jprdonnelly/MachineLearningNotebooks
1
0
Fork 0
mirror of https://github.com/Azure/MachineLearningNotebooks.git synced 2025-12-23 02:52:39 -05:00
Code Issues Projects Releases Wiki Activity

update notebooks for new version

Browse Source
This commit is contained in:
Roope Astala
2018-10-01 13:45:50 -04:00
parent 92be6bfd19
commit 231c1062a8
47 changed files with 19121 additions and 19240 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1620
01.getting-started/01.train-within-notebook/01.train-within-notebook.ipynb
View File

File diff suppressed because it is too large Load Diff

926
01.getting-started/02.train-on-local/02.train-on-local.ipynb
View File

@@ -1,465 +1,465 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 02. Train locally\n",
"* Create or load workspace.\n",
"* Create scripts locally.\n",
"* Create `train.py` in a folder, along with a `my.lib` file.\n",
"* Configure & execute a local run in a user-managed Python environment.\n",
"* Configure & execute a local run in a system-managed Python environment.\n",
"* Configure & execute a local run in a Docker environment.\n",
"* Query run metrics to find the best model\n",
"* Register model for operationalization."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.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": {},
"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": [
"## Create An Experiment\n",
"**Experiment** is a logical container in an Azure ML Workspace. It hosts run records which can include run metrics and output artifacts from your experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"experiment_name = 'train-on-local'\n",
"exp = Experiment(workspace=ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## View `train.py`\n",
"\n",
"`train.py` is already created for you."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('./train.py', 'r') as f:\n",
" print(f.read())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note `train.py` also references a `mylib.py` file."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('./mylib.py', 'r') as f:\n",
" print(f.read())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure & Run\n",
"### User-managed environment\n",
"Below, we use a user-managed run, which means you are responsible to ensure all the necessary packages are available in the Python environment you choose to run the script."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.runconfig import RunConfiguration\n",
"\n",
"# Editing a run configuration property on-fly.\n",
"run_config_user_managed = RunConfiguration()\n",
"\n",
"run_config_user_managed.environment.python.user_managed_dependencies = True\n",
"\n",
"# You can choose a specific Python environment by pointing to a Python path \n",
"#run_config.environment.python.interpreter_path = '/home/johndoe/miniconda3/envs/sdk2/bin/python'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Submit script to run in the user-managed environment\n",
"Note whole script folder is submitted for execution, including the `mylib.py` file."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import ScriptRunConfig\n",
"\n",
"src = ScriptRunConfig(source_directory='./', script='train.py', run_config=run_config_user_managed)\n",
"run = exp.submit(src)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Get run history details"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Block to wait till run finishes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### System-managed environment\n",
"You can also ask the system to build a new conda environment and execute your scripts in it. The environment is built once and will be reused in subsequent executions as long as the conda dependencies remain unchanged. "
]
},
{
"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",
"run_config_system_managed = RunConfiguration()\n",
"\n",
"run_config_system_managed.environment.python.user_managed_dependencies = False\n",
"run_config_system_managed.prepare_environment = True\n",
"\n",
"# Specify conda dependencies with scikit-learn\n",
"cd = CondaDependencies.create(conda_packages=['scikit-learn'])\n",
"run_config_system_managed.environment.python.conda_dependencies = cd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Submit script to run in the system-managed environment\n",
"A new conda environment is built based on the conda dependencies object. If you are running this for the first time, this might take up to 5 mninutes. But this conda environment is reused so long as you don't change the conda dependencies."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"src = ScriptRunConfig(source_directory=\"./\", script='train.py', run_config=run_config_system_managed)\n",
"run = exp.submit(src)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Get run history details"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Block and wait till run finishes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Docker-based execution\n",
"**IMPORTANT**: You must have Docker engine installed locally in order to use this execution mode. If your kernel is already running in a Docker container, such as **Azure Notebooks**, this mode will **NOT** work.\n",
"\n",
"You can also ask the system to pull down a Docker image and execute your scripts in it."
]
},
{
"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",
"run_config_docker = RunConfiguration()\n",
"\n",
"run_config_docker.environment.python.user_managed_dependencies = False\n",
"run_config_docker.prepare_environment = True\n",
"run_config_docker.environment.docker.enabled = True\n",
"run_config_docker.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
"\n",
"# Specify conda dependencies with scikit-learn\n",
"cd = CondaDependencies.create(conda_packages=['scikit-learn'])\n",
"run_config_docker.environment.python.conda_dependencies = cd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Submit script to run in the system-managed environment\n",
"A new conda environment is built based on the conda dependencies object. If you are running this for the first time, this might take up to 5 mninutes. But this conda environment is reused so long as you don't change the conda dependencies.\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"src = ScriptRunConfig(source_directory=\"./\", script='train.py', run_config=run_config_docker)\n",
"run = exp.submit(src)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Get run history details\n",
"run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Query run metrics"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"query history",
"get metrics"
]
},
"outputs": [],
"source": [
"# get all metris logged in the run\n",
"run.get_metrics()\n",
"metrics = run.get_metrics()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's find the model that has the lowest MSE value logged."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"best_alpha = metrics['alpha'][np.argmin(metrics['mse'])]\n",
"\n",
"print('When alpha is {1:0.2f}, we have min MSE {0:0.2f}.'.format(\n",
" min(metrics['mse']), \n",
" best_alpha\n",
"))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can also list all the files that are associated with this run record"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.get_file_names()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We know the model `ridge_0.40.pkl` is the best performing model from the eariler queries. So let's register it with the workspace."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# supply a model name, and the full path to the serialized model file.\n",
"model = run.register_model(model_name='best_ridge_model', model_path='./outputs/ridge_0.40.pkl')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(model.name, model.version, model.url)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now you can deploy this model following the example in the 01 notebook."
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# 02. Train locally\n",
"* Create or load workspace.\n",
"* Create scripts locally.\n",
"* Create `train.py` in a folder, along with a `my.lib` file.\n",
"* Configure & execute a local run in a user-managed Python environment.\n",
"* Configure & execute a local run in a system-managed Python environment.\n",
"* Configure & execute a local run in a Docker environment.\n",
"* Query run metrics to find the best model\n",
"* Register model for operationalization."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.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": {},
"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": [
"## Create An Experiment\n",
"**Experiment** is a logical container in an Azure ML Workspace. It hosts run records which can include run metrics and output artifacts from your experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"experiment_name = 'train-on-local'\n",
"exp = Experiment(workspace=ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## View `train.py`\n",
"\n",
"`train.py` is already created for you."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('./train.py', 'r') as f:\n",
" print(f.read())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Note `train.py` also references a `mylib.py` file."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('./mylib.py', 'r') as f:\n",
" print(f.read())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure & Run\n",
"### User-managed environment\n",
"Below, we use a user-managed run, which means you are responsible to ensure all the necessary packages are available in the Python environment you choose to run the script."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.runconfig import RunConfiguration\n",
"\n",
"# Editing a run configuration property on-fly.\n",
"run_config_user_managed = RunConfiguration()\n",
"\n",
"run_config_user_managed.environment.python.user_managed_dependencies = True\n",
"\n",
"# You can choose a specific Python environment by pointing to a Python path \n",
"#run_config.environment.python.interpreter_path = '/home/johndoe/miniconda3/envs/sdk2/bin/python'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Submit script to run in the user-managed environment\n",
"Note whole script folder is submitted for execution, including the `mylib.py` file."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import ScriptRunConfig\n",
"\n",
"src = ScriptRunConfig(source_directory='./', script='train.py', run_config=run_config_user_managed)\n",
"run = exp.submit(src)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Get run history details"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Block to wait till run finishes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### System-managed environment\n",
"You can also ask the system to build a new conda environment and execute your scripts in it. The environment is built once and will be reused in subsequent executions as long as the conda dependencies remain unchanged. "
]
},
{
"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",
"run_config_system_managed = RunConfiguration()\n",
"\n",
"run_config_system_managed.environment.python.user_managed_dependencies = False\n",
"run_config_system_managed.prepare_environment = True\n",
"\n",
"# Specify conda dependencies with scikit-learn\n",
"cd = CondaDependencies.create(conda_packages=['scikit-learn'])\n",
"run_config_system_managed.environment.python.conda_dependencies = cd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Submit script to run in the system-managed environment\n",
"A new conda environment is built based on the conda dependencies object. If you are running this for the first time, this might take up to 5 mninutes. But this conda environment is reused so long as you don't change the conda dependencies."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"src = ScriptRunConfig(source_directory=\"./\", script='train.py', run_config=run_config_system_managed)\n",
"run = exp.submit(src)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Get run history details"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Block and wait till run finishes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Docker-based execution\n",
"**IMPORTANT**: You must have Docker engine installed locally in order to use this execution mode. If your kernel is already running in a Docker container, such as **Azure Notebooks**, this mode will **NOT** work.\n",
"\n",
"You can also ask the system to pull down a Docker image and execute your scripts in it."
]
},
{
"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",
"run_config_docker = RunConfiguration()\n",
"\n",
"run_config_docker.environment.python.user_managed_dependencies = False\n",
"run_config_docker.prepare_environment = True\n",
"run_config_docker.environment.docker.enabled = True\n",
"run_config_docker.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
"\n",
"# Specify conda dependencies with scikit-learn\n",
"cd = CondaDependencies.create(conda_packages=['scikit-learn'])\n",
"run_config_docker.environment.python.conda_dependencies = cd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Submit script to run in the system-managed environment\n",
"A new conda environment is built based on the conda dependencies object. If you are running this for the first time, this might take up to 5 mninutes. But this conda environment is reused so long as you don't change the conda dependencies.\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"src = ScriptRunConfig(source_directory=\"./\", script='train.py', run_config=run_config_docker)\n",
"run = exp.submit(src)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Get run history details\n",
"run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Query run metrics"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"query history",
"get metrics"
]
},
"outputs": [],
"source": [
"# get all metris logged in the run\n",
"run.get_metrics()\n",
"metrics = run.get_metrics()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's find the model that has the lowest MSE value logged."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"best_alpha = metrics['alpha'][np.argmin(metrics['mse'])]\n",
"\n",
"print('When alpha is {1:0.2f}, we have min MSE {0:0.2f}.'.format(\n",
" min(metrics['mse']), \n",
" best_alpha\n",
"))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can also list all the files that are associated with this run record"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.get_file_names()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We know the model `ridge_0.40.pkl` is the best performing model from the eariler queries. So let's register it with the workspace."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# supply a model name, and the full path to the serialized model file.\n",
"model = run.register_model(model_name='best_ridge_model', model_path='./outputs/ridge_0.40.pkl')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(model.name, model.version, model.url)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now you can deploy this model following the example in the 01 notebook."
]
}
],
"metadata": {
"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
}

564
01.getting-started/03.train-on-aci/03.train-on-aci.ipynb
View File

@@ -1,284 +1,284 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 03. Train on Azure Container Instance\n",
"\n",
"* Create Workspace\n",
"* Create `train.py` in the project folder.\n",
"* Configure an ACI (Azure Container Instance) run\n",
"* Execute in ACI"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.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": [
"## Create An Experiment\n",
"\n",
"**Experiment** is a logical container in an Azure ML Workspace. It hosts run records which can include run metrics and output artifacts from your experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"experiment_name = 'train-on-aci'\n",
"experiment = Experiment(workspace = ws, name = experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Remote execution on ACI\n",
"\n",
"The training script `train.py` is already created for you. Let's have a look."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('./train.py', 'r') as f:\n",
" print(f.read())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure for using ACI\n",
"Linux-based ACI is available in `West US`, `East US`, `West Europe`, `North Europe`, `West US 2`, `Southeast Asia`, `Australia East`, `East US 2`, and `Central US` regions. See details [here](https://docs.microsoft.com/en-us/azure/container-instances/container-instances-quotas#region-availability)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"configure run"
]
},
"outputs": [],
"source": [
"from azureml.core.runconfig import RunConfiguration\n",
"from azureml.core.conda_dependencies import CondaDependencies\n",
"\n",
"# create a new runconfig object\n",
"run_config = RunConfiguration()\n",
"\n",
"# signal that you want to use ACI to execute script.\n",
"run_config.target = \"containerinstance\"\n",
"\n",
"# ACI container group is only supported in certain regions, which can be different than the region the Workspace is in.\n",
"run_config.container_instance.region = 'eastus2'\n",
"\n",
"# set the ACI CPU and Memory \n",
"run_config.container_instance.cpu_cores = 1\n",
"run_config.container_instance.memory_gb = 2\n",
"\n",
"# enable Docker \n",
"run_config.environment.docker.enabled = True\n",
"\n",
"# set Docker base image to the default CPU-based image\n",
"run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
"\n",
"# use conda_dependencies.yml to create a conda environment in the Docker image for execution\n",
"run_config.environment.python.user_managed_dependencies = False\n",
"\n",
"# auto-prepare the Docker image when used for execution (if it is not already prepared)\n",
"run_config.auto_prepare_environment = True\n",
"\n",
"# specify CondaDependencies obj\n",
"run_config.environment.python.conda_dependencies = CondaDependencies.create(conda_packages=['scikit-learn'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Submit the Experiment\n",
"Finally, run the training job on the ACI"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"remote run",
"aci"
]
},
"outputs": [],
"source": [
"%%time \n",
"from azureml.core.script_run_config import ScriptRunConfig\n",
"\n",
"script_run_config = ScriptRunConfig(source_directory='./',\n",
" script='train.py',\n",
" run_config=run_config)\n",
"\n",
"run = experiment.submit(script_run_config)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"query history"
]
},
"outputs": [],
"source": [
"# Show run details\n",
"run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"remote run",
"aci"
]
},
"outputs": [],
"source": [
"%%time\n",
"# Shows output of the run on stdout.\n",
"run.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"get metrics"
]
},
"outputs": [],
"source": [
"# get all metris logged in the run\n",
"run.get_metrics()\n",
"metrics = run.get_metrics()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"print('When alpha is {1:0.2f}, we have min MSE {0:0.2f}.'.format(\n",
" min(metrics['mse']), \n",
" metrics['alpha'][np.argmin(metrics['mse'])]\n",
"))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# show all the files stored within the run record\n",
"run.get_file_names()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now you can take a model produced here, register it and then deploy as a web service."
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# 03. Train on Azure Container Instance\n",
"\n",
"* Create Workspace\n",
"* Create `train.py` in the project folder.\n",
"* Configure an ACI (Azure Container Instance) run\n",
"* Execute in ACI"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.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": [
"## Create An Experiment\n",
"\n",
"**Experiment** is a logical container in an Azure ML Workspace. It hosts run records which can include run metrics and output artifacts from your experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"experiment_name = 'train-on-aci'\n",
"experiment = Experiment(workspace = ws, name = experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Remote execution on ACI\n",
"\n",
"The training script `train.py` is already created for you. Let's have a look."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('./train.py', 'r') as f:\n",
" print(f.read())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure for using ACI\n",
"Linux-based ACI is available in `West US`, `East US`, `West Europe`, `North Europe`, `West US 2`, `Southeast Asia`, `Australia East`, `East US 2`, and `Central US` regions. See details [here](https://docs.microsoft.com/en-us/azure/container-instances/container-instances-quotas#region-availability)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"configure run"
]
},
"outputs": [],
"source": [
"from azureml.core.runconfig import RunConfiguration\n",
"from azureml.core.conda_dependencies import CondaDependencies\n",
"\n",
"# create a new runconfig object\n",
"run_config = RunConfiguration()\n",
"\n",
"# signal that you want to use ACI to execute script.\n",
"run_config.target = \"containerinstance\"\n",
"\n",
"# ACI container group is only supported in certain regions, which can be different than the region the Workspace is in.\n",
"run_config.container_instance.region = 'eastus2'\n",
"\n",
"# set the ACI CPU and Memory \n",
"run_config.container_instance.cpu_cores = 1\n",
"run_config.container_instance.memory_gb = 2\n",
"\n",
"# enable Docker \n",
"run_config.environment.docker.enabled = True\n",
"\n",
"# set Docker base image to the default CPU-based image\n",
"run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_CPU_IMAGE\n",
"\n",
"# use conda_dependencies.yml to create a conda environment in the Docker image for execution\n",
"run_config.environment.python.user_managed_dependencies = False\n",
"\n",
"# auto-prepare the Docker image when used for execution (if it is not already prepared)\n",
"run_config.auto_prepare_environment = True\n",
"\n",
"# specify CondaDependencies obj\n",
"run_config.environment.python.conda_dependencies = CondaDependencies.create(conda_packages=['scikit-learn'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Submit the Experiment\n",
"Finally, run the training job on the ACI"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"remote run",
"aci"
]
},
"outputs": [],
"source": [
"%%time \n",
"from azureml.core.script_run_config import ScriptRunConfig\n",
"\n",
"script_run_config = ScriptRunConfig(source_directory='./',\n",
" script='train.py',\n",
" run_config=run_config)\n",
"\n",
"run = experiment.submit(script_run_config)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"query history"
]
},
"outputs": [],
"source": [
"# Show run details\n",
"run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"remote run",
"aci"
]
},
"outputs": [],
"source": [
"%%time\n",
"# Shows output of the run on stdout.\n",
"run.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"get metrics"
]
},
"outputs": [],
"source": [
"# get all metris logged in the run\n",
"run.get_metrics()\n",
"metrics = run.get_metrics()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"print('When alpha is {1:0.2f}, we have min MSE {0:0.2f}.'.format(\n",
" min(metrics['mse']), \n",
" metrics['alpha'][np.argmin(metrics['mse'])]\n",
"))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# show all the files stored within the run record\n",
"run.get_file_names()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now you can take a model produced here, register it and then deploy as a web service."
]
}
],
"metadata": {
"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
}

