 1. Azure subscription\n",
|
||||
" 1. Azure ML SDK and other library installation\n",
|
||||
" 1. Azure Container Instance registration\n",
|
||||
"1. [Configure your Azure ML Workspace](#Configure%20your%20Azure%20ML%20workspace)\n",
|
||||
" 1. Workspace parameters\n",
|
||||
" 1. Access your workspace\n",
|
||||
" 1. Create a new workspace\n",
|
||||
" 1. Create compute resources\n",
|
||||
"1. [Next steps](#Next%20steps)\n",
|
||||
"\n",
|
||||
"---\n",
|
||||
"\n",
|
||||
"## Introduction\n",
|
||||
"\n",
|
||||
"This notebook configures your library of notebooks to connect to an Azure Machine Learning (ML) workspace. In this case, a library contains all of the notebooks in the current folder and any nested folders. You can configure this notebook library to use an existing workspace or create a new workspace.\n",
|
||||
"\n",
|
||||
"Typically you will need to run this notebook only once per notebook library as all other notebooks will use connection information that is written here. If you want to redirect your notebook library to work with a different workspace, then you should re-run this notebook.\n",
|
||||
"\n",
|
||||
"In this notebook you will\n",
|
||||
"* Learn about getting an Azure subscription\n",
|
||||
"* Specify your workspace parameters\n",
|
||||
"* Access or create your workspace\n",
|
||||
"* Add a default compute cluster for your workspace\n",
|
||||
"\n",
|
||||
"### What is an Azure Machine Learning workspace\n",
|
||||
"\n",
|
||||
"An Azure ML Workspace is an Azure resource that organizes and coordinates the actions of many other Azure resources to assist in executing and sharing machine learning workflows. In particular, an Azure ML Workspace coordinates storage, databases, and compute resources providing added functionality for machine learning experimentation, deployment, inferencing, and the monitoring of deployed models."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"This section describes activities required before you can access any Azure ML services functionality."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 1. Azure Subscription\n",
|
||||
"\n",
|
||||
"In order to create an Azure ML Workspace, first you need access to an Azure subscription. An Azure subscription allows you to manage storage, compute, and other assets in the Azure cloud. You can [create a new subscription](https://azure.microsoft.com/en-us/free/) or access existing subscription information from the [Azure portal](https://portal.azure.com). Later in this notebook you will need information such as your subscription ID in order to create and access AML workspaces.\n",
|
||||
"\n",
|
||||
"### 2. Azure ML SDK and other library installation\n",
|
||||
"\n",
|
||||
"If you are running in your own environment, follow [SDK installation instructions](https://docs.microsoft.com/azure/machine-learning/service/how-to-configure-environment). If you are running in Azure Notebooks or another Microsoft managed environment, the SDK is already installed.\n",
|
||||
"\n",
|
||||
"Also install following libraries to your environment. Many of the example notebooks depend on them\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"(myenv) $ conda install -y matplotlib tqdm scikit-learn\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Once installation is complete, the following cell checks the Azure ML SDK version:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"install"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"This notebook was created using version of the Azure ML SDK\")\n",
|
||||
"print(\"You are currently using version\", azureml.core.VERSION, \"of the Azure ML SDK\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you are using an older version of the SDK then this notebook was created using, you should upgrade your SDK.\n",
|
||||
"\n",
|
||||
"### 3. Azure Container Instance registration\n",
|
||||
"Azure Machine Learning uses of [Azure Container Instance (ACI)](https://azure.microsoft.com/services/container-instances) to deploy dev/test web services. An Azure subscription needs to be registered to use ACI. If you or the subscription owner have not yet registered ACI on your subscription, you will need to use the [Azure CLI](https://docs.microsoft.com/en-us/cli/azure/install-azure-cli?view=azure-cli-latest) and execute the following commands. Note that if you ran through the AML [quickstart](https://docs.microsoft.com/en-us/azure/machine-learning/service/quickstart-get-started) you have already registered ACI. \n",
|
||||
"\n",
|
||||
"```shell\n",
|
||||
"# check to see if ACI is already registered\n",
|
||||
"(myenv) $ az provider show -n Microsoft.ContainerInstance -o table\n",
|
||||
"\n",
|
||||
"# if ACI is not registered, run this command.\n",
|
||||
"# note you need to be the subscription owner in order to execute this command successfully.\n",
|
||||
"(myenv) $ az provider register -n Microsoft.ContainerInstance\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Configure your Azure ML workspace\n",
|
||||
"\n",
|
||||
"### Workspace parameters\n",
|
||||
"\n",
|
||||
"To use an AML Workspace, you will need to import the Azure ML SDK and supply the following information:\n",
|
||||
"* Your subscription id\n",
|
||||
"* A resource group name\n",
|
||||
"* (optional) The region that will host your workspace\n",
|
||||
"* A name for your workspace\n",
|
||||
"\n",
|
||||
"You can get your subscription ID from the [Azure portal](https://portal.azure.com).\n",
|
||||
"\n",
|
||||
"You will also need access to a [_resource group_](https://docs.microsoft.com/en-us/azure/azure-resource-manager/resource-group-overview#resource-groups), which organizes Azure resources and provides a default region for the resources in a group. You can see what resource groups to which you have access, or create a new one in the [Azure portal](https://portal.azure.com). If you don't have a resource group, the create workspace command will create one for you using the name you provide.\n",
|
||||
"\n",
|
||||
"The region to host your workspace will be used if you are creating a new workspace. You do not need to specify this if you are using an existing workspace. You can find the list of supported regions [here](https://azure.microsoft.com/en-us/global-infrastructure/services/?products=machine-learning-service). You should pick a region that is close to your location or that contains your data.\n",
|
||||
"\n",
|
||||
"The name for your workspace is unique within the subscription and should be descriptive enough to discern among other AML Workspaces. The subscription may be used only by you, or it may be used by your department or your entire enterprise, so choose a name that makes sense for your situation.\n",
|
||||
"\n",
|
||||
"The following cell allows you to specify your workspace parameters. This cell uses the python method `os.getenv` to read values from environment variables which is useful for automation. If no environment variable exists, the parameters will be set to the specified default values. \n",
|
||||
"\n",
|
||||
"If you ran the Azure Machine Learning [quickstart](https://docs.microsoft.com/en-us/azure/machine-learning/service/quickstart-get-started) in Azure Notebooks, you already have a configured workspace! You can go to your Azure Machine Learning Getting Started library, view *config.json* file, and copy-paste the values for subscription ID, resource group and workspace name below.\n",
|
||||
"\n",
|
||||
"Replace the default values in the cell below with your workspace parameters"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"subscription_id = os.getenv(\"SUBSCRIPTION_ID\", default=\"<my-subscription-id>\")\n",
|
||||
"resource_group = os.getenv(\"RESOURCE_GROUP\", default=\"<my-resource-group>\")\n",
|
||||
"workspace_name = os.getenv(\"WORKSPACE_NAME\", default=\"<my-workspace-name>\")\n",
|
||||
"workspace_region = os.getenv(\"WORKSPACE_REGION\", default=\"eastus2\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Access your workspace\n",
|
||||
"\n",
|
||||
"The following cell uses the Azure ML SDK to attempt to load the workspace specified by your parameters. If this cell succeeds, your notebook library will be configured to access the workspace from all notebooks using the `Workspace.from_config()` method. The cell can fail if the specified workspace doesn't exist or you don't have permissions to access it. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"try:\n",
|
||||
" ws = Workspace(subscription_id = subscription_id, resource_group = resource_group, workspace_name = workspace_name)\n",
|
||||
" # write the details of the workspace to a configuration file to the notebook library\n",
|
||||
" ws.write_config()\n",
|
||||
" print(\"Workspace configuration succeeded. Skip the workspace creation steps below\")\n",
|
||||
"except:\n",
|
||||
" print(\"Workspace not accessible. Change your parameters or create a new workspace below\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a new workspace\n",
|
||||
"\n",
|
||||
"If you don't have an existing workspace and are the owner of the subscription or resource group, you can create a new workspace. If you don't have a resource group, the create workspace command will create one for you using the name you provide.\n",
|
||||
"\n",
|
||||
"**Note**: As with other Azure services, there are limits on certain resources (for example AmlCompute quota) associated with the Azure ML service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota.\n",
|
||||
"\n",
|
||||
"This cell will create an Azure ML workspace for you in a subscription provided you have the correct permissions.\n",
|
||||
"\n",
|
||||
"This will fail if:\n",
|
||||
"* You do not have permission to create a workspace in the resource group\n",
|
||||
"* You do not have permission to create a resource group if it's non-existing.\n",
|
||||
"* You are not a subscription owner or contributor and no Azure ML workspaces have ever been created in this subscription\n",
|
||||
"\n",
|
||||
"If workspace creation fails, please work with your IT admin to provide you with the appropriate permissions or to provision the required resources."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create workspace"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"# Create the workspace using the specified parameters\n",
|
||||
"ws = Workspace.create(name = workspace_name,\n",
|
||||
" subscription_id = subscription_id,\n",
|
||||
" resource_group = resource_group, \n",
|
||||
" location = workspace_region,\n",
|
||||
" create_resource_group = True,\n",
|
||||
" exist_ok = True)\n",
|
||||
"ws.get_details()\n",
|
||||
"\n",
|
||||
"# write the details of the workspace to a configuration file to the notebook library\n",
|
||||
"ws.write_config()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create compute resources for your training experiments\n",
|
||||
"\n",
|
||||
"Many of the sample notebooks use Azure ML managed compute (AmlCompute) to train models using a dynamically scalable pool of compute. In this section you will create default compute clusters for use by the other notebooks and any other operations you choose.\n",
|
||||
"\n",
|
||||
"To create a cluster, you need to specify a compute configuration that specifies the type of machine to be used and the scalability behaviors. Then you choose a name for the cluster that is unique within the workspace that can be used to address the cluster later.\n",
|
||||
"\n",
|
||||
"The cluster parameters are:\n",
|
||||
"* vm_size - this describes the virtual machine type and size used in the cluster. All machines in the cluster are the same type. You can get the list of vm sizes available in your region by using the CLI command\n",
|
||||
"\n",
|
||||
"```shell\n",
|
||||
"az vm list-skus -o tsv\n",
|
||||
"```\n",
|
||||
"* min_nodes - this sets the minimum size of the cluster. If you set the minimum to 0 the cluster will shut down all nodes while not in use. Setting this number to a value higher than 0 will allow for faster start-up times, but you will also be billed when the cluster is not in use.\n",
|
||||
"* max_nodes - this sets the maximum size of the cluster. Setting this to a larger number allows for more concurrency and a greater distributed processing of scale-out jobs.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"To create a **CPU** cluster now, run the cell below. The autoscale settings mean that the cluster will scale down to 0 nodes when inactive and up to 4 nodes when busy."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
|
||||
"from azureml.core.compute_target import ComputeTargetException\n",
|
||||
"\n",
|
||||
"# Choose a name for your CPU cluster\n",
|
||||
"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 cpu-cluster\")\n",
|
||||
"except ComputeTargetException:\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",
|
||||
" min_nodes=0,\n",
|
||||
" max_nodes=4)\n",
|
||||
"\n",
|
||||
" # Create the cluster with the specified name and configuration\n",
|
||||
" cpu_cluster = ComputeTarget.create(ws, cpu_cluster_name, compute_config)\n",
|
||||
" \n",
|
||||
" # Wait for the cluster to complete, show the output log\n",
|
||||
" cpu_cluster.wait_for_completion(show_output=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To create a **GPU** cluster, run the cell below. Note that your subscription must have sufficient quota for GPU VMs or the command will fail. To increase quota, see [these instructions](https://docs.microsoft.com/en-us/azure/azure-supportability/resource-manager-core-quotas-request). "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
|
||||
"from azureml.core.compute_target import ComputeTargetException\n",
|
||||
"\n",
|
||||
"# Choose a name for your GPU cluster\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 gpu-cluster\")\n",
|
||||
" \n",
|
||||
" # Specify the configuration for the new cluster\n",
|
||||
" compute_config = AmlCompute.provisioning_configuration(vm_size=\"STANDARD_NC6\",\n",
|
||||
" min_nodes=0,\n",
|
||||
" max_nodes=4)\n",
|
||||
" # Create the cluster with the specified name and configuration\n",
|
||||
" gpu_cluster = ComputeTarget.create(ws, gpu_cluster_name, compute_config)\n",
|
||||
"\n",
|
||||
" # Wait for the cluster to complete, show the output log\n",
|
||||
" gpu_cluster.wait_for_completion(show_output=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"---\n",
|
||||
"\n",
|
||||
"## Next steps\n",
|
||||
"\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 within notebook](./how-to-use-azureml/training/train-within-notebook) example that walks through a simplified but complete end to end machine learning process."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "roastala"
|
||||
}
|
||||
],
|
||||
"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": "3.6.5"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
4
configuration.yml
Normal file
4
configuration.yml
Normal file
@@ -0,0 +1,4 @@
|
||||
name: configuration
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
File diff suppressed because it is too large
Load Diff
709
contrib/datadrift/azure-ml-datadrift.ipynb
Normal file
709
contrib/datadrift/azure-ml-datadrift.ipynb
Normal file
@@ -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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"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
|
||||
}
|
||||
8
contrib/datadrift/azure-ml-datadrift.yml
Normal file
8
contrib/datadrift/azure-ml-datadrift.yml
Normal file
@@ -0,0 +1,8 @@
|
||||
name: azure-ml-datadrift
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-contrib-datadrift
|
||||
- azureml-contrib-opendatasets
|
||||
- lightgbm
|
||||
- azureml-widgets
|
||||
58
contrib/datadrift/score.py
Normal file
58
contrib/datadrift/score.py
Normal file
@@ -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
|
||||
@@ -179,6 +179,26 @@ jupyter notebook
|
||||
- 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.
|
||||
|
||||
|
||||
@@ -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.
|
||||
|
||||
|
||||
@@ -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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"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
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification-bank-marketing
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"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 (Universit\u00c3\u00a9 Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project\n",
|
||||
"Please cite the following works: \n",
|
||||
"\u00e2\u20ac\u00a2\tAndrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
|
||||
"\u00e2\u20ac\u00a2\tDal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
|
||||
"\u00e2\u20ac\u00a2\tDal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE\n",
|
||||
"o\tDal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
|
||||
"\u00e2\u20ac\u00a2\tCarcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-A\u00c3\u00abl; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier\n",
|
||||
"\u00e2\u20ac\u00a2\tCarcillo, Fabrizio; Le Borgne, Yann-A\u00c3\u00abl; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification-credit-card-fraud
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification-with-deployment
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -129,6 +129,22 @@
|
||||
" 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",
|
||||
@@ -158,6 +174,13 @@
|
||||
"|**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,
|
||||
@@ -299,7 +322,7 @@
|
||||
" onnxrt_present = False\n",
|
||||
"\n",
|
||||
"def get_onnx_res(run):\n",
|
||||
" res_path = '_debug_y_trans_converter.json'\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",
|
||||
@@ -316,7 +339,7 @@
|
||||
" print(pred_prob_onnx)\n",
|
||||
"else:\n",
|
||||
" if not python_version_compatible:\n",
|
||||
" print('Please use Python version 3.6 to run the inference helper.') \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.')"
|
||||
]
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-classification-with-onnx
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- onnxruntime
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification-with-whitelisting
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-classification
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -21,7 +21,7 @@
|
||||
"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",
|
||||
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-dataprep-remote-execution
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-dataprep
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-exploring-previous-runs
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -36,19 +36,17 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"In this example, we show how AutoML can be used for bike share forecasting.\n",
|
||||
"This notebook demonstrates demand forecasting for a bike-sharing service using AutoML.\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",
|
||||
"AutoML highlights here include built-in holiday featurization, accessing engineered feature names, and working with the `forecast` function. Please also look at the additional forecasting notebooks, which document lagging, rolling windows, forecast quantiles, other ways to use the forecast function, and forecaster deployment.\n",
|
||||
"\n",
|
||||
"Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
|
||||
"\n",
|
||||
"In this notebook you would see\n",
|
||||
"Notebook synopsis:\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"
|
||||
"2. Configuration and local run of AutoML for a time-series model with lag and holiday features \n",
|
||||
"3. Viewing the engineered names for featurized data and featurization summary for all raw features\n",
|
||||
"4. Evaluating the fitted model using a rolling test "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -69,10 +67,12 @@
|
||||
"import numpy as np\n",
|
||||
"import logging\n",
|
||||
"import warnings\n",
|
||||
"\n",
|
||||
"from pandas.tseries.frequencies import to_offset\n",
|
||||
"\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",
|
||||
"from azureml.train.automl import AutoMLConfig\n",
|
||||
@@ -84,7 +84,7 @@
|
||||
"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."
|
||||
"As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -129,14 +129,15 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = pd.read_csv('bike-no.csv', parse_dates=['date'])"
|
||||
"data = pd.read_csv('bike-no.csv', parse_dates=['date'])\n",
|
||||
"data.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's set up what we know abou the dataset. \n",
|
||||
"Let's set up what we know about the dataset. \n",
|
||||
"\n",
|
||||
"**Target column** is what we want to forecast.\n",
|
||||
"\n",
|
||||
@@ -194,8 +195,7 @@
|
||||
"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."
|
||||
"The forecast horizon is the number of periods into the future that the model should predict. Here, we set the horizon to 14 periods (i.e. 14 days). Notice that this is much shorter than the number of days in the test set; we will need to use a rolling test to evaluate the performance on the whole test set. For more discussion of forecast horizons and guiding principles for setting them, please see the [energy demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand). "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -204,10 +204,7 @@
|
||||
"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()"
|
||||
"max_horizon = 14"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -237,26 +234,25 @@
|
||||
"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",
|
||||
" 'time_column_name': time_column_name,\n",
|
||||
" 'max_horizon': max_horizon,\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",
|
||||
" 'country_or_region': 'US',\n",
|
||||
" 'target_lags': 1,\n",
|
||||
" # these columns are a breakdown of the total and therefore a leak\n",
|
||||
" 'drop_column_names': ['casual', 'registered']\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task = 'forecasting', \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",
|
||||
" 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",
|
||||
" verbosity=logging.INFO,\n",
|
||||
" **automl_settings)"
|
||||
]
|
||||
},
|
||||
@@ -264,7 +260,7 @@
|
||||
"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."
|
||||
"We will now run the experiment, starting with 10 iterations of model search. The experiment can be continued for more iterations if more accurate results are required. You will see the currently running iterations printing to the console."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -356,11 +352,16 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Test the Best Fitted Model\n",
|
||||
"## Evaluate"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now use the best fitted model from the AutoML Run to make forecasts for the test set. \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."
|
||||
"We always score on the original dataset whose schema matches the training set schema."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -372,21 +373,12 @@
|
||||
"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": [
|
||||
"We now define some functions for aligning output to input and for producing rolling forecasts over the full test set. As previously stated, the forecast horizon of 14 days is shorter than the length of the test set - which is about 120 days. To get predictions over the full test set, we iterate over the test set, making forecasts 14 days at a time and combining the results. We also make sure that each 14-day forecast uses up-to-date actuals - the current context - to construct lag features. \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."
|
||||
]
|
||||
},
|
||||
@@ -396,7 +388,8 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name = 'predicted'):\n",
|
||||
"def align_outputs(y_predicted, X_trans, X_test, y_test, predicted_column_name='predicted',\n",
|
||||
" horizon_colname='horizon_origin'):\n",
|
||||
" \"\"\"\n",
|
||||
" Demonstrates how to get the output aligned to the inputs\n",
|
||||
" using pandas indexes. Helps understand what happened if\n",
|
||||
@@ -408,7 +401,8 @@
|
||||
" * 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",
|
||||
" df_fcst = pd.DataFrame({predicted_column_name : y_predicted,\n",
|
||||
" horizon_colname: X_trans[horizon_colname]})\n",
|
||||
" # y and X outputs are aligned by forecast() function contract\n",
|
||||
" df_fcst.index = X_trans.index\n",
|
||||
" \n",
|
||||
@@ -427,7 +421,49 @@
|
||||
" 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"
|
||||
"def do_rolling_forecast(fitted_model, X_test, y_test, max_horizon, freq='D'):\n",
|
||||
" \"\"\"\n",
|
||||
" Produce forecasts on a rolling origin over the given test set.\n",
|
||||
" \n",
|
||||
" Each iteration makes a forecast for the next 'max_horizon' periods \n",
|
||||
" with respect to the current origin, then advances the origin by the horizon time duration. \n",
|
||||
" The prediction context for each forecast is set so that the forecaster uses \n",
|
||||
" the actual target values prior to the current origin time for constructing lag features.\n",
|
||||
" \n",
|
||||
" This function returns a concatenated DataFrame of rolling forecasts.\n",
|
||||
" \"\"\"\n",
|
||||
" df_list = []\n",
|
||||
" origin_time = X_test[time_column_name].min()\n",
|
||||
" while origin_time <= X_test[time_column_name].max():\n",
|
||||
" # Set the horizon time - end date of the forecast\n",
|
||||
" horizon_time = origin_time + max_horizon * to_offset(freq)\n",
|
||||
" \n",
|
||||
" # Extract test data from an expanding window up-to the horizon \n",
|
||||
" expand_wind = (X_test[time_column_name] < horizon_time)\n",
|
||||
" X_test_expand = X_test[expand_wind]\n",
|
||||
" y_query_expand = np.zeros(len(X_test_expand)).astype(np.float)\n",
|
||||
" y_query_expand.fill(np.NaN)\n",
|
||||
" \n",
|
||||
" if origin_time != X_test[time_column_name].min():\n",
|
||||
" # Set the context by including actuals up-to the origin time\n",
|
||||
" test_context_expand_wind = (X_test[time_column_name] < origin_time)\n",
|
||||
" context_expand_wind = (X_test_expand[time_column_name] < origin_time)\n",
|
||||
" y_query_expand[context_expand_wind] = y_test[test_context_expand_wind]\n",
|
||||
" \n",
|
||||
" # Make a forecast out to the maximum horizon\n",
|
||||
" y_fcst, X_trans = fitted_model.forecast(X_test_expand, y_query_expand)\n",
|
||||
" \n",
|
||||
" # Align forecast with test set for dates within the current rolling window \n",
|
||||
" trans_tindex = X_trans.index.get_level_values(time_column_name)\n",
|
||||
" trans_roll_wind = (trans_tindex >= origin_time) & (trans_tindex < horizon_time)\n",
|
||||
" test_roll_wind = expand_wind & (X_test[time_column_name] >= origin_time)\n",
|
||||
" df_list.append(align_outputs(y_fcst[trans_roll_wind], X_trans[trans_roll_wind],\n",
|
||||
" X_test[test_roll_wind], y_test[test_roll_wind]))\n",
|
||||
" \n",
|
||||
" # Advance the origin time\n",
|
||||
" origin_time = horizon_time\n",
|
||||
" \n",
|
||||
" return pd.concat(df_list, ignore_index=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -436,6 +472,30 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_all = do_rolling_forecast(fitted_model, X_test, y_test, max_horizon)\n",
|
||||
"df_all"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now calculate some error metrics for the forecasts and vizualize the predictions vs. the actuals."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def APE(actual, pred):\n",
|
||||
" \"\"\"\n",
|
||||
" Calculate absolute percentage error.\n",
|
||||
" Returns a vector of APE values with same length as actual/pred.\n",
|
||||
" \"\"\"\n",
|
||||
" return 100*np.abs((actual - pred)/actual)\n",
|
||||
"\n",
|
||||
"def MAPE(actual, pred):\n",
|
||||
" \"\"\"\n",
|
||||
" Calculate mean absolute percentage error.\n",
|
||||
@@ -445,8 +505,7 @@
|
||||
" 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)"
|
||||
" return np.mean(APE(actual_safe, pred_safe))"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -469,12 +528,57 @@
|
||||
"plt.legend((test_pred, test_test), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The MAPE seems high; it is being skewed by an actual with a small absolute value. For a more informative evaluation, we can calculate the metrics by forecast horizon:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_all.groupby('horizon_origin').apply(\n",
|
||||
" lambda df: pd.Series({'MAPE': MAPE(df[target_column_name], df['predicted']),\n",
|
||||
" 'RMSE': np.sqrt(mean_squared_error(df[target_column_name], df['predicted'])),\n",
|
||||
" 'MAE': mean_absolute_error(df[target_column_name], df['predicted'])}))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"It's also interesting to see the distributions of APE (absolute percentage error) by horizon. On a log scale, the outlying APE in the horizon-3 group is clear."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"df_all_APE = df_all.assign(APE=APE(df_all[target_column_name], df_all['predicted']))\n",
|
||||
"APEs = [df_all_APE[df_all['horizon_origin'] == h].APE.values for h in range(1, max_horizon + 1)]\n",
|
||||
"\n",
|
||||
"%matplotlib notebook\n",
|
||||
"plt.boxplot(APEs)\n",
|
||||
"plt.yscale('log')\n",
|
||||
"plt.xlabel('horizon')\n",
|
||||
"plt.ylabel('APE (%)')\n",
|
||||
"plt.title('Absolute Percentage Errors by Forecast Horizon')\n",
|
||||
"\n",
|
||||
"plt.show()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "xiaga@microsoft.com, tosingli@microsoft.com"
|
||||
"name": "xiaga@microsoft.com, tosingli@microsoft.com, erwright@microsoft.com"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
@@ -492,7 +596,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.7"
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-forecasting-bike-share
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- statsmodels
|
||||
@@ -35,17 +35,16 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"In this example, we show how AutoML can be used for energy demand forecasting.\n",
|
||||
"In this example, we show how AutoML can be used to forecast a single time-series in the energy demand application area. \n",
|
||||
"\n",
|
||||
"Make sure you have executed the [configuration](../../../configuration.ipynb) before running this notebook.\n",
|
||||
"\n",
|
||||
"In this notebook you would see\n",
|
||||
"Notebook synopsis:\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"
|
||||
"2. Configuration and local run of AutoML for a simple time-series model\n",
|
||||
"3. View engineered features and prediction results\n",
|
||||
"4. Configuration and local run of AutoML for a time-series model with lag and rolling window features\n",
|
||||
"5. Estimate feature importance"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -66,10 +65,10 @@
|
||||
"import numpy as np\n",
|
||||
"import logging\n",
|
||||
"import warnings\n",
|
||||
"\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",
|
||||
"from azureml.train.automl import AutoMLConfig\n",
|
||||
@@ -81,7 +80,7 @@
|
||||
"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."
|
||||
"As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -117,7 +116,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Data\n",
|
||||
"Read energy demanding data from file, and preview data."
|
||||
"We will use energy consumption data from New York City for model training. The data is stored in a tabular format and includes energy demand and basic weather data at an hourly frequency. Pandas CSV reader is used to read the file into memory. Special attention is given to the \"timeStamp\" column in the data since it contains text which should be parsed as datetime-type objects. "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -130,13 +129,20 @@
|
||||
"data.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We must now define the schema of this dataset. Every time-series must have a time column and a target. The target quantity is what will be eventually forecasted by a trained model. In this case, the target is the \"demand\" column. The other columns, \"temp\" and \"precip,\" are implicitly designated as features."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# let's take note of what columns means what in the data\n",
|
||||
"# Dataset schema\n",
|
||||
"time_column_name = 'timeStamp'\n",
|
||||
"target_column_name = 'demand'"
|
||||
]
|
||||
@@ -145,7 +151,14 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Split the data into train and test sets\n"
|
||||
"### Forecast Horizon\n",
|
||||
"\n",
|
||||
"In addition to the data schema, we must also specify the forecast horizon. A forecast horizon is a time span into the future (or just beyond the latest date in the training data) where forecasts of the target quantity are needed. Choosing a forecast horizon is application specific, but a rule-of-thumb is that **the horizon should be the time-frame where you need actionable decisions based on the forecast.** The horizon usually has a strong relationship with the frequency of the time-series data, that is, the sampling interval of the target quantity and the features. For instance, the NYC energy demand data has an hourly frequency. A decision that requires a demand forecast to the hour is unlikely to be made weeks or months in advance, particularly if we expect weather to be a strong determinant of demand. We may have fairly accurate meteorological forecasts of the hourly temperature and precipitation on a the time-scale of a day or two, however.\n",
|
||||
"\n",
|
||||
"Given the above discussion, we generally recommend that users set forecast horizons to less than 100 time periods (i.e. less than 100 hours in the NYC energy example). Furthermore, **AutoML's memory use and computation time increase in proportion to the length of the horizon**, so the user should consider carefully how they set this value. If a long horizon forecast really is necessary, it may be good practice to aggregate the series to a coarser time scale. \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Forecast horizons in AutoML are given as integer multiples of the time-series frequency. In this example, we set the horizon to 48 hours."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -154,8 +167,32 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_train = data[data[time_column_name] < '2017-02-01']\n",
|
||||
"X_test = data[data[time_column_name] >= '2017-02-01']\n",
|
||||
"max_horizon = 48"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Split the data into train and test sets\n",
|
||||
"We now split the data into a train and a test set so that we may evaluate model performance. We note that the tail of the dataset contains a large number of NA values in the target column, so we designate the test set as the 48 hour window ending on the latest date of known energy demand. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Find time point to split on\n",
|
||||
"latest_known_time = data[~pd.isnull(data[target_column_name])][time_column_name].max()\n",
|
||||
"split_time = latest_known_time - pd.Timedelta(hours=max_horizon)\n",
|
||||
"\n",
|
||||
"# Split into train/test sets\n",
|
||||
"X_train = data[data[time_column_name] <= split_time]\n",
|
||||
"X_test = data[(data[time_column_name] > split_time) & (data[time_column_name] <= latest_known_time)]\n",
|
||||
"\n",
|
||||
"# Move the target values into their own arrays \n",
|
||||
"y_train = X_train.pop(target_column_name).values\n",
|
||||
"y_test = X_test.pop(target_column_name).values"
|
||||
]
|
||||
@@ -166,7 +203,7 @@
|
||||
"source": [
|
||||
"## Train\n",
|
||||
"\n",
|
||||
"Instantiate a AutoMLConfig object. This defines the settings and data used to run the experiment.\n",
|
||||
"We now instantiate an AutoMLConfig object. This config defines the settings and data used to run the experiment. For forecasting tasks, we must provide extra configuration related to the time-series data schema and forecasting context. Here, only the name of the time column and the maximum forecast horizon are needed. Other settings are described below:\n",
|
||||
"\n",
|
||||
"|Property|Description|\n",
|
||||
"|-|-|\n",
|
||||
@@ -176,7 +213,7 @@
|
||||
"|**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",
|
||||
"|**n_cross_validations**|Number of cross validation splits. Rolling Origin Validation is used to split time-series in a temporally consistent way.|\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. "
|
||||
]
|
||||
},
|
||||
@@ -186,22 +223,22 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"automl_settings = {\n",
|
||||
" \"time_column_name\": time_column_name \n",
|
||||
"time_series_settings = {\n",
|
||||
" 'time_column_name': time_column_name,\n",
|
||||
" 'max_horizon': max_horizon\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task = 'forecasting',\n",
|
||||
" debug_log = 'automl_nyc_energy_errors.log',\n",
|
||||
"automl_config = 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",
|
||||
" 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)"
|
||||
" **time_series_settings)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -358,7 +395,8 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Calculate accuracy metrics\n"
|
||||
"### Calculate accuracy metrics\n",
|
||||
"Finally, we calculate some accuracy metrics for the forecast and plot the predictions vs. the actuals over the time range in the test set."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -395,9 +433,12 @@
|
||||
"\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",
|
||||
"pred, = plt.plot(df_all[time_column_name], df_all['predicted'], color='b')\n",
|
||||
"actual, = plt.plot(df_all[time_column_name], df_all[target_column_name], color='g')\n",
|
||||
"plt.xticks(fontsize=8)\n",
|
||||
"plt.legend((pred, actual), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.title('Prediction vs. Actual Time-Series')\n",
|
||||
"\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
@@ -412,16 +453,16 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Using lags and rolling window features to improve the forecast"
|
||||
"### Using lags and rolling window features"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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",
|
||||
"We did not use lags in the previous model specification. In effect, the prediction was the result of a simple regression on date, grain and any additional features. This is often a very good prediction as common time series patterns like seasonality and trends can be captured in this manner. Such simple regression is horizon-less: it doesn't matter how far into the future we are predicting, because we are not using past data. In the previous example, the horizon was only used to split the data for cross-validation.\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."