1224
01.getting-started/04.train-on-remote-vm/04.train-on-remote-vm.ipynb
View File

File diff suppressed because it is too large Load Diff

643
01.getting-started/05.train-in-spark/05.train-in-spark.ipynb
View File

@@ -1,321 +1,326 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 05. Train in Spark\n",
"* Create Workspace\n",
"* Create Experiment\n",
"* Copy relevant files to the script folder\n",
"* Configure and Run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.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": {},
"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": [
"## Create Experiment\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'train-on-spark'\n",
"\n",
"from azureml.core import Experiment\n",
"exp = Experiment(workspace=ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## View `train-spark.py`\n",
"\n",
"For convenience, we created a training script for you. It is printed below as a text, but you can also run `%pfile ./train-spark.py` in a cell to show the file."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('train-spark.py', 'r') as training_script:\n",
" print(training_script.read())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure & Run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Configure an ACI run\n",
"Before you try running on an actual Spark cluster, you can use a Docker image with Spark already baked in, and run it in ACI(Azure Container Registry)."
]
},
{
"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",
"# use pyspark framework\n",
"aci_run_config = RunConfiguration(framework=\"pyspark\")\n",
"\n",
"# use ACI to run the Spark job\n",
"aci_run_config.target = 'containerinstance'\n",
"aci_run_config.container_instance.region = 'eastus2'\n",
"aci_run_config.container_instance.cpu_cores = 1\n",
"aci_run_config.container_instance.memory_gb = 2\n",
"\n",
"# specify base Docker image to use\n",
"aci_run_config.environment.docker.enabled = True\n",
"aci_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_MMLSPARK_CPU_IMAGE\n",
"\n",
"# specify CondaDependencies\n",
"cd = CondaDependencies()\n",
"cd.add_conda_package('numpy')\n",
"aci_run_config.environment.python.conda_dependencies = cd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit script to ACI to run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import ScriptRunConfig\n",
"\n",
"script_run_config = ScriptRunConfig(source_directory = '.',\n",
" script= 'train-spark.py',\n",
" run_config = aci_run_config)\n",
"run = exp.submit(script_run_config)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Note** you can also create a new VM, or attach an existing VM, and use Docker-based execution to run the Spark job. Please see the `04.train-in-vm` for example on how to configure and run in Docker mode in a VM."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Attach an HDI cluster\n",
"Now we can use a real Spark cluster, HDInsight for Spark, to run this job. To use HDI commpute target:\n",
" 1. Create a Spark for HDI cluster in Azure. Here are some [quick instructions](https://docs.microsoft.com/en-us/azure/hdinsight/spark/apache-spark-jupyter-spark-sql). Make sure you use the Ubuntu flavor, NOT CentOS.\n",
" 2. Enter the IP address, username and password below"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import HDInsightCompute\n",
"from azureml.exceptions import ComputeTargetException\n",
"\n",
"try:\n",
" # if you want to connect using SSH key instead of username/password you can provide parameters private_key_file and private_key_passphrase\n",
" hdi_compute = HDInsightCompute.attach(workspace=ws, \n",
" name=\"myhdi\", \n",
" address=\"<myhdi-ssh>.azurehdinsight.net\", \n",
" ssh_port=22, \n",
" username='<ssh-username>', \n",
" password='<ssh-pwd>')\n",
"\n",
"except ComputeTargetException as e:\n",
" print(\"Caught = {}\".format(e.message))\n",
" \n",
" \n",
"hdi_compute.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Configure HDI run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.runconfig import RunConfiguration\n",
"from azureml.core.conda_dependencies import CondaDependencies\n",
"\n",
"\n",
"# use pyspark framework\n",
"hdi_run_config = RunConfiguration(framework=\"pyspark\")\n",
"\n",
"# Set compute target to the HDI cluster\n",
"hdi_run_config.target = hdi_compute.name\n",
"\n",
"# specify CondaDependencies object to ask system installing numpy\n",
"cd = CondaDependencies()\n",
"cd.add_conda_package('numpy')\n",
"hdi_run_config.environment.python.conda_dependencies = cd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit the script to HDI"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import ScriptRunConfig\n",
"\n",
"script_run_config = ScriptRunConfig(source_directory = '.',\n",
" script= 'train-spark.py',\n",
" run_config = hdi_run_config)\n",
"run = exp.submit(config=script_run_config)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# get the URL of the run history web page\n",
"run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# get all metris logged in the run\n",
"metrics = run.get_metrics()\n",
"print(metrics)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# 05. Train in Spark\n",
"* Create Workspace\n",
"* Create Experiment\n",
"* Copy relevant files to the script folder\n",
"* Configure and Run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.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": {},
"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": [
"## Create Experiment\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'train-on-spark'\n",
"\n",
"from azureml.core import Experiment\n",
"exp = Experiment(workspace=ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## View `train-spark.py`\n",
"\n",
"For convenience, we created a training script for you. It is printed below as a text, but you can also run `%pfile ./train-spark.py` in a cell to show the file."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('train-spark.py', 'r') as training_script:\n",
" print(training_script.read())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure & Run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Configure an ACI run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.runconfig import RunConfiguration\n",
"from azureml.core.conda_dependencies import CondaDependencies\n",
"\n",
"# use pyspark framework\n",
"aci_run_config = RunConfiguration(framework=\"pyspark\")\n",
"\n",
"# use ACI to run the Spark job\n",
"aci_run_config.target = 'containerinstance'\n",
"aci_run_config.container_instance.region = 'eastus2'\n",
"aci_run_config.container_instance.cpu_cores = 1\n",
"aci_run_config.container_instance.memory_gb = 2\n",
"\n",
"# specify base Docker image to use\n",
"aci_run_config.environment.docker.enabled = True\n",
"aci_run_config.environment.docker.base_image = azureml.core.runconfig.DEFAULT_MMLSPARK_CPU_IMAGE\n",
"\n",
"# specify CondaDependencies\n",
"cd = CondaDependencies()\n",
"cd.add_conda_package('numpy')\n",
"aci_run_config.environment.python.conda_dependencies = cd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit script to ACI to run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import ScriptRunConfig\n",
"\n",
"script_run_config = ScriptRunConfig(source_directory = '.',\n",
" script= 'train-spark.py',\n",
" run_config = aci_run_config)\n",
"run = exp.submit(script_run_config)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Attach an HDI cluster\n",
"Now we can use a real Spark cluster, HDInsight for Spark, to run this job. To use HDI commpute target:\n",
" 1. Create an Spark for HDI cluster in Azure. Here is some [quick instructions](https://docs.microsoft.com/en-us/azure/machine-learning/desktop-workbench/how-to-create-dsvm-hdi). Make sure you use the Ubuntu flavor, NOT CentOS.\n",
" 2. Enter the IP address, username and password below"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import HDInsightCompute\n",
"from azureml.exceptions import ComputeTargetException\n",
"\n",
"try:\n",
" # if you want to connect using SSH key instead of username/password you can provide parameters private_key_file and private_key_passphrase\n",
" hdi_compute = HDInsightCompute.attach(workspace=ws, \n",
" name=\"myhdi\", \n",
" address=\"myhdi-ssh.azurehdinsight.net\", \n",
" ssh_port=22, \n",
" username='<ssh-username>', \n",
" password='<ssh-pwd>')\n",
"\n",
"except ComputeTargetException as e:\n",
" print(\"Caught = {}\".format(e.message))\n",
" \n",
" \n",
"hdi_compute.wait_for_completion(show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Configure HDI run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.runconfig import RunConfiguration\n",
"from azureml.core.conda_dependencies import CondaDependencies\n",
"\n",
"\n",
"# Load the \"cpu-dsvm.runconfig\" file (created by the above attach operation) in memory\n",
"hdi_run_config = RunConfiguration(framework=\"pyspark\")\n",
"\n",
"# Set compute target to the Linux DSVM\n",
"hdi_run_config.target = hdi_compute.name\n",
"\n",
"# Ask system to provision a new one based on the conda_dependencies.yml file\n",
"hdi_run_config.environment.python.user_managed_dependencies = False\n",
"\n",
"# specify CondaDependencies obj\n",
"cd = CondaDependencies()\n",
"cd.add_conda_package('numpy')\n",
"hdi_run_config.environment.python.conda_dependencies = cd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submit the script to HDI"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import ScriptRunConfig\n",
"\n",
"script_run_config = ScriptRunConfig(source_directory = '.',\n",
" script= 'train-spark.py',\n",
" run_config = hdi_run_config)\n",
"run = exp.submit(script_run_config)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# get the URL of the run history web page\n",
"run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# get all metris logged in the run\n",
"metrics = run.get_metrics()\n",
"print(metrics)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"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
}

838
01.getting-started/10.register-model-create-image-deploy-service/10.register-model-create-image-deploy-service.ipynb
View File

@@ -1,421 +1,421 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 10. 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 \"01.SDK-101-Train-and-Deploy-to-ACI.ipynb\" Notebook\n",
" \n",
"The 101 Notebook 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",
"Make sure you go through the [00. Installation and Configuration](00.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",
" except Exception as e:\n",
" result = str(e)\n",
" return json.dumps({\"result\": result.tolist()})"
]
},
{
"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(\"pynacl==1.2.1\")\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 \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": [
"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()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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"
}
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"## 10. 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 \"01.SDK-101-Train-and-Deploy-to-ACI.ipynb\" Notebook\n",
" \n",
"The 101 Notebook 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",
"Make sure you go through the [00. Installation and Configuration](00.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",
" except Exception as e:\n",
" result = str(e)\n",
" return json.dumps({\"result\": result.tolist()})"
]
},
{
"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(\"pynacl==1.2.1\")\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 \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": [
"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()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

667
01.getting-started/11.production-deploy-to-aks/11.production-deploy-to-aks.ipynb
View File

@@ -1,335 +1,336 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "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."
]
},
{
"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",
" except Exception as e:\n",
" result = str(e)\n",
" return json.dumps({\"result\": result.tolist()})"
]
},
{
"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(\"pynacl==1.2.1\")\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": [
"# 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": "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",
"aks_target = AksCompute.attach(workspace=ws, name=create_name, resource_id=resource_id)\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 data."
]
},
{
"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": [
"# 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": {
"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"
}
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"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",
" except Exception as e:\n",
" result = str(e)\n",
" return json.dumps({\"result\": result.tolist()})"
]
},
{
"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": [
"# 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": "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",
"aks_target = AksCompute.attach(workspace=ws, name=create_name, resource_id=resource_id)\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 data."
]
},
{
"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": [
"# 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": {
"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"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

5
01.getting-started/12.enable-data-collection-for-models-in-aks/12.enable-data-collection-for-models-in-aks.ipynb
View File

@@ -102,7 +102,7 @@
"### b. In your init function add:\n", "### b. In your init function add:\n",
"```python \n", "```python \n",
"global inputs_dc, prediction_d\n", "global inputs_dc, prediction_d\n",
"inputs_dc = ModelDataCollector(\"best_model\", identifier=\"inputs\", feature_names=[\"feat1\", \"feat2\", \"feat3\". \"feat4\", \"feat5\", \"Feat6\"])\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", "prediction_dc = ModelDataCollector(\"best_model\", identifier=\"predictions\", feature_names=[\"prediction1\", \"prediction2\"])```\n",
" \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", "* Identifier: Identifier is later used for building the folder structure in your Blob, it can be used to divide \"raw\" data versus \"processed\".\n",
@@ -180,6 +180,7 @@
"\n", "\n",
"myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'])\n", "myenv = CondaDependencies.create(conda_packages=['numpy','scikit-learn'])\n",
"myenv.add_pip_package(\"azureml-monitoring\")\n", "myenv.add_pip_package(\"azureml-monitoring\")\n",
"myenv.add_pip_package(\"pynacl==1.2.1\")\n",
"\n", "\n",
"with open(\"myenv.yml\",\"w\") as f:\n", "with open(\"myenv.yml\",\"w\") as f:\n",
" f.write(myenv.serialize_to_string())" " f.write(myenv.serialize_to_string())"
@@ -286,7 +287,7 @@
" create_name= 'myaks4'\n", " create_name= 'myaks4'\n",
" aks_target = AksCompute.attach(workspace = ws, \n", " aks_target = AksCompute.attach(workspace = ws, \n",
" name = create_name, \n", " name = create_name, \n",
" #esource_id=resource_id)\n", " resource_id=resource_id)\n",
" ## Wait for the operation to complete\n", " ## Wait for the operation to complete\n",
" aks_target.wait_for_provisioning(True)```" " aks_target.wait_for_provisioning(True)```"
] ]