|
||||
"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 still specify the `max_horizon` that the model will learn to forecast. The `target_lags` keyword specifies how far back we will construct the lags of the target variable, and the `target_rolling_window_size` specifies the size of the rolling window over which we will generate the `max`, `min` and `sum` features."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -430,27 +471,32 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"automl_settings_lags = {\n",
|
||||
"time_series_settings_with_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",
|
||||
" 'max_horizon': max_horizon,\n",
|
||||
" 'target_lags': 12,\n",
|
||||
" 'target_rolling_window_size': 4\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)"
|
||||
"automl_config_lags = AutoMLConfig(task='forecasting',\n",
|
||||
" debug_log='automl_nyc_energy_errors.log',\n",
|
||||
" primary_metric='normalized_root_mean_squared_error',\n",
|
||||
" blacklist_models=['ElasticNet'],\n",
|
||||
" iterations=10,\n",
|
||||
" iteration_timeout_minutes=10,\n",
|
||||
" X=X_train,\n",
|
||||
" y=y_train,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" path=project_folder,\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
" **time_series_settings_with_lags)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now start a new local run, this time with lag and rolling window featurization. AutoML applies featurizations in the setup stage, prior to iterating over ML models. The full training set is featurized first, followed by featurization of each of the CV splits. Lag and rolling window features introduce additional complexity, so the run will take longer than in the previous example that lacked these featurizations."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -498,9 +544,10 @@
|
||||
"\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",
|
||||
"pred, = plt.plot(df_lags[time_column_name], df_lags['predicted'], color='b')\n",
|
||||
"actual, = plt.plot(df_lags[time_column_name], df_lags[target_column_name], color='g')\n",
|
||||
"plt.xticks(fontsize=8)\n",
|
||||
"plt.legend((pred, actual), ('prediction', 'truth'), loc='upper left', fontsize=8)\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
@@ -520,8 +567,8 @@
|
||||
"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",
|
||||
"features = X_trans_lags.columns[:-1]\n",
|
||||
"expl = explain_model(fitted_model_lags, X_train.copy(), X_test.copy(), 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"
|
||||
@@ -540,7 +587,7 @@
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "xiaga, tosingli"
|
||||
"name": "xiaga, tosingli, erwright"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
@@ -558,7 +605,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.7"
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -0,0 +1,10 @@
|
||||
name: auto-ml-forecasting-energy-demand
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- statsmodels
|
||||
- azureml-explain-model
|
||||
@@ -37,16 +37,10 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Introduction\n",
|
||||
"In this example, we use AutoML to find and tune a time-series forecasting model.\n",
|
||||
"In this example, we use AutoML to train, select, and operationalize a time-series forecasting model for multiple time-series.\n",
|
||||
"\n",
|
||||
"Make sure you have executed the [configuration notebook](../../../configuration.ipynb) before running this notebook.\n",
|
||||
"\n",
|
||||
"In this notebook, you will:\n",
|
||||
"1. Create an Experiment in an existing Workspace\n",
|
||||
"2. Instantiate an AutoMLConfig \n",
|
||||
"3. Find and train a forecasting model using local compute\n",
|
||||
"4. Evaluate the performance of the model\n",
|
||||
"\n",
|
||||
"The examples in the follow code samples use the University of Chicago's Dominick's Finer Foods dataset to forecast orange juice sales. Dominick's was a grocery chain in the Chicago metropolitan area."
|
||||
]
|
||||
},
|
||||
@@ -68,10 +62,10 @@
|
||||
"import numpy as np\n",
|
||||
"import logging\n",
|
||||
"import warnings\n",
|
||||
"\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",
|
||||
"from azureml.train.automl import AutoMLConfig\n",
|
||||
@@ -82,7 +76,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment is a named object in a Workspace which represents a predictive task, the output of which is a trained model and a set of evaluation metrics for the model. "
|
||||
"As part of the setup you have already created a <b>Workspace</b>. To run AutoML, you also need to create an <b>Experiment</b>. An Experiment corresponds to a prediction problem you are trying to solve, while a Run corresponds to a specific approach to the problem. "
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -236,7 +230,7 @@
|
||||
"\n",
|
||||
"For forecasting tasks, there are some additional parameters that can be set: the name of the column holding the date/time, the grain column names, and the maximum forecast horizon. A time column is required for forecasting, while the grain is optional. If a grain is not given, AutoML assumes that the whole dataset is a single time-series. We also pass a list of columns to drop prior to modeling. The _logQuantity_ column is completely correlated with the target quantity, so it must be removed to prevent a target leak.\n",
|
||||
"\n",
|
||||
"The forecast horizon is given in units of the time-series frequency; for instance, the OJ series frequency is weekly, so a horizon of 20 means that a trained model will estimate sales up-to 20 weeks beyond the latest date in the training data for each series. In this example, we set the maximum horizon to the number of samples per series in the test set (n_test_periods). Generally, the value of this parameter will be dictated by business needs. For example, a demand planning organizaion that needs to estimate the next month of sales would set the horizon accordingly. \n",
|
||||
"The forecast horizon is given in units of the time-series frequency; for instance, the OJ series frequency is weekly, so a horizon of 20 means that a trained model will estimate sales up-to 20 weeks beyond the latest date in the training data for each series. In this example, we set the maximum horizon to the number of samples per series in the test set (n_test_periods). Generally, the value of this parameter will be dictated by business needs. For example, a demand planning organizaion that needs to estimate the next month of sales would set the horizon accordingly. Please see the [energy_demand notebook](https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/automated-machine-learning/forecasting-energy-demand) for more discussion of forecast horizon.\n",
|
||||
"\n",
|
||||
"Finally, a note about the cross-validation (CV) procedure for time-series data. AutoML uses out-of-sample error estimates to select a best pipeline/model, so it is important that the CV fold splitting is done correctly. Time-series can violate the basic statistical assumptions of the canonical K-Fold CV strategy, so AutoML implements a [rolling origin validation](https://robjhyndman.com/hyndsight/tscv/) procedure to create CV folds for time-series data. To use this procedure, you just need to specify the desired number of CV folds in the AutoMLConfig object. It is also possible to bypass CV and use your own validation set by setting the *X_valid* and *y_valid* parameters of AutoMLConfig.\n",
|
||||
"\n",
|
||||
@@ -269,7 +263,7 @@
|
||||
" 'time_column_name': time_column_name,\n",
|
||||
" 'grain_column_names': grain_column_names,\n",
|
||||
" 'drop_column_names': ['logQuantity'],\n",
|
||||
" 'max_horizon': n_test_periods # optional\n",
|
||||
" 'max_horizon': n_test_periods\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"automl_config = AutoMLConfig(task='forecasting',\n",
|
||||
@@ -278,7 +272,7 @@
|
||||
" iterations=10,\n",
|
||||
" X=X_train,\n",
|
||||
" y=y_train,\n",
|
||||
" n_cross_validations=5,\n",
|
||||
" n_cross_validations=3,\n",
|
||||
" enable_ensembling=False,\n",
|
||||
" path=project_folder,\n",
|
||||
" verbosity=logging.INFO,\n",
|
||||
@@ -324,7 +318,8 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Predict\n",
|
||||
"# Forecasting\n",
|
||||
"\n",
|
||||
"Now that we have retrieved the best pipeline/model, it can be used to make predictions on test data. First, we remove the target values from the test set:"
|
||||
]
|
||||
},
|
||||
@@ -852,7 +847,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.7"
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-forecasting-orange-juice-sales
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- statsmodels
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-missing-data-blacklist-early-termination
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-model-explanation
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- azureml-explain-model
|
||||
@@ -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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"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 \u00e2\u20ac\u0153loading status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
|
||||
"Note: The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.widgets import RunDetails\n",
|
||||
"RunDetails(remote_run).show() "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"\n",
|
||||
"Retrieve All Child Runs\n",
|
||||
"You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"children = list(remote_run.get_children())\n",
|
||||
"metricslist = {}\n",
|
||||
"for run in children:\n",
|
||||
" properties = run.get_properties()\n",
|
||||
" metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)}\n",
|
||||
" metricslist[int(properties['iteration'])] = metrics\n",
|
||||
"\n",
|
||||
"rundata = pd.DataFrame(metricslist).sort_index(1)\n",
|
||||
"rundata"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Retrieve the Best Model\n",
|
||||
"Below we select the best pipeline from our iterations. The get_output method returns the best run and the fitted model. The Model includes the pipeline and any pre-processing. Overloads on get_output allow you to retrieve the best run and fitted model for any logged metric or for a particular iteration."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"best_run, fitted_model = remote_run.get_output()\n",
|
||||
"print(best_run)\n",
|
||||
"print(fitted_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Best Model Based on Any Other Metric\n",
|
||||
"Show the run and the model that has the smallest root_mean_squared_error value (which turned out to be the same as the one with largest spearman_correlation value):"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"lookup_metric = \"root_mean_squared_error\"\n",
|
||||
"best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
|
||||
"print(best_run)\n",
|
||||
"print(fitted_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"iteration = 3\n",
|
||||
"third_run, third_model = remote_run.get_output(iteration = iteration)\n",
|
||||
"print(third_run)\n",
|
||||
"print(third_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Register the Fitted Model for Deployment\n",
|
||||
"If neither metric nor iteration are specified in the register_model call, the iteration with the best primary metric is registered."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"description = 'AutoML Model'\n",
|
||||
"tags = None\n",
|
||||
"model = remote_run.register_model(description = description, tags = tags)\n",
|
||||
"\n",
|
||||
"print(remote_run.model_id) # This will be written to the script file later in the notebook."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create Scoring Script\n",
|
||||
"The scoring script is required to generate the image for deployment. It contains the code to do the predictions on input data."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy\n",
|
||||
"import azureml.train.automl\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" model_path = Model.get_model_path(model_name = '<<modelid>>') # this name is model.id of model that we want to deploy\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"def run(rawdata):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(rawdata)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" except Exception as e:\n",
|
||||
" result = str(e)\n",
|
||||
" return json.dumps({\"error\": result})\n",
|
||||
" return json.dumps({\"result\":result.tolist()})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a YAML File for the Environment"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To ensure the fit results are consistent with the training results, the SDK dependency versions need to be the same as the environment that trains the model. Details about retrieving the versions can be found in notebook [12.auto-ml-retrieve-the-training-sdk-versions](12.auto-ml-retrieve-the-training-sdk-versions.ipynb)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dependencies = remote_run.get_run_sdk_dependencies(iteration = 1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for p in ['azureml-train-automl', 'azureml-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
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-regression-concrete-strength
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"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
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-regression-hardware-performance
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,9 @@
|
||||
name: auto-ml-regression
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
- paramiko<2.5.0
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-remote-amlcompute
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-sample-weight
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-sparse-data-train-test-split
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,8 @@
|
||||
name: auto-ml-subsampling-local
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,4 @@
|
||||
name: model-register-and-deploy
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -1,494 +1,494 @@
|
||||
{
|
||||
"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": [
|
||||
"# Azure ML Hardware Accelerated Object Detection"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This tutorial will show you how to deploy an object detection service based on the SSD-VGG model in just a few minutes using the Azure Machine Learning Accelerated AI service.\n",
|
||||
"\n",
|
||||
"We will use the SSD-VGG model accelerated on an FPGA. Our Accelerated Models Service handles translating deep neural networks (DNN) into an FPGA program.\n",
|
||||
"\n",
|
||||
"The steps in this notebook are: \n",
|
||||
"1. [Setup Environment](#set-up-environment)\n",
|
||||
"* [Construct Model](#construct-model)\n",
|
||||
" * Image Preprocessing\n",
|
||||
" * Featurizer\n",
|
||||
" * Save Model\n",
|
||||
" * Save input and output tensor names\n",
|
||||
"* [Create Image](#create-image)\n",
|
||||
"* [Deploy Image](#deploy-image)\n",
|
||||
"* [Test the Service](#test-service)\n",
|
||||
" * Create Client\n",
|
||||
" * Serve the model\n",
|
||||
"* [Cleanup](#cleanup)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"set-up-environment\"></a>\n",
|
||||
"## 1. Set up Environment\n",
|
||||
"### 1.a. Imports"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import tensorflow as tf"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 1.b. Retrieve Workspace\n",
|
||||
"If you haven't created a Workspace, please follow [this notebook](\"../../../configuration.ipynb\") to do so. If you have, run the codeblock below to retrieve it. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"construct-model\"></a>\n",
|
||||
"## 2. Construct model\n",
|
||||
"### 2.a. Image preprocessing\n",
|
||||
"We'd like our service to accept JPEG images as input. However the input to SSD-VGG is a float tensor of shape \\[1, 300, 300, 3\\]. The first dimension is batch, then height, width, and channels (i.e. NHWC). To bridge this gap, we need code that decodes JPEG images and resizes them appropriately for input to SSD-VGG. The Accelerated AI service can execute TensorFlow graphs as part of the service and we'll use that ability to do the image preprocessing. This code defines a TensorFlow graph that preprocesses an array of JPEG images (as TensorFlow strings) and produces a tensor that is ready to be featurized by SSD-VGG.\n",
|
||||
"\n",
|
||||
"**Note:** Expect to see TF deprecation warnings until we port our SDK over to use Tensorflow 2.0."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Input images as a two-dimensional tensor containing an arbitrary number of images represented a strings\n",
|
||||
"import azureml.accel.models.utils as utils\n",
|
||||
"tf.reset_default_graph()\n",
|
||||
"\n",
|
||||
"in_images = tf.placeholder(tf.string)\n",
|
||||
"image_tensors = utils.preprocess_array(in_images, output_width=300, output_height=300, preserve_aspect_ratio=False)\n",
|
||||
"print(image_tensors.shape)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 2.b. Featurizer\n",
|
||||
"The SSD-VGG model is different from our other models in that it generates 12 tensor outputs. These corresponds to x,y displacements of the anchor boxes and the detection confidence (for 21 classes). Because these outputs are not convenient to work with, we will later use a pre-defined post-processing utility to transform the outputs into a simplified list of bounding boxes with their respective class and confidence.\n",
|
||||
"\n",
|
||||
"For more information about the output tensors, take this example: the output tensor 'ssd_300_vgg/block4_box/Reshape_1:0' has a shape of [None, 37, 37, 4, 21]. This gives the pre-softmax confidence for 4 anchor boxes situated at each site of a 37 x 37 grid imposed on the image, one confidence score for each of the 21 classes. The first dimension is the batch dimension. Likewise, 'ssd_300_vgg/block4_box/Reshape:0' has shape [None, 37, 37, 4, 4] and encodes the (cx, cy) center shift and rescaling (sw, sh) relative to each anchor box. Refer to the [SSD-VGG paper](https://arxiv.org/abs/1512.02325) to understand how these are computed. The other 10 tensors are defined similarly."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.accel.models import SsdVgg\n",
|
||||
"\n",
|
||||
"saved_model_dir = os.path.join(os.path.expanduser('~'), 'models')\n",
|
||||
"model_graph = SsdVgg(saved_model_dir, is_frozen = True)\n",
|
||||
"\n",
|
||||
"print('SSD-VGG Input Tensors:')\n",
|
||||
"for idx, input_name in enumerate(model_graph.input_tensor_list):\n",
|
||||
" print('{}, {}'.format(input_name, model_graph.get_input_dims(idx)))\n",
|
||||
" \n",
|
||||
"print('SSD-VGG Output Tensors:')\n",
|
||||
"for idx, output_name in enumerate(model_graph.output_tensor_list):\n",
|
||||
" print('{}, {}'.format(output_name, model_graph.get_output_dims(idx)))\n",
|
||||
"\n",
|
||||
"ssd_outputs = model_graph.import_graph_def(image_tensors, is_training=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 2.c. Save Model\n",
|
||||
"Now that we loaded both parts of the tensorflow graph (preprocessor and SSD-VGG featurizer), we can save the graph and associated variables to a directory which we can register as an Azure ML Model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model_name = \"ssdvgg\"\n",
|
||||
"model_save_path = os.path.join(saved_model_dir, model_name, \"saved_model\")\n",
|
||||
"print(\"Saving model in {}\".format(model_save_path))\n",
|
||||
"\n",
|
||||
"output_map = {}\n",
|
||||
"for i, output in enumerate(ssd_outputs):\n",
|
||||
" output_map['out_{}'.format(i)] = output\n",
|
||||
"\n",
|
||||
"with tf.Session() as sess:\n",
|
||||
" model_graph.restore_weights(sess)\n",
|
||||
" tf.saved_model.simple_save(sess, \n",
|
||||
" model_save_path, \n",
|
||||
" inputs={'images': in_images}, \n",
|
||||
" outputs=output_map)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 2.d. Important! Save names of input and output tensors\n",
|
||||
"\n",
|
||||
"These input and output tensors that were created during the preprocessing and classifier steps are also going to be used when **converting the model** to an Accelerated Model that can run on FPGA's and for **making an inferencing request**. It is very important to save this information!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"register model from file"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"input_tensors = in_images.name\n",
|
||||
"# We will use the list of output tensors during inferencing\n",
|
||||
"output_tensors = [output.name for output in ssd_outputs]\n",
|
||||
"# However, for multiple output tensors, our AccelOnnxConverter will \n",
|
||||
"# accept comma-delimited strings (lists will cause error)\n",
|
||||
"output_tensors_str = \",\".join(output_tensors)\n",
|
||||
"\n",
|
||||
"print(input_tensors)\n",
|
||||
"print(output_tensors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"create-image\"></a>\n",
|
||||
"## 3. Create AccelContainerImage\n",
|
||||
"Below we will execute all the same steps as in the [Quickstart](./accelerated-models-quickstart.ipynb#create-image) to package the model we have saved locally into an accelerated Docker image saved in our workspace. To complete all the steps, it may take a few minutes. For more details on each step, check out the [Quickstart section on model registration](./accelerated-models-quickstart.ipynb#register-model)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"from azureml.core.image import Image\n",
|
||||
"from azureml.accel import AccelOnnxConverter\n",
|
||||
"from azureml.accel import AccelContainerImage\n",
|
||||
"\n",
|
||||
"# Retrieve workspace\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(\"Successfully retrieved workspace:\", ws.name, ws.resource_group, ws.location, ws.subscription_id, '\\n')\n",
|
||||
"\n",
|
||||
"# Register model\n",
|
||||
"registered_model = Model.register(workspace = ws,\n",
|
||||
" model_path = model_save_path,\n",
|
||||
" model_name = model_name)\n",
|
||||
"print(\"Successfully registered: \", registered_model.name, registered_model.description, registered_model.version, '\\n', sep = '\\t')\n",
|
||||
"\n",
|
||||
"# Convert model\n",
|
||||
"convert_request = AccelOnnxConverter.convert_tf_model(ws, registered_model, input_tensors, output_tensors_str)\n",
|
||||
"# If it fails, you can run wait_for_completion again with show_output=True.\n",
|
||||
"convert_request.wait_for_completion(show_output=False)\n",
|
||||
"converted_model = convert_request.result\n",
|
||||
"print(\"\\nSuccessfully converted: \", converted_model.name, converted_model.url, converted_model.version, \n",
|
||||
" converted_model.id, converted_model.created_time, '\\n')\n",
|
||||
"\n",
|
||||
"# Package into AccelContainerImage\n",
|
||||
"image_config = AccelContainerImage.image_configuration()\n",
|
||||
"# Image name must be lowercase\n",
|
||||
"image_name = \"{}-image\".format(model_name)\n",
|
||||
"image = Image.create(name = image_name,\n",
|
||||
" models = [converted_model],\n",
|
||||
" image_config = image_config, \n",
|
||||
" workspace = ws)\n",
|
||||
"image.wait_for_creation()\n",
|
||||
"print(\"Created AccelContainerImage: {} {} {}\\n\".format(image.name, image.creation_state, image.image_location))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"deploy-image\"></a>\n",
|
||||
"## 4. Deploy image\n",
|
||||
"Once you have an Azure ML Accelerated Image in your Workspace, you can deploy it to two destinations, to a Databox Edge machine or to an AKS cluster. \n",
|
||||
"\n",
|
||||
"### 4.a. Deploy to Databox Edge Machine using IoT Hub\n",
|
||||
"See the sample [here](https://github.com/Azure-Samples/aml-real-time-ai/) for using the Azure IoT CLI extension for deploying your Docker image to your Databox Edge Machine.\n",
|
||||
"\n",
|
||||
"### 4.b. Deploy to AKS Cluster\n",
|
||||
"Same as in the [Quickstart section on image deployment](./accelerated-models-quickstart.ipynb#deploy-image), we are going to create an AKS cluster with FPGA-enabled machines, then deploy our service to it.\n",
|
||||
"#### Create AKS ComputeTarget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"\n",
|
||||
"# Uses the specific FPGA enabled VM (sku: Standard_PB6s)\n",
|
||||
"# Standard_PB6s are available in: eastus, westus2, westeurope, southeastasia\n",
|
||||
"prov_config = AksCompute.provisioning_configuration(vm_size = \"Standard_PB6s\",\n",
|
||||
" agent_count = 1, \n",
|
||||
" location = \"eastus\")\n",
|
||||
"\n",
|
||||
"aks_name = 'aks-pb6-obj'\n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Provisioning an AKS cluster might take awhile (15 or so minutes), and we want to wait until it's successfully provisioned before we can deploy a service to it. If you interrupt this cell, provisioning of the cluster will continue. You can re-run it or check the status in your Workspace under Compute."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_target.wait_for_completion(show_output = True)\n",
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Deploy AccelContainerImage to AKS ComputeTarget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice, AksWebservice\n",
|
||||
"\n",
|
||||
"# Set the web service configuration (for creating a test service, we don't want autoscale enabled)\n",
|
||||
"# Authentication is enabled by default, but for testing we specify False\n",
|
||||
"aks_config = AksWebservice.deploy_configuration(autoscale_enabled=False,\n",
|
||||
" num_replicas=1,\n",
|
||||
" auth_enabled = False)\n",
|
||||
"\n",
|
||||
"aks_service_name ='my-aks-service'\n",
|
||||
"\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"test-service\"></a>\n",
|
||||
"## 5. Test the service\n",
|
||||
"<a id=\"create-client\"></a>\n",
|
||||
"### 5.a. Create Client\n",
|
||||
"The image supports gRPC and the TensorFlow Serving \"predict\" API. We have a client that can call into the docker image to get predictions. \n",
|
||||
"\n",
|
||||
"**Note:** If you chose to use auth_enabled=True when creating your AksWebservice.deploy_configuration(), see documentation [here](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py#get-keys--) on how to retrieve your keys and use either key as an argument to PredictionClient(...,access_token=key).",
|
||||
"\n",
|
||||
"**WARNING:** If you are running on Azure Notebooks free compute, you will not be able to make outgoing calls to your service. Try locating your client on a different machine to consume it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Using the grpc client in AzureML Accelerated Models SDK\n",
|
||||
"from azureml.accel.client import PredictionClient\n",
|
||||
"\n",
|
||||
"address = aks_service.scoring_uri\n",
|
||||
"ssl_enabled = address.startswith(\"https\")\n",
|
||||
"address = address[address.find('/')+2:].strip('/')\n",
|
||||
"port = 443 if ssl_enabled else 80\n",
|
||||
"\n",
|
||||
"# Initialize AzureML Accelerated Models client\n",
|
||||
"client = PredictionClient(address=address,\n",
|
||||
" port=port,\n",
|
||||
" use_ssl=ssl_enabled,\n",
|
||||
" service_name=aks_service.name)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can adapt the client [code](https://github.com/Azure/aml-real-time-ai/blob/master/pythonlib/amlrealtimeai/client.py) to meet your needs. There is also an example C# [client](https://github.com/Azure/aml-real-time-ai/blob/master/sample-clients/csharp).\n",
|
||||
"\n",
|
||||
"The service provides an API that is compatible with TensorFlow Serving. There are instructions to download a sample client [here](https://www.tensorflow.org/serving/setup)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"serve-model\"></a>\n",
|
||||
"### 5.b. Serve the model\n",
|
||||
"The SSD-VGG model returns the confidence and bounding boxes for all possible anchor boxes. As mentioned earlier, we will use a post-processing routine to transform this into a list of bounding boxes (y1, x1, y2, x2) where x, y are fractional coordinates measured from left and top respectively. A respective list of classes and scores is also returned to tag each bounding box. Below we make use of this information to draw the bounding boxes on top the original image. Note that in the post-processing routine we select a confidence threshold of 0.5."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import cv2\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"\n",
|
||||
"colors_tableau = [(255, 255, 255), (31, 119, 180), (174, 199, 232), (255, 127, 14), (255, 187, 120),\n",
|
||||
" (44, 160, 44), (152, 223, 138), (214, 39, 40), (255, 152, 150),\n",
|
||||
" (148, 103, 189), (197, 176, 213), (140, 86, 75), (196, 156, 148),\n",
|
||||
" (227, 119, 194), (247, 182, 210), (127, 127, 127), (199, 199, 199),\n",
|
||||
" (188, 189, 34), (219, 219, 141), (23, 190, 207), (158, 218, 229)]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def draw_boxes_on_img(img, classes, scores, bboxes, thickness=2):\n",
|
||||
" shape = img.shape\n",
|
||||
" for i in range(bboxes.shape[0]):\n",
|
||||
" bbox = bboxes[i]\n",
|
||||
" color = colors_tableau[classes[i]]\n",
|
||||
" # Draw bounding box...\n",
|
||||
" p1 = (int(bbox[0] * shape[0]), int(bbox[1] * shape[1]))\n",
|
||||
" p2 = (int(bbox[2] * shape[0]), int(bbox[3] * shape[1]))\n",
|
||||
" cv2.rectangle(img, p1[::-1], p2[::-1], color, thickness)\n",
|
||||
" # Draw text...\n",
|
||||
" s = '%s/%.3f' % (classes[i], scores[i])\n",
|
||||
" p1 = (p1[0]-5, p1[1])\n",
|
||||
" cv2.putText(img, s, p1[::-1], cv2.FONT_HERSHEY_DUPLEX, 0.4, color, 1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.accel._external.ssdvgg_utils as ssdvgg_utils\n",
|
||||
"\n",
|
||||
"result = client.score_file(path=\"meeting.jpg\", input_name=input_tensors, outputs=output_tensors)\n",
|
||||
"classes, scores, bboxes = ssdvgg_utils.postprocess(result, select_threshold=0.5)\n",
|
||||
"\n",
|
||||
"img = cv2.imread('meeting.jpg', 1)\n",
|
||||
"img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n",
|
||||
"draw_boxes_on_img(img, classes, scores, bboxes)\n",
|
||||
"plt.imshow(img)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"cleanup\"></a>\n",
|
||||
"## 6. Cleanup\n",
|
||||
"It's important to clean up your resources, so that you won't incur unnecessary costs. In the [next notebook](./accelerated-models-training.ipynb) you will learn how to train a classfier on a new dataset using transfer learning."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_service.delete()\n",
|
||||
"aks_target.delete()\n",
|
||||
"image.delete()\n",
|
||||
"registered_model.delete()\n",
|
||||
"converted_model.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "coverste"
|
||||
},
|
||||
{
|
||||
"name": "paledger"
|
||||
},
|
||||
{
|
||||
"name": "sukha"
|
||||
}
|
||||
"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": [
|
||||
"# Azure ML Hardware Accelerated Object Detection"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This tutorial will show you how to deploy an object detection service based on the SSD-VGG model in just a few minutes using the Azure Machine Learning Accelerated AI service.\n",
|
||||
"\n",
|
||||
"We will use the SSD-VGG model accelerated on an FPGA. Our Accelerated Models Service handles translating deep neural networks (DNN) into an FPGA program.\n",
|
||||
"\n",
|
||||
"The steps in this notebook are: \n",
|
||||
"1. [Setup Environment](#set-up-environment)\n",
|
||||
"* [Construct Model](#construct-model)\n",
|
||||
" * Image Preprocessing\n",
|
||||
" * Featurizer\n",
|
||||
" * Save Model\n",
|
||||
" * Save input and output tensor names\n",
|
||||
"* [Create Image](#create-image)\n",
|
||||
"* [Deploy Image](#deploy-image)\n",
|
||||
"* [Test the Service](#test-service)\n",
|
||||
" * Create Client\n",
|
||||
" * Serve the model\n",
|
||||
"* [Cleanup](#cleanup)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"set-up-environment\"></a>\n",
|
||||
"## 1. Set up Environment\n",
|
||||
"### 1.a. Imports"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import tensorflow as tf"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 1.b. Retrieve Workspace\n",
|
||||
"If you haven't created a Workspace, please follow [this notebook](\"../../../configuration.ipynb\") to do so. If you have, run the codeblock below to retrieve it. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"construct-model\"></a>\n",
|
||||
"## 2. Construct model\n",
|
||||
"### 2.a. Image preprocessing\n",
|
||||
"We'd like our service to accept JPEG images as input. However the input to SSD-VGG is a float tensor of shape \\[1, 300, 300, 3\\]. The first dimension is batch, then height, width, and channels (i.e. NHWC). To bridge this gap, we need code that decodes JPEG images and resizes them appropriately for input to SSD-VGG. The Accelerated AI service can execute TensorFlow graphs as part of the service and we'll use that ability to do the image preprocessing. This code defines a TensorFlow graph that preprocesses an array of JPEG images (as TensorFlow strings) and produces a tensor that is ready to be featurized by SSD-VGG.\n",
|
||||
"\n",
|
||||
"**Note:** Expect to see TF deprecation warnings until we port our SDK over to use Tensorflow 2.0."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Input images as a two-dimensional tensor containing an arbitrary number of images represented a strings\n",
|
||||
"import azureml.accel.models.utils as utils\n",
|
||||
"tf.reset_default_graph()\n",
|
||||
"\n",
|
||||
"in_images = tf.placeholder(tf.string)\n",
|
||||
"image_tensors = utils.preprocess_array(in_images, output_width=300, output_height=300, preserve_aspect_ratio=False)\n",
|
||||
"print(image_tensors.shape)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 2.b. Featurizer\n",
|
||||
"The SSD-VGG model is different from our other models in that it generates 12 tensor outputs. These corresponds to x,y displacements of the anchor boxes and the detection confidence (for 21 classes). Because these outputs are not convenient to work with, we will later use a pre-defined post-processing utility to transform the outputs into a simplified list of bounding boxes with their respective class and confidence.\n",
|
||||
"\n",
|
||||
"For more information about the output tensors, take this example: the output tensor 'ssd_300_vgg/block4_box/Reshape_1:0' has a shape of [None, 37, 37, 4, 21]. This gives the pre-softmax confidence for 4 anchor boxes situated at each site of a 37 x 37 grid imposed on the image, one confidence score for each of the 21 classes. The first dimension is the batch dimension. Likewise, 'ssd_300_vgg/block4_box/Reshape:0' has shape [None, 37, 37, 4, 4] and encodes the (cx, cy) center shift and rescaling (sw, sh) relative to each anchor box. Refer to the [SSD-VGG paper](https://arxiv.org/abs/1512.02325) to understand how these are computed. The other 10 tensors are defined similarly."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.accel.models import SsdVgg\n",
|
||||
"\n",
|
||||
"saved_model_dir = os.path.join(os.path.expanduser('~'), 'models')\n",
|
||||
"model_graph = SsdVgg(saved_model_dir, is_frozen = True)\n",
|
||||
"\n",
|
||||
"print('SSD-VGG Input Tensors:')\n",
|
||||
"for idx, input_name in enumerate(model_graph.input_tensor_list):\n",
|
||||
" print('{}, {}'.format(input_name, model_graph.get_input_dims(idx)))\n",
|
||||
" \n",
|
||||
"print('SSD-VGG Output Tensors:')\n",
|
||||
"for idx, output_name in enumerate(model_graph.output_tensor_list):\n",
|
||||
" print('{}, {}'.format(output_name, model_graph.get_output_dims(idx)))\n",
|
||||
"\n",
|
||||
"ssd_outputs = model_graph.import_graph_def(image_tensors, is_training=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 2.c. Save Model\n",
|
||||
"Now that we loaded both parts of the tensorflow graph (preprocessor and SSD-VGG featurizer), we can save the graph and associated variables to a directory which we can register as an Azure ML Model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model_name = \"ssdvgg\"\n",
|
||||
"model_save_path = os.path.join(saved_model_dir, model_name, \"saved_model\")\n",
|
||||
"print(\"Saving model in {}\".format(model_save_path))\n",
|
||||
"\n",
|
||||
"output_map = {}\n",
|
||||
"for i, output in enumerate(ssd_outputs):\n",
|
||||
" output_map['out_{}'.format(i)] = output\n",
|
||||
"\n",
|
||||
"with tf.Session() as sess:\n",
|
||||
" model_graph.restore_weights(sess)\n",
|
||||
" tf.saved_model.simple_save(sess, \n",
|
||||
" model_save_path, \n",
|
||||
" inputs={'images': in_images}, \n",
|
||||
" outputs=output_map)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 2.d. Important! Save names of input and output tensors\n",
|
||||
"\n",
|
||||
"These input and output tensors that were created during the preprocessing and classifier steps are also going to be used when **converting the model** to an Accelerated Model that can run on FPGA's and for **making an inferencing request**. It is very important to save this information!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"register model from file"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"input_tensors = in_images.name\n",
|
||||
"# We will use the list of output tensors during inferencing\n",
|
||||
"output_tensors = [output.name for output in ssd_outputs]\n",
|
||||
"# However, for multiple output tensors, our AccelOnnxConverter will \n",
|
||||
"# accept comma-delimited strings (lists will cause error)\n",
|
||||
"output_tensors_str = \",\".join(output_tensors)\n",
|
||||
"\n",
|
||||
"print(input_tensors)\n",
|
||||
"print(output_tensors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"create-image\"></a>\n",
|
||||
"## 3. Create AccelContainerImage\n",
|
||||
"Below we will execute all the same steps as in the [Quickstart](./accelerated-models-quickstart.ipynb#create-image) to package the model we have saved locally into an accelerated Docker image saved in our workspace. To complete all the steps, it may take a few minutes. For more details on each step, check out the [Quickstart section on model registration](./accelerated-models-quickstart.ipynb#register-model)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"from azureml.core.image import Image\n",
|
||||
"from azureml.accel import AccelOnnxConverter\n",
|
||||
"from azureml.accel import AccelContainerImage\n",
|
||||
"\n",
|
||||
"# Retrieve workspace\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(\"Successfully retrieved workspace:\", ws.name, ws.resource_group, ws.location, ws.subscription_id, '\\n')\n",
|
||||
"\n",
|
||||
"# Register model\n",
|
||||
"registered_model = Model.register(workspace = ws,\n",
|
||||
" model_path = model_save_path,\n",
|
||||
" model_name = model_name)\n",
|
||||
"print(\"Successfully registered: \", registered_model.name, registered_model.description, registered_model.version, '\\n', sep = '\\t')\n",
|
||||
"\n",
|
||||
"# Convert model\n",
|
||||
"convert_request = AccelOnnxConverter.convert_tf_model(ws, registered_model, input_tensors, output_tensors_str)\n",
|
||||
"# If it fails, you can run wait_for_completion again with show_output=True.\n",
|
||||
"convert_request.wait_for_completion(show_output=False)\n",
|
||||
"converted_model = convert_request.result\n",
|
||||
"print(\"\\nSuccessfully converted: \", converted_model.name, converted_model.url, converted_model.version, \n",
|
||||
" converted_model.id, converted_model.created_time, '\\n')\n",
|
||||
"\n",
|
||||
"# Package into AccelContainerImage\n",
|
||||
"image_config = AccelContainerImage.image_configuration()\n",
|
||||
"# Image name must be lowercase\n",
|
||||
"image_name = \"{}-image\".format(model_name)\n",
|
||||
"image = Image.create(name = image_name,\n",
|
||||
" models = [converted_model],\n",
|
||||
" image_config = image_config, \n",
|
||||
" workspace = ws)\n",
|
||||
"image.wait_for_creation()\n",
|
||||
"print(\"Created AccelContainerImage: {} {} {}\\n\".format(image.name, image.creation_state, image.image_location))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"deploy-image\"></a>\n",
|
||||
"## 4. Deploy image\n",
|
||||
"Once you have an Azure ML Accelerated Image in your Workspace, you can deploy it to two destinations, to a Databox Edge machine or to an AKS cluster. \n",
|
||||
"\n",
|
||||
"### 4.a. Deploy to Databox Edge Machine using IoT Hub\n",
|
||||
"See the sample [here](https://github.com/Azure-Samples/aml-real-time-ai/) for using the Azure IoT CLI extension for deploying your Docker image to your Databox Edge Machine.\n",
|
||||
"\n",
|
||||
"### 4.b. Deploy to AKS Cluster\n",
|
||||
"Same as in the [Quickstart section on image deployment](./accelerated-models-quickstart.ipynb#deploy-image), we are going to create an AKS cluster with FPGA-enabled machines, then deploy our service to it.\n",
|
||||
"#### Create AKS ComputeTarget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"\n",
|
||||
"# Uses the specific FPGA enabled VM (sku: Standard_PB6s)\n",
|
||||
"# Standard_PB6s are available in: eastus, westus2, westeurope, southeastasia\n",
|
||||
"prov_config = AksCompute.provisioning_configuration(vm_size = \"Standard_PB6s\",\n",
|
||||
" agent_count = 1, \n",
|
||||
" location = \"eastus\")\n",
|
||||
"\n",
|
||||
"aks_name = 'aks-pb6-obj'\n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Provisioning an AKS cluster might take awhile (15 or so minutes), and we want to wait until it's successfully provisioned before we can deploy a service to it. If you interrupt this cell, provisioning of the cluster will continue. You can re-run it or check the status in your Workspace under Compute."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_target.wait_for_completion(show_output = True)\n",
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Deploy AccelContainerImage to AKS ComputeTarget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice, AksWebservice\n",
|
||||
"\n",
|
||||
"# Set the web service configuration (for creating a test service, we don't want autoscale enabled)\n",
|
||||
"# Authentication is enabled by default, but for testing we specify False\n",
|
||||
"aks_config = AksWebservice.deploy_configuration(autoscale_enabled=False,\n",
|
||||
" num_replicas=1,\n",
|
||||
" auth_enabled = False)\n",
|
||||
"\n",
|
||||
"aks_service_name ='my-aks-service'\n",
|
||||
"\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"test-service\"></a>\n",
|
||||
"## 5. Test the service\n",
|
||||
"<a id=\"create-client\"></a>\n",
|
||||
"### 5.a. Create Client\n",
|
||||
"The image supports gRPC and the TensorFlow Serving \"predict\" API. We have a client that can call into the docker image to get predictions. \n",
|
||||
"\n",
|
||||
"**Note:** If you chose to use auth_enabled=True when creating your AksWebservice.deploy_configuration(), see documentation [here](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py#get-keys--) on how to retrieve your keys and use either key as an argument to PredictionClient(...,access_token=key).",
|
||||
"\n",
|
||||
"**WARNING:** If you are running on Azure Notebooks free compute, you will not be able to make outgoing calls to your service. Try locating your client on a different machine to consume it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Using the grpc client in AzureML Accelerated Models SDK\n",
|
||||
"from azureml.accel.client import PredictionClient\n",
|
||||
"\n",
|
||||
"address = aks_service.scoring_uri\n",
|
||||
"ssl_enabled = address.startswith(\"https\")\n",
|
||||
"address = address[address.find('/')+2:].strip('/')\n",
|
||||
"port = 443 if ssl_enabled else 80\n",
|
||||
"\n",
|
||||
"# Initialize AzureML Accelerated Models client\n",
|
||||
"client = PredictionClient(address=address,\n",
|
||||
" port=port,\n",
|
||||
" use_ssl=ssl_enabled,\n",
|
||||
" service_name=aks_service.name)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can adapt the client [code](https://github.com/Azure/aml-real-time-ai/blob/master/pythonlib/amlrealtimeai/client.py) to meet your needs. There is also an example C# [client](https://github.com/Azure/aml-real-time-ai/blob/master/sample-clients/csharp).\n",
|
||||
"\n",
|
||||
"The service provides an API that is compatible with TensorFlow Serving. There are instructions to download a sample client [here](https://www.tensorflow.org/serving/setup)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"serve-model\"></a>\n",
|
||||
"### 5.b. Serve the model\n",
|
||||
"The SSD-VGG model returns the confidence and bounding boxes for all possible anchor boxes. As mentioned earlier, we will use a post-processing routine to transform this into a list of bounding boxes (y1, x1, y2, x2) where x, y are fractional coordinates measured from left and top respectively. A respective list of classes and scores is also returned to tag each bounding box. Below we make use of this information to draw the bounding boxes on top the original image. Note that in the post-processing routine we select a confidence threshold of 0.5."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import cv2\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"\n",
|
||||
"colors_tableau = [(255, 255, 255), (31, 119, 180), (174, 199, 232), (255, 127, 14), (255, 187, 120),\n",
|
||||
" (44, 160, 44), (152, 223, 138), (214, 39, 40), (255, 152, 150),\n",
|
||||
" (148, 103, 189), (197, 176, 213), (140, 86, 75), (196, 156, 148),\n",
|
||||
" (227, 119, 194), (247, 182, 210), (127, 127, 127), (199, 199, 199),\n",
|
||||
" (188, 189, 34), (219, 219, 141), (23, 190, 207), (158, 218, 229)]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def draw_boxes_on_img(img, classes, scores, bboxes, thickness=2):\n",
|
||||
" shape = img.shape\n",
|
||||
" for i in range(bboxes.shape[0]):\n",
|
||||
" bbox = bboxes[i]\n",
|
||||
" color = colors_tableau[classes[i]]\n",
|
||||
" # Draw bounding box...\n",
|
||||
" p1 = (int(bbox[0] * shape[0]), int(bbox[1] * shape[1]))\n",
|
||||
" p2 = (int(bbox[2] * shape[0]), int(bbox[3] * shape[1]))\n",
|
||||
" cv2.rectangle(img, p1[::-1], p2[::-1], color, thickness)\n",
|
||||
" # Draw text...\n",
|
||||
" s = '%s/%.3f' % (classes[i], scores[i])\n",
|
||||
" p1 = (p1[0]-5, p1[1])\n",
|
||||
" cv2.putText(img, s, p1[::-1], cv2.FONT_HERSHEY_DUPLEX, 0.4, color, 1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.accel._external.ssdvgg_utils as ssdvgg_utils\n",
|
||||
"\n",
|
||||
"result = client.score_file(path=\"meeting.jpg\", input_name=input_tensors, outputs=output_tensors)\n",
|
||||
"classes, scores, bboxes = ssdvgg_utils.postprocess(result, select_threshold=0.5)\n",
|
||||
"\n",
|
||||
"img = cv2.imread('meeting.jpg', 1)\n",
|
||||
"img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n",
|
||||
"draw_boxes_on_img(img, classes, scores, bboxes)\n",
|
||||
"plt.imshow(img)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id=\"cleanup\"></a>\n",
|
||||
"## 6. Cleanup\n",
|
||||
"It's important to clean up your resources, so that you won't incur unnecessary costs. In the [next notebook](./accelerated-models-training.ipynb) you will learn how to train a classfier on a new dataset using transfer learning."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_service.delete()\n",
|
||||
"aks_target.delete()\n",
|
||||
"image.delete()\n",
|
||||
"registered_model.delete()\n",
|
||||
"converted_model.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "coverste"
|
||||
},
|
||||
{
|
||||
"name": "paledger"
|
||||
},
|
||||
{
|
||||
"name": "sukha"
|
||||
}
|
||||
],
|
||||
"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": "3.6.0"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.0"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,498 +1,498 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Enabling App Insights for Services in Production\n",
|
||||
"With this notebook, you can learn how to enable App Insights for standard service monitoring, plus, we provide examples for doing custom logging within a scoring files in a model. \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## What does Application Insights monitor?\n",
|
||||
"It monitors request rates, response times, failure rates, etc. For more information visit [App Insights docs.](https://docs.microsoft.com/en-us/azure/application-insights/app-insights-overview)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## What is different compared to standard production deployment process?\n",
|
||||
"If you want to enable generic App Insights for a service run:\n",
|
||||
"```python\n",
|
||||
"aks_service= Webservice(ws, \"aks-w-dc2\")\n",
|
||||
"aks_service.update(enable_app_insights=True)```\n",
|
||||
"Where \"aks-w-dc2\" is your service name. You can also do this from the Azure Portal under your Workspace--> deployments--> Select deployment--> Edit--> Advanced Settings--> Select \"Enable AppInsights diagnostics\"\n",
|
||||
"\n",
|
||||
"If you want to log custom traces, you will follow the standard deplyment process for AKS and you will:\n",
|
||||
"1. Update scoring file.\n",
|
||||
"2. Update aks configuration.\n",
|
||||
"3. Build new image and deploy it. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1. Import your dependencies"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"from azureml.core.webservice import AksWebservice\n",
|
||||
"import azureml.core\n",
|
||||
"import json\n",
|
||||
"print(azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 2. Set up your configuration and create a workspace\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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": [
|
||||
"## 3. Register Model\n",
|
||||
"Register an existing trained model, add descirption and tags."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Register the model\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
|
||||
" model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
|
||||
" description = \"Ridge regression model to predict diabetes\",\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 4. *Update your scoring file with custom print statements*\n",
|
||||
"Here is an example:\n",
|
||||
"### a. In your init function add:\n",
|
||||
"```python\n",
|
||||
"print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))```\n",
|
||||
"\n",
|
||||
"### b. In your run function add:\n",
|
||||
"```python\n",
|
||||
"print (\"Prediction created\" + time.strftime(\"%H:%M:%S\"))```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy \n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from sklearn.linear_model import Ridge\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"import time\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" #Print statement for appinsights custom traces:\n",
|
||||
" print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" \n",
|
||||
" # note here \"sklearn_regression_model.pkl\" is the name of the model registered under the workspace\n",
|
||||
" # this call should return the path to the model.pkl file on the local disk.\n",
|
||||
" model_path = Model.get_model_path(model_name = 'sklearn_regression_model.pkl')\n",
|
||||
" \n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"# note you can pass in multiple rows for scoring\n",
|
||||
"def run(raw_data):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(raw_data)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" print (\"Prediction created\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" # you can return any datatype as long as it is JSON-serializable\n",
|
||||
" return result.tolist()\n",
|
||||
" except Exception as e:\n",
|
||||
" error = str(e)\n",
|
||||
" print (error + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" return error"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 5. *Create myenv.yml file*"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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'])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 6. Create your new Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" description = \"Image with ridge regression model\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"myimage1\",\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploy to ACI (Optional)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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': \"diabetes\", 'type': \"regression\"}, \n",
|
||||
" description = 'Predict diabetes using regression model',\n",
|
||||
" enable_app_insights = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"\n",
|
||||
"aci_service_name = 'my-aci-service-4'\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": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,28,13,45,54,6,57,8,8,10], \n",
|
||||
" [101,9,8,37,6,45,4,3,2,41]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding='utf8')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aci_service.state == \"Healthy\":\n",
|
||||
" prediction = aci_service.run(input_data=test_sample)\n",
|
||||
" print(prediction)\n",
|
||||
"else:\n",
|
||||
" raise ValueError(\"Service deployment isn't healthy, can't call the service. Error: \", aci_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 7. Deploy to AKS service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create AKS compute if you haven't done so."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"prov_config = AksCompute.provisioning_configuration()\n",
|
||||
"\n",
|
||||
"aks_name = 'my-aks-test3' \n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_target.wait_for_completion(show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you already have a cluster you can attach the service to it:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"```python \n",
|
||||
"%%time\n",
|
||||
"resource_id = '/subscriptions/<subscriptionid>/resourcegroups/<resourcegroupname>/providers/Microsoft.ContainerService/managedClusters/<aksservername>'\n",
|
||||
"create_name= 'myaks4'\n",
|
||||
"attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
|
||||
"aks_target = ComputeTarget.attach(workspace = ws, \n",
|
||||
" name = create_name, \n",
|
||||
" attach_configuration=attach_config)\n",
|
||||
"## Wait for the operation to complete\n",
|
||||
"aks_target.wait_for_provisioning(True)```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### a. *Activate App Insights through updating AKS Webservice configuration*\n",
|
||||
"In order to enable App Insights in your service you will need to update your AKS configuration file:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Set the web service configuration\n",
|
||||
"aks_config = AksWebservice.deploy_configuration(enable_app_insights=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### b. Deploy your service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aks_target.provisioning_state== \"Succeeded\": \n",
|
||||
" aks_service_name ='aks-w-dc5'\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",
|
||||
" )\n",
|
||||
" aks_service.wait_for_deployment(show_output = True)\n",
|
||||
" print(aks_service.state)\n",
|
||||
"else:\n",
|
||||
" raise ValueError(\"AKS provisioning failed. Error: \", aks_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 8. Test your service "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,28,13,45,54,6,57,8,8,10], \n",
|
||||
" [101,9,8,37,6,45,4,3,2,41]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding='utf8')\n",
|
||||
"\n",
|
||||
"if aks_service.state == \"Healthy\":\n",
|
||||
" prediction = aks_service.run(input_data=test_sample)\n",
|
||||
" print(prediction)\n",
|
||||
"else:\n",
|
||||
" raise ValueError(\"Service deployment isn't healthy, can't call the service. Error: \", aks_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 9. See your service telemetry in App Insights\n",
|
||||
"1. Go to the [Azure Portal](https://portal.azure.com/)\n",
|
||||
"2. All resources--> Select the subscription/resource group where you created your Workspace--> Select the App Insights type\n",
|
||||
"3. Click on the AppInsights resource. You'll see a highlevel dashboard with information on Requests, Server response time and availability.\n",
|
||||
"4. Click on the top banner \"Analytics\"\n",
|
||||
"5. In the \"Schema\" section select \"traces\" and run your query.\n",
|
||||
"6. Voila! All your custom traces should be there."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Disable App Insights"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_service.update(enable_app_insights=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Clean up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service.delete()\n",
|
||||
"aci_service.delete()\n",
|
||||
"image.delete()\n",
|
||||
"model.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "shipatel"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Enabling App Insights for Services in Production\n",
|
||||
"With this notebook, you can learn how to enable App Insights for standard service monitoring, plus, we provide examples for doing custom logging within a scoring files in a model. \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## What does Application Insights monitor?\n",
|
||||
"It monitors request rates, response times, failure rates, etc. For more information visit [App Insights docs.](https://docs.microsoft.com/en-us/azure/application-insights/app-insights-overview)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## What is different compared to standard production deployment process?\n",
|
||||
"If you want to enable generic App Insights for a service run:\n",
|
||||
"```python\n",
|
||||
"aks_service= Webservice(ws, \"aks-w-dc2\")\n",
|
||||
"aks_service.update(enable_app_insights=True)```\n",
|
||||
"Where \"aks-w-dc2\" is your service name. You can also do this from the Azure Portal under your Workspace--> deployments--> Select deployment--> Edit--> Advanced Settings--> Select \"Enable AppInsights diagnostics\"\n",
|
||||
"\n",
|
||||
"If you want to log custom traces, you will follow the standard deplyment process for AKS and you will:\n",
|
||||
"1. Update scoring file.\n",
|
||||
"2. Update aks configuration.\n",
|
||||
"3. Build new image and deploy it. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1. Import your dependencies"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"from azureml.core.webservice import AksWebservice\n",
|
||||
"import azureml.core\n",
|
||||
"import json\n",
|
||||
"print(azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 2. Set up your configuration and create a workspace\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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": [
|
||||
"## 3. Register Model\n",
|
||||
"Register an existing trained model, add descirption and tags."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Register the model\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
|
||||
" model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
|
||||
" description = \"Ridge regression model to predict diabetes\",\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 4. *Update your scoring file with custom print statements*\n",
|
||||
"Here is an example:\n",
|
||||
"### a. In your init function add:\n",
|
||||
"```python\n",
|
||||
"print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))```\n",
|
||||
"\n",
|
||||
"### b. In your run function add:\n",
|
||||
"```python\n",
|
||||
"print (\"Prediction created\" + time.strftime(\"%H:%M:%S\"))```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy \n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from sklearn.linear_model import Ridge\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"import time\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" #Print statement for appinsights custom traces:\n",
|
||||
" print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" \n",
|
||||
" # note here \"sklearn_regression_model.pkl\" is the name of the model registered under the workspace\n",
|
||||
" # this call should return the path to the model.pkl file on the local disk.\n",
|
||||
" model_path = Model.get_model_path(model_name = 'sklearn_regression_model.pkl')\n",
|
||||
" \n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"# note you can pass in multiple rows for scoring\n",
|
||||
"def run(raw_data):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(raw_data)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" print (\"Prediction created\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" # you can return any datatype as long as it is JSON-serializable\n",
|
||||
" return result.tolist()\n",
|
||||
" except Exception as e:\n",
|
||||
" error = str(e)\n",
|
||||
" print (error + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" return error"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 5. *Create myenv.yml file*"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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'])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 6. Create your new Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" description = \"Image with ridge regression model\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"myimage1\",\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploy to ACI (Optional)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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': \"diabetes\", 'type': \"regression\"}, \n",
|
||||
" description = 'Predict diabetes using regression model',\n",
|
||||
" enable_app_insights = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"\n",
|
||||
"aci_service_name = 'my-aci-service-4'\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": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,28,13,45,54,6,57,8,8,10], \n",
|
||||
" [101,9,8,37,6,45,4,3,2,41]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding='utf8')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aci_service.state == \"Healthy\":\n",
|
||||
" prediction = aci_service.run(input_data=test_sample)\n",
|
||||
" print(prediction)\n",
|
||||
"else:\n",
|
||||
" raise ValueError(\"Service deployment isn't healthy, can't call the service. Error: \", aci_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 7. Deploy to AKS service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create AKS compute if you haven't done so."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"prov_config = AksCompute.provisioning_configuration()\n",
|
||||
"\n",
|
||||
"aks_name = 'my-aks-test3' \n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_target.wait_for_completion(show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you already have a cluster you can attach the service to it:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"```python \n",
|
||||
"%%time\n",
|
||||
"resource_id = '/subscriptions/<subscriptionid>/resourcegroups/<resourcegroupname>/providers/Microsoft.ContainerService/managedClusters/<aksservername>'\n",
|
||||
"create_name= 'myaks4'\n",
|
||||
"attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
|
||||
"aks_target = ComputeTarget.attach(workspace = ws, \n",
|
||||
" name = create_name, \n",
|
||||
" attach_configuration=attach_config)\n",
|
||||
"## Wait for the operation to complete\n",
|
||||
"aks_target.wait_for_provisioning(True)```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### a. *Activate App Insights through updating AKS Webservice configuration*\n",
|
||||
"In order to enable App Insights in your service you will need to update your AKS configuration file:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Set the web service configuration\n",
|
||||
"aks_config = AksWebservice.deploy_configuration(enable_app_insights=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### b. Deploy your service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aks_target.provisioning_state== \"Succeeded\": \n",
|
||||
" aks_service_name ='aks-w-dc5'\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",
|
||||
" )\n",
|
||||
" aks_service.wait_for_deployment(show_output = True)\n",
|
||||
" print(aks_service.state)\n",
|
||||
"else:\n",
|
||||
" raise ValueError(\"AKS provisioning failed. Error: \", aks_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 8. Test your service "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,28,13,45,54,6,57,8,8,10], \n",
|
||||
" [101,9,8,37,6,45,4,3,2,41]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding='utf8')\n",
|
||||
"\n",
|
||||
"if aks_service.state == \"Healthy\":\n",
|
||||
" prediction = aks_service.run(input_data=test_sample)\n",
|
||||
" print(prediction)\n",
|
||||
"else:\n",
|
||||
" raise ValueError(\"Service deployment isn't healthy, can't call the service. Error: \", aks_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 9. See your service telemetry in App Insights\n",
|
||||
"1. Go to the [Azure Portal](https://portal.azure.com/)\n",
|
||||
"2. All resources--> Select the subscription/resource group where you created your Workspace--> Select the App Insights type\n",
|
||||
"3. Click on the AppInsights resource. You'll see a highlevel dashboard with information on Requests, Server response time and availability.\n",
|
||||
"4. Click on the top banner \"Analytics\"\n",
|
||||
"5. In the \"Schema\" section select \"traces\" and run your query.\n",
|
||||
"6. Voila! All your custom traces should be there."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Disable App Insights"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_service.update(enable_app_insights=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Clean up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service.delete()\n",
|
||||
"aci_service.delete()\n",
|
||||
"image.delete()\n",
|
||||
"model.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "shipatel"
|
||||
}
|
||||
],
|
||||
"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": "3.6.3"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,4 @@
|
||||
name: enable-app-insights-in-production-service
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -1,478 +1,478 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Enabling Data Collection for Models in Production\n",
|
||||
"With this notebook, you can learn how to collect input model data from your Azure Machine Learning service in an Azure Blob storage. Once enabled, this data collected gives you the opportunity:\n",
|
||||
"\n",
|
||||
"* Monitor data drifts as production data enters your model\n",
|
||||
"* Make better decisions on when to retrain or optimize your model\n",
|
||||
"* Retrain your model with the data collected\n",
|
||||
"\n",
|
||||
"## What data is collected?\n",
|
||||
"* Model input data (voice, images, and video are not supported) from services deployed in Azure Kubernetes Cluster (AKS)\n",
|
||||
"* Model predictions using production input data.\n",
|
||||
"\n",
|
||||
"**Note:** pre-aggregation or pre-calculations on this data are done by user and not included in this version of the product.\n",
|
||||
"\n",
|
||||
"## What is different compared to standard production deployment process?\n",
|
||||
"1. Update scoring file.\n",
|
||||
"2. Update yml file with new dependency.\n",
|
||||
"3. Update aks configuration.\n",
|
||||
"4. Build new image and deploy it. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1. Import your dependencies"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"from azureml.core.webservice import Webservice, AksWebservice\n",
|
||||
"import azureml.core\n",
|
||||
"print(azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 2. Set up your configuration and create a workspace"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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": [
|
||||
"## 3. Register Model\n",
|
||||
"Register an existing trained model, add descirption and tags."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Register the model\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
|
||||
" model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
|
||||
" description = \"Ridge regression model to predict diabetes\",\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 4. *Update your scoring file with Data Collection*\n",
|
||||
"The file below, compared to the file used in notebook 11, has the following changes:\n",
|
||||
"### a. Import the module\n",
|
||||
"```python \n",
|
||||
"from azureml.monitoring import ModelDataCollector```\n",
|
||||
"### b. In your init function add:\n",
|
||||
"```python \n",
|
||||
"global inputs_dc, prediction_d\n",
|
||||
"inputs_dc = ModelDataCollector(\"best_model\", identifier=\"inputs\", feature_names=[\"feat1\", \"feat2\", \"feat3\", \"feat4\", \"feat5\", \"Feat6\"])\n",
|
||||
"prediction_dc = ModelDataCollector(\"best_model\", identifier=\"predictions\", feature_names=[\"prediction1\", \"prediction2\"])```\n",
|
||||
" \n",
|
||||
"* Identifier: Identifier is later used for building the folder structure in your Blob, it can be used to divide \"raw\" data versus \"processed\".\n",
|
||||
"* CorrelationId: is an optional parameter, you do not need to set it up if your model doesn't require it. Having a correlationId in place does help you for easier mapping with other data. (Examples include: LoanNumber, CustomerId, etc.)\n",
|
||||
"* Feature Names: These need to be set up in the order of your features in order for them to have column names when the .csv is created.\n",
|
||||
"\n",
|
||||
"### c. In your run function add:\n",
|
||||
"```python\n",
|
||||
"inputs_dc.collect(data)\n",
|
||||
"prediction_dc.collect(result)```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy \n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from sklearn.linear_model import Ridge\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"from azureml.monitoring import ModelDataCollector\n",
|
||||
"import time\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" # note here \"sklearn_regression_model.pkl\" is the name of the model registered under the workspace\n",
|
||||
" # this call should return the path to the model.pkl file on the local disk.\n",
|
||||
" model_path = Model.get_model_path(model_name = 'sklearn_regression_model.pkl')\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
" global inputs_dc, prediction_dc\n",
|
||||
" # this setup will help us save our inputs under the \"inputs\" path in our Azure Blob\n",
|
||||
" inputs_dc = ModelDataCollector(model_name=\"sklearn_regression_model\", identifier=\"inputs\", feature_names=[\"feat1\", \"feat2\"]) \n",
|
||||
" # this setup will help us save our ipredictions under the \"predictions\" path in our Azure Blob\n",
|
||||
" prediction_dc = ModelDataCollector(\"sklearn_regression_model\", identifier=\"predictions\", feature_names=[\"prediction1\", \"prediction2\"]) \n",
|
||||
" \n",
|
||||
"# note you can pass in multiple rows for scoring\n",
|
||||
"def run(raw_data):\n",
|
||||
" global inputs_dc, prediction_dc\n",
|
||||
" try:\n",
|
||||
" data = json.loads(raw_data)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" print (\"saving input data\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" inputs_dc.collect(data) #this call is saving our input data into our blob\n",
|
||||
" prediction_dc.collect(result)#this call is saving our prediction data into our blob\n",
|
||||
" print (\"saving prediction data\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" # you can return any data type as long as it is JSON-serializable\n",
|
||||
" return result.tolist()\n",
|
||||
" except Exception as e:\n",
|
||||
" error = str(e)\n",
|
||||
" print (error + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" return error"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 5. *Update your myenv.yml file with the required module*"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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'])\n",
|
||||
"myenv.add_pip_package(\"azureml-monitoring\")\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 6. Create your new Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" description = \"Image with ridge regression model\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"myimage1\",\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 7. Deploy to AKS service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create AKS compute if you haven't done so."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"prov_config = AksCompute.provisioning_configuration()\n",
|
||||
"\n",
|
||||
"aks_name = 'my-aks-test1' \n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_target.wait_for_completion(show_output = True)\n",
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you already have a cluster you can attach the service to it:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"```python \n",
|
||||
" %%time\n",
|
||||
" resource_id = '/subscriptions/<subscriptionid>/resourcegroups/<resourcegroupname>/providers/Microsoft.ContainerService/managedClusters/<aksservername>'\n",
|
||||
" create_name= 'myaks4'\n",
|
||||
" attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
|
||||
" aks_target = ComputeTarget.attach(workspace = ws, \n",
|
||||
" name = create_name, \n",
|
||||
" attach_configuration=attach_config)\n",
|
||||
" ## Wait for the operation to complete\n",
|
||||
" aks_target.wait_for_provisioning(True)```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### a. *Activate Data Collection and App Insights through updating AKS Webservice configuration*\n",
|
||||
"In order to enable Data Collection and App Insights in your service you will need to update your AKS configuration file:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Set the web service configuration\n",
|
||||
"aks_config = AksWebservice.deploy_configuration(collect_model_data=True, enable_app_insights=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### b. Deploy your service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aks_target.provisioning_state== \"Succeeded\": \n",
|
||||
" aks_service_name ='aks-w-dc0'\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",
|
||||
" )\n",
|
||||
" aks_service.wait_for_deployment(show_output = True)\n",
|
||||
" print(aks_service.state)\n",
|
||||
"else: \n",
|
||||