526
automl/00.configuration.ipynb
View File

@@ -1,265 +1,265 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 00. Configuration\n",
"\n",
"In this example you will create an Azure Machine Learning `Workspace` object and initialize your notebook directory to easily reload this object from a configuration file. Typically you will only need to run this once per notebook directory, and all other notebooks in this directory or any sub-directories will automatically use the settings you indicate here.\n",
"\n",
"\n",
"## Prerequisites:\n",
"\n",
"Before running this notebook, run the `automl_setup` script described in README.md.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Connect to Your Azure Subscription\n",
"\n",
"In order to use an Azure ML workspace, you need access to an Azure Subscription. You can [create a new Azure Subscription](https://azure.microsoft.com/en-us/free) or get existing subscription information from the [Azure portal](https://portal.azure.com).\n",
"\n",
"First login to Azure and follow prompts to authenticate. Then check that your subscription is correct."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!az login"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!az account show"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If you have multiple subscriptions and need to change the active one, you can use this command:\n",
"```shell\n",
"az account set -s <subscription-id>\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register Machine Learning Services Resource Provider\n",
"\n",
"This step is required to use the Azure ML services backing the SDK."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Register the new resource provider.\n",
"!az provider register -n Microsoft.MachineLearningServices\n",
"\n",
"# Check resource provider registration status.\n",
"!az provider show -n Microsoft.MachineLearningServices"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Check the Azure ML Core SDK Version to Validate Your Installation"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import azureml.core\n",
"\n",
"print(\"SDK Version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize an Azure ML Workspace\n",
"### What is an Azure ML Workspace and Why Do I Need One?\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, operationalization, and the monitoring of operationalized models.\n",
"\n",
"\n",
"### What do I Need?\n",
"\n",
"To create or access an Azure ML workspace, you will need to import the Azure ML library and specify following information:\n",
"* A name for your workspace. You can choose one.\n",
"* Your subscription id. Use the `id` value from the `az account show` command output above.\n",
"* The resource group name. The resource group organizes Azure resources and provides default region for the resources in the group. You can either specify a new one, in which case it gets created for your workspace, or use an existing one or create a new one from [Azure portal](https://portal.azure.com)\n",
"* Supported regions include `eastus2`, `eastus`,`westcentralus`, `southeastasia`, `westeurope`, `australiaeast`, `westus2`, `southcentralus`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"subscription_id = \"<subscription_id>\"\n",
"resource_group = \"myrg\"\n",
"workspace_name = \"myws\"\n",
"workspace_region = \"eastus2\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Creating a Workspace\n",
"If you already have access to an Azure ML workspace you want to use, you can skip this cell. Otherwise, this cell will create an Azure ML workspace for you in the specified subscription, provided you have the correct permissions for the given `subscription_id`.\n",
"\n",
"This will fail when:\n",
"1. The workspace already exists.\n",
"2. You do not have permission to create a workspace in the resource group.\n",
"3. 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 for any reason other than already existing, please work with your IT administrator to provide you with the appropriate permissions or to provision the required resources.\n",
"\n",
"**Note:** Creation of a new workspace can take several minutes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Import the Workspace class and check the Azure ML SDK version.\n",
"from azureml.core import Workspace\n",
"\n",
"ws = Workspace.create(name = workspace_name,\n",
" subscription_id = subscription_id,\n",
" resource_group = resource_group, \n",
" location = workspace_region)\n",
"ws.get_details()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configuring Your Local Environment\n",
"You can validate that you have access to the specified workspace and write a configuration file to the default configuration location, `./aml_config/config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Workspace\n",
"\n",
"ws = Workspace(workspace_name = workspace_name,\n",
" subscription_id = subscription_id,\n",
" resource_group = resource_group)\n",
"\n",
"# Persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
"ws.write_config()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can then load the workspace from this config file from any notebook in the current directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Load workspace configuration from ./aml_config/config.json file.\n",
"my_workspace = Workspace.from_config()\n",
"my_workspace.get_details()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a Folder to Host All Sample Projects\n",
"Finally, create a folder where all the sample projects will be hosted."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"sample_projects_folder = './sample_projects'\n",
"\n",
"if not os.path.isdir(sample_projects_folder):\n",
" os.mkdir(sample_projects_folder)\n",
" \n",
"print('Sample projects will be created in {}.'.format(sample_projects_folder))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Success!\n",
"Great, you are ready to move on to the rest of the sample notebooks."
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 00. configuration\n",
"\n",
"In this example you will create an Azure Machine Learning Workspace and initialize your notebook directory to easily use this workspace. Typically you will only need to run this once per notebook directory, and all other notebooks in this directory or any sub-directories will automatically use the settings you indicate here.\n",
"\n",
"\n",
"## Prerequisites:\n",
"\n",
"Before running this notebook, run the automl_setup script described in README.md.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Connect to your Azure Subscription\n",
"\n",
"In order to use an AML Workspace, first you need access to an Azure Subscription. You can [create your own](https://azure.microsoft.com/en-us/free/) or get your existing subscription information from the [Azure portal](https://portal.azure.com).\n",
"\n",
"First login to azure and follow prompts to authenticate. Then check that your subscription is correct"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!az login"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!az account show"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If you have multiple subscriptions and need to change the active one, you can use a command\n",
"```shell\n",
"az account set -s <subscription-id>\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register Machine Learning Services Resource Provider\n",
"\n",
"This step is required to use the Azure ML services backing the SDK."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# register the new RP\n",
"!az provider register -n Microsoft.MachineLearningServices\n",
"\n",
"# check the registration status\n",
"!az provider show -n Microsoft.MachineLearningServices"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Check core SDK version number for validate your installation and for debugging purposes"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import azureml.core\n",
"\n",
"print(\"SDK Version:\", azureml.core.VERSION)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialize an Azure ML Workspace\n",
"### What is an Azure ML Workspace and why do I need one?\n",
"\n",
"An AML Workspace is an Azure resource that organaizes and coordinates the actions of many other Azure resources to assist in executing and sharing machine learning workflows. In particular, an AML Workspace coordinates storage, databases, and compute resources providing added functionality for machine learning experimentation, operationalization, and the monitoring of operationalized models.\n",
"\n",
"\n",
"### What do I need\n",
"\n",
"To create or access an Azure ML Workspace, you will need to import the AML library and specify following information:\n",
"* A name for your workspace. You can choose one.\n",
"* Your subscription id. Use *id* value from *az account show* output above. \n",
"* The resource group name. Resource group organizes Azure resources and provides default region for the resources in the group. You can either specify a new one, in which case it gets created for your Workspace, or use an existing one or create a new one from [Azure portal](https://portal.azure.com)\n",
"* Supported regions include `eastus2`, `eastus`,`westcentralus`, `southeastasia`, `westeurope`, `australiaeast`, `westus2`, `southcentralus`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"subscription_id = \"<subscription_id>\"\n",
"resource_group = \"myrg\"\n",
"workspace_name = \"myws\"\n",
"workspace_region = \"eastus2\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Creating a workspace\n",
"If you already have access to an AML Workspace you want to use, you can skip this cell. Otherwise, this cell will create an AML workspace for you in a subscription provided you have the correct permissions for the given `subscription_id`.\n",
"\n",
"This will fail when:\n",
"1. The workspace already exists\n",
"2. You do not have permission to create a workspace in the resource group\n",
"3. 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 for any reason other than already existing, please work with your IT admin to provide you with the appropriate permissions or to provision the required resources.\n",
"\n",
"**Note** The workspace creation can take several minutes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# import the Workspace class and check the azureml SDK version\n",
"from azureml.core import Workspace\n",
"\n",
"ws = Workspace.create(name = workspace_name,\n",
" subscription_id = subscription_id,\n",
" resource_group = resource_group, \n",
" location = workspace_region)\n",
"ws.get_details()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configuring your local environment\n",
"You can validate that you have access to the specified workspace and write a configuration file to the default configuration location, `./aml_config/config.json`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Workspace\n",
"\n",
"ws = Workspace(workspace_name = workspace_name,\n",
" subscription_id = subscription_id,\n",
" resource_group = resource_group)\n",
"\n",
"# persist the subscription id, resource group name, and workspace name in aml_config/config.json.\n",
"ws.write_config()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can then load the workspace from this config file from any notebook in the current directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load workspace configuratio from ./aml_config/config.json file.\n",
"my_workspace = Workspace.from_config()\n",
"my_workspace.get_details()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a folder to host all sample projects\n",
"Lastly, create a folder where all the sample projects will be hosted."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"sample_projects_folder = './sample_projects'\n",
"\n",
"if not os.path.isdir(sample_projects_folder):\n",
" os.mkdir(sample_projects_folder)\n",
" \n",
"print('Sample projects will be created in {}.'.format(sample_projects_folder))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Success!\n",
"Great, you are ready to move on to the rest of the sample notebooks."
]
}
],
"metadata": {
"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
}

802
automl/01.auto-ml-classification.ipynb
View File

@@ -1,399 +1,407 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 01: Classification with Local Compute\n",
"\n",
"In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for a simple classification problem.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you will learn how to:\n",
"1. Create an `Experiment` in an existing `Workspace`.\n",
"2. Configure AutoML using `AutoMLConfig`.\n",
"3. Train the model using local compute.\n",
"4. Explore the results.\n",
"5. Test the best fitted model.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create an Experiment\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",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the experiment and specify the project folder.\n",
"experiment_name = 'automl-local-classification'\n",
"project_folder = './sample_projects/automl-local-classification'\n",
"\n",
"experiment = Experiment(ws, experiment_name)\n",
"\n",
"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",
"pd.DataFrame(data = output, index = ['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Training Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn import datasets\n",
"\n",
"digits = datasets.load_digits()\n",
"\n",
"# Exclude the first 100 rows from training so that they can be used for test.\n",
"X_train = digits.data[100:,:]\n",
"y_train = digits.target[100:]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure AutoML\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. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration.|\n",
"|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
"|**n_cross_validations**|Number of cross validation splits.|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 3600,\n",
" iterations = 50,\n",
" n_cross_validations = 3,\n",
" verbosity = logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" path = project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train the Model\n",
"\n",
"Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
"In this example, we specify `show_output = True` to print currently running iterations to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output = True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Optionally, you can continue an interrupted local run by calling `continue_experiment` without the `iterations` parameter, or run more iterations for a completed run by specifying the `iterations` parameter:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = local_run.continue_experiment(X = X_train, \n",
" y = y_train, \n",
" show_output = True,\n",
" iterations = 5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore the 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.train.widgets import RunDetails\n",
"RunDetails(local_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(local_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",
"\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 = local_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 `log_loss` value:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"lookup_metric = \"log_loss\"\n",
"best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a Specific Iteration\n",
"Show the run and the model from the third iteration:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 3\n",
"third_run, third_model = local_run.get_output(iteration = iteration)\n",
"print(third_run)\n",
"print(third_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Test the Best Fitted Model\n",
"\n",
"#### Load Test Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_test = digits.data[:10, :]\n",
"y_test = digits.target[:10]\n",
"images = digits.images[:10]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Testing Our Best Pipeline\n",
"We will try to predict 2 digits and see how our model works."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Randomly select digits and test.\n",
"for index in np.random.choice(len(y_test), 2, replace = False):\n",
" print(index)\n",
" predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
" label = y_test[index]\n",
" title = \"Label value = %d Predicted value = %d \" % (label, predicted)\n",
" fig = plt.figure(1, figsize = (3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
" plt.show()"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 01: Classification with local compute\n",
"\n",
"In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for a simple classification problem.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. Creating an Experiment in an existing Workspace\n",
"2. Instantiating AutoMLConfig\n",
"3. Training the Model using local compute\n",
"4. Exploring the results\n",
"5. Testing the fitted model\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Experiment\n",
"\n",
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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-local-classification'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-classification'\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",
"pd.DataFrame(data = output, index = ['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Digits Dataset"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn import datasets\n",
"\n",
"digits = datasets.load_digits()\n",
"\n",
"# Exclude the first 100 rows from training so that they can be used for test.\n",
"X_digits = digits.data[100:,:]\n",
"y_digits = digits.target[100:]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiate Auto ML Config\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.<br> Classification supports the following primary metrics <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration|\n",
"|**iterations**|Number of iterations. In each iteration Auto ML trains a specific pipeline with the data |\n",
"|**n_cross_validations**|Number of cross validation splits|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers. |\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. |"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 3600,\n",
" iterations = 50,\n",
" n_cross_validations = 3,\n",
" verbosity = logging.INFO,\n",
" X = X_digits, \n",
" y = y_digits,\n",
" path=project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Training the Model\n",
"\n",
"You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
"You will see the currently running iterations printing to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Optionally, you can continue an interrupted local run by calling continue_experiment without the <b>iterations</b> parameter, or run more iterations to a completed run by specifying the <b>iterations</b> parameter:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = local_run.continue_experiment(X = X_digits, \n",
" y = y_digits, \n",
" show_output = True,\n",
" iterations = 5)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploring the results"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Widget for monitoring runs\n",
"\n",
"The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
"\n",
"NOTE: The widget displays a link at the bottom. This links to a web-ui to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(local_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(local_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",
"\n",
"Below we select the best pipeline from our iterations. The *get_output* method on automl_classifier returns the best run and the fitted model for the last *fit* invocation. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"best_run, fitted_model = local_run.get_output()\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model based on any other metric\n",
"Give me the run and the model that has the smallest `log_loss`:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"lookup_metric = \"log_loss\"\n",
"best_run, fitted_model = local_run.get_output(metric = lookup_metric)\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a specific iteration\n",
"Give me the run and the model from the 3rd iteration:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 3\n",
"third_run, third_model = local_run.get_output(iteration = iteration)\n",
"print(third_run)\n",
"print(third_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Model \n",
"\n",
"#### Load Test Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_digits = digits.data[:10, :]\n",
"y_digits = digits.target[:10]\n",
"images = digits.images[:10]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Testing our best pipeline\n",
"We will try to predict 2 digits and see how our model works."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Randomly select digits and test\n",
"for index in np.random.choice(len(y_digits), 2):\n",
" print(index)\n",
" predicted = fitted_model.predict(X_digits[index:index + 1])[0]\n",
" label = y_digits[index]\n",
" title = \"Label value = %d Predicted value = %d \" % ( label,predicted)\n",
" fig = plt.figure(1, figsize=(3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap=plt.cm.gray_r, interpolation='nearest')\n",
" plt.show()"
]
}
],
"metadata": {
"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
}

814
automl/02.auto-ml-regression.ipynb
View File

@@ -1,409 +1,409 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 02: Regression with Local Compute\n",
"\n",
"In this example we use the scikit-learn's [diabetes dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_diabetes.html) to showcase how you can use AutoML for a simple regression problem.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you will learn how to:\n",
"1. Create an `Experiment` in an existing `Workspace`.\n",
"2. Configure AutoML using `AutoMLConfig`.\n",
"3. Train the model using local compute.\n",
"4. Explore the results.\n",
"5. Test the best fitted model.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create an Experiment\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",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the experiment and specify the project folder.\n",
"experiment_name = 'automl-local-regression'\n",
"project_folder = './sample_projects/automl-local-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",
"pd.DataFrame(data = output, index = ['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Load Training Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Load the diabetes dataset, a well-known built-in small dataset that comes with scikit-learn.\n",
"from sklearn.datasets import load_diabetes\n",
"from sklearn.linear_model import Ridge\n",
"from sklearn.metrics import mean_squared_error\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"X, y = load_diabetes(return_X_y = True)\n",
"\n",
"columns = ['age', 'gender', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']\n",
"\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": [
"## Configure AutoML\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",
"|**max_time_sec**|Time limit in seconds for each iteration.|\n",
"|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
"|**n_cross_validations**|Number of cross validation splits.|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task = 'regression',\n",
" max_time_sec = 600,\n",
" iterations = 10,\n",
" primary_metric = 'spearman_correlation',\n",
" n_cross_validations = 5,\n",
" debug_log = 'automl.log',\n",
" verbosity = logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" path = project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train the Model\n",
"\n",
"Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
"In this example, we specify `show_output = True` to print currently running iterations to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output = True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore the 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.train.widgets import RunDetails\n",
"RunDetails(local_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(local_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",
"\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 = local_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 = local_run.get_output(metric = lookup_metric)\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a Specific Iteration\n",
"Show the run and the model from the third iteration:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 3\n",
"third_run, third_model = local_run.get_output(iteration = iteration)\n",
"print(third_run)\n",
"print(third_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Test the Best Fitted Model"
]
},
{
"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": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"from sklearn import datasets\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', bins = 10, histtype = 'step');\n",
"a0.hist(y_residual_train, orientation = 'horizontal', color = 'b', 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', bins = 10, histtype = 'step')\n",
"a1.hist(y_residual_test, orientation = 'horizontal', color = 'b', alpha = 0.2, bins = 10)\n",
"\n",
"plt.show()"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 02: Regression with local compute\n",
"\n",
"In this example we use the scikit learn's [diabetes dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_diabetes.html) to showcase how you can use AutoML for a simple regression problem.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. Creating an Experiment using an existing Workspace\n",
"2. Instantiating AutoMLConfig\n",
"3. Training the Model using local compute\n",
"4. Exploring the results\n",
"5. Testing the fitted model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Experiment\n",
"\n",
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the experiment\n",
"experiment_name = 'automl-local-regression'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-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",
"pd.DataFrame(data = output, index = ['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Read Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load diabetes dataset, a well-known built-in small dataset that comes with scikit-learn\n",
"from sklearn.datasets import load_diabetes\n",
"from sklearn.linear_model import Ridge\n",
"from sklearn.metrics import mean_squared_error\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"X, y = load_diabetes(return_X_y = True)\n",
"\n",
"columns = ['age', 'gender', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']\n",
"\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": [
"## Instantiate Auto ML Config\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.<br> 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><br><i>normalized_root_mean_squared_log_error</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration|\n",
"|**iterations**|Number of iterations. In each iteration Auto ML trains a specific pipeline with the data|\n",
"|**n_cross_validations**|Number of cross validation splits|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers. |\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task='regression',\n",
" max_time_sec = 600,\n",
" iterations = 10,\n",
" primary_metric = 'spearman_correlation', \n",
" n_cross_validations = 5,\n",
" debug_log = 'automl.log',\n",
" verbosity = logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" path=project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Training the Model\n",
"\n",
"You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
"You will see the currently running iterations printing to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploring the results"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Widget for monitoring runs\n",
"\n",
"The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
"\n",
"NOTE: The widget displays a link at the bottom. This links to a web-ui to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(local_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(local_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",
"\n",
"Below we select the best pipeline from our iterations. The *get_output* method on automl_classifier returns the best run and the fitted model for the last *fit* invocation. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"best_run, fitted_model = local_run.get_output()\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model based on any other metric\n",
"Show the run and model that has the smallest `root_mean_squared_error` (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 = local_run.get_output(metric=lookup_metric)\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a specific iteration\n",
"\n",
"Simply show the run and model from the 3rd iteration:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 3\n",
"third_run, third_model = local_run.get_output(iteration = iteration)\n",
"print(third_run)\n",
"print(third_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Model"
]
},
{
"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": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"from sklearn import datasets\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",
"# plot histogram\n",
"a0.hist(y_residual_train, orientation = 'horizontal', color = 'b', bins = 10, histtype = 'step');\n",
"a0.hist(y_residual_train, orientation = 'horizontal', color = 'b', 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",
"# plot histogram\n",
"a1.hist(y_residual_test, orientation = 'horizontal', color = 'b', bins = 10, histtype = 'step');\n",
"a1.hist(y_residual_test, orientation = 'horizontal', color = 'b', alpha = 0.2, bins = 10);\n",
"\n",
"plt.show()"
]
}
],
"metadata": {
"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
}