" raise ValueError(\"aks provisioning failed, can't deploy service. Error: \", aks_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 8. Test your service and send some data\n",
|
||||
"**Note**: It will take around 15 mins for your data to appear in your blob.\n",
|
||||
"The data will appear in your Azure Blob following this format:\n",
|
||||
"\n",
|
||||
"/modeldata/subscriptionid/resourcegroupname/workspacename/webservicename/modelname/modelversion/identifier/year/month/day/data.csv "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"import json\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,2,3,4,54,6,7,8,88,10], \n",
|
||||
" [10,9,8,37,36,45,4,33,2,1]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding = 'utf8')\n",
|
||||
"\n",
|
||||
"if aks_service.state == \"Healthy\":\n",
|
||||
" prediction = aks_service.run(input_data=test_sample)\n",
|
||||
" print(prediction)\n",
|
||||
"else:\n",
|
||||
" raise ValueError(\"Service deployment isn't healthy, can't call the service. Error: \", aks_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 9. Validate you data and analyze it\n",
|
||||
"You can look into your data following this path format in your Azure Blob (it takes up to 15 minutes for the data to appear):\n",
|
||||
"\n",
|
||||
"/modeldata/**subscriptionid>**/**resourcegroupname>**/**workspacename>**/**webservicename>**/**modelname>**/**modelversion>>**/**identifier>**/*year/month/day*/data.csv \n",
|
||||
"\n",
|
||||
"For doing further analysis you have multiple options:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### a. Create DataBricks cluter and connect it to your blob\n",
|
||||
"https://docs.microsoft.com/en-us/azure/azure-databricks/quickstart-create-databricks-workspace-portal or in your databricks workspace you can look for the template \"Azure Blob Storage Import Example Notebook\".\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Here is an example for setting up the file location to extract the relevant data:\n",
|
||||
"\n",
|
||||
"<code> file_location = \"wasbs://mycontainer@storageaccountname.blob.core.windows.net/unknown/unknown/unknown-bigdataset-unknown/my_iterate_parking_inputs/2018/°/°/data.csv\" \n",
|
||||
"file_type = \"csv\"</code>\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### b. Connect Blob to Power Bi (Small Data only)\n",
|
||||
"1. Download and Open PowerBi Desktop\n",
|
||||
"2. Select \"Get Data\" and click on \"Azure Blob Storage\" >> Connect\n",
|
||||
"3. Add your storage account and enter your storage key.\n",
|
||||
"4. Select the container where your Data Collection is stored and click on Edit. \n",
|
||||
"5. In the query editor, click under \"Name\" column and add your Storage account Model path into the filter. Note: if you want to only look into files from a specific year or month, just expand the filter path. For example, just look into March data: /modeldata/subscriptionid>/resourcegroupname>/workspacename>/webservicename>/modelname>/modelversion>/identifier>/year>/3\n",
|
||||
"6. Click on the double arrow aside the \"Content\" column to combine the files. \n",
|
||||
"7. Click OK and the data will preload.\n",
|
||||
"8. You can now click Close and Apply and start building your custom reports on your Model Input data."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Disable Data Collection"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_service.update(collect_model_data=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Clean up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service.delete()\n",
|
||||
"image.delete()\n",
|
||||
"model.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "shipatel"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Enabling Data Collection for Models in Production\n",
|
||||
"With this notebook, you can learn how to collect input model data from your Azure Machine Learning service in an Azure Blob storage. Once enabled, this data collected gives you the opportunity:\n",
|
||||
"\n",
|
||||
"* Monitor data drifts as production data enters your model\n",
|
||||
"* Make better decisions on when to retrain or optimize your model\n",
|
||||
"* Retrain your model with the data collected\n",
|
||||
"\n",
|
||||
"## What data is collected?\n",
|
||||
"* Model input data (voice, images, and video are not supported) from services deployed in Azure Kubernetes Cluster (AKS)\n",
|
||||
"* Model predictions using production input data.\n",
|
||||
"\n",
|
||||
"**Note:** pre-aggregation or pre-calculations on this data are done by user and not included in this version of the product.\n",
|
||||
"\n",
|
||||
"## What is different compared to standard production deployment process?\n",
|
||||
"1. Update scoring file.\n",
|
||||
"2. Update yml file with new dependency.\n",
|
||||
"3. Update aks configuration.\n",
|
||||
"4. Build new image and deploy it. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1. Import your dependencies"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"from azureml.core.webservice import Webservice, AksWebservice\n",
|
||||
"import azureml.core\n",
|
||||
"print(azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 2. Set up your configuration and create a workspace"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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": [
|
||||
"## 3. Register Model\n",
|
||||
"Register an existing trained model, add descirption and tags."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Register the model\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
|
||||
" model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
|
||||
" description = \"Ridge regression model to predict diabetes\",\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 4. *Update your scoring file with Data Collection*\n",
|
||||
"The file below, compared to the file used in notebook 11, has the following changes:\n",
|
||||
"### a. Import the module\n",
|
||||
"```python \n",
|
||||
"from azureml.monitoring import ModelDataCollector```\n",
|
||||
"### b. In your init function add:\n",
|
||||
"```python \n",
|
||||
"global inputs_dc, prediction_d\n",
|
||||
"inputs_dc = ModelDataCollector(\"best_model\", identifier=\"inputs\", feature_names=[\"feat1\", \"feat2\", \"feat3\", \"feat4\", \"feat5\", \"Feat6\"])\n",
|
||||
"prediction_dc = ModelDataCollector(\"best_model\", identifier=\"predictions\", feature_names=[\"prediction1\", \"prediction2\"])```\n",
|
||||
" \n",
|
||||
"* Identifier: Identifier is later used for building the folder structure in your Blob, it can be used to divide \"raw\" data versus \"processed\".\n",
|
||||
"* CorrelationId: is an optional parameter, you do not need to set it up if your model doesn't require it. Having a correlationId in place does help you for easier mapping with other data. (Examples include: LoanNumber, CustomerId, etc.)\n",
|
||||
"* Feature Names: These need to be set up in the order of your features in order for them to have column names when the .csv is created.\n",
|
||||
"\n",
|
||||
"### c. In your run function add:\n",
|
||||
"```python\n",
|
||||
"inputs_dc.collect(data)\n",
|
||||
"prediction_dc.collect(result)```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy \n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from sklearn.linear_model import Ridge\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"from azureml.monitoring import ModelDataCollector\n",
|
||||
"import time\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" print (\"model initialized\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" # note here \"sklearn_regression_model.pkl\" is the name of the model registered under the workspace\n",
|
||||
" # this call should return the path to the model.pkl file on the local disk.\n",
|
||||
" model_path = Model.get_model_path(model_name = 'sklearn_regression_model.pkl')\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
" global inputs_dc, prediction_dc\n",
|
||||
" # this setup will help us save our inputs under the \"inputs\" path in our Azure Blob\n",
|
||||
" inputs_dc = ModelDataCollector(model_name=\"sklearn_regression_model\", identifier=\"inputs\", feature_names=[\"feat1\", \"feat2\"]) \n",
|
||||
" # this setup will help us save our ipredictions under the \"predictions\" path in our Azure Blob\n",
|
||||
" prediction_dc = ModelDataCollector(\"sklearn_regression_model\", identifier=\"predictions\", feature_names=[\"prediction1\", \"prediction2\"]) \n",
|
||||
" \n",
|
||||
"# note you can pass in multiple rows for scoring\n",
|
||||
"def run(raw_data):\n",
|
||||
" global inputs_dc, prediction_dc\n",
|
||||
" try:\n",
|
||||
" data = json.loads(raw_data)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" print (\"saving input data\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" inputs_dc.collect(data) #this call is saving our input data into our blob\n",
|
||||
" prediction_dc.collect(result)#this call is saving our prediction data into our blob\n",
|
||||
" print (\"saving prediction data\" + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" # you can return any data type as long as it is JSON-serializable\n",
|
||||
" return result.tolist()\n",
|
||||
" except Exception as e:\n",
|
||||
" error = str(e)\n",
|
||||
" print (error + time.strftime(\"%H:%M:%S\"))\n",
|
||||
" return error"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 5. *Update your myenv.yml file with the required module*"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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'])\n",
|
||||
"myenv.add_pip_package(\"azureml-monitoring\")\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 6. Create your new Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" description = \"Image with ridge regression model\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"myimage1\",\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 7. Deploy to AKS service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create AKS compute if you haven't done so."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"prov_config = AksCompute.provisioning_configuration()\n",
|
||||
"\n",
|
||||
"aks_name = 'my-aks-test1' \n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_target.wait_for_completion(show_output = True)\n",
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you already have a cluster you can attach the service to it:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"```python \n",
|
||||
" %%time\n",
|
||||
" resource_id = '/subscriptions/<subscriptionid>/resourcegroups/<resourcegroupname>/providers/Microsoft.ContainerService/managedClusters/<aksservername>'\n",
|
||||
" create_name= 'myaks4'\n",
|
||||
" attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
|
||||
" aks_target = ComputeTarget.attach(workspace = ws, \n",
|
||||
" name = create_name, \n",
|
||||
" attach_configuration=attach_config)\n",
|
||||
" ## Wait for the operation to complete\n",
|
||||
" aks_target.wait_for_provisioning(True)```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### a. *Activate Data Collection and App Insights through updating AKS Webservice configuration*\n",
|
||||
"In order to enable Data Collection and App Insights in your service you will need to update your AKS configuration file:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Set the web service configuration\n",
|
||||
"aks_config = AksWebservice.deploy_configuration(collect_model_data=True, enable_app_insights=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### b. Deploy your service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aks_target.provisioning_state== \"Succeeded\": \n",
|
||||
" aks_service_name ='aks-w-dc0'\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",
|
||||
" )\n",
|
||||
" aks_service.wait_for_deployment(show_output = True)\n",
|
||||
" print(aks_service.state)\n",
|
||||
"else: \n",
|
||||
" raise ValueError(\"aks provisioning failed, can't deploy service. Error: \", aks_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 8. Test your service and send some data\n",
|
||||
"**Note**: It will take around 15 mins for your data to appear in your blob.\n",
|
||||
"The data will appear in your Azure Blob following this format:\n",
|
||||
"\n",
|
||||
"/modeldata/subscriptionid/resourcegroupname/workspacename/webservicename/modelname/modelversion/identifier/year/month/day/data.csv "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"import json\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,2,3,4,54,6,7,8,88,10], \n",
|
||||
" [10,9,8,37,36,45,4,33,2,1]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding = 'utf8')\n",
|
||||
"\n",
|
||||
"if aks_service.state == \"Healthy\":\n",
|
||||
" prediction = aks_service.run(input_data=test_sample)\n",
|
||||
" print(prediction)\n",
|
||||
"else:\n",
|
||||
" raise ValueError(\"Service deployment isn't healthy, can't call the service. Error: \", aks_service.error)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 9. Validate you data and analyze it\n",
|
||||
"You can look into your data following this path format in your Azure Blob (it takes up to 15 minutes for the data to appear):\n",
|
||||
"\n",
|
||||
"/modeldata/**subscriptionid>**/**resourcegroupname>**/**workspacename>**/**webservicename>**/**modelname>**/**modelversion>>**/**identifier>**/*year/month/day*/data.csv \n",
|
||||
"\n",
|
||||
"For doing further analysis you have multiple options:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### a. Create DataBricks cluter and connect it to your blob\n",
|
||||
"https://docs.microsoft.com/en-us/azure/azure-databricks/quickstart-create-databricks-workspace-portal or in your databricks workspace you can look for the template \"Azure Blob Storage Import Example Notebook\".\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Here is an example for setting up the file location to extract the relevant data:\n",
|
||||
"\n",
|
||||
"<code> file_location = \"wasbs://mycontainer@storageaccountname.blob.core.windows.net/unknown/unknown/unknown-bigdataset-unknown/my_iterate_parking_inputs/2018/°/°/data.csv\" \n",
|
||||
"file_type = \"csv\"</code>\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### b. Connect Blob to Power Bi (Small Data only)\n",
|
||||
"1. Download and Open PowerBi Desktop\n",
|
||||
"2. Select \"Get Data\" and click on \"Azure Blob Storage\" >> Connect\n",
|
||||
"3. Add your storage account and enter your storage key.\n",
|
||||
"4. Select the container where your Data Collection is stored and click on Edit. \n",
|
||||
"5. In the query editor, click under \"Name\" column and add your Storage account Model path into the filter. Note: if you want to only look into files from a specific year or month, just expand the filter path. For example, just look into March data: /modeldata/subscriptionid>/resourcegroupname>/workspacename>/webservicename>/modelname>/modelversion>/identifier>/year>/3\n",
|
||||
"6. Click on the double arrow aside the \"Content\" column to combine the files. \n",
|
||||
"7. Click OK and the data will preload.\n",
|
||||
"8. You can now click Close and Apply and start building your custom reports on your Model Input data."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Disable Data Collection"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aks_service.update(collect_model_data=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Clean up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service.delete()\n",
|
||||
"image.delete()\n",
|
||||
"model.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "shipatel"
|
||||
}
|
||||
],
|
||||
"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": "3.6.3"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,4 @@
|
||||
name: enable-data-collection-for-models-in-aks
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
@@ -1,443 +1,443 @@
|
||||
{
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# YOLO Real-time Object Detection using ONNX on AzureML\n",
|
||||
"\n",
|
||||
"This example shows how to convert the TinyYOLO model from CoreML to ONNX and operationalize it as a web service using Azure Machine Learning services and the ONNX Runtime.\n",
|
||||
"\n",
|
||||
"## What is ONNX\n",
|
||||
"ONNX is an open format for representing machine learning and deep learning models. ONNX enables open and interoperable AI by enabling data scientists and developers to use the tools of their choice without worrying about lock-in and flexibility to deploy to a variety of platforms. ONNX is developed and supported by a community of partners including Microsoft, Facebook, and Amazon. For more information, explore the [ONNX website](http://onnx.ai).\n",
|
||||
"\n",
|
||||
"## YOLO Details\n",
|
||||
"You Only Look Once (YOLO) is a state-of-the-art, real-time object detection system. For more information about YOLO, please visit the [YOLO website](https://pjreddie.com/darknet/yolo/)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Prerequisites\n",
|
||||
"\n",
|
||||
"To make the best use of your time, make sure you have done the following:\n",
|
||||
"\n",
|
||||
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
|
||||
"* If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook to:\n",
|
||||
" * install the AML SDK\n",
|
||||
" * create a workspace and its configuration file (config.json)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Check core SDK version number\n",
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Install necessary packages\n",
|
||||
"\n",
|
||||
"You'll need to run the following commands to use this tutorial:\n",
|
||||
"\n",
|
||||
"```sh\n",
|
||||
"pip install onnxmltools\n",
|
||||
"pip install coremltools # use this on Linux and Mac\n",
|
||||
"pip install git+https://github.com/apple/coremltools # use this on Windows\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Convert model to ONNX\n",
|
||||
"\n",
|
||||
"First we download the CoreML model. We use the CoreML model from [Matthijs Hollemans's tutorial](https://github.com/hollance/YOLO-CoreML-MPSNNGraph). This may take a few minutes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import urllib.request\n",
|
||||
"\n",
|
||||
"coreml_model_url = \"https://github.com/hollance/YOLO-CoreML-MPSNNGraph/raw/master/TinyYOLO-CoreML/TinyYOLO-CoreML/TinyYOLO.mlmodel\"\n",
|
||||
"urllib.request.urlretrieve(coreml_model_url, filename=\"TinyYOLO.mlmodel\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Then we use ONNXMLTools to convert the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import onnxmltools\n",
|
||||
"import coremltools\n",
|
||||
"\n",
|
||||
"# Load a CoreML model\n",
|
||||
"coreml_model = coremltools.utils.load_spec('TinyYOLO.mlmodel')\n",
|
||||
"\n",
|
||||
"# Convert from CoreML into ONNX\n",
|
||||
"onnx_model = onnxmltools.convert_coreml(coreml_model, 'TinyYOLOv2')\n",
|
||||
"\n",
|
||||
"# Save ONNX model\n",
|
||||
"onnxmltools.utils.save_model(onnx_model, 'tinyyolov2.onnx')\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"print(os.path.getsize('tinyyolov2.onnx'))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploying as a web service with Azure ML\n",
|
||||
"\n",
|
||||
"### Load Azure ML workspace\n",
|
||||
"\n",
|
||||
"We begin by instantiating a workspace object from the existing workspace created earlier in the configuration notebook."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.location, ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Registering your model with Azure ML\n",
|
||||
"\n",
|
||||
"Now we upload the model and register it in the workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"model = Model.register(model_path = \"tinyyolov2.onnx\",\n",
|
||||
" model_name = \"tinyyolov2\",\n",
|
||||
" tags = {\"onnx\": \"demo\"},\n",
|
||||
" description = \"TinyYOLO\",\n",
|
||||
" workspace = ws)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Displaying your registered models\n",
|
||||
"\n",
|
||||
"You can optionally list out all the models that you have registered in this workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"models = ws.models\n",
|
||||
"for name, m in models.items():\n",
|
||||
" print(\"Name:\", name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Write scoring file\n",
|
||||
"\n",
|
||||
"We are now going to deploy our ONNX model on Azure ML using the ONNX Runtime. We begin by writing a score.py file that will be invoked by the web service call. The `init()` function is called once when the container is started so we load the model using the ONNX Runtime into a global session object."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import json\n",
|
||||
"import time\n",
|
||||
"import sys\n",
|
||||
"import os\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"import numpy as np # we're going to use numpy to process input and output data\n",
|
||||
"import onnxruntime # to inference ONNX models, we use the ONNX Runtime\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global session\n",
|
||||
" model = Model.get_model_path(model_name = 'tinyyolov2')\n",
|
||||
" session = onnxruntime.InferenceSession(model)\n",
|
||||
"\n",
|
||||
"def preprocess(input_data_json):\n",
|
||||
" # convert the JSON data into the tensor input\n",
|
||||
" return np.array(json.loads(input_data_json)['data']).astype('float32')\n",
|
||||
"\n",
|
||||
"def postprocess(result):\n",
|
||||
" return np.array(result).tolist()\n",
|
||||
"\n",
|
||||
"def run(input_data_json):\n",
|
||||
" try:\n",
|
||||
" start = time.time() # start timer\n",
|
||||
" input_data = preprocess(input_data_json)\n",
|
||||
" input_name = session.get_inputs()[0].name # get the id of the first input of the model \n",
|
||||
" result = session.run([], {input_name: input_data})\n",
|
||||
" end = time.time() # stop timer\n",
|
||||
" return {\"result\": postprocess(result),\n",
|
||||
" \"time\": end - start}\n",
|
||||
" except Exception as e:\n",
|
||||
" result = str(e)\n",
|
||||
" return {\"error\": result}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create container image\n",
|
||||
"First we create a YAML file that specifies which dependencies we would like to see in our container."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.conda_dependencies import CondaDependencies \n",
|
||||
"\n",
|
||||
"myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime==0.4.0\",\"azureml-core\"])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Then we have Azure ML create the container. This step will likely take a few minutes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" docker_file = \"Dockerfile\",\n",
|
||||
" description = \"TinyYOLO ONNX Demo\",\n",
|
||||
" tags = {\"demo\": \"onnx\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"onnxyolo\",\n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config,\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"image.wait_for_creation(show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In case you need to debug your code, the next line of code accesses the log file."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(image.image_build_log_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We're all set! Let's get our model chugging.\n",
|
||||
"\n",
|
||||
"### Deploy the container image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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 = {'demo': 'onnx'}, \n",
|
||||
" description = 'web service for TinyYOLO ONNX model')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The following cell will likely take a few minutes to run as well."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"from random import randint\n",
|
||||
"\n",
|
||||
"aci_service_name = 'onnx-tinyyolo'+str(randint(0,100))\n",
|
||||
"print(\"Service\", 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",
|
||||
"\n",
|
||||
"aci_service.wait_for_deployment(True)\n",
|
||||
"print(aci_service.state)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In case the deployment fails, you can check the logs. Make sure to delete your aci_service before trying again."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aci_service.state != 'Healthy':\n",
|
||||
" # run this command for debugging.\n",
|
||||
" print(aci_service.get_logs())\n",
|
||||
" aci_service.delete()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Success!\n",
|
||||
"\n",
|
||||
"If you've made it this far, you've deployed a working web service that does object detection using an ONNX model. You can get the URL for the webservice with the code below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(aci_service.scoring_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"When you are eventually done using the web service, remember to delete it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "viswamy"
|
||||
}
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# YOLO Real-time Object Detection using ONNX on AzureML\n",
|
||||
"\n",
|
||||
"This example shows how to convert the TinyYOLO model from CoreML to ONNX and operationalize it as a web service using Azure Machine Learning services and the ONNX Runtime.\n",
|
||||
"\n",
|
||||
"## What is ONNX\n",
|
||||
"ONNX is an open format for representing machine learning and deep learning models. ONNX enables open and interoperable AI by enabling data scientists and developers to use the tools of their choice without worrying about lock-in and flexibility to deploy to a variety of platforms. ONNX is developed and supported by a community of partners including Microsoft, Facebook, and Amazon. For more information, explore the [ONNX website](http://onnx.ai).\n",
|
||||
"\n",
|
||||
"## YOLO Details\n",
|
||||
"You Only Look Once (YOLO) is a state-of-the-art, real-time object detection system. For more information about YOLO, please visit the [YOLO website](https://pjreddie.com/darknet/yolo/)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Prerequisites\n",
|
||||
"\n",
|
||||
"To make the best use of your time, make sure you have done the following:\n",
|
||||
"\n",
|
||||
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
|
||||
"* If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration](../../../configuration.ipynb) notebook to:\n",
|
||||
" * install the AML SDK\n",
|
||||
" * create a workspace and its configuration file (config.json)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Check core SDK version number\n",
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Install necessary packages\n",
|
||||
"\n",
|
||||
"You'll need to run the following commands to use this tutorial:\n",
|
||||
"\n",
|
||||
"```sh\n",
|
||||
"pip install onnxmltools\n",
|
||||
"pip install coremltools # use this on Linux and Mac\n",
|
||||
"pip install git+https://github.com/apple/coremltools # use this on Windows\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Convert model to ONNX\n",
|
||||
"\n",
|
||||
"First we download the CoreML model. We use the CoreML model from [Matthijs Hollemans's tutorial](https://github.com/hollance/YOLO-CoreML-MPSNNGraph). This may take a few minutes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import urllib.request\n",
|
||||
"\n",
|
||||
"coreml_model_url = \"https://github.com/hollance/YOLO-CoreML-MPSNNGraph/raw/master/TinyYOLO-CoreML/TinyYOLO-CoreML/TinyYOLO.mlmodel\"\n",
|
||||
"urllib.request.urlretrieve(coreml_model_url, filename=\"TinyYOLO.mlmodel\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Then we use ONNXMLTools to convert the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import onnxmltools\n",
|
||||
"import coremltools\n",
|
||||
"\n",
|
||||
"# Load a CoreML model\n",
|
||||
"coreml_model = coremltools.utils.load_spec('TinyYOLO.mlmodel')\n",
|
||||
"\n",
|
||||
"# Convert from CoreML into ONNX\n",
|
||||
"onnx_model = onnxmltools.convert_coreml(coreml_model, 'TinyYOLOv2')\n",
|
||||
"\n",
|
||||
"# Save ONNX model\n",
|
||||
"onnxmltools.utils.save_model(onnx_model, 'tinyyolov2.onnx')\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"print(os.path.getsize('tinyyolov2.onnx'))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploying as a web service with Azure ML\n",
|
||||
"\n",
|
||||
"### Load Azure ML workspace\n",
|
||||
"\n",
|
||||
"We begin by instantiating a workspace object from the existing workspace created earlier in the configuration notebook."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.location, ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Registering your model with Azure ML\n",
|
||||
"\n",
|
||||
"Now we upload the model and register it in the workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"model = Model.register(model_path = \"tinyyolov2.onnx\",\n",
|
||||
" model_name = \"tinyyolov2\",\n",
|
||||
" tags = {\"onnx\": \"demo\"},\n",
|
||||
" description = \"TinyYOLO\",\n",
|
||||
" workspace = ws)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Displaying your registered models\n",
|
||||
"\n",
|
||||
"You can optionally list out all the models that you have registered in this workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"models = ws.models\n",
|
||||
"for name, m in models.items():\n",
|
||||
" print(\"Name:\", name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Write scoring file\n",
|
||||
"\n",
|
||||
"We are now going to deploy our ONNX model on Azure ML using the ONNX Runtime. We begin by writing a score.py file that will be invoked by the web service call. The `init()` function is called once when the container is started so we load the model using the ONNX Runtime into a global session object."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import json\n",
|
||||
"import time\n",
|
||||
"import sys\n",
|
||||
"import os\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"import numpy as np # we're going to use numpy to process input and output data\n",
|
||||
"import onnxruntime # to inference ONNX models, we use the ONNX Runtime\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global session\n",
|
||||
" model = Model.get_model_path(model_name = 'tinyyolov2')\n",
|
||||
" session = onnxruntime.InferenceSession(model)\n",
|
||||
"\n",
|
||||
"def preprocess(input_data_json):\n",
|
||||
" # convert the JSON data into the tensor input\n",
|
||||
" return np.array(json.loads(input_data_json)['data']).astype('float32')\n",
|
||||
"\n",
|
||||
"def postprocess(result):\n",
|
||||
" return np.array(result).tolist()\n",
|
||||
"\n",
|
||||
"def run(input_data_json):\n",
|
||||
" try:\n",
|
||||
" start = time.time() # start timer\n",
|
||||
" input_data = preprocess(input_data_json)\n",
|
||||
" input_name = session.get_inputs()[0].name # get the id of the first input of the model \n",
|
||||
" result = session.run([], {input_name: input_data})\n",
|
||||
" end = time.time() # stop timer\n",
|
||||
" return {\"result\": postprocess(result),\n",
|
||||
" \"time\": end - start}\n",
|
||||
" except Exception as e:\n",
|
||||
" result = str(e)\n",
|
||||
" return {\"error\": result}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create container image\n",
|
||||
"First we create a YAML file that specifies which dependencies we would like to see in our container."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.conda_dependencies import CondaDependencies \n",
|
||||
"\n",
|
||||
"myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime==0.4.0\",\"azureml-core\"])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Then we have Azure ML create the container. This step will likely take a few minutes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" docker_file = \"Dockerfile\",\n",
|
||||
" description = \"TinyYOLO ONNX Demo\",\n",
|
||||
" tags = {\"demo\": \"onnx\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"onnxyolo\",\n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config,\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"image.wait_for_creation(show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In case you need to debug your code, the next line of code accesses the log file."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(image.image_build_log_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We're all set! Let's get our model chugging.\n",
|
||||
"\n",
|
||||
"### Deploy the container image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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 = {'demo': 'onnx'}, \n",
|
||||
" description = 'web service for TinyYOLO ONNX model')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The following cell will likely take a few minutes to run as well."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"from random import randint\n",
|
||||
"\n",
|
||||
"aci_service_name = 'onnx-tinyyolo'+str(randint(0,100))\n",
|
||||
"print(\"Service\", 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",
|
||||
"\n",
|
||||
"aci_service.wait_for_deployment(True)\n",
|
||||
"print(aci_service.state)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In case the deployment fails, you can check the logs. Make sure to delete your aci_service before trying again."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aci_service.state != 'Healthy':\n",
|
||||
" # run this command for debugging.\n",
|
||||
" print(aci_service.get_logs())\n",
|
||||
" aci_service.delete()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Success!\n",
|
||||
"\n",
|
||||
"If you've made it this far, you've deployed a working web service that does object detection using an ONNX model. You can get the URL for the webservice with the code below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(aci_service.scoring_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"When you are eventually done using the web service, remember to delete it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "viswamy"
|
||||
}
|
||||
],
|
||||
"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": "3.6.5"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
name: onnx-convert-aml-deploy-tinyyolo
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- git+https://github.com/apple/coremltools
|
||||
- onnxmltools==1.3.1
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,9 @@
|
||||
name: onnx-inference-facial-expression-recognition-deploy
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- numpy
|
||||
- onnx
|
||||
- opencv-python
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,9 @@
|
||||
name: onnx-inference-mnist-deploy
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- numpy
|
||||
- onnx
|
||||
- opencv-python
|
||||
@@ -1,427 +1,427 @@
|
||||
{
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ResNet50 Image Classification using ONNX and AzureML\n",
|
||||
"\n",
|
||||
"This example shows how to deploy the ResNet50 ONNX model as a web service using Azure Machine Learning services and the ONNX Runtime.\n",
|
||||
"\n",
|
||||
"## What is ONNX\n",
|
||||
"ONNX is an open format for representing machine learning and deep learning models. ONNX enables open and interoperable AI by enabling data scientists and developers to use the tools of their choice without worrying about lock-in and flexibility to deploy to a variety of platforms. ONNX is developed and supported by a community of partners including Microsoft, Facebook, and Amazon. For more information, explore the [ONNX website](http://onnx.ai).\n",
|
||||
"\n",
|
||||
"## ResNet50 Details\n",
|
||||
"ResNet classifies the major object in an input image into a set of 1000 pre-defined classes. For more information about the ResNet50 model and how it was created can be found on the [ONNX Model Zoo github](https://github.com/onnx/models/tree/master/models/image_classification/resnet). "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Prerequisites\n",
|
||||
"\n",
|
||||
"To make the best use of your time, make sure you have done the following:\n",
|
||||
"\n",
|
||||
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
|
||||
"* If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) to:\n",
|
||||
" * install the AML SDK\n",
|
||||
" * create a workspace and its configuration file (config.json)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Check core SDK version number\n",
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Download pre-trained ONNX model from ONNX Model Zoo.\n",
|
||||
"\n",
|
||||
"Download the [ResNet50v2 model and test data](https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.tar.gz) and extract it in the same folder as this tutorial notebook.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import urllib.request\n",
|
||||
"\n",
|
||||
"onnx_model_url = \"https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.tar.gz\"\n",
|
||||
"urllib.request.urlretrieve(onnx_model_url, filename=\"resnet50v2.tar.gz\")\n",
|
||||
"\n",
|
||||
"!tar xvzf resnet50v2.tar.gz"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploying as a web service with Azure ML"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load your Azure ML workspace\n",
|
||||
"\n",
|
||||
"We begin by instantiating a workspace object from the existing workspace created earlier in the configuration notebook."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.location, ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Register your model with Azure ML\n",
|
||||
"\n",
|
||||
"Now we upload the model and register it in the workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"model = Model.register(model_path = \"resnet50v2/resnet50v2.onnx\",\n",
|
||||
" model_name = \"resnet50v2\",\n",
|
||||
" tags = {\"onnx\": \"demo\"},\n",
|
||||
" description = \"ResNet50v2 from ONNX Model Zoo\",\n",
|
||||
" workspace = ws)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Displaying your registered models\n",
|
||||
"\n",
|
||||
"You can optionally list out all the models that you have registered in this workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"models = ws.models\n",
|
||||
"for name, m in models.items():\n",
|
||||
" print(\"Name:\", name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Write scoring file\n",
|
||||
"\n",
|
||||
"We are now going to deploy our ONNX model on Azure ML using the ONNX Runtime. We begin by writing a score.py file that will be invoked by the web service call. The `init()` function is called once when the container is started so we load the model using the ONNX Runtime into a global session object."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import json\n",
|
||||
"import time\n",
|
||||
"import sys\n",
|
||||
"import os\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"import numpy as np # we're going to use numpy to process input and output data\n",
|
||||
"import onnxruntime # to inference ONNX models, we use the ONNX Runtime\n",
|
||||
"\n",
|
||||
"def softmax(x):\n",
|
||||
" x = x.reshape(-1)\n",
|
||||
" e_x = np.exp(x - np.max(x))\n",
|
||||
" return e_x / e_x.sum(axis=0)\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global session\n",
|
||||
" model = Model.get_model_path(model_name = 'resnet50v2')\n",
|
||||
" session = onnxruntime.InferenceSession(model, None)\n",
|
||||
"\n",
|
||||
"def preprocess(input_data_json):\n",
|
||||
" # convert the JSON data into the tensor input\n",
|
||||
" img_data = np.array(json.loads(input_data_json)['data']).astype('float32')\n",
|
||||
" \n",
|
||||
" #normalize\n",
|
||||
" mean_vec = np.array([0.485, 0.456, 0.406])\n",
|
||||
" stddev_vec = np.array([0.229, 0.224, 0.225])\n",
|
||||
" norm_img_data = np.zeros(img_data.shape).astype('float32')\n",
|
||||
" for i in range(img_data.shape[0]):\n",
|
||||
" norm_img_data[i,:,:] = (img_data[i,:,:]/255 - mean_vec[i]) / stddev_vec[i]\n",
|
||||
"\n",
|
||||
" return norm_img_data\n",
|
||||
"\n",
|
||||
"def postprocess(result):\n",
|
||||
" return softmax(np.array(result)).tolist()\n",
|
||||
"\n",
|
||||
"def run(input_data_json):\n",
|
||||
" try:\n",
|
||||
" start = time.time()\n",
|
||||
" # load in our data which is expected as NCHW 224x224 image\n",
|
||||
" input_data = preprocess(input_data_json)\n",
|
||||
" input_name = session.get_inputs()[0].name # get the id of the first input of the model \n",
|
||||
" result = session.run([], {input_name: input_data})\n",
|
||||
" end = time.time() # stop timer\n",
|
||||
" return {\"result\": postprocess(result),\n",
|
||||
" \"time\": end - start}\n",
|
||||
" except Exception as e:\n",
|
||||
" result = str(e)\n",
|
||||
" return {\"error\": result}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create container image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"First we create a YAML file that specifies which dependencies we would like to see in our container."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.conda_dependencies import CondaDependencies \n",
|
||||
"\n",
|
||||
"myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime\",\"azureml-core\"])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Then we have Azure ML create the container. This step will likely take a few minutes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" docker_file = \"Dockerfile\",\n",
|
||||
" description = \"ONNX ResNet50 Demo\",\n",
|
||||
" tags = {\"demo\": \"onnx\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"onnxresnet50v2\",\n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config,\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"image.wait_for_creation(show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In case you need to debug your code, the next line of code accesses the log file."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(image.image_build_log_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We're all set! Let's get our model chugging.\n",
|
||||
"\n",
|
||||
"### Deploy the container image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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 = {'demo': 'onnx'}, \n",
|
||||
" description = 'web service for ResNet50 ONNX model')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The following cell will likely take a few minutes to run as well."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"from random import randint\n",
|
||||
"\n",
|
||||
"aci_service_name = 'onnx-demo-resnet50'+str(randint(0,100))\n",
|
||||
"print(\"Service\", 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",
|
||||
"\n",
|
||||
"aci_service.wait_for_deployment(True)\n",
|
||||
"print(aci_service.state)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In case the deployment fails, you can check the logs. Make sure to delete your aci_service before trying again."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aci_service.state != 'Healthy':\n",
|
||||
" # run this command for debugging.\n",
|
||||
" print(aci_service.get_logs())\n",
|
||||
" aci_service.delete()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Success!\n",
|
||||
"\n",
|
||||
"If you've made it this far, you've deployed a working web service that does image classification using an ONNX model. You can get the URL for the webservice with the code below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(aci_service.scoring_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"When you are eventually done using the web service, remember to delete it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "viswamy"
|
||||
}
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ResNet50 Image Classification using ONNX and AzureML\n",
|
||||
"\n",
|
||||
"This example shows how to deploy the ResNet50 ONNX model as a web service using Azure Machine Learning services and the ONNX Runtime.\n",
|
||||
"\n",
|
||||
"## What is ONNX\n",
|
||||
"ONNX is an open format for representing machine learning and deep learning models. ONNX enables open and interoperable AI by enabling data scientists and developers to use the tools of their choice without worrying about lock-in and flexibility to deploy to a variety of platforms. ONNX is developed and supported by a community of partners including Microsoft, Facebook, and Amazon. For more information, explore the [ONNX website](http://onnx.ai).\n",
|
||||
"\n",
|
||||
"## ResNet50 Details\n",
|
||||
"ResNet classifies the major object in an input image into a set of 1000 pre-defined classes. For more information about the ResNet50 model and how it was created can be found on the [ONNX Model Zoo github](https://github.com/onnx/models/tree/master/models/image_classification/resnet). "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Prerequisites\n",
|
||||
"\n",
|
||||
"To make the best use of your time, make sure you have done the following:\n",
|
||||
"\n",
|
||||
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning\n",
|
||||
"* If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) to:\n",
|
||||
" * install the AML SDK\n",
|
||||
" * create a workspace and its configuration file (config.json)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Check core SDK version number\n",
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Download pre-trained ONNX model from ONNX Model Zoo.\n",
|
||||
"\n",
|
||||
"Download the [ResNet50v2 model and test data](https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.tar.gz) and extract it in the same folder as this tutorial notebook.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import urllib.request\n",
|
||||
"\n",
|
||||
"onnx_model_url = \"https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.tar.gz\"\n",
|
||||
"urllib.request.urlretrieve(onnx_model_url, filename=\"resnet50v2.tar.gz\")\n",
|
||||
"\n",
|
||||
"!tar xvzf resnet50v2.tar.gz"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploying as a web service with Azure ML"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load your Azure ML workspace\n",
|
||||
"\n",
|
||||
"We begin by instantiating a workspace object from the existing workspace created earlier in the configuration notebook."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.location, ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Register your model with Azure ML\n",
|
||||
"\n",
|
||||
"Now we upload the model and register it in the workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"model = Model.register(model_path = \"resnet50v2/resnet50v2.onnx\",\n",
|
||||
" model_name = \"resnet50v2\",\n",
|
||||
" tags = {\"onnx\": \"demo\"},\n",
|
||||
" description = \"ResNet50v2 from ONNX Model Zoo\",\n",
|
||||
" workspace = ws)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Displaying your registered models\n",
|
||||
"\n",
|
||||
"You can optionally list out all the models that you have registered in this workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"models = ws.models\n",
|
||||
"for name, m in models.items():\n",
|
||||
" print(\"Name:\", name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Write scoring file\n",
|
||||
"\n",
|
||||
"We are now going to deploy our ONNX model on Azure ML using the ONNX Runtime. We begin by writing a score.py file that will be invoked by the web service call. The `init()` function is called once when the container is started so we load the model using the ONNX Runtime into a global session object."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import json\n",
|
||||
"import time\n",
|
||||
"import sys\n",
|
||||
"import os\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"import numpy as np # we're going to use numpy to process input and output data\n",
|
||||
"import onnxruntime # to inference ONNX models, we use the ONNX Runtime\n",
|
||||
"\n",
|
||||
"def softmax(x):\n",
|
||||
" x = x.reshape(-1)\n",
|
||||
" e_x = np.exp(x - np.max(x))\n",
|
||||
" return e_x / e_x.sum(axis=0)\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global session\n",
|
||||
" model = Model.get_model_path(model_name = 'resnet50v2')\n",
|
||||
" session = onnxruntime.InferenceSession(model, None)\n",
|
||||
"\n",
|
||||
"def preprocess(input_data_json):\n",
|
||||
" # convert the JSON data into the tensor input\n",
|
||||
" img_data = np.array(json.loads(input_data_json)['data']).astype('float32')\n",
|
||||
" \n",
|
||||
" #normalize\n",
|
||||
" mean_vec = np.array([0.485, 0.456, 0.406])\n",
|
||||
" stddev_vec = np.array([0.229, 0.224, 0.225])\n",
|
||||
" norm_img_data = np.zeros(img_data.shape).astype('float32')\n",
|
||||
" for i in range(img_data.shape[0]):\n",
|
||||
" norm_img_data[i,:,:] = (img_data[i,:,:]/255 - mean_vec[i]) / stddev_vec[i]\n",
|
||||
"\n",
|
||||
" return norm_img_data\n",
|
||||
"\n",
|
||||
"def postprocess(result):\n",
|
||||
" return softmax(np.array(result)).tolist()\n",
|
||||
"\n",
|
||||
"def run(input_data_json):\n",
|
||||
" try:\n",
|
||||
" start = time.time()\n",
|
||||
" # load in our data which is expected as NCHW 224x224 image\n",
|
||||
" input_data = preprocess(input_data_json)\n",
|
||||
" input_name = session.get_inputs()[0].name # get the id of the first input of the model \n",
|
||||
" result = session.run([], {input_name: input_data})\n",
|
||||
" end = time.time() # stop timer\n",
|
||||
" return {\"result\": postprocess(result),\n",
|
||||
" \"time\": end - start}\n",
|
||||
" except Exception as e:\n",
|
||||
" result = str(e)\n",
|
||||
" return {\"error\": result}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create container image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"First we create a YAML file that specifies which dependencies we would like to see in our container."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.conda_dependencies import CondaDependencies \n",
|
||||
"\n",
|
||||
"myenv = CondaDependencies.create(pip_packages=[\"numpy\",\"onnxruntime\",\"azureml-core\"])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Then we have Azure ML create the container. This step will likely take a few minutes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" docker_file = \"Dockerfile\",\n",
|
||||
" description = \"ONNX ResNet50 Demo\",\n",
|
||||
" tags = {\"demo\": \"onnx\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"onnxresnet50v2\",\n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config,\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"image.wait_for_creation(show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In case you need to debug your code, the next line of code accesses the log file."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(image.image_build_log_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We're all set! Let's get our model chugging.\n",
|
||||
"\n",
|
||||
"### Deploy the container image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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 = {'demo': 'onnx'}, \n",
|
||||
" description = 'web service for ResNet50 ONNX model')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The following cell will likely take a few minutes to run as well."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"from random import randint\n",
|
||||
"\n",
|
||||
"aci_service_name = 'onnx-demo-resnet50'+str(randint(0,100))\n",
|
||||
"print(\"Service\", 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",
|
||||
"\n",
|
||||
"aci_service.wait_for_deployment(True)\n",
|
||||
"print(aci_service.state)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In case the deployment fails, you can check the logs. Make sure to delete your aci_service before trying again."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if aci_service.state != 'Healthy':\n",
|
||||
" # run this command for debugging.\n",
|
||||
" print(aci_service.get_logs())\n",
|
||||
" aci_service.delete()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Success!\n",
|
||||
"\n",
|
||||
"If you've made it this far, you've deployed a working web service that does image classification using an ONNX model. You can get the URL for the webservice with the code below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(aci_service.scoring_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"When you are eventually done using the web service, remember to delete it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#aci_service.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "viswamy"
|
||||
}
|
||||
],
|
||||
"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": "3.6.5"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,4 @@
|
||||
name: onnx-modelzoo-aml-deploy-resnet50
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,5 @@
|
||||
name: onnx-train-pytorch-aml-deploy-mnist
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -1,407 +1,407 @@
|
||||
{
|
||||
"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": [
|
||||
"# Deploying a web service to Azure Kubernetes Service (AKS)\n",
|
||||
"This notebook shows the steps for deploying a service: registering a model, creating an image, provisioning a cluster (one time action), and deploying a service to it. \n",
|
||||
"We then test and delete the service, image and model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"from azureml.core.webservice import Webservice, AksWebservice\n",
|
||||
"from azureml.core.image import Image\n",
|
||||
"from azureml.core.model import Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"print(azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Get workspace\n",
|
||||
"Load existing workspace from the config file info."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Register the model\n",
|
||||
"Register an existing trained model, add descirption and tags. Prior to registering the model, you should have a TensorFlow [Saved Model](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/saved_model/README.md) in the `resnet50` directory. You can download a [pretrained resnet50](https://github.com/tensorflow/models/tree/master/official/resnet#pre-trained-model) and unpack it to that directory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Register the model\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"model = Model.register(model_path = \"resnet50\", # this points to a local file\n",
|
||||
" model_name = \"resnet50\", # this is the name the model is registered as\n",
|
||||
" tags = {'area': \"Image classification\", 'type': \"classification\"},\n",
|
||||
" description = \"Image classification trained on Imagenet Dataset\",\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create an image\n",
|
||||
"Create an image using the registered model the script that will load and run the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import tensorflow as tf\n",
|
||||
"import numpy as np\n",
|
||||
"import ujson\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"from azureml.contrib.services.aml_request import AMLRequest, rawhttp\n",
|
||||
"from azureml.contrib.services.aml_response import AMLResponse\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global session\n",
|
||||
" global input_name\n",
|
||||
" global output_name\n",
|
||||
" \n",
|
||||
" session = tf.Session()\n",
|
||||
"\n",
|
||||
" model_path = Model.get_model_path('resnet50')\n",
|
||||
" model = tf.saved_model.loader.load(session, ['serve'], model_path)\n",
|
||||
" if len(model.signature_def['serving_default'].inputs) > 1:\n",
|
||||
" raise ValueError(\"This score.py only supports one input\")\n",
|
||||
" if len(model.signature_def['serving_default'].outputs) > 1:\n",
|
||||
" raise ValueError(\"This score.py only supports one input\")\n",
|
||||
" input_name = [tensor.name for tensor in model.signature_def['serving_default'].inputs.values()][0]\n",
|
||||
" output_name = [tensor.name for tensor in model.signature_def['serving_default'].outputs.values()][0]\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"@rawhttp\n",
|
||||
"def run(request):\n",
|
||||
" if request.method == 'POST':\n",
|
||||
" reqBody = request.get_data(False)\n",
|
||||
" resp = score(reqBody)\n",
|
||||
" return AMLResponse(resp, 200)\n",
|
||||
" if request.method == 'GET':\n",
|
||||
" respBody = str.encode(\"GET is not supported\")\n",
|
||||
" return AMLResponse(respBody, 405)\n",
|
||||
" return AMLResponse(\"bad request\", 500)\n",
|
||||
"\n",
|
||||
"def score(data):\n",
|
||||
" result = session.run(output_name, {input_name: [data]})\n",
|
||||
" return ujson.dumps(result[0])\n",
|
||||
"\n",
|
||||
"if __name__ == \"__main__\":\n",
|
||||
" init()\n",
|
||||
" with open(\"test_image.jpg\", 'rb') as f:\n",
|
||||
" content = f.read()\n",
|
||||
" print(score(content))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.conda_dependencies import CondaDependencies \n",
|
||||
"\n",
|
||||
"myenv = CondaDependencies.create(conda_packages=['tensorflow-gpu==1.12.0','numpy','ujson','azureml-contrib-services'])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" gpu_enabled = True\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"GpuImage\",\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Provision the AKS Cluster\n",
|
||||
"This is a one time setup. You can reuse this cluster for multiple deployments after it has been created. If you delete the cluster or the resource group that contains it, then you would have to recreate it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"prov_config = AksCompute.provisioning_configuration(vm_size=\"Standard_NC6\")\n",
|
||||
"\n",
|
||||
"aks_name = 'my-aks-9' \n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create AKS Cluster in an existing virtual network (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-enable-virtual-network#use-azure-kubernetes-service) for more details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"from azureml.core.compute import ComputeTarget, AksCompute\n",
|
||||
"\n",
|
||||
"# Create the compute configuration and set virtual network information\n",
|
||||
"config = AksCompute.provisioning_configuration(vm_size=\"Standard_NC6\", location=\"eastus2\")\n",
|
||||
"config.vnet_resourcegroup_name = \"mygroup\"\n",
|
||||
"config.vnet_name = \"mynetwork\"\n",
|
||||
"config.subnet_name = \"default\"\n",
|
||||
"config.service_cidr = \"10.0.0.0/16\"\n",
|
||||
"config.dns_service_ip = \"10.0.0.10\"\n",
|
||||
"config.docker_bridge_cidr = \"172.17.0.1/16\"\n",
|
||||
"\n",
|
||||
"# Create the compute target\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws,\n",
|
||||
" name = \"myaks\",\n",
|
||||
" provisioning_configuration = config)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Enable SSL on the AKS Cluster (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-secure-web-service) for more details"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# provisioning_config = AksCompute.provisioning_configuration(ssl_cert_pem_file=\"cert.pem\", ssl_key_pem_file=\"key.pem\", ssl_cname=\"www.contoso.com\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_target.wait_for_completion(show_output = True)\n",
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Optional step: Attach existing AKS cluster\n",
|
||||
"\n",
|
||||
"If you have existing AKS cluster in your Azure subscription, you can attach it to the Workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"resource_id = '/subscriptions/92c76a2f-0e1c-4216-b65e-abf7a3f34c1e/resourcegroups/raymondsdk0604/providers/Microsoft.ContainerService/managedClusters/my-aks-0605d37425356b7d01'\n",
|
||||
"\n",
|
||||
"create_name='my-existing-aks' \n",
|
||||
"# Create the cluster\n",
|
||||
"attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
|
||||
"aks_target = ComputeTarget.attach(workspace=ws, name=create_name, attach_configuration=attach_config)\n",
|
||||
"# Wait for the operation to complete\n",
|
||||
"aks_target.wait_for_completion(True)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Deploy web service to AKS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Set the web service configuration (using default here)\n",
|
||||
"aks_config = AksWebservice.deploy_configuration()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service_name ='aks-service-1'\n",
|
||||
"\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Test the web service\n",
|
||||
"We test the web sevice by passing the test images content."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"import requests\n",
|
||||
"key1, key2 = aks_service.get_keys()\n",
|
||||
"\n",
|
||||
"headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
|
||||
"test_sampe = open('test_image.jpg', 'rb').read()\n",
|
||||
"resp = requests.post(aks_service.scoring_uri, test_sample, headers=headers)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Clean up\n",
|
||||
"Delete the service, image, model and compute target"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service.delete()\n",
|
||||
"image.delete()\n",
|
||||
"model.delete()\n",
|
||||
"aks_target.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "aashishb"
|
||||
}
|
||||
"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": [
|
||||
"# Deploying a web service to Azure Kubernetes Service (AKS)\n",
|
||||
"This notebook shows the steps for deploying a service: registering a model, creating an image, provisioning a cluster (one time action), and deploying a service to it. \n",
|
||||
"We then test and delete the service, image and model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"from azureml.core.webservice import Webservice, AksWebservice\n",
|
||||
"from azureml.core.image import Image\n",
|
||||
"from azureml.core.model import Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"print(azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Get workspace\n",
|
||||
"Load existing workspace from the config file info."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Register the model\n",
|
||||
"Register an existing trained model, add descirption and tags. Prior to registering the model, you should have a TensorFlow [Saved Model](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/saved_model/README.md) in the `resnet50` directory. You can download a [pretrained resnet50](https://github.com/tensorflow/models/tree/master/official/resnet#pre-trained-model) and unpack it to that directory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Register the model\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"model = Model.register(model_path = \"resnet50\", # this points to a local file\n",
|
||||
" model_name = \"resnet50\", # this is the name the model is registered as\n",
|
||||
" tags = {'area': \"Image classification\", 'type': \"classification\"},\n",
|
||||
" description = \"Image classification trained on Imagenet Dataset\",\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create an image\n",
|
||||
"Create an image using the registered model the script that will load and run the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import tensorflow as tf\n",
|
||||
"import numpy as np\n",
|
||||
"import ujson\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"from azureml.contrib.services.aml_request import AMLRequest, rawhttp\n",
|
||||
"from azureml.contrib.services.aml_response import AMLResponse\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global session\n",
|
||||
" global input_name\n",
|
||||
" global output_name\n",
|
||||
" \n",
|
||||
" session = tf.Session()\n",
|
||||
"\n",
|
||||
" model_path = Model.get_model_path('resnet50')\n",
|
||||
" model = tf.saved_model.loader.load(session, ['serve'], model_path)\n",
|
||||
" if len(model.signature_def['serving_default'].inputs) > 1:\n",
|
||||
" raise ValueError(\"This score.py only supports one input\")\n",
|
||||
" if len(model.signature_def['serving_default'].outputs) > 1:\n",
|
||||
" raise ValueError(\"This score.py only supports one input\")\n",
|
||||
" input_name = [tensor.name for tensor in model.signature_def['serving_default'].inputs.values()][0]\n",
|
||||
" output_name = [tensor.name for tensor in model.signature_def['serving_default'].outputs.values()][0]\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"@rawhttp\n",
|
||||
"def run(request):\n",
|
||||
" if request.method == 'POST':\n",
|
||||
" reqBody = request.get_data(False)\n",
|
||||
" resp = score(reqBody)\n",
|
||||
" return AMLResponse(resp, 200)\n",
|
||||
" if request.method == 'GET':\n",
|
||||
" respBody = str.encode(\"GET is not supported\")\n",
|
||||
" return AMLResponse(respBody, 405)\n",
|
||||
" return AMLResponse(\"bad request\", 500)\n",
|
||||
"\n",
|
||||
"def score(data):\n",
|
||||
" result = session.run(output_name, {input_name: [data]})\n",
|
||||
" return ujson.dumps(result[0])\n",
|
||||
"\n",
|
||||
"if __name__ == \"__main__\":\n",
|
||||
" init()\n",
|
||||
" with open(\"test_image.jpg\", 'rb') as f:\n",
|
||||
" content = f.read()\n",
|
||||
" print(score(content))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.conda_dependencies import CondaDependencies \n",
|
||||
"\n",
|
||||
"myenv = CondaDependencies.create(conda_packages=['tensorflow-gpu==1.12.0','numpy','ujson','azureml-contrib-services'])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" gpu_enabled = True\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"GpuImage\",\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Provision the AKS Cluster\n",
|
||||
"This is a one time setup. You can reuse this cluster for multiple deployments after it has been created. If you delete the cluster or the resource group that contains it, then you would have to recreate it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"prov_config = AksCompute.provisioning_configuration(vm_size=\"Standard_NC6\")\n",
|
||||
"\n",
|
||||
"aks_name = 'my-aks-9' \n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create AKS Cluster in an existing virtual network (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-enable-virtual-network#use-azure-kubernetes-service) for more details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"from azureml.core.compute import ComputeTarget, AksCompute\n",
|
||||
"\n",
|
||||
"# Create the compute configuration and set virtual network information\n",
|
||||
"config = AksCompute.provisioning_configuration(vm_size=\"Standard_NC6\", location=\"eastus2\")\n",
|
||||
"config.vnet_resourcegroup_name = \"mygroup\"\n",
|
||||
"config.vnet_name = \"mynetwork\"\n",
|
||||
"config.subnet_name = \"default\"\n",
|
||||
"config.service_cidr = \"10.0.0.0/16\"\n",
|
||||
"config.dns_service_ip = \"10.0.0.10\"\n",
|
||||
"config.docker_bridge_cidr = \"172.17.0.1/16\"\n",
|
||||
"\n",
|
||||
"# Create the compute target\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws,\n",
|
||||
" name = \"myaks\",\n",
|
||||
" provisioning_configuration = config)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Enable SSL on the AKS Cluster (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-secure-web-service) for more details"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# provisioning_config = AksCompute.provisioning_configuration(ssl_cert_pem_file=\"cert.pem\", ssl_key_pem_file=\"key.pem\", ssl_cname=\"www.contoso.com\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_target.wait_for_completion(show_output = True)\n",
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Optional step: Attach existing AKS cluster\n",
|
||||
"\n",
|
||||
"If you have existing AKS cluster in your Azure subscription, you can attach it to the Workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"resource_id = '/subscriptions/92c76a2f-0e1c-4216-b65e-abf7a3f34c1e/resourcegroups/raymondsdk0604/providers/Microsoft.ContainerService/managedClusters/my-aks-0605d37425356b7d01'\n",
|
||||
"\n",
|
||||
"create_name='my-existing-aks' \n",
|
||||
"# Create the cluster\n",
|
||||
"attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
|
||||
"aks_target = ComputeTarget.attach(workspace=ws, name=create_name, attach_configuration=attach_config)\n",
|
||||
"# Wait for the operation to complete\n",
|
||||
"aks_target.wait_for_completion(True)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Deploy web service to AKS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Set the web service configuration (using default here)\n",
|
||||
"aks_config = AksWebservice.deploy_configuration()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service_name ='aks-service-1'\n",
|
||||
"\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Test the web service\n",
|
||||
"We test the web sevice by passing the test images content."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"import requests\n",
|
||||
"key1, key2 = aks_service.get_keys()\n",
|
||||
"\n",
|
||||
"headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
|
||||
"test_sampe = open('test_image.jpg', 'rb').read()\n",
|
||||
"resp = requests.post(aks_service.scoring_uri, test_sample, headers=headers)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Clean up\n",
|
||||
"Delete the service, image, model and compute target"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service.delete()\n",
|
||||
"image.delete()\n",
|
||||
"model.delete()\n",
|
||||
"aks_target.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "aashishb"
|
||||
}
|
||||
],
|
||||
"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": "3.7.0"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.0"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -1,477 +1,477 @@
|
||||
{
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Deploying a web service to Azure Kubernetes Service (AKS)\n",
|
||||
"This notebook shows the steps for deploying a service: registering a model, creating an image, provisioning a cluster (one time action), and deploying a service to it. \n",
|
||||
"We then test and delete the service, image and model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"from azureml.core.webservice import Webservice, AksWebservice\n",
|
||||
"from azureml.core.image import Image\n",
|
||||
"from azureml.core.model import Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"print(azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Get workspace\n",
|
||||
"Load existing workspace from the config file info."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Register the model\n",
|
||||
"Register an existing trained model, add descirption and tags."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Register the model\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
|
||||
" model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
|
||||
" description = \"Ridge regression model to predict diabetes\",\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create an image\n",
|
||||
"Create an image using the registered model the script that will load and run the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from sklearn.linear_model import Ridge\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" # note here \"sklearn_regression_model.pkl\" is the name of the model registered under\n",
|
||||
" # this is a different behavior than before when the code is run locally, even though the code is the same.\n",
|
||||
" model_path = Model.get_model_path('sklearn_regression_model.pkl')\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"# note you can pass in multiple rows for scoring\n",
|
||||
"def run(raw_data):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(raw_data)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" # you can return any data type as long as it is JSON-serializable\n",
|
||||
" return result.tolist()\n",
|
||||
" except Exception as e:\n",
|
||||
" error = str(e)\n",
|
||||
" return error"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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'])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" description = \"Image with ridge regression model\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"myimage1\",\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Use a custom Docker image\n",
|
||||
"\n",
|
||||
"You can also specify a custom Docker image to be used as base image if you don't want to use the default base image provided by Azure ML. Please make sure the custom Docker image has Ubuntu >= 16.04, Conda >= 4.5.\\* and Python(3.5.\\* or 3.6.\\*).\n",
|
||||
"\n",
|
||||
"Only Supported for `ContainerImage`(from azureml.core.image) with `python` runtime.\n",
|
||||
"```python\n",
|
||||
"# use an image available in public Container Registry without authentication\n",
|
||||
"image_config.base_image = \"mcr.microsoft.com/azureml/o16n-sample-user-base/ubuntu-miniconda\"\n",
|
||||
"\n",
|
||||
"# or, use an image available in a private Container Registry\n",
|
||||
"image_config.base_image = \"myregistry.azurecr.io/mycustomimage:1.0\"\n",
|
||||
"image_config.base_image_registry.address = \"myregistry.azurecr.io\"\n",
|
||||
"image_config.base_image_registry.username = \"username\"\n",
|
||||
"image_config.base_image_registry.password = \"password\"\n",
|
||||
"\n",
|
||||
"# or, use an image built during training.\n",
|
||||
"image_config.base_image = run.properties[\"AzureML.DerivedImageName\"]\n",
|
||||
"```\n",
|
||||
"You can get the address of training image from the properties of a Run object. Only new runs submitted with azureml-sdk>=1.0.22 to AMLCompute targets will have the 'AzureML.DerivedImageName' property. Instructions on how to get a Run can be found in [manage-runs](../../training/manage-runs/manage-runs.ipynb). \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Provision the AKS Cluster\n",
|
||||
"This is a one time setup. You can reuse this cluster for multiple deployments after it has been created. If you delete the cluster or the resource group that contains it, then you would have to recreate it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"prov_config = AksCompute.provisioning_configuration()\n",
|
||||
"\n",
|
||||
"aks_name = 'my-aks-9' \n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create AKS Cluster in an existing virtual network (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-enable-virtual-network#use-azure-kubernetes-service) for more details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"from azureml.core.compute import ComputeTarget, AksCompute\n",
|
||||
"\n",
|
||||
"# Create the compute configuration and set virtual network information\n",
|
||||
"config = AksCompute.provisioning_configuration(location=\"eastus2\")\n",