947
automl/03.auto-ml-remote-execution.ipynb
View File

@@ -1,471 +1,480 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 03: Remote Execution using DSVM (Ubuntu)\n",
"\n",
"In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for a simple classification problem.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you wiil learn how to:\n",
"1. Create an `Experiment` in an existing `Workspace`.\n",
"2. Attach an existing DSVM to a workspace.\n",
"3. Configure AutoML using `AutoMLConfig`.\n",
"4. Train the model using the DSVM.\n",
"5. Explore the results.\n",
"6. Test the best fitted model.\n",
"\n",
"In addition, this notebook showcases the following features:\n",
"- **Parallel** executions for iterations\n",
"- **Asynchronous** tracking of progress\n",
"- **Cancellation** of individual iterations or the entire run\n",
"- Retrieving models for any iteration or logged metric\n",
"- Specifying AutoML settings as `**kwargs`\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create an Experiment\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",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the run history container in the workspace.\n",
"experiment_name = 'automl-remote-dsvm4'\n",
"project_folder = './sample_projects/automl-remote-dsvm4'\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",
"pd.DataFrame(data = output, index = ['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a Remote Linux DSVM\n",
"**Note:** If creation fails with a message about Marketplace purchase eligibilty, start creation of a DSVM through the [Azure portal](https://portal.azure.com), and select \"Want to create programmatically\" to enable programmatic creation. Once you've enabled this setting, you can exit the portal without actually creating the DSVM, and creation of the DSVM through the notebook should work.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import DsvmCompute\n",
"\n",
"dsvm_name = 'mydsvm'\n",
"try:\n",
" dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
" print('Found an existing DSVM.')\n",
"except:\n",
" print('Creating a new DSVM.')\n",
" dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
" dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
" dsvm_compute.wait_for_completion(show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Get Data File\n",
"For remote executions you should author a `get_data.py` file containing a `get_data()` function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
"In this example, the `get_data()` function returns data from scikit-learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if not os.path.exists(project_folder):\n",
" os.makedirs(project_folder)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%writefile $project_folder/get_data.py\n",
"\n",
"from sklearn import datasets\n",
"from scipy import sparse\n",
"import numpy as np\n",
"\n",
"def get_data():\n",
" \n",
" digits = datasets.load_digits()\n",
" X_train = digits.data[100:,:]\n",
" y_train = digits.target[100:]\n",
"\n",
" return { \"X\" : X_train, \"y\" : y_train }"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure AutoML <a class=\"anchor\" id=\"Instantiate-AutoML-Remote-DSVM\"></a>\n",
"\n",
"You can specify `automl_settings` as `**kwargs` as well. Also note that you can use a `get_data()` function for local excutions too.\n",
"\n",
"**Note:** When using Remote DSVM, you can't pass Numpy arrays directly to the fit method.\n",
"\n",
"|Property|Description|\n",
"|-|-|\n",
"|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds 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",
"|**concurrent_iterations**|Maximum number of iterations to execute in parallel. This should be less than the number of cores on the DSVM.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_settings = {\n",
" \"max_time_sec\": 600,\n",
" \"iterations\": 20,\n",
" \"n_cross_validations\": 5,\n",
" \"primary_metric\": 'AUC_weighted',\n",
" \"preprocess\": False,\n",
" \"concurrent_iterations\": 2,\n",
" \"verbosity\": logging.INFO\n",
"}\n",
"\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" path = project_folder, \n",
" compute_target = dsvm_compute,\n",
" data_script = project_folder + \"/get_data.py\",\n",
" **automl_settings\n",
" )\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Note:** The first run on a new DSVM may take several minutes to prepare the environment."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train the Model\n",
"\n",
"Call the `submit` method on the experiment object and pass the run configuration. For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets and models even when the experiment is running to retrieve the best model up to that point. Once you are satisfied with the model, you can cancel a particular iteration or the whole run.\n",
"\n",
"In this example, we specify `show_output = False` to suppress console output while the run is in progress."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"remote_run = experiment.submit(automl_config, show_output = False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore the Results\n",
"\n",
"#### Loading Executed Runs\n",
"In case you need to load a previously executed run, enable the cell below and replace the `run_id` value."
]
},
{
"cell_type": "raw",
"metadata": {},
"source": [
"remote_run = AutoMLRun(experiment=experiment, run_id = 'AutoML_480d3ed6-fc94-44aa-8f4e-0b945db9d3ef')"
]
},
{
"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",
"You can click on a pipeline to see run properties and output logs. Logs are also available on the DSVM under `/tmp/azureml_run/{iterationid}/azureml-logs`\n",
"\n",
"**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(remote_run).show() "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Wait until the run finishes.\n",
"remote_run.wait_for_completion(show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"#### Retrieve All Child Runs\n",
"You can also use SDK methods to fetch all the child runs and see individual metrics that we log."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"children = list(remote_run.get_children())\n",
"metricslist = {}\n",
"for run in children:\n",
" properties = run.get_properties()\n",
" metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)} \n",
" metricslist[int(properties['iteration'])] = metrics\n",
"\n",
"rundata = pd.DataFrame(metricslist).sort_index(1)\n",
"rundata"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Cancelling Runs\n",
"\n",
"You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Cancel the ongoing experiment and stop scheduling new iterations.\n",
"# remote_run.cancel()\n",
"\n",
"# Cancel iteration 1 and move onto iteration 2.\n",
"# remote_run.cancel_iteration(1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Retrieve the Best Model\n",
"\n",
"Below we select the best pipeline from our iterations. The `get_output` method 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()\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model Based on Any Other Metric\n",
"Show the run and the model which has the smallest `log_loss` value:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"lookup_metric = \"log_loss\"\n",
"best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a Specific Iteration\n",
"Show the run and the model from the third iteration:"
]
},
{
"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": [
"### Test the Best Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n",
"\n",
"#### Load Test Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_test = digits.data[:10, :]\n",
"y_test = digits.target[:10]\n",
"images = digits.images[:10]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Test Our Best Pipeline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Randomly select digits and test.\n",
"for index in np.random.choice(len(y_test), 2, replace = False):\n",
" print(index)\n",
" predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
" label = y_test[index]\n",
" title = \"Label value = %d Predicted value = %d \" % (label, predicted)\n",
" fig = plt.figure(1, figsize=(3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
" plt.show()"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 03: Remote Execution using DSVM (Ubuntu)\n",
"\n",
"In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for a simple classification problem.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. Creating an Experiment using an existing Workspace\n",
"2. Attaching an existing DSVM to a workspace\n",
"3. Instantiating AutoMLConfig \n",
"4. Training the Model using the DSVM\n",
"5. Exploring the results\n",
"6. Testing the fitted model\n",
"\n",
"In addition this notebook showcases the following features\n",
"- **Parallel** Executions for iterations\n",
"- Asyncronous tracking of progress\n",
"- **Cancelling** individual iterations or the entire run\n",
"- Retrieving models for any iteration or logged metric\n",
"- specify automl settings as **kwargs**\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Experiment\n",
"\n",
"As part of the setup you have already created a workspace. For AutoML you would need to create a <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the run history container in the workspace\n",
"experiment_name = 'automl-remote-dsvm4'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-remote-dsvm4'\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",
"pd.DataFrame(data = output, index = ['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a Remote Linux DSVM\n",
"Note: If creation fails with a message about Marketplace purchase eligibilty, go to portal.azure.com, start creating DSVM there, and select \"Want to create programmatically\" to enable programmatic creation. Once you've enabled it, you can exit without actually creating VM.\n",
"\n",
"**Note**: By default SSH runs on port 22 and you don't need to specify it. But if for security reasons you can switch to a different port (such as 5022), you can append the port number to the address. [Read more](https://render.githubusercontent.com/documentation/sdk/ssh-issue.md) on this."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import DsvmCompute\n",
"\n",
"dsvm_name = 'mydsvm'\n",
"try:\n",
" dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
" print('found existing dsvm.')\n",
"except:\n",
" print('creating new dsvm.')\n",
" dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
" dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
" dsvm_compute.wait_for_completion(show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Get Data File\n",
"For remote executions you should author a get_data.py file containing a get_data() function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if not os.path.exists(project_folder):\n",
" os.makedirs(project_folder)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%writefile $project_folder/get_data.py\n",
"\n",
"from sklearn import datasets\n",
"from scipy import sparse\n",
"import numpy as np\n",
"\n",
"def get_data():\n",
" \n",
" digits = datasets.load_digits()\n",
" X_digits = digits.data[100:,:]\n",
" y_digits = digits.target[100:]\n",
"\n",
" return { \"X\" : X_digits, \"y\" : y_digits }"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiate AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\n",
"\n",
"You can specify automl_settings as **kwargs** as well. Also note that you can use the get_data() symantic for local excutions too. \n",
"\n",
"<i>Note: For Remote DSVM and Batch AI you cannot pass Numpy arrays directly to the fit method.</i>\n",
"\n",
"|Property|Description|\n",
"|-|-|\n",
"|**primary_metric**|This is the metric that you want to optimize.<br> Classification supports the following primary metrics <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration|\n",
"|**iterations**|Number of iterations. In each iteration Auto ML trains a specific pipeline with the data|\n",
"|**n_cross_validations**|Number of cross validation splits|\n",
"|**concurrent_iterations**|Max number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_settings = {\n",
" \"max_time_sec\": 600,\n",
" \"iterations\": 20,\n",
" \"n_cross_validations\": 5,\n",
" \"primary_metric\": 'AUC_weighted',\n",
" \"preprocess\": False,\n",
" \"concurrent_iterations\": 2,\n",
" \"verbosity\": logging.INFO\n",
"}\n",
"\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" path=project_folder, \n",
" compute_target = dsvm_compute,\n",
" data_script = project_folder + \"/get_data.py\",\n",
" **automl_settings\n",
" )\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<b>Note</b> that the first run on a new DSVM may take a several minutes to preparing the environment."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"remote_run = experiment.submit(automl_config, show_output=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploring the Results\n",
"\n",
"#### Loading executed runs\n",
"In case you need to load a previously executed run given a run id please enable the below cell"
]
},
{
"cell_type": "raw",
"metadata": {},
"source": [
"remote_run = AutoMLRun(experiment=experiment, run_id='AutoML_480d3ed6-fc94-44aa-8f4e-0b945db9d3ef')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Widget for monitoring runs\n",
"\n",
"The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
"\n",
"You can click on a pipeline to see run properties and output logs. Logs are also available on the DSVM under /tmp/azureml_run/{iterationid}/azureml-logs\n",
"\n",
"NOTE: The widget displays a link at the bottom. This links to a web-ui to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(remote_run).show() "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# wait till the run finishes\n",
"remote_run.wait_for_completion(show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"#### Retrieve All Child Runs\n",
"You can also use sdk methods to fetch all the child runs and see individual metrics that we log. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"children = list(remote_run.get_children())\n",
"metricslist = {}\n",
"for run in children:\n",
" properties = run.get_properties()\n",
" metrics = {k: v for k, v in run.get_metrics().items() if isinstance(v, float)} \n",
" metricslist[int(properties['iteration'])] = metrics\n",
"\n",
"rundata = pd.DataFrame(metricslist).sort_index(1)\n",
"rundata"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Canceling runs\n",
"\n",
"You can cancel ongoing remote runs using the *cancel()* and *cancel_iteration()* functions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Cancel the ongoing experiment and stop scheduling new iterations\n",
"# remote_run.cancel()\n",
"\n",
"# Cancel iteration 1 and move onto iteration 2\n",
"# remote_run.cancel_iteration(1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Retrieve the Best Model\n",
"\n",
"Below we select the best pipeline from our iterations. The *get_output* method on automl_classifier returns the best run and the fitted model for the last *fit* invocation. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"best_run, fitted_model = 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/model which has the smallest `log_loss` value."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"lookup_metric = \"log_loss\"\n",
"best_run, fitted_model = remote_run.get_output(metric = lookup_metric)\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a specific iteration\n",
"Show the run and model from the 3rd iteration."
]
},
{
"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": [
"### Testing the Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n",
"\n",
"#### Load Test Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_digits = digits.data[:10, :]\n",
"y_digits = digits.target[:10]\n",
"images = digits.images[:10]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Testing our best pipeline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Randomly select digits and test\n",
"for index in np.random.choice(len(y_digits), 2):\n",
" print(index)\n",
" predicted = fitted_model.predict(X_digits[index:index + 1])[0]\n",
" label = y_digits[index]\n",
" title = \"Label value = %d Predicted value = %d \" % ( label,predicted)\n",
" fig = plt.figure(1, figsize=(3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap=plt.cm.gray_r, interpolation='nearest')\n",
" plt.show()"
]
}
],
"metadata": {
"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
}

1043
automl/03b.auto-ml-remote-batchai.ipynb
View File

File diff suppressed because it is too large Load Diff

979
automl/04.auto-ml-remote-execution-text-data-blob-store.ipynb
View File

@@ -1,495 +1,488 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Auto ML 04: Remote Execution with Text Data from Azure Blob Storage\n",
"\n",
"In this example we use the [Burning Man 2016 dataset](https://innovate.burningman.org/datasets-page/) to showcase how you can use AutoML to handle text data from Azure Blob Storage.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you will learn how to:\n",
"1. Create an `Experiment` in an existing `Workspace`.\n",
"2. Attach an existing DSVM to a workspace.\n",
"3. Configure AutoML using `AutoMLConfig`.\n",
"4. Train the model using the DSVM.\n",
"5. Explore the results.\n",
"6. Test the best fitted model.\n",
"\n",
"In addition this notebook showcases the following features\n",
"- **Parallel** executions for iterations\n",
"- **Asynchronous** tracking of progress\n",
"- **Cancellation** of individual iterations or the entire run\n",
"- Retrieving models for any iteration or logged metric\n",
"- Specifying AutoML settings as `**kwargs`\n",
"- Handling **text** data using the `preprocess` flag\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create an Experiment\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",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the run history container in the workspace.\n",
"experiment_name = 'automl-remote-dsvm-blobstore'\n",
"project_folder = './sample_projects/automl-remote-dsvm-blobstore'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Attach a Remote Linux DSVM\n",
"To use a remote Docker compute target:\n",
"1. Create a Linux DSVM in Azure, following these [quick instructions](https://docs.microsoft.com/en-us/azure/machine-learning/desktop-workbench/how-to-create-dsvm-hdi). Make sure you use the Ubuntu flavor (not CentOS). Make sure that disk space is available under `/tmp` because AutoML creates files under `/tmp/azureml_run`s. The DSVM should have more cores than the number of parallel runs that you plan to enable. It should also have at least 4GB per core.\n",
"2. Enter the IP address, user name and password below.\n",
"\n",
"**Note:** By default, SSH runs on port 22 and you don't need to change the port number below. If you've configured SSH to use a different port, change `dsvm_ssh_port` accordinglyaddress. [Read more](https://render.githubusercontent.com/documentation/sdk/ssh-issue.md) on changing SSH ports for security reasons."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import RemoteCompute\n",
"\n",
"# Add your VM information below\n",
"dsvm_name = 'mydsvm1'\n",
"dsvm_ip_addr = '<<ip_addr>>'\n",
"dsvm_ssh_port = 22\n",
"dsvm_username = '<<username>>'\n",
"dsvm_password = '<<password>>'\n",
"\n",
"dsvm_compute = RemoteCompute.attach(workspace=ws, name=dsvm_name, address=dsvm_ip_addr, username=dsvm_username, password=dsvm_password, ssh_port=dsvm_ssh_port)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Get Data File\n",
"For remote executions you should author a `get_data.py` file containing a `get_data()` function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
"In this example, the `get_data()` function returns a [dictionary](README.md#getdata)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if not os.path.exists(project_folder):\n",
" os.makedirs(project_folder)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%writefile $project_folder/get_data.py\n",
"\n",
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import LabelEncoder\n",
"\n",
"def get_data():\n",
" # Load Burning Man 2016 data.\n",
" df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
" delimiter=\"\\t\", quotechar='\"')\n",
" # Get integer labels.\n",
" le = LabelEncoder()\n",
" le.fit(df[\"Label\"].values)\n",
" y = le.transform(df[\"Label\"].values)\n",
" df = df.drop([\"Label\"], axis=1)\n",
"\n",
" df_train, _, y_train, _ = train_test_split(df, y, test_size = 0.1, random_state = 42)\n",
"\n",
" return { \"X\" : df, \"y\" : y }"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### View data\n",
"\n",
"You can execute the `get_data()` function locally to view the training data."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%run $project_folder/get_data.py\n",
"data_dict = get_data()\n",
"df = data_dict[\"X\"]\n",
"y = data_dict[\"y\"]\n",
"pd.set_option('display.max_colwidth', 15)\n",
"df['Label'] = pd.Series(y, index=df.index)\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\n",
"\n",
"You can specify `automl_settings` as `**kwargs` as well. Also note that you can use a `get_data()` function for local excutions too.\n",
"\n",
"**Note:** When using Remote DSVM, you can't pass Numpy arrays directly to the fit method.\n",
"\n",
"|Property|Description|\n",
"|-|-|\n",
"|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds 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",
"|**concurrent_iterations**|Maximum number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM.|\n",
"|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.|\n",
"|**max_cores_per_iteration**|Indicates how many cores on the compute target would be used to train a single pipeline.<br>Default is *1*; you can set it to *-1* to use all cores.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_settings = {\n",
" \"max_time_sec\": 3600,\n",
" \"iterations\": 10,\n",
" \"n_cross_validations\": 5,\n",
" \"primary_metric\": 'AUC_weighted',\n",
" \"preprocess\": True,\n",
" \"max_cores_per_iteration\": 2\n",
"}\n",
"\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" path = project_folder,\n",
" compute_target = dsvm_compute,\n",
" data_script = project_folder + \"/get_data.py\",\n",
" **automl_settings\n",
" )\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train the Model <a class=\"anchor\" id=\"Training-the-model-Remote-DSVM\"></a>\n",
"\n",
"Call the `submit` method on the experiment object and pass the run configuration. For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets and models even when the experiment is running to retrieve the best model up to that point. Once you are satisfied with the model, you can cancel a particular iteration or the whole run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"remote_run = experiment.submit(automl_config)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploring the results <a class=\"anchor\" id=\"Exploring-the-Results-Remote-DSVM\"></a>\n",
"#### Widget for Monitoring Runs\n",
"\n",
"The widget will first report a \"loading\" status while running the first iteration. After completing the first iteration, an auto-updating graph and table will be shown. The widget will refresh once per minute, so you should see the graph update as child runs complete.\n",
"\n",
"You can click on a pipeline to see run properties and output logs. Logs are also available on the DSVM under `/tmp/azureml_run/{iterationid}/azureml-logs`\n",
"\n",
"**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.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": [
"## Cancelling runs\n",
"You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Cancel the ongoing experiment and stop scheduling new iterations.\n",
"remote_run.cancel()\n",
"\n",
"# Cancel iteration 1 and move onto iteration 2.\n",
"# remote_run.cancel_iteration(1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Retrieve the Best Model\n",
"\n",
"Below we select the best pipeline from our iterations. The `get_output` method 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()\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model Based on Any Other Metric\n",
"Show the run and the model which has the smallest `accuracy` value:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# lookup_metric = \"accuracy\"\n",
"# best_run, fitted_model = remote_run.get_output(metric = lookup_metric)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a Specific Iteration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 0\n",
"zero_run, zero_model = remote_run.get_output(iteration = iteration)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register the Fitted Model for Deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"remote_run.register_model(description = description, tags = tags)\n",
"print(remote_run.model_id) # Use this id to deploy the model as a web service in Azure."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import sklearn\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import LabelEncoder\n",
"from pandas_ml import ConfusionMatrix\n",
"\n",
"df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
" delimiter=\"\\t\", quotechar='\"')\n",
"\n",
"# get integer labels\n",
"le = LabelEncoder()\n",
"le.fit(df[\"Label\"].values)\n",
"y = le.transform(df[\"Label\"].values)\n",
"df = df.drop([\"Label\"], axis=1)\n",
"\n",
"_, df_test, _, y_test = train_test_split(df, y, test_size=0.1, random_state=42)\n",
"\n",
"\n",
"ypred = fitted_model.predict(df_test.values)\n",
"\n",
"\n",
"ypred_strings = le.inverse_transform(ypred)\n",
"ytest_strings = le.inverse_transform(y_test)\n",
"\n",
"cm = ConfusionMatrix(ytest_strings, ypred_strings)\n",
"\n",
"print(cm)\n",
"\n",
"cm.plot()"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# Auto ML : Remote Execution with Text data from Blobstorage\n",
"\n",
"In this example we use the [Burning Man 2016 dataset](https://innovate.burningman.org/datasets-page/) to showcase how you can use AutoML to handle text data from a Azure blobstorage.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. Creating an Experiment using an existing Workspace\n",
"2. Attaching an existing DSVM to a workspace\n",
"3. Instantiating AutoMLConfig \n",
"4. Training the Model using the DSVM\n",
"5. Exploring the results\n",
"6. Testing the fitted model\n",
"\n",
"In addition this notebook showcases the following features\n",
"- **Parallel** Executions for iterations\n",
"- Asyncronous tracking of progress\n",
"- **Cancelling** individual iterations or the entire run\n",
"- Retrieving models for any iteration or logged metric\n",
"- specify automl settings as **kwargs**\n",
"- handling **text** data with **preprocess** flag\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Experiment\n",
"\n",
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the run history container in the workspace\n",
"experiment_name = 'automl-remote-dsvm-blobstore'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-remote-dsvm-blobstore'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Attach a Remote Linux DSVM\n",
"To use remote docker commpute target:\n",
"1. Create a Linux DSVM in Azure. Here is some [quick instructions](https://docs.microsoft.com/en-us/azure/machine-learning/desktop-workbench/how-to-create-dsvm-hdi). Make sure you use the Ubuntu flavor, NOT CentOS. Make sure that disk space is available under /tmp because AutoML creates files under /tmp/azureml_runs. The DSVM should have more cores than the number of parallel runs that you plan to enable. It should also have at least 4Gb per core.\n",
"2. Enter the IP address, username and password below\n",
"\n",
"**Note**: By default SSH runs on port 22 and you don't need to specify it. But if for security reasons you can switch to a different port (such as 5022), you can append the port number to the address. [Read more](https://render.githubusercontent.com/documentation/sdk/ssh-issue.md) on this."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import RemoteCompute\n",
"\n",
"# Add your VM information below\n",
"dsvm_name = 'mydsvm1'\n",
"dsvm_ip_addr = '<<ip_addr>>'\n",
"dsvm_username = '<<username>>'\n",
"dsvm_password = '<<password>>'\n",
"\n",
"dsvm_compute = RemoteCompute.attach(workspace=ws, name=dsvm_name, address=dsvm_ip_addr, username=dsvm_username, password=dsvm_password, ssh_port=22)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Get Data File\n",
"For remote executions you should author a get_data.py file containing a get_data() function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
"\n",
"The *get_data()* function returns a [dictionary](README.md#getdata)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if not os.path.exists(project_folder):\n",
" os.makedirs(project_folder)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%writefile $project_folder/get_data.py\n",
"\n",
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import LabelEncoder\n",
"\n",
"def get_data():\n",
" # Burning man 2016 data\n",
" df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
" delimiter=\"\\t\", quotechar='\"')\n",
" # get integer labels\n",
" le = LabelEncoder()\n",
" le.fit(df[\"Label\"].values)\n",
" y = le.transform(df[\"Label\"].values)\n",
" df = df.drop([\"Label\"], axis=1)\n",
"\n",
" df_train, _, y_train, _ = train_test_split(df, y, test_size=0.1, random_state=42)\n",
"\n",
" return { \"X\" : df, \"y\" : y }"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### View data\n",
"\n",
"You can execute the *get_data()* function locally to view the *train* data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%run $project_folder/get_data.py\n",
"data_dict = get_data()\n",
"df = data_dict[\"X\"]\n",
"y = data_dict[\"y\"]\n",
"pd.set_option('display.max_colwidth', 15)\n",
"df['Label'] = pd.Series(y, index=df.index)\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiate AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\n",
"\n",
"You can specify automl_settings as **kwargs** as well. Also note that you can use the get_data() symantic for local excutions too. \n",
"\n",
"<i>Note: For Remote DSVM and Batch AI you cannot pass Numpy arrays directly to the fit method.</i>\n",
"\n",
"|Property|Description|\n",
"|-|-|\n",
"|**primary_metric**|This is the metric that you want to optimize.<br> Classification supports the following primary metrics <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration|\n",
"|**iterations**|Number of iterations. In each iteration Auto ML trains a specific pipeline with the data|\n",
"|**n_cross_validations**|Number of cross validation splits|\n",
"|**concurrent_iterations**|Max number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM\n",
"|**preprocess**| *True/False* <br>Setting this to *True* enables AutoML to perform preprocessing <br>on the input to handle *missing data*, and perform some common *feature extraction*|\n",
"|**max_cores_per_iteration**| Indicates how many cores on the compute target would be used to train a single pipeline.<br> Default is *1*, you can set it to *-1* to use all cores|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_settings = {\n",
" \"max_time_sec\": 3600,\n",
" \"iterations\": 10,\n",
" \"n_cross_validations\": 5,\n",
" \"primary_metric\": 'AUC_weighted',\n",
" \"preprocess\": True,\n",
" \"max_cores_per_iteration\": 2\n",
"}\n",
"\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" path=project_folder,\n",
" compute_target = dsvm_compute,\n",
" data_script = project_folder + \"/get_data.py\",\n",
" **automl_settings\n",
" )\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Training the Model <a class=\"anchor\" id=\"Training-the-model-Remote-DSVM\"></a>\n",
"\n",
"For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets/models even when the experiment is running to retreive the best model up to that point. Once you are satisfied with the model you can cancel a particular iteration or the whole run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"remote_run = experiment.submit(automl_config)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploring the Results <a class=\"anchor\" id=\"Exploring-the-Results-Remote-DSVM\"></a>\n",
"#### Widget for monitoring runs\n",
"\n",
"The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
"\n",
"You can click on a pipeline to see run properties and output logs. Logs are also available on the DSVM under /tmp/azureml_run/{iterationid}/azureml-logs\n",
"\n",
"NOTE: The widget displays a link at the bottom. This links to a web-ui to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.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": [
"## Canceling runs\n",
"You can cancel ongoing remote runs using the *cancel()* and *cancel_iteration()* functions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Cancel the ongoing experiment and stop scheduling new iterations\n",
"remote_run.cancel()\n",
"\n",
"# Cancel iteration 1 and move onto iteration 2\n",
"# remote_run.cancel_iteration(1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 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 *fit* invocation. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"best_run, fitted_model = remote_run.get_output()\n",
"print(best_run)\n",
"print(fitted_model)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model based on any other metric"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# lookup_metric = \"accuracy\"\n",
"# best_run, fitted_model = remote_run.get_output(metric=lookup_metric)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a specific iteration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 0\n",
"zero_run, zero_model = remote_run.get_output(iteration=iteration)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register fitted model for deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"remote_run.register_model(description=description, tags=tags)\n",
"remote_run.model_id # Use this id to deploy the model as a web service in Azure"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import sklearn\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import LabelEncoder\n",
"from pandas_ml import ConfusionMatrix\n",
"\n",
"df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
" delimiter=\"\\t\", quotechar='\"')\n",
"\n",
"# get integer labels\n",
"le = LabelEncoder()\n",
"le.fit(df[\"Label\"].values)\n",
"y = le.transform(df[\"Label\"].values)\n",
"df = df.drop([\"Label\"], axis=1)\n",
"\n",
"_, df_test, _, y_test = train_test_split(df, y, test_size=0.1, random_state=42)\n",
"\n",
"\n",
"ypred = fitted_model.predict(df_test.values)\n",
"\n",
"\n",
"ypred_strings = le.inverse_transform(ypred)\n",
"ytest_strings = le.inverse_transform(y_test)\n",
"\n",
"cm = ConfusionMatrix(ytest_strings, ypred_strings)\n",
"\n",
"print(cm)\n",
"\n",
"cm.plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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
}