|
||||
"config.vnet_resourcegroup_name = \"mygroup\"\n",
|
||||
"config.vnet_name = \"mynetwork\"\n",
|
||||
"config.subnet_name = \"default\"\n",
|
||||
"config.service_cidr = \"10.0.0.0/16\"\n",
|
||||
"config.dns_service_ip = \"10.0.0.10\"\n",
|
||||
"config.docker_bridge_cidr = \"172.17.0.1/16\"\n",
|
||||
"\n",
|
||||
"# Create the compute target\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws,\n",
|
||||
" name = \"myaks\",\n",
|
||||
" provisioning_configuration = config)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Enable SSL on the AKS Cluster (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-secure-web-service) for more details"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# provisioning_config = AksCompute.provisioning_configuration(ssl_cert_pem_file=\"cert.pem\", ssl_key_pem_file=\"key.pem\", ssl_cname=\"www.contoso.com\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_target.wait_for_completion(show_output = True)\n",
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Optional step: Attach existing AKS cluster\n",
|
||||
"\n",
|
||||
"If you have existing AKS cluster in your Azure subscription, you can attach it to the Workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"resource_id = '/subscriptions/92c76a2f-0e1c-4216-b65e-abf7a3f34c1e/resourcegroups/raymondsdk0604/providers/Microsoft.ContainerService/managedClusters/my-aks-0605d37425356b7d01'\n",
|
||||
"\n",
|
||||
"create_name='my-existing-aks' \n",
|
||||
"# Create the cluster\n",
|
||||
"attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
|
||||
"aks_target = ComputeTarget.attach(workspace=ws, name=create_name, attach_configuration=attach_config)\n",
|
||||
"# Wait for the operation to complete\n",
|
||||
"aks_target.wait_for_completion(True)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Deploy web service to AKS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Set the web service configuration (using default here)\n",
|
||||
"aks_config = AksWebservice.deploy_configuration()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service_name ='aks-service-1'\n",
|
||||
"\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Test the web service using run method\n",
|
||||
"We test the web sevice by passing data.\n",
|
||||
"Run() method retrieves API keys behind the scenes to make sure that call is authenticated."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"import json\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,2,3,4,5,6,7,8,9,10], \n",
|
||||
" [10,9,8,7,6,5,4,3,2,1]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding = 'utf8')\n",
|
||||
"\n",
|
||||
"prediction = aks_service.run(input_data = test_sample)\n",
|
||||
"print(prediction)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Test the web service using raw HTTP request (optional)\n",
|
||||
"Alternatively you can construct a raw HTTP request and send it to the service. In this case you need to explicitly pass the HTTP header. This process is shown in the next 2 cells."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# retreive the API keys. AML generates two keys.\n",
|
||||
"'''\n",
|
||||
"key1, Key2 = aks_service.get_keys()\n",
|
||||
"print(key1)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# construct raw HTTP request and send to the service\n",
|
||||
"'''\n",
|
||||
"%%time\n",
|
||||
"\n",
|
||||
"import requests\n",
|
||||
"\n",
|
||||
"import json\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,2,3,4,5,6,7,8,9,10], \n",
|
||||
" [10,9,8,7,6,5,4,3,2,1]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding = 'utf8')\n",
|
||||
"\n",
|
||||
"# Don't forget to add key to the HTTP header.\n",
|
||||
"headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
|
||||
"\n",
|
||||
"resp = requests.post(aks_service.scoring_uri, test_sample, headers=headers)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"print(\"prediction:\", resp.text)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Clean up\n",
|
||||
"Delete the service, image and model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service.delete()\n",
|
||||
"image.delete()\n",
|
||||
"model.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "aashishb"
|
||||
}
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Deploying a web service to Azure Kubernetes Service (AKS)\n",
|
||||
"This notebook shows the steps for deploying a service: registering a model, creating an image, provisioning a cluster (one time action), and deploying a service to it. \n",
|
||||
"We then test and delete the service, image and model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.compute import AksCompute, ComputeTarget\n",
|
||||
"from azureml.core.webservice import Webservice, AksWebservice\n",
|
||||
"from azureml.core.image import Image\n",
|
||||
"from azureml.core.model import Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"print(azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Get workspace\n",
|
||||
"Load existing workspace from the config file info."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Register the model\n",
|
||||
"Register an existing trained model, add descirption and tags."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Register the model\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"model = Model.register(model_path = \"sklearn_regression_model.pkl\", # this points to a local file\n",
|
||||
" model_name = \"sklearn_regression_model.pkl\", # this is the name the model is registered as\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
|
||||
" description = \"Ridge regression model to predict diabetes\",\n",
|
||||
" workspace = ws)\n",
|
||||
"\n",
|
||||
"print(model.name, model.description, model.version)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create an image\n",
|
||||
"Create an image using the registered model the script that will load and run the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from sklearn.linear_model import Ridge\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" # note here \"sklearn_regression_model.pkl\" is the name of the model registered under\n",
|
||||
" # this is a different behavior than before when the code is run locally, even though the code is the same.\n",
|
||||
" model_path = Model.get_model_path('sklearn_regression_model.pkl')\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"# note you can pass in multiple rows for scoring\n",
|
||||
"def run(raw_data):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(raw_data)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" # you can return any data type as long as it is JSON-serializable\n",
|
||||
" return result.tolist()\n",
|
||||
" except Exception as e:\n",
|
||||
" error = str(e)\n",
|
||||
" return error"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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'])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(execution_script = \"score.py\",\n",
|
||||
" runtime = \"python\",\n",
|
||||
" conda_file = \"myenv.yml\",\n",
|
||||
" description = \"Image with ridge regression model\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"}\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"image = ContainerImage.create(name = \"myimage1\",\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Use a custom Docker image\n",
|
||||
"\n",
|
||||
"You can also specify a custom Docker image to be used as base image if you don't want to use the default base image provided by Azure ML. Please make sure the custom Docker image has Ubuntu >= 16.04, Conda >= 4.5.\\* and Python(3.5.\\* or 3.6.\\*).\n",
|
||||
"\n",
|
||||
"Only Supported for `ContainerImage`(from azureml.core.image) with `python` runtime.\n",
|
||||
"```python\n",
|
||||
"# use an image available in public Container Registry without authentication\n",
|
||||
"image_config.base_image = \"mcr.microsoft.com/azureml/o16n-sample-user-base/ubuntu-miniconda\"\n",
|
||||
"\n",
|
||||
"# or, use an image available in a private Container Registry\n",
|
||||
"image_config.base_image = \"myregistry.azurecr.io/mycustomimage:1.0\"\n",
|
||||
"image_config.base_image_registry.address = \"myregistry.azurecr.io\"\n",
|
||||
"image_config.base_image_registry.username = \"username\"\n",
|
||||
"image_config.base_image_registry.password = \"password\"\n",
|
||||
"\n",
|
||||
"# or, use an image built during training.\n",
|
||||
"image_config.base_image = run.properties[\"AzureML.DerivedImageName\"]\n",
|
||||
"```\n",
|
||||
"You can get the address of training image from the properties of a Run object. Only new runs submitted with azureml-sdk>=1.0.22 to AMLCompute targets will have the 'AzureML.DerivedImageName' property. Instructions on how to get a Run can be found in [manage-runs](../../training/manage-runs/manage-runs.ipynb). \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Provision the AKS Cluster\n",
|
||||
"This is a one time setup. You can reuse this cluster for multiple deployments after it has been created. If you delete the cluster or the resource group that contains it, then you would have to recreate it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"prov_config = AksCompute.provisioning_configuration()\n",
|
||||
"\n",
|
||||
"aks_name = 'my-aks-9' \n",
|
||||
"# Create the cluster\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws, \n",
|
||||
" name = aks_name, \n",
|
||||
" provisioning_configuration = prov_config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Create AKS Cluster in an existing virtual network (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-enable-virtual-network#use-azure-kubernetes-service) for more details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"from azureml.core.compute import ComputeTarget, AksCompute\n",
|
||||
"\n",
|
||||
"# Create the compute configuration and set virtual network information\n",
|
||||
"config = AksCompute.provisioning_configuration(location=\"eastus2\")\n",
|
||||
"config.vnet_resourcegroup_name = \"mygroup\"\n",
|
||||
"config.vnet_name = \"mynetwork\"\n",
|
||||
"config.subnet_name = \"default\"\n",
|
||||
"config.service_cidr = \"10.0.0.0/16\"\n",
|
||||
"config.dns_service_ip = \"10.0.0.10\"\n",
|
||||
"config.docker_bridge_cidr = \"172.17.0.1/16\"\n",
|
||||
"\n",
|
||||
"# Create the compute target\n",
|
||||
"aks_target = ComputeTarget.create(workspace = ws,\n",
|
||||
" name = \"myaks\",\n",
|
||||
" provisioning_configuration = config)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Enable SSL on the AKS Cluster (optional)\n",
|
||||
"See code snippet below. Check the documentation [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-secure-web-service) for more details"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# provisioning_config = AksCompute.provisioning_configuration(ssl_cert_pem_file=\"cert.pem\", ssl_key_pem_file=\"key.pem\", ssl_cname=\"www.contoso.com\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_target.wait_for_completion(show_output = True)\n",
|
||||
"print(aks_target.provisioning_state)\n",
|
||||
"print(aks_target.provisioning_errors)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Optional step: Attach existing AKS cluster\n",
|
||||
"\n",
|
||||
"If you have existing AKS cluster in your Azure subscription, you can attach it to the Workspace."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"# Use the default configuration (can also provide parameters to customize)\n",
|
||||
"resource_id = '/subscriptions/92c76a2f-0e1c-4216-b65e-abf7a3f34c1e/resourcegroups/raymondsdk0604/providers/Microsoft.ContainerService/managedClusters/my-aks-0605d37425356b7d01'\n",
|
||||
"\n",
|
||||
"create_name='my-existing-aks' \n",
|
||||
"# Create the cluster\n",
|
||||
"attach_config = AksCompute.attach_configuration(resource_id=resource_id)\n",
|
||||
"aks_target = ComputeTarget.attach(workspace=ws, name=create_name, attach_configuration=attach_config)\n",
|
||||
"# Wait for the operation to complete\n",
|
||||
"aks_target.wait_for_completion(True)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Deploy web service to AKS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Set the web service configuration (using default here)\n",
|
||||
"aks_config = AksWebservice.deploy_configuration()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service_name ='aks-service-1'\n",
|
||||
"\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)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Test the web service using run method\n",
|
||||
"We test the web sevice by passing data.\n",
|
||||
"Run() method retrieves API keys behind the scenes to make sure that call is authenticated."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"import json\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,2,3,4,5,6,7,8,9,10], \n",
|
||||
" [10,9,8,7,6,5,4,3,2,1]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding = 'utf8')\n",
|
||||
"\n",
|
||||
"prediction = aks_service.run(input_data = test_sample)\n",
|
||||
"print(prediction)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Test the web service using raw HTTP request (optional)\n",
|
||||
"Alternatively you can construct a raw HTTP request and send it to the service. In this case you need to explicitly pass the HTTP header. This process is shown in the next 2 cells."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# retreive the API keys. AML generates two keys.\n",
|
||||
"'''\n",
|
||||
"key1, Key2 = aks_service.get_keys()\n",
|
||||
"print(key1)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# construct raw HTTP request and send to the service\n",
|
||||
"'''\n",
|
||||
"%%time\n",
|
||||
"\n",
|
||||
"import requests\n",
|
||||
"\n",
|
||||
"import json\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,2,3,4,5,6,7,8,9,10], \n",
|
||||
" [10,9,8,7,6,5,4,3,2,1]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding = 'utf8')\n",
|
||||
"\n",
|
||||
"# Don't forget to add key to the HTTP header.\n",
|
||||
"headers = {'Content-Type':'application/json', 'Authorization': 'Bearer ' + key1}\n",
|
||||
"\n",
|
||||
"resp = requests.post(aks_service.scoring_uri, test_sample, headers=headers)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"print(\"prediction:\", resp.text)\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Clean up\n",
|
||||
"Delete the service, image and model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"aks_service.delete()\n",
|
||||
"image.delete()\n",
|
||||
"model.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "aashishb"
|
||||
}
|
||||
],
|
||||
"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"
|
||||
}
|
||||
},
|
||||
"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
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: production-deploy-to-aks
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- matplotlib
|
||||
- tqdm
|
||||
- scipy
|
||||
- sklearn
|
||||
@@ -1,453 +1,453 @@
|
||||
{
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Register Model, Create Image and Deploy Service\n",
|
||||
"\n",
|
||||
"This example shows how to deploy a web service in step-by-step fashion:\n",
|
||||
"\n",
|
||||
" 1. Register model\n",
|
||||
" 2. Query versions of models and select one to deploy\n",
|
||||
" 3. Create Docker image\n",
|
||||
" 4. Query versions of images\n",
|
||||
" 5. Deploy the image as web service\n",
|
||||
" \n",
|
||||
"**IMPORTANT**:\n",
|
||||
" * This notebook requires you to first complete [train-within-notebook](../../training/train-within-notebook/train-within-notebook.ipynb) example\n",
|
||||
" \n",
|
||||
"The train-within-notebook example taught you how to deploy a web service directly from model in one step. This Notebook shows a more advanced approach that gives you more control over model versions and Docker image versions. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Prerequisites\n",
|
||||
"If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Check core SDK version number\n",
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialize Workspace\n",
|
||||
"\n",
|
||||
"Initialize a workspace object from persisted configuration."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create workspace"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Register Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can add tags and descriptions to your models. Note you need to have a `sklearn_linreg_model.pkl` file in the current directory. This file is generated by the 01 notebook. The below call registers that file as a model with the same name `sklearn_linreg_model.pkl` in the workspace.\n",
|
||||
"\n",
|
||||
"Using tags, you can track useful information such as the name and version of the machine learning library used to train the model. Note that tags must be alphanumeric."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"register model from file"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.model import Model\n",
|
||||
"import sklearn\n",
|
||||
"\n",
|
||||
"library_version = \"sklearn\"+sklearn.__version__.replace(\".\",\"x\")\n",
|
||||
"\n",
|
||||
"model = Model.register(model_path = \"sklearn_regression_model.pkl\",\n",
|
||||
" model_name = \"sklearn_regression_model.pkl\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\", 'version': library_version},\n",
|
||||
" description = \"Ridge regression model to predict diabetes\",\n",
|
||||
" workspace = ws)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can explore the registered models within your workspace and query by tag. Models are versioned. If you call the register_model command many times with same model name, you will get multiple versions of the model with increasing version numbers."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"register model from file"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"regression_models = Model.list(workspace=ws, tags=['area'])\n",
|
||||
"for m in regression_models:\n",
|
||||
" print(\"Name:\", m.name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can pick a specific model to deploy"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(model.name, model.description, model.version, sep = '\\t')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create Docker Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Show `score.py`. Note that the `sklearn_regression_model.pkl` in the `get_model_path` call is referring to a model named `sklearn_linreg_model.pkl` registered under the workspace. It is NOT referenceing the local file."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from sklearn.linear_model import Ridge\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" # note here \"sklearn_regression_model.pkl\" is the name of the model registered under\n",
|
||||
" # this is a different behavior than before when the code is run locally, even though the code is the same.\n",
|
||||
" model_path = Model.get_model_path('sklearn_regression_model.pkl')\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"# note you can pass in multiple rows for scoring\n",
|
||||
"def run(raw_data):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(raw_data)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" # you can return any datatype as long as it is JSON-serializable\n",
|
||||
" return result.tolist()\n",
|
||||
" except Exception as e:\n",
|
||||
" error = str(e)\n",
|
||||
" return error"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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'])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note that following command can take few minutes. \n",
|
||||
"\n",
|
||||
"You can add tags and descriptions to images. Also, an image can contain multiple models."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create image"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import Image, ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
|
||||
" execution_script=\"score.py\",\n",
|
||||
" conda_file=\"myenv.yml\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
|
||||
" description = \"Image with ridge regression model\")\n",
|
||||
"\n",
|
||||
"image = Image.create(name = \"myimage1\",\n",
|
||||
" # this is the model object. note you can pass in 0-n models via this list-type parameter\n",
|
||||
" # in case you need to reference multiple models, or none at all, in your scoring script.\n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config, \n",
|
||||
" workspace = ws)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create image"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"image.wait_for_creation(show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Use a custom Docker image\n",
|
||||
"\n",
|
||||
"You can also specify a custom Docker image to be used as base image if you don't want to use the default base image provided by Azure ML. Please make sure the custom Docker image has Ubuntu >= 16.04, Conda >= 4.5.\\* and Python(3.5.\\* or 3.6.\\*).\n",
|
||||
"\n",
|
||||
"Only Supported for `ContainerImage`(from azureml.core.image) with `python` runtime.\n",
|
||||
"```python\n",
|
||||
"# use an image available in public Container Registry without authentication\n",
|
||||
"image_config.base_image = \"mcr.microsoft.com/azureml/o16n-sample-user-base/ubuntu-miniconda\"\n",
|
||||
"\n",
|
||||
"# or, use an image available in a private Container Registry\n",
|
||||
"image_config.base_image = \"myregistry.azurecr.io/mycustomimage:1.0\"\n",
|
||||
"image_config.base_image_registry.address = \"myregistry.azurecr.io\"\n",
|
||||
"image_config.base_image_registry.username = \"username\"\n",
|
||||
"image_config.base_image_registry.password = \"password\"\n",
|
||||
"\n",
|
||||
"# or, use an image built during training.\n",
|
||||
"image_config.base_image = run.properties[\"AzureML.DerivedImageName\"]\n",
|
||||
"```\n",
|
||||
"You can get the address of training image from the properties of a Run object. Only new runs submitted with azureml-sdk>=1.0.22 to AMLCompute targets will have the 'AzureML.DerivedImageName' property. Instructions on how to get a Run can be found in [manage-runs](../../training/manage-runs/manage-runs.ipynb). \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"List images by tag and find out the detailed build log for debugging."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create image"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for i in Image.list(workspace = ws,tags = [\"area\"]):\n",
|
||||
" print('{}(v.{} [{}]) stored at {} with build log {}'.format(i.name, i.version, i.creation_state, i.image_location, i.image_build_log_uri))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Deploy image as web service on Azure Container Instance\n",
|
||||
"\n",
|
||||
"Note that the service creation can take few minutes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"deploy service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import AciWebservice\n",
|
||||
"\n",
|
||||
"aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
|
||||
" memory_gb = 1, \n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"}, \n",
|
||||
" description = 'Predict diabetes using regression model')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"deploy service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"\n",
|
||||
"aci_service_name = 'my-aci-service-2'\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": [
|
||||
"### Test web service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Call the web service with some dummy input data to get a prediction."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"deploy service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,2,3,4,5,6,7,8,9,10], \n",
|
||||
" [10,9,8,7,6,5,4,3,2,1]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding = 'utf8')\n",
|
||||
"\n",
|
||||
"prediction = aci_service.run(input_data=test_sample)\n",
|
||||
"print(prediction)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Delete ACI to clean up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"deploy service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aci_service.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "aashishb"
|
||||
}
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Register Model, Create Image and Deploy Service\n",
|
||||
"\n",
|
||||
"This example shows how to deploy a web service in step-by-step fashion:\n",
|
||||
"\n",
|
||||
" 1. Register model\n",
|
||||
" 2. Query versions of models and select one to deploy\n",
|
||||
" 3. Create Docker image\n",
|
||||
" 4. Query versions of images\n",
|
||||
" 5. Deploy the image as web service\n",
|
||||
" \n",
|
||||
"**IMPORTANT**:\n",
|
||||
" * This notebook requires you to first complete [train-within-notebook](../../training/train-within-notebook/train-within-notebook.ipynb) example\n",
|
||||
" \n",
|
||||
"The train-within-notebook example taught you how to deploy a web service directly from model in one step. This Notebook shows a more advanced approach that gives you more control over model versions and Docker image versions. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Prerequisites\n",
|
||||
"If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, make sure you go through the [configuration](../../../configuration.ipynb) Notebook first if you haven't."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Check core SDK version number\n",
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialize Workspace\n",
|
||||
"\n",
|
||||
"Initialize a workspace object from persisted configuration."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create workspace"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Register Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can add tags and descriptions to your models. Note you need to have a `sklearn_linreg_model.pkl` file in the current directory. This file is generated by the 01 notebook. The below call registers that file as a model with the same name `sklearn_linreg_model.pkl` in the workspace.\n",
|
||||
"\n",
|
||||
"Using tags, you can track useful information such as the name and version of the machine learning library used to train the model. Note that tags must be alphanumeric."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"register model from file"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.model import Model\n",
|
||||
"import sklearn\n",
|
||||
"\n",
|
||||
"library_version = \"sklearn\"+sklearn.__version__.replace(\".\",\"x\")\n",
|
||||
"\n",
|
||||
"model = Model.register(model_path = \"sklearn_regression_model.pkl\",\n",
|
||||
" model_name = \"sklearn_regression_model.pkl\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\", 'version': library_version},\n",
|
||||
" description = \"Ridge regression model to predict diabetes\",\n",
|
||||
" workspace = ws)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can explore the registered models within your workspace and query by tag. Models are versioned. If you call the register_model command many times with same model name, you will get multiple versions of the model with increasing version numbers."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"register model from file"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"regression_models = Model.list(workspace=ws, tags=['area'])\n",
|
||||
"for m in regression_models:\n",
|
||||
" print(\"Name:\", m.name,\"\\tVersion:\", m.version, \"\\tDescription:\", m.description, m.tags)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can pick a specific model to deploy"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(model.name, model.description, model.version, sep = '\\t')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create Docker Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Show `score.py`. Note that the `sklearn_regression_model.pkl` in the `get_model_path` call is referring to a model named `sklearn_linreg_model.pkl` registered under the workspace. It is NOT referenceing the local file."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import pickle\n",
|
||||
"import json\n",
|
||||
"import numpy\n",
|
||||
"from sklearn.externals import joblib\n",
|
||||
"from sklearn.linear_model import Ridge\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" # note here \"sklearn_regression_model.pkl\" is the name of the model registered under\n",
|
||||
" # this is a different behavior than before when the code is run locally, even though the code is the same.\n",
|
||||
" model_path = Model.get_model_path('sklearn_regression_model.pkl')\n",
|
||||
" # deserialize the model file back into a sklearn model\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"# note you can pass in multiple rows for scoring\n",
|
||||
"def run(raw_data):\n",
|
||||
" try:\n",
|
||||
" data = json.loads(raw_data)['data']\n",
|
||||
" data = numpy.array(data)\n",
|
||||
" result = model.predict(data)\n",
|
||||
" # you can return any datatype as long as it is JSON-serializable\n",
|
||||
" return result.tolist()\n",
|
||||
" except Exception as e:\n",
|
||||
" error = str(e)\n",
|
||||
" return error"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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'])\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note that following command can take few minutes. \n",
|
||||
"\n",
|
||||
"You can add tags and descriptions to images. Also, an image can contain multiple models."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create image"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.image import Image, ContainerImage\n",
|
||||
"\n",
|
||||
"image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
|
||||
" execution_script=\"score.py\",\n",
|
||||
" conda_file=\"myenv.yml\",\n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"},\n",
|
||||
" description = \"Image with ridge regression model\")\n",
|
||||
"\n",
|
||||
"image = Image.create(name = \"myimage1\",\n",
|
||||
" # this is the model object. note you can pass in 0-n models via this list-type parameter\n",
|
||||
" # in case you need to reference multiple models, or none at all, in your scoring script.\n",
|
||||
" models = [model],\n",
|
||||
" image_config = image_config, \n",
|
||||
" workspace = ws)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create image"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"image.wait_for_creation(show_output = True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Use a custom Docker image\n",
|
||||
"\n",
|
||||
"You can also specify a custom Docker image to be used as base image if you don't want to use the default base image provided by Azure ML. Please make sure the custom Docker image has Ubuntu >= 16.04, Conda >= 4.5.\\* and Python(3.5.\\* or 3.6.\\*).\n",
|
||||
"\n",
|
||||
"Only Supported for `ContainerImage`(from azureml.core.image) with `python` runtime.\n",
|
||||
"```python\n",
|
||||
"# use an image available in public Container Registry without authentication\n",
|
||||
"image_config.base_image = \"mcr.microsoft.com/azureml/o16n-sample-user-base/ubuntu-miniconda\"\n",
|
||||
"\n",
|
||||
"# or, use an image available in a private Container Registry\n",
|
||||
"image_config.base_image = \"myregistry.azurecr.io/mycustomimage:1.0\"\n",
|
||||
"image_config.base_image_registry.address = \"myregistry.azurecr.io\"\n",
|
||||
"image_config.base_image_registry.username = \"username\"\n",
|
||||
"image_config.base_image_registry.password = \"password\"\n",
|
||||
"\n",
|
||||
"# or, use an image built during training.\n",
|
||||
"image_config.base_image = run.properties[\"AzureML.DerivedImageName\"]\n",
|
||||
"```\n",
|
||||
"You can get the address of training image from the properties of a Run object. Only new runs submitted with azureml-sdk>=1.0.22 to AMLCompute targets will have the 'AzureML.DerivedImageName' property. Instructions on how to get a Run can be found in [manage-runs](../../training/manage-runs/manage-runs.ipynb). \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"List images by tag and find out the detailed build log for debugging."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"create image"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for i in Image.list(workspace = ws,tags = [\"area\"]):\n",
|
||||
" print('{}(v.{} [{}]) stored at {} with build log {}'.format(i.name, i.version, i.creation_state, i.image_location, i.image_build_log_uri))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Deploy image as web service on Azure Container Instance\n",
|
||||
"\n",
|
||||
"Note that the service creation can take few minutes."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"deploy service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import AciWebservice\n",
|
||||
"\n",
|
||||
"aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
|
||||
" memory_gb = 1, \n",
|
||||
" tags = {'area': \"diabetes\", 'type': \"regression\"}, \n",
|
||||
" description = 'Predict diabetes using regression model')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"deploy service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"\n",
|
||||
"aci_service_name = 'my-aci-service-2'\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": [
|
||||
"### Test web service"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Call the web service with some dummy input data to get a prediction."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"deploy service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"\n",
|
||||
"test_sample = json.dumps({'data': [\n",
|
||||
" [1,2,3,4,5,6,7,8,9,10], \n",
|
||||
" [10,9,8,7,6,5,4,3,2,1]\n",
|
||||
"]})\n",
|
||||
"test_sample = bytes(test_sample,encoding = 'utf8')\n",
|
||||
"\n",
|
||||
"prediction = aci_service.run(input_data=test_sample)\n",
|
||||
"print(prediction)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Delete ACI to clean up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"deploy service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"aci_service.delete()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "aashishb"
|
||||
}
|
||||
],
|
||||
"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"
|
||||
}
|
||||
},
|
||||
"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
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
name: register-model-create-image-deploy-service
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- matplotlib
|
||||
- tqdm
|
||||
- scipy
|
||||
- sklearn
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,6 @@
|
||||
name: regression-sklearn-on-amlcompute
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -1,279 +1,279 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Breast cancer diagnosis classification with scikit-learn (run model explainer locally)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a SVM classification model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with full data in local mode, which doesn't contact any Azure services\n",
|
||||
"3. Run 'explain_model' with summarized data in local mode, which doesn't contact any Azure services\n",
|
||||
"4. Visualize the global and local explanations with the visualization dashboard."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.datasets import load_breast_cancer\n",
|
||||
"from sklearn import svm\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the breast cancer diagnosis data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"breast_cancer_data = load_breast_cancer()\n",
|
||||
"classes = breast_cancer_data.target_names.tolist()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(breast_cancer_data.data, breast_cancer_data.target, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a SVM classification model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = svm.SVC(gamma=0.001, C=100., probability=True)\n",
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features=breast_cancer_data.feature_names, classes=classes)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Sorted SHAP values\n",
|
||||
"print('ranked global importance values: {}'.format(global_explanation.get_ranked_global_values()))\n",
|
||||
"# Corresponding feature names\n",
|
||||
"print('ranked global importance names: {}'.format(global_explanation.get_ranked_global_names()))\n",
|
||||
"# feature ranks (based on original order of features)\n",
|
||||
"print('global importance rank: {}'.format(global_explanation.global_importance_rank))\n",
|
||||
"# per class feature names\n",
|
||||
"print('ranked per class feature names: {}'.format(global_explanation.get_ranked_per_class_names()))\n",
|
||||
"# per class feature importance values\n",
|
||||
"print('ranked per class feature values: {}'.format(global_explanation.get_ranked_per_class_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dict(zip(global_explanation.get_ranked_global_names(), global_explanation.get_ranked_global_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions as a collection of local (instance-level) explanations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# feature shap values for all features and all data points in the training data\n",