787
automl/05.auto-ml-missing-data-Blacklist-Early-Termination.ipynb
View File

@@ -1,396 +1,395 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 05: Blacklisting Models, Early Termination, and Handling Missing Data\n",
"\n",
"In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for handling missing values in data. We also provide a stopping metric indicating a target for the primary metrics so that AutoML can terminate the run without necessarly going through all the iterations. Finally, if you want to avoid a certain pipeline, we allow you to specify a blacklist of algorithms that AutoML will ignore for this run.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you will learn how to:\n",
"1. Create an `Experiment` in an existing `Workspace`.\n",
"2. Configure AutoML using `AutoMLConfig`.\n",
"4. Train the model.\n",
"5. Explore the results.\n",
"6. Test the best fitted model.\n",
"\n",
"In addition this notebook showcases the following features\n",
"- **Blacklisting** certain pipelines\n",
"- Specifying **target metrics** to indicate stopping criteria\n",
"- Handling **missing data** in the input\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create an Experiment\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",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the experiment.\n",
"experiment_name = 'automl-local-missing-data'\n",
"project_folder = './sample_projects/automl-local-missing-data'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Creating missing data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from scipy import sparse\n",
"\n",
"digits = datasets.load_digits()\n",
"X_train = digits.data[10:,:]\n",
"y_train = digits.target[10:]\n",
"\n",
"# Add missing values in 75% of the lines.\n",
"missing_rate = 0.75\n",
"n_missing_samples = int(np.floor(X_train.shape[0] * missing_rate))\n",
"missing_samples = np.hstack((np.zeros(X_train.shape[0] - n_missing_samples, dtype=np.bool), np.ones(n_missing_samples, dtype=np.bool)))\n",
"rng = np.random.RandomState(0)\n",
"rng.shuffle(missing_samples)\n",
"missing_features = rng.randint(0, X_train.shape[1], n_missing_samples)\n",
"X_train[np.where(missing_samples)[0], missing_features] = np.nan"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(data = X_train)\n",
"df['Label'] = pd.Series(y_train, index=df.index)\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure AutoML\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. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration.|\n",
"|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
"|**n_cross_validations**|Number of cross validation splits.|\n",
"|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.|\n",
"|**exit_score**|*double* value indicating the target for *primary_metric*. <br>Once the target is surpassed the run terminates.|\n",
"|**blacklist_algos**|*Array* of *strings* indicating pipelines to ignore for AutoML.<br><br> Allowed values for **Classification**<br><i>LogisticRegression</i><br><i>SGDClassifierWrapper</i><br><i>NBWrapper</i><br><i>BernoulliNB</i><br><i>SVCWrapper</i><br><i>LinearSVMWrapper</i><br><i>KNeighborsClassifier</i><br><i>DecisionTreeClassifier</i><br><i>RandomForestClassifier</i><br><i>ExtraTreesClassifier</i><br><i>LightGBMClassifier</i><br><br>Allowed values for **Regression**<br><i>ElasticNet<i><br><i>GradientBoostingRegressor<i><br><i>DecisionTreeRegressor<i><br><i>KNeighborsRegressor<i><br><i>LassoLars<i><br><i>SGDRegressor<i><br><i>RandomForestRegressor<i><br><i>ExtraTreesRegressor<i>|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 3600,\n",
" iterations = 20,\n",
" n_cross_validations = 5,\n",
" preprocess = True,\n",
" exit_score = 0.994,\n",
" blacklist_algos = ['KNeighborsClassifier','LinearSVMWrapper'],\n",
" verbosity = logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" path = project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train the Model\n",
"\n",
"Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
"In this example, we specify `show_output = True` to print currently running iterations to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore the 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.train.widgets import RunDetails\n",
"RunDetails(local_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(local_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",
"\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 = local_run.get_output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model Based on Any Other Metric\n",
"Show the run and the model which has the smallest `accuracy` value:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# lookup_metric = \"accuracy\"\n",
"# best_run, fitted_model = local_run.get_output(metric = lookup_metric)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a Specific Iteration\n",
"Show the run and the model from the third iteration:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# iteration = 3\n",
"# best_run, fitted_model = local_run.get_output(iteration = iteration)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register the Fitted Model for Deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"local_run.register_model(description = description, tags = tags)\n",
"local_run.model_id # Use this id to deploy the model as a web service in Azure."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Model"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_test = digits.data[:10, :]\n",
"y_test = digits.target[:10]\n",
"images = digits.images[:10]\n",
"\n",
"# Randomly select digits and test.\n",
"for index in np.random.choice(len(y_test), 2, replace = False):\n",
" print(index)\n",
" predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
" label = y_test[index]\n",
" title = \"Label value = %d Predicted value = %d \" % (label, predicted)\n",
" fig = plt.figure(1, figsize=(3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
" plt.show()\n"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 05 : Blacklisting models, Early termination and handling missing data\n",
"\n",
"In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for handling missing values in data. We also provide a stopping metric indicating a target for the primary metric so that AutoML can terminate the run without necessarly going through all the iterations. Finally, if you want to avoid a certain pipeline, we allow you to specify a black list of algos that AutoML will ignore for this run.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. Creating an Experiment using an existing Workspace\n",
"2. Instantiating AutoMLConfig\n",
"4. Training the Model\n",
"5. Exploring the results\n",
"6. Testing the fitted model\n",
"\n",
"In addition this notebook showcases the following features\n",
"- **Blacklist** certain pipelines\n",
"- Specify a **target metrics** to indicate stopping criteria\n",
"- Handling **Missing Data** in the input\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"## Create Experiment\n",
"\n",
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the experiment\n",
"experiment_name = 'automl-local-missing-data'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-missing-data'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Creating Missing Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from scipy import sparse\n",
"\n",
"digits = datasets.load_digits()\n",
"X_digits = digits.data[10:,:]\n",
"y_digits = digits.target[10:]\n",
"\n",
"# Add missing values in 75% of the lines\n",
"missing_rate = 0.75\n",
"n_missing_samples = int(np.floor(X_digits.shape[0] * missing_rate))\n",
"missing_samples = np.hstack((np.zeros(X_digits.shape[0] - n_missing_samples, dtype=np.bool), np.ones(n_missing_samples, dtype=np.bool)))\n",
"rng = np.random.RandomState(0)\n",
"rng.shuffle(missing_samples)\n",
"missing_features = rng.randint(0, X_digits.shape[1], n_missing_samples)\n",
"X_digits[np.where(missing_samples)[0], missing_features] = np.nan"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(data=X_digits)\n",
"df['Label'] = pd.Series(y_digits, index=df.index)\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiate Auto ML Config\n",
"\n",
"\n",
"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.<br> Classification supports the following primary metrics <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration|\n",
"|**iterations**|Number of iterations. In each iteration Auto ML trains the data with a specific pipeline|\n",
"|**n_cross_validations**|Number of cross validation splits|\n",
"|**preprocess**| *True/False* <br>Setting this to *True* enables Auto ML to perform preprocessing <br>on the input to handle *missing data*, and perform some common *feature extraction*|\n",
"|**exit_score**|*double* value indicating the target for *primary_metric*. <br> Once the target is surpassed the run terminates|\n",
"|**blacklist_algos**|*Array* of *strings* indicating pipelines to ignore for Auto ML.<br><br> Allowed values for **Classification**<br><i>LogisticRegression</i><br><i>SGDClassifierWrapper</i><br><i>NBWrapper</i><br><i>BernoulliNB</i><br><i>SVCWrapper</i><br><i>LinearSVMWrapper</i><br><i>KNeighborsClassifier</i><br><i>DecisionTreeClassifier</i><br><i>RandomForestClassifier</i><br><i>ExtraTreesClassifier</i><br><i>LightGBMClassifier</i><br><br>Allowed values for **Regression**<br><i>ElasticNet<i><br><i>GradientBoostingRegressor<i><br><i>DecisionTreeRegressor<i><br><i>KNeighborsRegressor<i><br><i>LassoLars<i><br><i>SGDRegressor<i><br><i>RandomForestRegressor<i><br><i>ExtraTreesRegressor<i>|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers. |\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. |"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 3600,\n",
" iterations = 20,\n",
" n_cross_validations = 5,\n",
" preprocess = True,\n",
" exit_score = 0.994,\n",
" blacklist_algos = ['KNeighborsClassifier','LinearSVMWrapper'],\n",
" verbosity = logging.INFO,\n",
" X = X_digits, \n",
" y = y_digits,\n",
" path=project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Training the Model\n",
"\n",
"You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
"You will see the currently running iterations printing to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploring the results"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Widget for monitoring runs\n",
"\n",
"The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
"\n",
"NOTE: The widget will display a link at the bottom. This will not currently work, but will eventually link to a web-ui to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(local_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(local_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",
"\n",
"Below we select the best pipeline from our iterations. Each pipeline is a tuple of three elements. The first element is the score for the pipeline the second element is the string description of the pipeline and the last element are the pipeline objects used for each fold in the cross-validation."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"best_run, fitted_model = local_run.get_output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model based on any other metric"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# lookup_metric = \"accuracy\"\n",
"# best_run, fitted_model = local_run.get_output(metric=lookup_metric)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a specific iteration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# iteration = 3\n",
"# best_run, fitted_model = local_run.get_output(iteration=iteration)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register fitted model for deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"local_run.register_model(description=description, tags=tags)\n",
"local_run.model_id # Use this id to deploy the model as a web service in Azure"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Model "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_digits = digits.data[:10, :]\n",
"y_digits = digits.target[:10]\n",
"images = digits.images[:10]\n",
"\n",
"#Randomly select digits and test\n",
"for index in np.random.choice(len(y_digits), 2):\n",
" print(index)\n",
" predicted = fitted_model.predict(X_digits[index:index + 1])[0]\n",
" label = y_digits[index]\n",
" title = \"Label value = %d Predicted value = %d \" % ( label,predicted)\n",
" fig = plt.figure(1, figsize=(3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap=plt.cm.gray_r, interpolation='nearest')\n",
" plt.show()\n"
]
}
],
"metadata": {
"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
}

832
automl/06.auto-ml-sparse-data-custom-cv-split.ipynb
View File

@@ -1,418 +1,418 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 06: Custom CV Splits and Handling Sparse Data\n",
"\n",
"In this example we use the scikit-learn's [20newsgroup](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_20newsgroups.html) to showcase how you can use AutoML for handling sparse data and how to specify custom cross validations splits.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you will learn how to:\n",
"1. Create an `Experiment` in an existing `Workspace`.\n",
"2. Configure AutoML using `AutoMLConfig`.\n",
"4. Train the model.\n",
"5. Explore the results.\n",
"6. Test the best fitted model.\n",
"\n",
"In addition this notebook showcases the following features\n",
"- **Custom CV** splits \n",
"- Handling **sparse data** in the input"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create an Experiment\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",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the experiment\n",
"experiment_name = 'automl-local-missing-data'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-missing-data'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Creating Sparse Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.datasets import fetch_20newsgroups\n",
"from sklearn.feature_extraction.text import HashingVectorizer\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"remove = ('headers', 'footers', 'quotes')\n",
"categories = [\n",
" 'alt.atheism',\n",
" 'talk.religion.misc',\n",
" 'comp.graphics',\n",
" 'sci.space',\n",
"]\n",
"data_train = fetch_20newsgroups(subset = 'train', categories = categories,\n",
" shuffle = True, random_state = 42,\n",
" remove = remove)\n",
"\n",
"X_train, X_validation, y_train, y_validation = train_test_split(data_train.data, data_train.target, test_size = 0.33, random_state = 42)\n",
"\n",
"\n",
"vectorizer = HashingVectorizer(stop_words = 'english', alternate_sign = False,\n",
" n_features = 2**16)\n",
"X_train = vectorizer.transform(X_train)\n",
"X_validation = vectorizer.transform(X_validation)\n",
"\n",
"summary_df = pd.DataFrame(index = ['No of Samples', 'No of Features'])\n",
"summary_df['Train Set'] = [X_train.shape[0], X_train.shape[1]]\n",
"summary_df['Validation Set'] = [X_validation.shape[0], X_validation.shape[1]]\n",
"summary_df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure AutoML\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. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration.|\n",
"|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
"|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and to perform some common *feature extraction*.<br>**Note:** If input data is sparse, you cannot use *True*.|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
"|**X_valid**|(sparse) array-like, shape = [n_samples, n_features] for the custom validation set.|\n",
"|**y_valid**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification for the custom validation set.|\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 3600,\n",
" iterations = 5,\n",
" preprocess = False,\n",
" verbosity = logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" X_valid = X_validation, \n",
" y_valid = y_validation, \n",
" path = project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train the Model\n",
"\n",
"Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
"In this example, we specify `show_output = True` to print currently running iterations to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore the 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.train.widgets import RunDetails\n",
"RunDetails(local_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(local_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": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 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 = local_run.get_output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model Based on Any Other Metric\n",
"Show the run and the model which has the smallest `accuracy` value:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# lookup_metric = \"accuracy\"\n",
"# best_run, fitted_model = local_run.get_output(metric = lookup_metric)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a Specific Iteration\n",
"Show the run and the model from the third iteration:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# iteration = 3\n",
"# best_run, fitted_model = local_run.get_output(iteration = iteration)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register the Fitted Model for Deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"local_run.register_model(description = description, tags = tags)\n",
"local_run.model_id # Use this id to deploy the model as a web service in Azure."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Model"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Load test data.\n",
"import sklearn\n",
"from pandas_ml import ConfusionMatrix\n",
"\n",
"remove = ('headers', 'footers', 'quotes')\n",
"categories = [\n",
" 'alt.atheism',\n",
" 'talk.religion.misc',\n",
" 'comp.graphics',\n",
" 'sci.space',\n",
"]\n",
"\n",
"\n",
"data_test = fetch_20newsgroups(subset = 'test', categories = categories,\n",
" shuffle = True, random_state = 42,\n",
" remove = remove)\n",
"\n",
"vectorizer = HashingVectorizer(stop_words = 'english', alternate_sign = False,\n",
" n_features = 2**16)\n",
"\n",
"X_test = vectorizer.transform(data_test.data)\n",
"y_test = data_test.target\n",
"\n",
"# Test our best pipeline.\n",
"\n",
"y_pred = fitted_model.predict(X_test)\n",
"y_pred_strings = [data_test.target_names[i] for i in y_pred]\n",
"y_test_strings = [data_test.target_names[i] for i in y_test]\n",
"\n",
"cm = ConfusionMatrix(y_test_strings, y_pred_strings)\n",
"print(cm)\n",
"cm.plot()"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 06: Custom CV splits, handling sparse data\n",
"\n",
"In this example we use the scikit learn's [20newsgroup](In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for handling sparse data and specify custom cross validation splits.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. Creating an Experiment using an existing Workspace\n",
"2. Instantiating AutoMLConfig\n",
"4. Training the Model\n",
"5. Exploring the results\n",
"6. Testing the fitted model\n",
"\n",
"In addition this notebook showcases the following features\n",
"- **Custom CV** splits \n",
"- Handling **Sparse Data** in the input"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Experiment\n",
"\n",
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 the experiment\n",
"experiment_name = 'automl-local-missing-data'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-missing-data'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Creating Sparse Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.datasets import fetch_20newsgroups\n",
"from sklearn.feature_extraction.text import HashingVectorizer\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"remove = ('headers', 'footers', 'quotes')\n",
"categories = [\n",
" 'alt.atheism',\n",
" 'talk.religion.misc',\n",
" 'comp.graphics',\n",
" 'sci.space',\n",
"]\n",
"data_train = fetch_20newsgroups(subset='train', categories=categories,\n",
" shuffle=True, random_state=42,\n",
" remove=remove)\n",
"\n",
"X_train, X_validation, y_train, y_validation = train_test_split(data_train.data, data_train.target, test_size=0.33, random_state=42)\n",
"\n",
"\n",
"vectorizer = HashingVectorizer(stop_words='english', alternate_sign=False,\n",
" n_features=2**16)\n",
"X_train = vectorizer.transform(X_train)\n",
"X_validation = vectorizer.transform(X_validation)\n",
"\n",
"summary_df = pd.DataFrame(index = ['No of Samples', 'No of Features'])\n",
"summary_df['Train Set'] = [X_train.shape[0], X_train.shape[1]]\n",
"summary_df['Validation Set'] = [X_validation.shape[0], X_validation.shape[1]]\n",
"summary_df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiate Auto ML Config\n",
"\n",
"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.<br> Classification supports the following primary metrics <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration|\n",
"|**iterations**|Number of iterations. In each iteration Auto ML trains a specific pipeline with the data|\n",
"|**preprocess**| *True/False* <br>Setting this to *True* enables Auto ML to perform preprocessing <br>on the input to handle *missing data*, and perform some common *feature extraction*<br>*Note: If input data is Sparse you cannot use preprocess=True*|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers. |\n",
"|**X_valid**|(sparse) array-like, shape = [n_samples, n_features] for the custom Validation set|\n",
"|**y_valid**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. for the custom Validation set|\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log='automl_errors.log',\n",
" primary_metric='AUC_weighted',\n",
" max_time_sec=3600,\n",
" iterations=5,\n",
" preprocess=False,\n",
" verbosity=logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" X_valid = X_validation, \n",
" y_valid = y_validation, \n",
" path=project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Training the Model\n",
"\n",
"You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
"You will see the currently running iterations printing to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploring the results"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Widget for monitoring runs\n",
"\n",
"The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
"\n",
"NOTE: The widget displays a link at the bottom. This links to a web-ui to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(local_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(local_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": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 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 *fit* invocation. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"best_run, fitted_model = local_run.get_output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model based on any other metric"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# lookup_metric = \"accuracy\"\n",
"# best_run, fitted_model = local_run.get_output(metric=lookup_metric)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a specific iteration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# iteration = 3\n",
"# best_run, fitted_model = local_run.get_output(iteration=iteration)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register fitted model for deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"local_run.register_model(description=description, tags=tags)\n",
"local_run.model_id # Use this id to deploy the model as a web service in Azure"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Model "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()### Testing the Fitted Model\n",
"\n",
"#### Load Test Data\n",
"import sklearn\n",
"from pandas_ml import ConfusionMatrix\n",
"\n",
"remove = ('headers', 'footers', 'quotes')\n",
"categories = [\n",
" 'alt.atheism',\n",
" 'talk.religion.misc',\n",
" 'comp.graphics',\n",
" 'sci.space',\n",
"]\n",
"\n",
"\n",
"data_test = fetch_20newsgroups(subset='test', categories=categories,\n",
" shuffle=True, random_state=42,\n",
" remove=remove)\n",
"\n",
"vectorizer = HashingVectorizer(stop_words='english', alternate_sign=False,\n",
" n_features=2**16)\n",
"\n",
"X_test = vectorizer.transform(data_test.data)\n",
"y_test = data_test.target\n",
"\n",
"#### Testing our best pipeline\n",
"\n",
"ypred = fitted_model.predict(X_test)\n",
"ypred_strings = [categories[i] for i in ypred]\n",
"ytest_strings = [categories[i] for i in y_test]\n",
"\n",
"cm = ConfusionMatrix(ytest_strings, ypred_strings)\n",
"print(cm)\n",
"cm.plot()"
]
}
],
"metadata": {
"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
}

649
automl/07.auto-ml-exploring-previous-runs.ipynb
View File

@@ -1,326 +1,327 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 07: Exploring Previous Runs\n",
"\n",
"In this example we present some examples on navigating previously executed runs. We also show how you can download a fitted model for any previous run.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you will learn how to:\n",
"1. List all experiments in a workspace.\n",
"2. List all AutoML runs in an experiment.\n",
"3. Get details for an AutoML run, including settings, run widget, and all metrics.\n",
"4. Download a fitted pipeline for any iteration.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# List all AutoML Experiments in a Workspace"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"import re\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\n",
"\n",
"import azureml.core\n",
"from azureml.core.experiment import Experiment\n",
"from azureml.core.run import Run\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",
"experiment_list = Experiment.list(workspace=ws)\n",
"\n",
"summary_df = pd.DataFrame(index = ['No of Runs'])\n",
"pattern = re.compile('^AutoML_[^_]*$')\n",
"for experiment in experiment_list:\n",
" all_runs = list(experiment.get_runs())\n",
" automl_runs = []\n",
" for run in all_runs:\n",
" if(pattern.match(run.id)):\n",
" automl_runs.append(run) \n",
" summary_df[experiment.name] = [len(automl_runs)]\n",
" \n",
"pd.set_option('display.max_colwidth', -1)\n",
"summary_df.T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# List AutoML runs for an experiment\n",
"Set `experiment_name` to any experiment name from the result of the Experiment.list cell to load the AutoML runs."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'automl-local-classification' # Replace this with any project name from previous cell.\n",
"\n",
"proj = ws.experiments()[experiment_name]\n",
"summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name'])\n",
"pattern = re.compile('^AutoML_[^_]*$')\n",
"all_runs = list(proj.get_runs(properties={'azureml.runsource': 'automl'}))\n",
"for run in all_runs:\n",
" if(pattern.match(run.id)):\n",
" properties = run.get_properties()\n",
" tags = run.get_tags()\n",
" amlsettings = eval(properties['RawAMLSettingsString'])\n",
" if 'iterations' in tags:\n",
" iterations = tags['iterations']\n",
" else:\n",
" iterations = properties['num_iterations']\n",
" summary_df[run.id] = [amlsettings['task_type'], run.get_details()['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name']]\n",
" \n",
"from IPython.display import HTML\n",
"projname_html = HTML(\"<h3>{}</h3>\".format(proj.name))\n",
"\n",
"from IPython.display import display\n",
"display(projname_html)\n",
"display(summary_df.T)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Get details for an AutoML run\n",
"\n",
"Copy the project name and run id from the previous cell output to find more details on a particular run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run_id = '' # Filling your own run_id from above run ids\n",
"assert (run_id in summary_df.keys()),\"Run id not found! Please set run id to a value from above run ids\"\n",
"\n",
"from azureml.train.widgets import RunDetails\n",
"\n",
"experiment = Experiment(ws, experiment_name)\n",
"ml_run = AutoMLRun(experiment = experiment, run_id = run_id)\n",
"\n",
"summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name', 'Start Time', 'End Time'])\n",
"properties = ml_run.get_properties()\n",
"tags = ml_run.get_tags()\n",
"status = ml_run.get_details()\n",
"amlsettings = eval(properties['RawAMLSettingsString'])\n",
"if 'iterations' in tags:\n",
" iterations = tags['iterations']\n",
"else:\n",
" iterations = properties['num_iterations']\n",
"start_time = None\n",
"if 'startTimeUtc' in status:\n",
" start_time = status['startTimeUtc']\n",
"end_time = None\n",
"if 'endTimeUtc' in status:\n",
" end_time = status['endTimeUtc']\n",
"summary_df[ml_run.id] = [amlsettings['task_type'], status['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name'], start_time, end_time]\n",
"display(HTML('<h3>Runtime Details</h3>'))\n",
"display(summary_df)\n",
"\n",
"#settings_df = pd.DataFrame(data = amlsettings, index = [''])\n",
"display(HTML('<h3>AutoML Settings</h3>'))\n",
"display(amlsettings)\n",
"\n",
"display(HTML('<h3>Iterations</h3>'))\n",
"RunDetails(ml_run).show() \n",
"\n",
"children = list(ml_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",
"display(HTML('<h3>Metrics</h3>'))\n",
"display(rundata)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Download fitted models"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Download the Best Model for Any Given Metric"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"metric = 'AUC_weighted' # Replace with a metric name.\n",
"best_run, fitted_model = ml_run.get_output(metric = metric)\n",
"fitted_model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Download the Model for Any Given Iteration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 4 # Replace with an iteration number.\n",
"best_run, fitted_model = ml_run.get_output(iteration = iteration)\n",
"fitted_model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Register fitted model for deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"ml_run.register_model(description = description, tags = tags)\n",
"ml_run.model_id # Use this id to deploy the model as a web service in Azure."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Register the Best Model for Any Given Metric"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"metric = 'AUC_weighted' # Replace with a metric name.\n",
"description = 'AutoML Model'\n",
"tags = None\n",
"ml_run.register_model(description = description, tags = tags, metric = metric)\n",
"print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Register the Model for Any Given Iteration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 4 # Replace with an iteration number.\n",
"description = 'AutoML Model'\n",
"tags = None\n",
"ml_run.register_model(description = description, tags = tags, iteration = iteration)\n",
"print(ml_run.model_id) # Use this id to deploy the model as a web service in Azure."
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 07: Exploring previous runs\n",
"\n",
"In this example we present some examples on navigating previously executed runs. We also show how you can download a fitted model for any previous run.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. List all Experiments for the workspace\n",
"2. List AutoML runs for an Experiment\n",
"3. Get details for a AutoML Run. (Automl settings, run widget & all metrics)\n",
"4. Download fitted pipeline for any iteration\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# List all AutoML Experiments in a Workspace"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"import re\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\n",
"\n",
"import azureml.core\n",
"from azureml.core.experiment import Experiment\n",
"from azureml.core.run import Run\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",
"experiment_list = Experiment.list(workspace=ws)\n",
"\n",
"summary_df = pd.DataFrame(index = ['No of Runs'])\n",
"pattern = re.compile('^AutoML_[^_]*$')\n",
"for experiment in experiment_list:\n",
" all_runs = list(experiment.get_runs())\n",
" automl_runs = []\n",
" for run in all_runs:\n",
" if(pattern.match(run.id)):\n",
" automl_runs.append(run) \n",
" summary_df[experiment.name] = [len(automl_runs)]\n",
" \n",
"pd.set_option('display.max_colwidth', -1)\n",
"summary_df.T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# List AutoML runs for an Experiment\n",
"You can set <i>Experiment</i> name with any experiment name from the result of the Experiment.list cell to load the AutoML runs."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'automl-local-classification' # Replace this with any project name from previous cell\n",
"\n",
"proj = ws.experiments()[experiment_name]\n",
"summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name'])\n",
"pattern = re.compile('^AutoML_[^_]*$')\n",
"all_runs = list(proj.get_runs(properties={'azureml.runsource': 'automl'}))\n",
"for run in all_runs:\n",
" if(pattern.match(run.id)):\n",
" properties = run.get_properties()\n",
" tags = run.get_tags()\n",
" amlsettings = eval(properties['RawAMLSettingsString'])\n",
" if 'iterations' in tags:\n",
" iterations = tags['iterations']\n",
" else:\n",
" iterations = properties['num_iterations']\n",
" summary_df[run.id] = [amlsettings['task_type'], run.get_details()['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name']]\n",
" \n",
"from IPython.display import HTML\n",
"projname_html = HTML(\"<h3>{}</h3>\".format(proj.name))\n",
"\n",
"from IPython.display import display\n",
"display(projname_html)\n",
"display(summary_df.T)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Get Details for a Auto ML Run\n",
"\n",
"Copy the project name and run id from the previous cell output to find more details on a particular run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run_id = '' # Filling your own run_id\n",
"\n",
"from azureml.train.widgets import RunDetails\n",
"\n",
"experiment = Experiment(ws, experiment_name)\n",
"ml_run = AutoMLRun(experiment=experiment, run_id=run_id)\n",
"\n",
"summary_df = pd.DataFrame(index = ['Type', 'Status', 'Primary Metric', 'Iterations', 'Compute', 'Name', 'Start Time', 'End Time'])\n",
"properties = ml_run.get_properties()\n",
"tags = ml_run.get_tags()\n",
"status = ml_run.get_details()\n",
"amlsettings = eval(properties['RawAMLSettingsString'])\n",
"if 'iterations' in tags:\n",
" iterations = tags['iterations']\n",
"else:\n",
" iterations = properties['num_iterations']\n",
"start_time = None\n",
"if 'startTimeUtc' in status:\n",
" start_time = status['startTimeUtc']\n",
"end_time = None\n",
"if 'endTimeUtc' in status:\n",
" end_time = status['endTimeUtc']\n",
"summary_df[ml_run.id] = [amlsettings['task_type'], status['status'], properties['primary_metric'], iterations, properties['target'], amlsettings['name'], start_time, end_time]\n",
"display(HTML('<h3>Runtime Details</h3>'))\n",
"display(summary_df)\n",
"\n",
"#settings_df = pd.DataFrame(data=amlsettings, index=[''])\n",
"display(HTML('<h3>AutoML Settings</h3>'))\n",
"display(amlsettings)\n",
"\n",
"display(HTML('<h3>Iterations</h3>'))\n",
"RunDetails(ml_run).show() \n",
"\n",
"children = list(ml_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",
"display(HTML('<h3>Metrics</h3>'))\n",
"display(rundata)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Download fitted models"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Download best model for any given metric"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"metric = 'AUC_weighted' # Replace with a metric name\n",
"best_run, fitted_model = ml_run.get_output(metric=metric)\n",
"fitted_model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Download model for any given iteration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 4 # Replace with an interation number\n",
"best_run, fitted_model = ml_run.get_output(iteration=iteration)\n",
"fitted_model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Register fitted model for deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"ml_run.register_model(description=description, tags=tags)\n",
"ml_run.model_id # Use this id to deploy the model as a web service in Azure"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Register best model for any given metric"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"metric = 'AUC_weighted' # Replace with a metric name\n",
"description = 'AutoML Model'\n",
"tags = None\n",
"ml_run.register_model(description=description, tags=tags, metric=metric)\n",
"ml_run.model_id # Use this id to deploy the model as a web service in Azure"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Register model for any given iteration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 4 # Replace with an interation number\n",
"description = 'AutoML Model'\n",
"tags = None\n",
"ml_run.register_model(description=description, tags=tags, iteration=iteration)\n",
"ml_run.model_id # Use this id to deploy the model as a web service in Azure"
]
}
],
"metadata": {
"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
}