|
||||
"print('local importance values: {}'.format(global_explanation.local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain local data points (individual instances)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# explain the first member of the test set\n",
|
||||
"instance_num = 0\n",
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[instance_num,:])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# get the prediction for the first member of the test set and explain why model made that prediction\n",
|
||||
"prediction_value = clf.predict(x_test)[instance_num]\n",
|
||||
"\n",
|
||||
"sorted_local_importance_values = local_explanation.get_ranked_local_values()[prediction_value]\n",
|
||||
"sorted_local_importance_names = local_explanation.get_ranked_local_names()[prediction_value]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"dict(zip(sorted_local_importance_names, sorted_local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 2. Load visualization dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
|
||||
"!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"# Or, in Jupyter Labs, uncomment below\n",
|
||||
"# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
|
||||
"# jupyter labextension install microsoft-mli-widget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.contrib.explain.model.visualize import ExplanationDashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ExplanationDashboard(global_explanation, model, x_test)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Breast cancer diagnosis classification with scikit-learn (run model explainer locally)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a SVM classification model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with full data in local mode, which doesn't contact any Azure services\n",
|
||||
"3. Run 'explain_model' with summarized data in local mode, which doesn't contact any Azure services\n",
|
||||
"4. Visualize the global and local explanations with the visualization dashboard."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.datasets import load_breast_cancer\n",
|
||||
"from sklearn import svm\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the breast cancer diagnosis data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"breast_cancer_data = load_breast_cancer()\n",
|
||||
"classes = breast_cancer_data.target_names.tolist()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(breast_cancer_data.data, breast_cancer_data.target, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a SVM classification model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = svm.SVC(gamma=0.001, C=100., probability=True)\n",
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features=breast_cancer_data.feature_names, classes=classes)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Sorted SHAP values\n",
|
||||
"print('ranked global importance values: {}'.format(global_explanation.get_ranked_global_values()))\n",
|
||||
"# Corresponding feature names\n",
|
||||
"print('ranked global importance names: {}'.format(global_explanation.get_ranked_global_names()))\n",
|
||||
"# feature ranks (based on original order of features)\n",
|
||||
"print('global importance rank: {}'.format(global_explanation.global_importance_rank))\n",
|
||||
"# per class feature names\n",
|
||||
"print('ranked per class feature names: {}'.format(global_explanation.get_ranked_per_class_names()))\n",
|
||||
"# per class feature importance values\n",
|
||||
"print('ranked per class feature values: {}'.format(global_explanation.get_ranked_per_class_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dict(zip(global_explanation.get_ranked_global_names(), global_explanation.get_ranked_global_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions as a collection of local (instance-level) explanations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# feature shap values for all features and all data points in the training data\n",
|
||||
"print('local importance values: {}'.format(global_explanation.local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain local data points (individual instances)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# explain the first member of the test set\n",
|
||||
"instance_num = 0\n",
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[instance_num,:])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# get the prediction for the first member of the test set and explain why model made that prediction\n",
|
||||
"prediction_value = clf.predict(x_test)[instance_num]\n",
|
||||
"\n",
|
||||
"sorted_local_importance_values = local_explanation.get_ranked_local_values()[prediction_value]\n",
|
||||
"sorted_local_importance_names = local_explanation.get_ranked_local_names()[prediction_value]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"dict(zip(sorted_local_importance_names, sorted_local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 2. Load visualization dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
|
||||
"!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"# Or, in Jupyter Labs, uncomment below\n",
|
||||
"# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
|
||||
"# jupyter labextension install microsoft-mli-widget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.contrib.explain.model.visualize import ExplanationDashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ExplanationDashboard(global_explanation, model, x_test)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-local-sklearn-binary-classification
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -1,280 +1,280 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Iris flower classification with scikit-learn (run model explainer locally)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a SVM classification model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with full data in local mode, which doesn't contact any Azure services\n",
|
||||
"3. Run 'explain_model' with summarized data in local mode, which doesn't contact any Azure services\n",
|
||||
"4. Visualize the global and local explanations with the visualization dashboard."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.datasets import load_iris\n",
|
||||
"from sklearn import svm\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the breast cancer diagnosis data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"iris = load_iris()\n",
|
||||
"X = iris['data']\n",
|
||||
"y = iris['target']\n",
|
||||
"classes = iris['target_names']\n",
|
||||
"feature_names = iris['feature_names']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a SVM classification model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = svm.SVC(gamma=0.001, C=100., probability=True)\n",
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features = feature_names, classes=classes)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Sorted SHAP values\n",
|
||||
"print('ranked global importance values: {}'.format(global_explanation.get_ranked_global_values()))\n",
|
||||
"# Corresponding feature names\n",
|
||||
"print('ranked global importance names: {}'.format(global_explanation.get_ranked_global_names()))\n",
|
||||
"# feature ranks (based on original order of features)\n",
|
||||
"print('global importance rank: {}'.format(global_explanation.global_importance_rank))\n",
|
||||
"# per class feature names\n",
|
||||
"print('ranked per class feature names: {}'.format(global_explanation.get_ranked_per_class_names()))\n",
|
||||
"# per class feature importance values\n",
|
||||
"print('ranked per class feature values: {}'.format(global_explanation.get_ranked_per_class_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dict(zip(global_explanation.get_ranked_global_names(), global_explanation.get_ranked_global_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions as a collection of local (instance-level) explanations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# feature shap values for all features and all data points in the training data\n",
|
||||
"print('local importance values: {}'.format(global_explanation.local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain local data points (individual instances)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# explain the first member of the test set\n",
|
||||
"instance_num = 0\n",
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[instance_num,:])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# get the prediction for the first member of the test set and explain why model made that prediction\n",
|
||||
"prediction_value = clf.predict(x_test)[instance_num]\n",
|
||||
"\n",
|
||||
"sorted_local_importance_values = local_explanation.get_ranked_local_values()[prediction_value]\n",
|
||||
"sorted_local_importance_names = local_explanation.get_ranked_local_names()[prediction_value]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"dict(zip(sorted_local_importance_names, sorted_local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load visualization dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
|
||||
"!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"# Or, in Jupyter Labs, uncomment below\n",
|
||||
"# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
|
||||
"# jupyter labextension install microsoft-mli-widget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.contrib.explain.model.visualize import ExplanationDashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ExplanationDashboard(global_explanation, model, x_test)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Iris flower classification with scikit-learn (run model explainer locally)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a SVM classification model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with full data in local mode, which doesn't contact any Azure services\n",
|
||||
"3. Run 'explain_model' with summarized data in local mode, which doesn't contact any Azure services\n",
|
||||
"4. Visualize the global and local explanations with the visualization dashboard."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.datasets import load_iris\n",
|
||||
"from sklearn import svm\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the breast cancer diagnosis data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"iris = load_iris()\n",
|
||||
"X = iris['data']\n",
|
||||
"y = iris['target']\n",
|
||||
"classes = iris['target_names']\n",
|
||||
"feature_names = iris['feature_names']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a SVM classification model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = svm.SVC(gamma=0.001, C=100., probability=True)\n",
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features = feature_names, classes=classes)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Sorted SHAP values\n",
|
||||
"print('ranked global importance values: {}'.format(global_explanation.get_ranked_global_values()))\n",
|
||||
"# Corresponding feature names\n",
|
||||
"print('ranked global importance names: {}'.format(global_explanation.get_ranked_global_names()))\n",
|
||||
"# feature ranks (based on original order of features)\n",
|
||||
"print('global importance rank: {}'.format(global_explanation.global_importance_rank))\n",
|
||||
"# per class feature names\n",
|
||||
"print('ranked per class feature names: {}'.format(global_explanation.get_ranked_per_class_names()))\n",
|
||||
"# per class feature importance values\n",
|
||||
"print('ranked per class feature values: {}'.format(global_explanation.get_ranked_per_class_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dict(zip(global_explanation.get_ranked_global_names(), global_explanation.get_ranked_global_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions as a collection of local (instance-level) explanations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# feature shap values for all features and all data points in the training data\n",
|
||||
"print('local importance values: {}'.format(global_explanation.local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain local data points (individual instances)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# explain the first member of the test set\n",
|
||||
"instance_num = 0\n",
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[instance_num,:])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# get the prediction for the first member of the test set and explain why model made that prediction\n",
|
||||
"prediction_value = clf.predict(x_test)[instance_num]\n",
|
||||
"\n",
|
||||
"sorted_local_importance_values = local_explanation.get_ranked_local_values()[prediction_value]\n",
|
||||
"sorted_local_importance_names = local_explanation.get_ranked_local_names()[prediction_value]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"dict(zip(sorted_local_importance_names, sorted_local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load visualization dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
|
||||
"!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"# Or, in Jupyter Labs, uncomment below\n",
|
||||
"# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
|
||||
"# jupyter labextension install microsoft-mli-widget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.contrib.explain.model.visualize import ExplanationDashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ExplanationDashboard(global_explanation, model, x_test)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-local-sklearn-multiclass-classification
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -1,272 +1,272 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Boston Housing Price Prediction with scikit-learn (run model explainer locally)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a GradientBoosting regression model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with full dataset in local mode, which doesn't contact any Azure services.\n",
|
||||
"3. Run 'explain_model' with summarized dataset in local mode, which doesn't contact any Azure services.\n",
|
||||
"4. Visualize the global and local explanations with the visualization dashboard."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn import datasets\n",
|
||||
"from sklearn.ensemble import GradientBoostingRegressor\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the Boston house price data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"boston_data = datasets.load_boston()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(boston_data.data, boston_data.target, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a GradientBoosting Regression model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reg = GradientBoostingRegressor(n_estimators=100, max_depth=4,\n",
|
||||
" learning_rate=0.1, loss='huber',\n",
|
||||
" random_state=1)\n",
|
||||
"model = reg.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features = boston_data.feature_names)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Sorted SHAP values \n",
|
||||
"print('ranked global importance values: {}'.format(global_explanation.get_ranked_global_values()))\n",
|
||||
"# Corresponding feature names\n",
|
||||
"print('ranked global importance names: {}'.format(global_explanation.get_ranked_global_names()))\n",
|
||||
"# feature ranks (based on original order of features)\n",
|
||||
"print('global importance rank: {}'.format(global_explanation.global_importance_rank))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dict(zip(global_explanation.get_ranked_global_names(), global_explanation.get_ranked_global_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions as a collection of local (instance-level) explanations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# feature shap values for all features and all data points in the training data\n",
|
||||
"print('local importance values: {}'.format(global_explanation.local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain local data points (individual instances)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[0,:])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# sorted local feature importance information; reflects the original feature order\n",
|
||||
"sorted_local_importance_names = local_explanation.get_ranked_local_names()\n",
|
||||
"sorted_local_importance_values = local_explanation.get_ranked_local_values()\n",
|
||||
"\n",
|
||||
"print('sorted local importance names: {}'.format(sorted_local_importance_names))\n",
|
||||
"print('sorted local importance values: {}'.format(sorted_local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load visualization dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
|
||||
"!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"# Or, in Jupyter Labs, uncomment below\n",
|
||||
"# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
|
||||
"# jupyter labextension install microsoft-mli-widget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.contrib.explain.model.visualize import ExplanationDashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ExplanationDashboard(global_explanation, model, x_test)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Boston Housing Price Prediction with scikit-learn (run model explainer locally)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a GradientBoosting regression model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with full dataset in local mode, which doesn't contact any Azure services.\n",
|
||||
"3. Run 'explain_model' with summarized dataset in local mode, which doesn't contact any Azure services.\n",
|
||||
"4. Visualize the global and local explanations with the visualization dashboard."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn import datasets\n",
|
||||
"from sklearn.ensemble import GradientBoostingRegressor\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the Boston house price data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"boston_data = datasets.load_boston()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(boston_data.data, boston_data.target, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a GradientBoosting Regression model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"reg = GradientBoostingRegressor(n_estimators=100, max_depth=4,\n",
|
||||
" learning_rate=0.1, loss='huber',\n",
|
||||
" random_state=1)\n",
|
||||
"model = reg.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features = boston_data.feature_names)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Sorted SHAP values \n",
|
||||
"print('ranked global importance values: {}'.format(global_explanation.get_ranked_global_values()))\n",
|
||||
"# Corresponding feature names\n",
|
||||
"print('ranked global importance names: {}'.format(global_explanation.get_ranked_global_names()))\n",
|
||||
"# feature ranks (based on original order of features)\n",
|
||||
"print('global importance rank: {}'.format(global_explanation.global_importance_rank))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dict(zip(global_explanation.get_ranked_global_names(), global_explanation.get_ranked_global_values()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions as a collection of local (instance-level) explanations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# feature shap values for all features and all data points in the training data\n",
|
||||
"print('local importance values: {}'.format(global_explanation.local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain local data points (individual instances)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[0,:])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# sorted local feature importance information; reflects the original feature order\n",
|
||||
"sorted_local_importance_names = local_explanation.get_ranked_local_names()\n",
|
||||
"sorted_local_importance_values = local_explanation.get_ranked_local_values()\n",
|
||||
"\n",
|
||||
"print('sorted local importance names: {}'.format(sorted_local_importance_names))\n",
|
||||
"print('sorted local importance values: {}'.format(sorted_local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load visualization dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
|
||||
"!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"# Or, in Jupyter Labs, uncomment below\n",
|
||||
"# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
|
||||
"# jupyter labextension install microsoft-mli-widget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.contrib.explain.model.visualize import ExplanationDashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ExplanationDashboard(global_explanation, model, x_test)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-local-sklearn-regression
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -1,337 +1,337 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Summary\n",
|
||||
"From raw data that is a mixture of categoricals and numeric, featurize the categoricals using one hot encoding. Use tabular explainer to get explain object and then get raw feature importances"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package on raw features\n",
|
||||
"\n",
|
||||
"1. Train a Logistic Regression model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with full dataset in local mode, which doesn't contact any Azure services.\n",
|
||||
"3. Run 'explain_model' with summarized dataset in local mode, which doesn't contact any Azure services.\n",
|
||||
"4. Visualize the global and local explanations with the visualization dashboard."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.pipeline import Pipeline\n",
|
||||
"from sklearn.impute import SimpleImputer\n",
|
||||
"from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
|
||||
"from sklearn.linear_model import LogisticRegression\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"titanic_url = ('https://raw.githubusercontent.com/amueller/'\n",
|
||||
" 'scipy-2017-sklearn/091d371/notebooks/datasets/titanic3.csv')\n",
|
||||
"data = pd.read_csv(titanic_url)\n",
|
||||
"# fill missing values\n",
|
||||
"data = data.fillna(method=\"ffill\")\n",
|
||||
"data = data.fillna(method=\"bfill\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Similar to example [here](https://scikit-learn.org/stable/auto_examples/compose/plot_column_transformer_mixed_types.html#sphx-glr-auto-examples-compose-plot-column-transformer-mixed-types-py), use a subset of columns"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"\n",
|
||||
"numeric_features = ['age', 'fare']\n",
|
||||
"categorical_features = ['embarked', 'sex', 'pclass']\n",
|
||||
"\n",
|
||||
"y = data['survived'].values\n",
|
||||
"X = data[categorical_features + numeric_features]\n",
|
||||
"\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"sklearn imports"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.pipeline import Pipeline\n",
|
||||
"from sklearn.impute import SimpleImputer\n",
|
||||
"from sklearn.preprocessing import StandardScaler, OneHotEncoder"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can explain raw features by either using a `sklearn.compose.ColumnTransformer` or a list of fitted transformer tuples. The cell below uses `sklearn.compose.ColumnTransformer`. In case you want to run the example with the list of fitted transformer tuples, comment the cell below and uncomment the cell that follows after. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.compose import ColumnTransformer\n",
|
||||
"\n",
|
||||
"transformations = ColumnTransformer([\n",
|
||||
" (\"age_fare\", Pipeline(steps=[\n",
|
||||
" ('imputer', SimpleImputer(strategy='median')),\n",
|
||||
" ('scaler', StandardScaler())\n",
|
||||
" ]), [\"age\", \"fare\"]),\n",
|
||||
" (\"embarked\", Pipeline(steps=[\n",
|
||||
" (\"imputer\", SimpleImputer(strategy='constant', fill_value='missing')), \n",
|
||||
" (\"encoder\", OneHotEncoder(sparse=False))]), [\"embarked\"]),\n",
|
||||
" (\"sex_pclass\", OneHotEncoder(sparse=False), [\"sex\", \"pclass\"]) \n",
|
||||
"])\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Append classifier to preprocessing pipeline.\n",
|
||||
"# Now we have a full prediction pipeline.\n",
|
||||
"clf = Pipeline(steps=[('preprocessor', transformations),\n",
|
||||
" ('classifier', LogisticRegression(solver='lbfgs'))])\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"# Uncomment below if sklearn-pandas is not installed\n",
|
||||
"#!pip install sklearn-pandas\n",
|
||||
"from sklearn_pandas import DataFrameMapper\n",
|
||||
"\n",
|
||||
"# Impute, standardize the numeric features and one-hot encode the categorical features. \n",
|
||||
"\n",
|
||||
"transformations = [\n",
|
||||
" ([\"age\", \"fare\"], Pipeline(steps=[\n",
|
||||
" ('imputer', SimpleImputer(strategy='median')),\n",
|
||||
" ('scaler', StandardScaler())\n",
|
||||
" ])),\n",
|
||||
" ([\"embarked\"], Pipeline(steps=[\n",
|
||||
" (\"imputer\", SimpleImputer(strategy='constant', fill_value='missing')), \n",
|
||||
" (\"encoder\", OneHotEncoder(sparse=False))])),\n",
|
||||
" ([\"sex\", \"pclass\"], OneHotEncoder(sparse=False)) \n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Append classifier to preprocessing pipeline.\n",
|
||||
"# Now we have a full prediction pipeline.\n",
|
||||
"clf = Pipeline(steps=[('preprocessor', DataFrameMapper(transformations)),\n",
|
||||
" ('classifier', LogisticRegression(solver='lbfgs'))])\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a Logistic Regression model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(clf.steps[-1][1], initialization_examples=x_train, features=x_train.columns, transformations=transformations)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sorted_global_importance_values = global_explanation.get_ranked_global_values()\n",
|
||||
"sorted_global_importance_names = global_explanation.get_ranked_global_names()\n",
|
||||
"dict(zip(sorted_global_importance_names, sorted_global_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions as a collection of local (instance-level) explanations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# explain the first member of the test set\n",
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[:1])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# get the prediction for the first member of the test set and explain why model made that prediction\n",
|
||||
"prediction_value = clf.predict(x_test)[0]\n",
|
||||
"\n",
|
||||
"sorted_local_importance_values = local_explanation.get_ranked_local_values()[prediction_value]\n",
|
||||
"sorted_local_importance_names = local_explanation.get_ranked_local_names()[prediction_value]\n",
|
||||
"\n",
|
||||
"# Sorted local SHAP values\n",
|
||||
"print('ranked local importance values: {}'.format(sorted_local_importance_values))\n",
|
||||
"# Corresponding feature names\n",
|
||||
"print('ranked local importance names: {}'.format(sorted_local_importance_names))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 2. Load visualization dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
|
||||
"!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"# Or, in Jupyter Labs, uncomment below\n",
|
||||
"# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
|
||||
"# jupyter labextension install microsoft-mli-widget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.contrib.explain.model.visualize import ExplanationDashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ExplanationDashboard(global_explanation, model, x_test)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Summary\n",
|
||||
"From raw data that is a mixture of categoricals and numeric, featurize the categoricals using one hot encoding. Use tabular explainer to get explain object and then get raw feature importances"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package on raw features\n",
|
||||
"\n",
|
||||
"1. Train a Logistic Regression model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with full dataset in local mode, which doesn't contact any Azure services.\n",
|
||||
"3. Run 'explain_model' with summarized dataset in local mode, which doesn't contact any Azure services.\n",
|
||||
"4. Visualize the global and local explanations with the visualization dashboard."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.pipeline import Pipeline\n",
|
||||
"from sklearn.impute import SimpleImputer\n",
|
||||
"from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
|
||||
"from sklearn.linear_model import LogisticRegression\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"titanic_url = ('https://raw.githubusercontent.com/amueller/'\n",
|
||||
" 'scipy-2017-sklearn/091d371/notebooks/datasets/titanic3.csv')\n",
|
||||
"data = pd.read_csv(titanic_url)\n",
|
||||
"# fill missing values\n",
|
||||
"data = data.fillna(method=\"ffill\")\n",
|
||||
"data = data.fillna(method=\"bfill\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Similar to example [here](https://scikit-learn.org/stable/auto_examples/compose/plot_column_transformer_mixed_types.html#sphx-glr-auto-examples-compose-plot-column-transformer-mixed-types-py), use a subset of columns"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"\n",
|
||||
"numeric_features = ['age', 'fare']\n",
|
||||
"categorical_features = ['embarked', 'sex', 'pclass']\n",
|
||||
"\n",
|
||||
"y = data['survived'].values\n",
|
||||
"X = data[categorical_features + numeric_features]\n",
|
||||
"\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"sklearn imports"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.pipeline import Pipeline\n",
|
||||
"from sklearn.impute import SimpleImputer\n",
|
||||
"from sklearn.preprocessing import StandardScaler, OneHotEncoder"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can explain raw features by either using a `sklearn.compose.ColumnTransformer` or a list of fitted transformer tuples. The cell below uses `sklearn.compose.ColumnTransformer`. In case you want to run the example with the list of fitted transformer tuples, comment the cell below and uncomment the cell that follows after. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.compose import ColumnTransformer\n",
|
||||
"\n",
|
||||
"transformations = ColumnTransformer([\n",
|
||||
" (\"age_fare\", Pipeline(steps=[\n",
|
||||
" ('imputer', SimpleImputer(strategy='median')),\n",
|
||||
" ('scaler', StandardScaler())\n",
|
||||
" ]), [\"age\", \"fare\"]),\n",
|
||||
" (\"embarked\", Pipeline(steps=[\n",
|
||||
" (\"imputer\", SimpleImputer(strategy='constant', fill_value='missing')), \n",
|
||||
" (\"encoder\", OneHotEncoder(sparse=False))]), [\"embarked\"]),\n",
|
||||
" (\"sex_pclass\", OneHotEncoder(sparse=False), [\"sex\", \"pclass\"]) \n",
|
||||
"])\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Append classifier to preprocessing pipeline.\n",
|
||||
"# Now we have a full prediction pipeline.\n",
|
||||
"clf = Pipeline(steps=[('preprocessor', transformations),\n",
|
||||
" ('classifier', LogisticRegression(solver='lbfgs'))])\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"'''\n",
|
||||
"# Uncomment below if sklearn-pandas is not installed\n",
|
||||
"#!pip install sklearn-pandas\n",
|
||||
"from sklearn_pandas import DataFrameMapper\n",
|
||||
"\n",
|
||||
"# Impute, standardize the numeric features and one-hot encode the categorical features. \n",
|
||||
"\n",
|
||||
"transformations = [\n",
|
||||
" ([\"age\", \"fare\"], Pipeline(steps=[\n",
|
||||
" ('imputer', SimpleImputer(strategy='median')),\n",
|
||||
" ('scaler', StandardScaler())\n",
|
||||
" ])),\n",
|
||||
" ([\"embarked\"], Pipeline(steps=[\n",
|
||||
" (\"imputer\", SimpleImputer(strategy='constant', fill_value='missing')), \n",
|
||||
" (\"encoder\", OneHotEncoder(sparse=False))])),\n",
|
||||
" ([\"sex\", \"pclass\"], OneHotEncoder(sparse=False)) \n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Append classifier to preprocessing pipeline.\n",
|
||||
"# Now we have a full prediction pipeline.\n",
|
||||
"clf = Pipeline(steps=[('preprocessor', DataFrameMapper(transformations)),\n",
|
||||
" ('classifier', LogisticRegression(solver='lbfgs'))])\n",
|
||||
"'''"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a Logistic Regression model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(clf.steps[-1][1], initialization_examples=x_train, features=x_train.columns, transformations=transformations)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sorted_global_importance_values = global_explanation.get_ranked_global_values()\n",
|
||||
"sorted_global_importance_names = global_explanation.get_ranked_global_names()\n",
|
||||
"dict(zip(sorted_global_importance_names, sorted_global_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions as a collection of local (instance-level) explanations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# explain the first member of the test set\n",
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[:1])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# get the prediction for the first member of the test set and explain why model made that prediction\n",
|
||||
"prediction_value = clf.predict(x_test)[0]\n",
|
||||
"\n",
|
||||
"sorted_local_importance_values = local_explanation.get_ranked_local_values()[prediction_value]\n",
|
||||
"sorted_local_importance_names = local_explanation.get_ranked_local_names()[prediction_value]\n",
|
||||
"\n",
|
||||
"# Sorted local SHAP values\n",
|
||||
"print('ranked local importance values: {}'.format(sorted_local_importance_values))\n",
|
||||
"# Corresponding feature names\n",
|
||||
"print('ranked local importance names: {}'.format(sorted_local_importance_names))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 2. Load visualization dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Note you will need to have extensions enabled prior to jupyter kernel starting\n",
|
||||
"!jupyter nbextension install --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"!jupyter nbextension enable --py --sys-prefix azureml.contrib.explain.model.visualize\n",
|
||||
"# Or, in Jupyter Labs, uncomment below\n",
|
||||
"# jupyter labextension install @jupyter-widgets/jupyterlab-manager\n",
|
||||
"# jupyter labextension install microsoft-mli-widget"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.contrib.explain.model.visualize import ExplanationDashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ExplanationDashboard(global_explanation, model, x_test)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
name: explain-sklearn-raw-features
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
- sklearn-pandas
|
||||
@@ -1,262 +1,262 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Breast cancer diagnosis classification with scikit-learn (save model explanations via AML Run History)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a SVM classification model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with AML Run History, which leverages run history service to store and manage the explanation data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.datasets import load_breast_cancer\n",
|
||||
"from sklearn import svm\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the breast cancer diagnosis data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"breast_cancer_data = load_breast_cancer()\n",
|
||||
"classes = breast_cancer_data.target_names.tolist()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(breast_cancer_data.data, breast_cancer_data.target, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a SVM classification model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = svm.SVC(gamma=0.001, C=100., probability=True)\n",
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features=breast_cancer_data.feature_names, classes=classes)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 2. Save Model Explanation With AML Run History"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"from azureml.core import Workspace, Experiment, Run\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer\n",
|
||||
"from azureml.contrib.explain.model.explanation.explanation_client import ExplanationClient\n",
|
||||
"# Check core SDK version number\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print('Workspace name: ' + ws.name, \n",
|
||||
" 'Azure region: ' + ws.location, \n",
|
||||
" 'Subscription id: ' + ws.subscription_id, \n",
|
||||
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"experiment_name = 'explain_model'\n",
|
||||
"experiment = Experiment(ws, experiment_name)\n",
|
||||
"run = experiment.start_logging()\n",
|
||||
"client = ExplanationClient.from_run(run)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Uploading model explanation data for storage or visualization in webUX\n",
|
||||
"# The explanation can then be downloaded on any compute\n",
|
||||
"client.upload_model_explanation(global_explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get model explanation data\n",
|
||||
"explanation = client.download_model_explanation()\n",
|
||||
"local_importance_values = explanation.local_importance_values\n",
|
||||
"expected_values = explanation.expected_values"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get the top k (e.g., 4) most important features with their importance values\n",
|
||||
"explanation = client.download_model_explanation(top_k=4)\n",
|
||||
"global_importance_values = explanation.get_ranked_global_values()\n",
|
||||
"global_importance_names = explanation.get_ranked_global_names()\n",
|
||||
"per_class_names = explanation.get_ranked_per_class_names()[0]\n",
|
||||
"per_class_values = explanation.get_ranked_per_class_values()[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print('per class feature importance values: {}'.format(per_class_values))\n",
|
||||
"print('per class feature importance names: {}'.format(per_class_names))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dict(zip(per_class_names, per_class_values))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Breast cancer diagnosis classification with scikit-learn (save model explanations via AML Run History)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a SVM classification model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with AML Run History, which leverages run history service to store and manage the explanation data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.datasets import load_breast_cancer\n",
|
||||
"from sklearn import svm\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1. Run model explainer locally with full data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the breast cancer diagnosis data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"breast_cancer_data = load_breast_cancer()\n",
|
||||
"classes = breast_cancer_data.target_names.tolist()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(breast_cancer_data.data, breast_cancer_data.target, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a SVM classification model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = svm.SVC(gamma=0.001, C=100., probability=True)\n",
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features=breast_cancer_data.feature_names, classes=classes)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 2. Save Model Explanation With AML Run History"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import azureml.core\n",
|
||||
"from azureml.core import Workspace, Experiment, Run\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer\n",
|
||||
"from azureml.contrib.explain.model.explanation.explanation_client import ExplanationClient\n",
|
||||
"# Check core SDK version number\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print('Workspace name: ' + ws.name, \n",
|
||||
" 'Azure region: ' + ws.location, \n",
|
||||
" 'Subscription id: ' + ws.subscription_id, \n",
|
||||
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"experiment_name = 'explain_model'\n",
|
||||
"experiment = Experiment(ws, experiment_name)\n",
|
||||
"run = experiment.start_logging()\n",
|
||||
"client = ExplanationClient.from_run(run)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Uploading model explanation data for storage or visualization in webUX\n",
|
||||
"# The explanation can then be downloaded on any compute\n",
|
||||
"client.upload_model_explanation(global_explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get model explanation data\n",
|
||||
"explanation = client.download_model_explanation()\n",
|
||||
"local_importance_values = explanation.local_importance_values\n",
|
||||
"expected_values = explanation.expected_values"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get the top k (e.g., 4) most important features with their importance values\n",
|
||||
"explanation = client.download_model_explanation(top_k=4)\n",
|
||||
"global_importance_values = explanation.get_ranked_global_values()\n",
|
||||
"global_importance_names = explanation.get_ranked_global_names()\n",
|
||||
"per_class_names = explanation.get_ranked_per_class_names()[0]\n",
|
||||
"per_class_values = explanation.get_ranked_per_class_values()[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print('per class feature importance values: {}'.format(per_class_values))\n",
|
||||
"print('per class feature importance names: {}'.format(per_class_names))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"dict(zip(per_class_names, per_class_values))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-run-history-sklearn-classification
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -1,276 +1,276 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Boston Housing Price Prediction with scikit-learn (save model explanations via AML Run History)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a GradientBoosting regression model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with AML Run History, which leverages run history service to store and manage the explanation data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Save Model Explanation With AML Run History"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Import Iris dataset\n",
|
||||
"from sklearn import datasets\n",
|
||||
"from sklearn.ensemble import GradientBoostingRegressor\n",
|
||||
"\n",
|
||||
"import azureml.core\n",
|
||||
"from azureml.core import Workspace, Experiment, Run\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer\n",
|
||||
"from azureml.contrib.explain.model.explanation.explanation_client import ExplanationClient\n",
|
||||
"# Check core SDK version number\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print('Workspace name: ' + ws.name, \n",
|
||||
" 'Azure region: ' + ws.location, \n",
|
||||
" 'Subscription id: ' + ws.subscription_id, \n",
|
||||
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"experiment_name = 'explain_model'\n",
|
||||
"experiment = Experiment(ws, experiment_name)\n",
|
||||
"run = experiment.start_logging()\n",
|
||||
"client = ExplanationClient.from_run(run)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the Boston house price data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"boston_data = datasets.load_boston()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(boston_data.data, boston_data.target, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a GradientBoosting Regression model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = GradientBoostingRegressor(n_estimators=100, max_depth=4,\n",
|
||||
" learning_rate=0.1, loss='huber',\n",
|
||||
" random_state=1)\n",
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features=boston_data.feature_names)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Uploading model explanation data for storage or visualization in webUX\n",
|
||||
"# The explanation can then be downloaded on any compute\n",
|
||||
"client.upload_model_explanation(global_explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get model explanation data\n",
|
||||
"explanation = client.download_model_explanation()\n",
|
||||
"local_importance_values = explanation.local_importance_values\n",
|
||||
"expected_values = explanation.expected_values"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Print the values\n",
|
||||
"print('expected values: {}'.format(expected_values))\n",
|
||||
"print('local importance values: {}'.format(local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get the top k (e.g., 4) most important features with their importance values\n",
|
||||
"explanation = client.download_model_explanation(top_k=4)\n",
|
||||
"global_importance_values = explanation.get_ranked_global_values()\n",
|
||||
"global_importance_names = explanation.get_ranked_global_names()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print('global importance values: {}'.format(global_importance_values))\n",
|
||||
"print('global importance names: {}'.format(global_importance_names))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain individual instance predictions (local explanation) ##### needs to get updated with the new build"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[0,:])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# local feature importance information\n",
|
||||
"local_importance_values = local_explanation.local_importance_values\n",
|
||||
"print('local importance values: {}'.format(local_importance_values))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Boston Housing Price Prediction with scikit-learn (save model explanations via AML Run History)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Explain a model with the AML explain-model package\n",
|
||||
"\n",
|
||||
"1. Train a GradientBoosting regression model using Scikit-learn\n",
|
||||
"2. Run 'explain_model' with AML Run History, which leverages run history service to store and manage the explanation data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Save Model Explanation With AML Run History"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Import Iris dataset\n",
|
||||
"from sklearn import datasets\n",
|
||||
"from sklearn.ensemble import GradientBoostingRegressor\n",
|
||||
"\n",
|
||||
"import azureml.core\n",
|
||||
"from azureml.core import Workspace, Experiment, Run\n",
|
||||
"from azureml.explain.model.tabular_explainer import TabularExplainer\n",
|
||||
"from azureml.contrib.explain.model.explanation.explanation_client import ExplanationClient\n",
|
||||
"# Check core SDK version number\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print('Workspace name: ' + ws.name, \n",
|
||||
" 'Azure region: ' + ws.location, \n",
|
||||
" 'Subscription id: ' + ws.subscription_id, \n",
|
||||
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"experiment_name = 'explain_model'\n",
|
||||
"experiment = Experiment(ws, experiment_name)\n",
|
||||
"run = experiment.start_logging()\n",
|
||||
"client = ExplanationClient.from_run(run)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load the Boston house price data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"boston_data = datasets.load_boston()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Split data into train and test\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"x_train, x_test, y_train, y_test = train_test_split(boston_data.data, boston_data.target, test_size=0.2, random_state=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train a GradientBoosting Regression model, which you want to explain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"clf = GradientBoostingRegressor(n_estimators=100, max_depth=4,\n",
|
||||
" learning_rate=0.1, loss='huber',\n",
|
||||
" random_state=1)\n",
|
||||
"model = clf.fit(x_train, y_train)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain predictions on your local machine"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tabular_explainer = TabularExplainer(model, x_train, features=boston_data.feature_names)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain overall model predictions (global explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data\n",
|
||||
"# x_train can be passed as well, but with more examples explanations will take longer although they may be more accurate\n",
|
||||
"global_explanation = tabular_explainer.explain_global(x_test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Uploading model explanation data for storage or visualization in webUX\n",
|
||||
"# The explanation can then be downloaded on any compute\n",
|
||||
"client.upload_model_explanation(global_explanation)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get model explanation data\n",
|
||||
"explanation = client.download_model_explanation()\n",
|
||||
"local_importance_values = explanation.local_importance_values\n",
|
||||
"expected_values = explanation.expected_values"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Print the values\n",
|
||||
"print('expected values: {}'.format(expected_values))\n",
|
||||
"print('local importance values: {}'.format(local_importance_values))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get the top k (e.g., 4) most important features with their importance values\n",
|
||||
"explanation = client.download_model_explanation(top_k=4)\n",
|
||||
"global_importance_values = explanation.get_ranked_global_values()\n",
|
||||
"global_importance_names = explanation.get_ranked_global_names()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print('global importance values: {}'.format(global_importance_values))\n",
|
||||
"print('global importance names: {}'.format(global_importance_names))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Explain individual instance predictions (local explanation) ##### needs to get updated with the new build"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"local_explanation = tabular_explainer.explain_local(x_test[0,:])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# local feature importance information\n",
|
||||
"local_importance_values = local_explanation.local_importance_values\n",
|
||||
"print('local importance values: {}'.format(local_importance_values))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "mesameki"
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
name: explain-run-history-sklearn-regression
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-explain-model
|
||||
- azureml-contrib-explain-model
|
||||
@@ -0,0 +1,5 @@
|
||||
name: aml-pipelines-data-transfer
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,5 @@
|
||||
name: aml-pipelines-getting-started
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,5 @@
|
||||
name: aml-pipelines-how-to-use-estimatorstep
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,6 @@
|
||||
name: aml-pipelines-publish-and-run-using-rest-endpoint
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- requests
|
||||
@@ -0,0 +1,8 @@
|
||||
name: aml-pipelines-with-automated-machine-learning-step
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-train-automl
|
||||
- azureml-widgets
|
||||
- matplotlib
|
||||
- pandas_ml
|
||||
@@ -0,0 +1,5 @@
|
||||
name: aml-pipelines-with-data-dependency-steps
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
@@ -0,0 +1,24 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
# Licensed under the MIT license.
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
print("In compare.py")
|
||||
print("As a data scientist, this is where I use my compare code.")
|
||||
parser = argparse.ArgumentParser("compare")
|
||||
parser.add_argument("--compare_data1", type=str, help="compare_data1 data")
|
||||
parser.add_argument("--compare_data2", type=str, help="compare_data2 data")
|
||||
parser.add_argument("--output_compare", type=str, help="output_compare directory")
|
||||
parser.add_argument("--pipeline_param", type=int, help="pipeline parameter")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
print("Argument 1: %s" % args.compare_data1)
|
||||
print("Argument 2: %s" % args.compare_data2)
|
||||
print("Argument 3: %s" % args.output_compare)
|
||||
print("Argument 4: %s" % args.pipeline_param)
|
||||
|
||||
if not (args.output_compare is None):
|
||||
os.makedirs(args.output_compare, exist_ok=True)
|
||||
print("%s created" % args.output_compare)
|
||||
@@ -0,0 +1,21 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
# Licensed under the MIT license.
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
print("In extract.py")
|
||||
print("As a data scientist, this is where I use my extract code.")
|
||||
|
||||
parser = argparse.ArgumentParser("extract")
|
||||
parser.add_argument("--input_extract", type=str, help="input_extract data")
|
||||
parser.add_argument("--output_extract", type=str, help="output_extract directory")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
print("Argument 1: %s" % args.input_extract)
|
||||
print("Argument 2: %s" % args.output_extract)
|
||||
|
||||
if not (args.output_extract is None):
|
||||
os.makedirs(args.output_extract, exist_ok=True)
|
||||
print("%s created" % args.output_extract)
|
||||
@@ -0,0 +1,22 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
# Licensed under the MIT license.
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
print("In train.py")
|
||||
print("As a data scientist, this is where I use my training code.")
|
||||
|
||||
parser = argparse.ArgumentParser("train")
|
||||
|
||||
parser.add_argument("--input_data", type=str, help="input data")
|
||||
parser.add_argument("--output_train", type=str, help="output_train directory")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
print("Argument 1: %s" % args.input_data)
|
||||
print("Argument 2: %s" % args.output_train)
|
||||
|
||||
if not (args.output_train is None):
|
||||
os.makedirs(args.output_train, exist_ok=True)
|
||||
print("%s created" % args.output_train)
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,9 @@
|
||||
name: nyc-taxi-data-regression-model-building
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- azureml-contrib-opendatasets
|
||||
- azureml-dataprep
|
||||
- azureml-train-automl
|
||||
- matplotlib
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,7 @@
|
||||
name: pipeline-batch-scoring
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- pandas
|
||||
- requests
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,6 @@
|
||||
name: pipeline-style-transfer
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
- requests
|
||||
@@ -19,12 +19,12 @@
|
||||
"The interactive authentication is suitable for local experimentation on your own computer. Azure CLI authentication is suitable if you are already using Azure CLI for managing Azure resources, and want to sign in only once. The Service Principal authentication is suitable for automated workflows, for example as part of Azure Devops build."
|
||||
]
|
||||
},
|
||||
{
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
@@ -257,4 +257,4 @@
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
}
|
||||
@@ -6,8 +6,20 @@
|
||||
"source": [
|
||||
"Copyright (c) Microsoft Corporation. All rights reserved.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License.\n",
|
||||
"\n",
|
||||
"Licensed under the MIT License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Authentication in Azure Machine Learning\n",
|
||||
"\n",
|
||||
"This notebook shows you how to authenticate to your Azure ML Workspace using\n",
|
||||
@@ -19,13 +31,6 @@
|
||||
"The interactive authentication is suitable for local experimentation on your own computer. Azure CLI authentication is suitable if you are already using Azure CLI for managing Azure resources, and want to sign in only once. The Service Principal authentication is suitable for automated workflows, for example as part of Azure Devops build."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
@@ -92,7 +97,7 @@
|
||||
"source": [
|
||||
"In some cases, you may see a version of the error message containing text: ```All the subscriptions that you have access to = []```\n",
|
||||
"\n",
|
||||
"In such a case, you may have to specify the tenant ID of the Azure Active Directory you're using. An example would be accessing a subscription as a guest to a tenant that is not your default. You specify the tenant by explicitly instantiating _InteractiveLoginAuthentication_ with tenant ID as argument ([see instructions how to obtain tenant Id](#get-tenant-id))."
|
||||
"In such a case, you may have to specify the tenant ID of the Azure Active Directory you're using. An example would be accessing a subscription as a guest to a tenant that is not your default. You specify the tenant by explicitly instantiating _InteractiveLoginAuthentication_ with Tenant ID as argument. The Tenant ID can be found, for example, from https://portal.azure.com under **Azure Active Directory**, **Properties** as Directory ID."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -150,31 +155,27 @@
|
||||
"\n",
|
||||
"Note that you must have administrator privileges over the Azure subscription to complete these steps.\n",
|
||||
"\n",
|
||||
"The first step is to create a service principal. First, go to [Azure Portal](https://portal.azure.com), select **Azure Active Directory** and **App Registrations**. Then select **+New application registration**, give your service principal a name, for example _my-svc-principal_. You can leave application type as is, and specify a dummy value for Sign-on URL, such as _https://invalid_.\n",
|
||||
"The first step is to create a service principal. First, go to [Azure Portal](https://portal.azure.com), select **Azure Active Directory** and **App Registrations**. Then select **+New application**, give your service principal a name, for example _my-svc-principal_. You can leave other parameters as is.\n",
|
||||
"\n",
|
||||
"Then click **Create**.\n",
|
||||
"Then click **Register**.\n",
|
||||
"\n",
|
||||
"![service principal creation]<img src=\"images/svc-pr-1.PNG\">"
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The next step is to obtain the _Application ID_ (also called username) and create _password_ for the service principal.\n",
|
||||
"\n",
|
||||
"From the page for your newly created service principal, copy the _Application ID_. Then select **Settings** and **Keys**, write a description for your key, and select duration. Then click **Save**, and copy the _password_ to a secure location.\n",
|
||||
"\n",
|
||||
""
|
||||
"From the page for your newly created service principal, copy the _Application ID_ and _Tenant ID_ as they are needed later.\n",
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a id =\"get-tenant-id\"></a>\n",
|
||||
"Then select **Certificates & secrets**, and **+New client secret** write a description for your key, and select duration. Then click **Add**, and copy the value of client secret to a secure location.\n",
|
||||
"\n",
|
||||
"Also, you need to obtain the tenant ID of your Azure subscription. Go back to **Azure Active Directory**, select **Properties** and copy _Directory ID_.\n",
|
||||
"\n",
|
||||
""
|
||||
]
|
||||
@@ -229,6 +230,20 @@
|
||||
"\n",
|
||||
"print(\"Found workspace {} at location {}\".format(ws.name, ws.location))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"See [Register an application with the Microsoft identity platform](https://docs.microsoft.com/en-us/azure/active-directory/develop/quickstart-register-app) quickstart for more details about application registrations. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@@ -252,7 +267,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.5"
|
||||
"version": "3.6.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 37 KiB After Width: | Height: | Size: 97 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 68 KiB After Width: | Height: | Size: 82 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 67 KiB After Width: | Height: | Size: 62 KiB |
@@ -1,322 +1,322 @@
|
||||
{
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Distributed Chainer\n",
|
||||
"In this tutorial, you will run a Chainer training example on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using ChainerMN distributed training across a GPU cluster."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Prerequisites\n",
|
||||
"* If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [Configuration](../../../configuration.ipynb) notebook to install the Azure Machine Learning Python SDK and create an Azure ML `Workspace`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Check core SDK version number\n",
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Diagnostics\n",
|
||||
"Opt-in diagnostics for better experience, quality, and security of future releases."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"Diagnostics"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.telemetry import set_diagnostics_collection\n",
|
||||
"\n",
|
||||
"set_diagnostics_collection(send_diagnostics=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialize workspace\n",
|
||||
"\n",
|
||||
"Initialize a [Workspace](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print('Workspace name: ' + ws.name, \n",
|
||||
" 'Azure region: ' + ws.location, \n",
|
||||
" 'Subscription id: ' + ws.subscription_id, \n",
|
||||
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create or attach existing AmlCompute\n",
|
||||
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for training your model. In this tutorial, we use Azure ML managed compute ([AmlCompute](https://docs.microsoft.com/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute)) for our remote training compute resource. Specifically, the below code creates an `STANDARD_NC6` GPU cluster that autoscales from `0` to `4` nodes.\n",
|
||||
"\n",
|
||||
"**Creation of AmlCompute takes approximately 5 minutes.** If the AmlCompute with that name is already in your workspace, this code will skip the creation process.\n",
|
||||
"\n",
|
||||
"As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
|
||||
"from azureml.core.compute_target import ComputeTargetException\n",
|
||||
"\n",
|
||||
"# choose a name for your cluster\n",
|
||||
"cluster_name = \"gpu-cluster\"\n",
|
||||
"\n",
|
||||
"try:\n",
|
||||
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
|
||||
" print('Found existing compute target.')\n",
|
||||
"except ComputeTargetException:\n",
|
||||
" print('Creating a new compute target...')\n",
|
||||
" compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6',\n",
|
||||
" max_nodes=4)\n",
|
||||
"\n",
|
||||
" # create the cluster\n",
|
||||
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
|
||||
"\n",
|
||||
" compute_target.wait_for_completion(show_output=True)\n",
|
||||
"\n",
|
||||
"# use get_status() to get a detailed status for the current AmlCompute. \n",
|
||||
"print(compute_target.get_status().serialize())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The above code creates GPU compute. If you instead want to create CPU compute, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train model on the remote compute\n",
|
||||
"Now that we have the AmlCompute ready to go, let's run our distributed training job."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a project directory\n",
|
||||
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script and any additional files your training script depends on."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"project_folder = './chainer-distr'\n",
|
||||
"os.makedirs(project_folder, exist_ok=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Prepare training script\n",
|
||||
"Now you will need to create your training script. In this tutorial, the script for distributed training of MNIST is already provided for you at `train_mnist.py`. In practice, you should be able to take any custom Chainer training script as is and run it with Azure ML without having to modify your code."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Once your script is ready, copy the training script `train_mnist.py` into the project directory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import shutil\n",
|
||||
"\n",
|
||||
"shutil.copy('train_mnist.py', project_folder)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create an experiment\n",
|
||||
"Create an [Experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed Chainer tutorial. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Experiment\n",
|
||||
"\n",
|
||||
"experiment_name = 'chainer-distr'\n",
|
||||
"experiment = Experiment(ws, name=experiment_name)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a Chainer estimator\n",
|
||||
"The Azure ML SDK's Chainer estimator enables you to easily submit Chainer training jobs for both single-node and distributed runs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.runconfig import MpiConfiguration\n",
|
||||
"from azureml.train.dnn import Chainer\n",
|
||||
"\n",
|
||||
"estimator = Chainer(source_directory=project_folder,\n",
|
||||
" compute_target=compute_target,\n",
|
||||
" entry_script='train_mnist.py',\n",
|
||||
" node_count=2,\n",
|
||||
" distributed_training=MpiConfiguration(),\n",
|
||||
" use_gpu=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, Chainer and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `Chainer` constructor's `pip_packages` or `conda_packages` parameters."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Submit job\n",
|
||||
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"run = experiment.submit(estimator)\n",
|
||||
"print(run)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Monitor your run\n",
|
||||
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes. You can see that the widget automatically plots and visualizes the loss metric that we logged to the Azure ML run."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.widgets import RunDetails\n",
|
||||
"\n",
|
||||
"RunDetails(run).show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"run.wait_for_completion(show_output=True)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "minxia"
|
||||
}
|
||||
"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": [
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Distributed Chainer\n",
|
||||
"In this tutorial, you will run a Chainer training example on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using ChainerMN distributed training across a GPU cluster."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Prerequisites\n",
|
||||
"* If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [Configuration](../../../configuration.ipynb) notebook to install the Azure Machine Learning Python SDK and create an Azure ML `Workspace`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Check core SDK version number\n",
|
||||
"import azureml.core\n",
|
||||
"\n",
|
||||
"print(\"SDK version:\", azureml.core.VERSION)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Diagnostics\n",
|
||||
"Opt-in diagnostics for better experience, quality, and security of future releases."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"Diagnostics"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.telemetry import set_diagnostics_collection\n",
|
||||
"\n",
|
||||
"set_diagnostics_collection(send_diagnostics=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initialize workspace\n",
|
||||
"\n",
|
||||
"Initialize a [Workspace](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#workspace) object from the existing workspace you created in the Prerequisites step. `Workspace.from_config()` creates a workspace object from the details stored in `config.json`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.workspace import Workspace\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"print('Workspace name: ' + ws.name, \n",
|
||||
" 'Azure region: ' + ws.location, \n",
|
||||
" 'Subscription id: ' + ws.subscription_id, \n",
|
||||
" 'Resource group: ' + ws.resource_group, sep = '\\n')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create or attach existing AmlCompute\n",
|
||||
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) for training your model. In this tutorial, we use Azure ML managed compute ([AmlCompute](https://docs.microsoft.com/azure/machine-learning/service/how-to-set-up-training-targets#amlcompute)) for our remote training compute resource. Specifically, the below code creates an `STANDARD_NC6` GPU cluster that autoscales from `0` to `4` nodes.\n",
|
||||
"\n",
|
||||
"**Creation of AmlCompute takes approximately 5 minutes.** If the AmlCompute with that name is already in your workspace, this code will skip the creation process.\n",
|
||||
"\n",
|
||||
"As with other Azure services, there are limits on certain resources (e.g. AmlCompute) associated with the Azure Machine Learning service. Please read [this article](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-manage-quotas) on the default limits and how to request more quota."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.compute import ComputeTarget, AmlCompute\n",
|
||||
"from azureml.core.compute_target import ComputeTargetException\n",
|
||||
"\n",
|
||||
"# choose a name for your cluster\n",
|
||||
"cluster_name = \"gpu-cluster\"\n",
|
||||
"\n",
|
||||
"try:\n",
|
||||
" compute_target = ComputeTarget(workspace=ws, name=cluster_name)\n",
|
||||
" print('Found existing compute target.')\n",
|
||||
"except ComputeTargetException:\n",
|
||||
" print('Creating a new compute target...')\n",
|
||||
" compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_NC6',\n",
|
||||
" max_nodes=4)\n",
|
||||
"\n",
|
||||
" # create the cluster\n",
|
||||
" compute_target = ComputeTarget.create(ws, cluster_name, compute_config)\n",
|
||||
"\n",
|
||||
" compute_target.wait_for_completion(show_output=True)\n",
|
||||
"\n",
|
||||
"# use get_status() to get a detailed status for the current AmlCompute. \n",
|
||||
"print(compute_target.get_status().serialize())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The above code creates GPU compute. If you instead want to create CPU compute, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Train model on the remote compute\n",
|
||||
"Now that we have the AmlCompute ready to go, let's run our distributed training job."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a project directory\n",
|
||||
"Create a directory that will contain all the necessary code from your local machine that you will need access to on the remote resource. This includes the training script and any additional files your training script depends on."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"project_folder = './chainer-distr'\n",
|
||||
"os.makedirs(project_folder, exist_ok=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Prepare training script\n",
|
||||
"Now you will need to create your training script. In this tutorial, the script for distributed training of MNIST is already provided for you at `train_mnist.py`. In practice, you should be able to take any custom Chainer training script as is and run it with Azure ML without having to modify your code."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Once your script is ready, copy the training script `train_mnist.py` into the project directory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import shutil\n",
|
||||
"\n",
|
||||
"shutil.copy('train_mnist.py', project_folder)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create an experiment\n",
|
||||
"Create an [Experiment](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#experiment) to track all the runs in your workspace for this distributed Chainer tutorial. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Experiment\n",
|
||||
"\n",
|
||||
"experiment_name = 'chainer-distr'\n",
|
||||
"experiment = Experiment(ws, name=experiment_name)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create a Chainer estimator\n",
|
||||
"The Azure ML SDK's Chainer estimator enables you to easily submit Chainer training jobs for both single-node and distributed runs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.runconfig import MpiConfiguration\n",
|
||||
"from azureml.train.dnn import Chainer\n",
|
||||
"\n",
|
||||
"estimator = Chainer(source_directory=project_folder,\n",
|
||||
" compute_target=compute_target,\n",
|
||||
" entry_script='train_mnist.py',\n",
|
||||
" node_count=2,\n",
|
||||
" distributed_training=MpiConfiguration(),\n",
|
||||
" use_gpu=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to execute a distributed run using MPI, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, Chainer and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `Chainer` constructor's `pip_packages` or `conda_packages` parameters."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Submit job\n",
|
||||
"Run your experiment by submitting your estimator object. Note that this call is asynchronous."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"run = experiment.submit(estimator)\n",
|
||||
"print(run)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Monitor your run\n",
|
||||
"You can monitor the progress of the run with a Jupyter widget. Like the run submission, the widget is asynchronous and provides live updates every 10-15 seconds until the job completes. You can see that the widget automatically plots and visualizes the loss metric that we logged to the Azure ML run."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.widgets import RunDetails\n",
|
||||
"\n",
|
||||
"RunDetails(run).show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"run.wait_for_completion(show_output=True)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.6",
|
||||
"language": "python",
|
||||
"name": "python36"
|
||||
"metadata": {
|
||||
"authors": [
|
||||
{
|
||||
"name": "minxia"
|
||||
}
|
||||
],
|
||||
"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"
|
||||
},
|
||||
"msauthor": "minxia"
|
||||
},
|
||||
"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"
|
||||
},
|
||||
"msauthor": "minxia"
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -0,0 +1,5 @@
|
||||
name: distributed-chainer
|
||||
dependencies:
|
||||
- pip:
|
||||
- azureml-sdk
|
||||
- azureml-widgets
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user