954
automl/08.auto-ml-remote-execution-with-text-file-on-DSVM.ipynb
View File

@@ -1,480 +1,478 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 08: Remote Execution with Text File\n",
"\n",
"This sample accesses a data file on a remote DSVM. This is more efficient than reading the file from Azure Blob storage in the `get_data` method.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you will learn how to:\n",
"1. Configure the DSVM to allow files to be accessed directly by the `get_data` function.\n",
"2. Using `get_data` to return data from a local file.\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create an Experiment\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",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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-remote-dsvm-file'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-remote-dsvm-file'\n",
"\n",
"experiment=Experiment(ws, experiment_name)\n",
"\n",
"output = {}\n",
"output['SDK version'] = azureml.core.VERSION\n",
"output['Subscription ID'] = ws.subscription_id\n",
"output['Workspace'] = ws.name\n",
"output['Resource Group'] = ws.resource_group\n",
"output['Location'] = ws.location\n",
"output['Project Directory'] = project_folder\n",
"output['Experiment Name'] = experiment.name\n",
"pd.set_option('display.max_colwidth', -1)\n",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a Remote Linux DSVM\n",
"**Note:** If creation fails with a message about Marketplace purchase eligibilty, start creation of a DSVM through the [Azure portal](https://portal.azure.com), and select \"Want to create programmatically\" to enable programmatic creation. Once you've enabled this setting, you can exit the portal without actually creating the DSVM, and creation of the DSVM through the notebook should work.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import DsvmCompute\n",
"\n",
"dsvm_name = 'mydsvm'\n",
"try:\n",
" dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
" print('Found existing DSVM.')\n",
"except:\n",
" print('Creating a new DSVM.')\n",
" dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
" dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
" dsvm_compute.wait_for_completion(show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Copy the Data File to the DSVM\n",
"Download the data file and copy the data file to the `/tmp/data` on the DSVM."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
" delimiter=\"\\t\", quotechar='\"')\n",
"df.to_csv(\"data.tsv\", sep=\"\\t\", quotechar='\"', index=False)\n",
"\n",
"# Now copy the file data.tsv to the folder /tmp/data on the DSVM."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create the `get_data.py` File\n",
"For remote executions you should author a `get_data.py` file containing a `get_data()` function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
"In this example, the `get_data()` function returns a [dictionary](README.md#getdata)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if not os.path.exists(project_folder):\n",
" os.makedirs(project_folder)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%writefile $project_folder/get_data.py\n",
"\n",
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import LabelEncoder\n",
"import os\n",
"\n",
"def get_data():\n",
" # Burning man 2016 data\n",
" df = pd.read_csv('/tmp/data/data.tsv',\n",
" delimiter=\"\\t\", quotechar='\"')\n",
" # get integer labels\n",
" le = LabelEncoder()\n",
" le.fit(df[\"Label\"].values)\n",
" y = le.transform(df[\"Label\"].values)\n",
" df = df.drop([\"Label\"], axis=1)\n",
"\n",
" df_train, _, y_train, _ = train_test_split(df, y, test_size = 0.1, random_state = 42)\n",
"\n",
" return { \"X\" : df.values, \"y\" : y }"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\n",
"\n",
"You can specify `automl_settings` as `**kwargs` as well. Also note that you can use a `get_data()` function for local excutions too.\n",
"\n",
"**Note:** When using Remote DSVM, you can't pass Numpy arrays directly to the fit method.\n",
"\n",
"|Property|Description|\n",
"|-|-|\n",
"|**primary_metric**|This is the metric that you want to optimize. Classification supports the following primary metrics: <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds 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",
"|**concurrent_iterations**|Maximum number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM.|\n",
"|**preprocess**|Setting this to *True* enables AutoML to perform preprocessing on the input to handle *missing data*, and perform some common *feature extraction*.|\n",
"|**max_cores_per_iteration**|Indicates how many cores on the compute target would be used to train a single pipeline.<br>Default is *1*, you can set it to *-1* to use all cores.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_settings = {\n",
" \"max_time_sec\": 3600,\n",
" \"iterations\": 10,\n",
" \"n_cross_validations\": 5,\n",
" \"primary_metric\": 'AUC_weighted',\n",
" \"preprocess\": True,\n",
" \"max_cores_per_iteration\": 2,\n",
" \"verbosity\": logging.INFO\n",
"}\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" path = project_folder,\n",
" compute_target = dsvm_compute,\n",
" data_script = project_folder + \"/get_data.py\",\n",
" **automl_settings)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train the Model <a class=\"anchor\" id=\"Training-the-model-Remote-DSVM\"></a>\n",
"\n",
"Call the `submit` method on the experiment object and pass the run configuration. For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets and models even when the experiment is running to retrieve the best model up to that point. Once you are satisfied with the model, you can cancel a particular iteration or the whole run.\n",
"\n",
"In this example, we specify `show_output = False` to suppress console output while the run is in progress."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"remote_run = experiment.submit(automl_config, show_output = False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploring the 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",
"You can click on a pipeline to see run properties and output logs. Logs are also available on the DSVM under `/tmp/azureml_run/{iterationid}/azureml-logs`.\n",
"\n",
"**Note:** The widget displays a link at the bottom. Use this link to open a web interface to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.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": [
"## Cancelling Runs\n",
"You can cancel ongoing remote runs using the `cancel` and `cancel_iteration` functions."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Cancel the ongoing experiment and stop scheduling new iterations.\n",
"# remote_run.cancel()\n",
"\n",
"# Cancel iteration 1 and move onto iteration 2.\n",
"# remote_run.cancel_iteration(1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Retrieve the Best Model\n",
"\n",
"Below we select the best pipeline from our iterations. The `get_output` method 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": [
"#### Best Model Based on Any Other Metric\n",
"Show the run and the model which has the smallest `accuracy` value:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# lookup_metric = \"accuracy\"\n",
"# best_run, fitted_model = remote_run.get_output(metric = lookup_metric)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a Specific Iteration\n",
"Show the run and the model from the first iteration:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# iteration = 1\n",
"# best_run, fitted_model = remote_run.get_output(iteration = iteration)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register the Fitted Model for Deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"remote_run.register_model(description = description, tags = tags)\n",
"remote_run.model_id # Use this id to deploy the model as a web service in Azure."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Test the Best Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import sklearn\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import LabelEncoder\n",
"from pandas_ml import ConfusionMatrix\n",
"\n",
"df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
" delimiter=\"\\t\", quotechar='\"')\n",
"\n",
"# get integer labels\n",
"le = LabelEncoder()\n",
"le.fit(df[\"Label\"].values)\n",
"y = le.transform(df[\"Label\"].values)\n",
"df = df.drop([\"Label\"], axis = 1)\n",
"\n",
"_, df_test, _, y_test = train_test_split(df, y, test_size = 0.1, random_state = 42)\n",
"\n",
"y_pred = fitted_model.predict(df_test.values)\n",
"\n",
"y_pred_strings = le.inverse_transform(y_pred)\n",
"y_test_strings = le.inverse_transform(y_test)\n",
"\n",
"cm = ConfusionMatrix(y_test_strings, y_pred_strings)\n",
"\n",
"print(cm)\n",
"\n",
"cm.plot()"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 08: Remote Execution with Text file\n",
"\n",
"In this sample accesses a data file on a remote DSVM. This is more efficient than reading the file from Blob storage in the get_data method.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. Configuring the DSVM to allow files to be access directly by the get_data method.\n",
"2. get_data returning data from a local file.\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Experiment\n",
"\n",
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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-remote-dsvm-file'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-remote-dsvm-file'\n",
"\n",
"experiment=Experiment(ws, experiment_name)\n",
"\n",
"output = {}\n",
"output['SDK version'] = azureml.core.VERSION\n",
"output['Subscription ID'] = ws.subscription_id\n",
"output['Workspace'] = ws.name\n",
"output['Resource Group'] = ws.resource_group\n",
"output['Location'] = ws.location\n",
"output['Project Directory'] = project_folder\n",
"output['Experiment Name'] = experiment.name\n",
"pd.set_option('display.max_colwidth', -1)\n",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a Remote Linux DSVM\n",
"Note: If creation fails with a message about Marketplace purchase eligibilty, go to portal.azure.com, start creating DSVM there, and select \"Want to create programmatically\" to enable programmatic creation. Once you've enabled it, you can exit without actually creating VM.\n",
"\n",
"**Note**: By default SSH runs on port 22 and you don't need to specify it. But if for security reasons you can switch to a different port (such as 5022), you can append the port number to the address. [Read more](https://render.githubusercontent.com/documentation/sdk/ssh-issue.md) on this."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import DsvmCompute\n",
"\n",
"dsvm_name = 'mydsvm'\n",
"try:\n",
" dsvm_compute = DsvmCompute(ws, dsvm_name)\n",
" print('found existing dsvm.')\n",
"except:\n",
" print('creating new dsvm.')\n",
" dsvm_config = DsvmCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\")\n",
" dsvm_compute = DsvmCompute.create(ws, name = dsvm_name, provisioning_configuration = dsvm_config)\n",
" dsvm_compute.wait_for_completion(show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Copy data file to the DSVM\n",
"Download the data file.\n",
"Copy the data file to the DSVM under the folder: /tmp/data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
" delimiter=\"\\t\", quotechar='\"')\n",
"df.to_csv(\"data.tsv\", sep=\"\\t\", quotechar='\"', index=False)\n",
"\n",
"# Now copy the file data.tsv to the folder /tmp/data on the DSVM"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Get Data File\n",
"For remote executions you should author a get_data.py file containing a get_data() function. This file should be in the root directory of the project. You can encapsulate code to read data either from a blob storage or local disk in this file.\n",
"\n",
"The *get_data()* function returns a [dictionary](README.md#getdata)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if not os.path.exists(project_folder):\n",
" os.makedirs(project_folder)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%writefile $project_folder/get_data.py\n",
"\n",
"import pandas as pd\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import LabelEncoder\n",
"import os\n",
"\n",
"def get_data():\n",
" # Burning man 2016 data\n",
" df = pd.read_csv('/tmp/data/data.tsv',\n",
" delimiter=\"\\t\", quotechar='\"')\n",
" # get integer labels\n",
" le = LabelEncoder()\n",
" le.fit(df[\"Label\"].values)\n",
" y = le.transform(df[\"Label\"].values)\n",
" df = df.drop([\"Label\"], axis=1)\n",
"\n",
" df_train, _, y_train, _ = train_test_split(df, y, test_size=0.1, random_state=42)\n",
"\n",
" return { \"X\" : df.values, \"y\" : y }"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiate AutoML <a class=\"anchor\" id=\"Instatiate-AutoML-Remote-DSVM\"></a>\n",
"\n",
"You can specify automl_settings as **kwargs** as well. Also note that you can use the get_data() symantic for local excutions too. \n",
"\n",
"<i>Note: For Remote DSVM and Batch AI you cannot pass Numpy arrays directly to the fit method.</i>\n",
"\n",
"|Property|Description|\n",
"|-|-|\n",
"|**primary_metric**|This is the metric that you want to optimize.<br> Classification supports the following primary metrics <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration|\n",
"|**iterations**|Number of iterations. In each iteration Auto ML trains a specific pipeline with the data|\n",
"|**n_cross_validations**|Number of cross validation splits|\n",
"|**concurrent_iterations**|Max number of iterations that would be executed in parallel. This should be less than the number of cores on the DSVM\n",
"|**preprocess**| *True/False* <br>Setting this to *True* enables Auto ML to perform preprocessing <br>on the input to handle *missing data*, and perform some common *feature extraction*|\n",
"|**max_cores_per_iteration**| Indicates how many cores on the compute target would be used to train a single pipeline.<br> Default is *1*, you can set it to *-1* to use all cores|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_settings = {\n",
" \"max_time_sec\": 3600,\n",
" \"iterations\": 10,\n",
" \"n_cross_validations\": 5,\n",
" \"primary_metric\": 'AUC_weighted',\n",
" \"preprocess\": True,\n",
" \"max_cores_per_iteration\": 2,\n",
" \"verbosity\": logging.INFO\n",
"}\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" path=project_folder,\n",
" compute_target = dsvm_compute,\n",
" data_script = project_folder + \"/get_data.py\",\n",
" **automl_settings\n",
" )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Training the Model <a class=\"anchor\" id=\"Training-the-model-Remote-DSVM\"></a>\n",
"\n",
"For remote runs the execution is asynchronous, so you will see the iterations get populated as they complete. You can interact with the widgets/models even when the experiment is running to retreive the best model up to that point. Once you are satisfied with the model you can cancel a particular iteration or the whole run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"remote_run = experiment.submit(automl_config, show_output=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploring the Results <a class=\"anchor\" id=\"Exploring-the-Results-Remote-DSVM\"></a>\n",
"#### Widget for monitoring runs\n",
"\n",
"The widget will sit on \"loading\" until the first iteration completed, then you will see an auto-updating graph and table show up. It refreshed once per minute, so you should see the graph update as child runs complete.\n",
"\n",
"You can click on a pipeline to see run properties and output logs. Logs are also available on the DSVM under /tmp/azureml_run/{iterationid}/azureml-logs\n",
"\n",
"NOTE: The widget displays a link at the bottom. This links to a web-ui to explore the individual run details."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.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": [
"## Canceling runs\n",
"You can cancel ongoing remote runs using the *cancel()* and *cancel_iteration()* functions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Cancel the ongoing experiment and stop scheduling new iterations\n",
"# remote_run.cancel()\n",
"\n",
"# Cancel iteration 1 and move onto iteration 2\n",
"# remote_run.cancel_iteration(1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 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 *fit* invocation. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"best_run, fitted_model = remote_run.get_output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Best Model based on any other metric"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# lookup_metric = \"accuracy\"\n",
"# best_run, fitted_model = remote_run.get_output(metric=lookup_metric)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Model from a specific iteration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# iteration = 1\n",
"# best_run, fitted_model = remote_run.get_output(iteration=iteration)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register fitted model for deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"remote_run.register_model(description=description, tags=tags)\n",
"remote_run.model_id # Use this id to deploy the model as a web service in Azure"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Model <a class=\"anchor\" id=\"Testing-the-Fitted-Model-Remote-DSVM\"></a>\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import sklearn\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import LabelEncoder\n",
"from pandas_ml import ConfusionMatrix\n",
"\n",
"df = pd.read_csv(\"https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv\",\n",
" delimiter=\"\\t\", quotechar='\"')\n",
"\n",
"# get integer labels\n",
"le = LabelEncoder()\n",
"le.fit(df[\"Label\"].values)\n",
"y = le.transform(df[\"Label\"].values)\n",
"df = df.drop([\"Label\"], axis=1)\n",
"\n",
"_, df_test, _, y_test = train_test_split(df, y, test_size=0.1, random_state=42)\n",
"\n",
"ypred = fitted_model.predict(df_test.values)\n",
"\n",
"ypred_strings = le.inverse_transform(ypred)\n",
"ytest_strings = le.inverse_transform(y_test)\n",
"\n",
"cm = ConfusionMatrix(ytest_strings, ypred_strings)\n",
"\n",
"print(cm)\n",
"\n",
"cm.plot()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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
}

990
automl/09.auto-ml-classification-with-deployment.ipynb
View File

@@ -1,500 +1,494 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 09: Classification with Deployment\n",
"\n",
"In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for a simple classification problem and deploy it to an Azure Container Instance (ACI).\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\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 and create and ACI service.\n",
"7. Test the ACI service.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create an Experiment\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",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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-local-classification'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-classification'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure AutoML\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>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration.|\n",
"|**iterations**|Number of iterations. In each iteration AutoML trains a specific pipeline with the data.|\n",
"|**n_cross_validations**|Number of cross validation splits.|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers.|\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder.|"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_train = digits.data[10:,:]\n",
"y_train = digits.target[10:]\n",
"\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" name = experiment_name,\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 1200,\n",
" iterations = 10,\n",
" n_cross_validations = 2,\n",
" verbosity = logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" path = project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train the Model\n",
"\n",
"Call the `submit` method on the experiment object and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
"In this example, we specify `show_output = True` to print currently running iterations to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 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 = local_run.get_output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register the Fitted Model for Deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"model = local_run.register_model(description = description, tags = tags, iteration = 8)\n",
"local_run.model_id # This will be written to the script file later in the notebook."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create Scoring Script"
]
},
{
"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 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 consistency of the fit results 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": [
"experiment_name = 'automl-local-classification'\n",
"\n",
"experiment = Experiment(ws, experiment_name)\n",
"ml_run = AutoMLRun(experiment = experiment, run_id = local_run.id)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dependencies = ml_run.get_run_sdk_dependencies(iteration = 7)"
]
},
{
"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": [
"%%writefile myenv.yml\n",
"name: myenv\n",
"channels:\n",
" - defaults\n",
"dependencies:\n",
" - pip:\n",
" - numpy==1.14.2\n",
" - scikit-learn==0.19.2\n",
" - pynacl==1.2.1\n",
" - azureml-sdk[notebooks,automl]==<<azureml-version>>"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Substitute the actual version number in the environment file.\n",
"\n",
"conda_env_file_name = 'myenv.yml'\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-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>>', local_run.model_id))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a Container Image"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.image import Image, ContainerImage\n",
"\n",
"image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
" execution_script = script_file_name,\n",
" conda_file = conda_env_file_name,\n",
" tags = {'area': \"digits\", '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)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Deploy the Image as a Web Service on Azure Container Instance"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.webservice import AciWebservice\n",
"\n",
"aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
" memory_gb = 1, \n",
" tags = {'area': \"digits\", '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-01'\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"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#aci_service.delete()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Get 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 a Web Service"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Randomly select digits and test\n",
"digits = datasets.load_digits()\n",
"X_test = digits.data[:10, :]\n",
"y_test = digits.target[:10]\n",
"images = digits.images[:10]\n",
"\n",
"for index in np.random.choice(len(y_test), 3, replace = False):\n",
" print(index)\n",
" test_sample = json.dumps({'data':X_test[index:index + 1].tolist()})\n",
" predicted = aci_service.run(input_data = test_sample)\n",
" label = y_test[index]\n",
" predictedDict = json.loads(predicted)\n",
" title = \"Label value = %d Predicted value = %s \" % ( label,predictedDict['result'][0])\n",
" fig = plt.figure(1, figsize = (3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
" plt.show()"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 09: Classification with deployment\n",
"\n",
"In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use AutoML for a simple classification problem.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. Creating an Experiment using an existing Workspace\n",
"2. Instantiating AutoMLConfig\n",
"3. Training the Model using local compute\n",
"4. Exploring the results\n",
"5. Registering the model\n",
"6. Creating Image and creating aci service\n",
"7. Testing the aci service\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Experiment\n",
"\n",
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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-local-classification'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-classification'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiate Auto ML Config\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.<br> Classification supports the following primary metrics <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i>|\n",
"|**max_time_sec**|Time limit in seconds for each iteration|\n",
"|**iterations**|Number of iterations. In each iteration Auto ML trains a specific pipeline with the data|\n",
"|**n_cross_validations**|Number of cross validation splits|\n",
"|**X**|(sparse) array-like, shape = [n_samples, n_features]|\n",
"|**y**|(sparse) array-like, shape = [n_samples, ], [n_samples, n_classes]<br>Multi-class targets. An indicator matrix turns on multilabel classification. This should be an array of integers. |\n",
"|**path**|Relative path to the project folder. AutoML stores configuration files for the experiment under this folder. You can specify a new empty folder. |"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_digits = digits.data[10:,:]\n",
"y_digits = digits.target[10:]\n",
"\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" name=experiment_name,\n",
" debug_log='automl_errors.log',\n",
" primary_metric='AUC_weighted',\n",
" max_time_sec=1200,\n",
" iterations=10,\n",
" n_cross_validations=2,\n",
" verbosity=logging.INFO,\n",
" X = X_digits, \n",
" y = y_digits,\n",
" path=project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Training the Model\n",
"\n",
"You can call the submit method on the experiment object and pass the run configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
"You will see the currently running iterations printing to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 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 *fit* invocation. There are overloads on *get_output* that allow you to retrieve the best run and fitted model for *any* logged metric or a particular *iteration*."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"best_run, fitted_model = local_run.get_output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register fitted model for deployment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"description = 'AutoML Model'\n",
"tags = None\n",
"model = local_run.register_model(description=description, tags=tags, iteration=8)\n",
"local_run.model_id # This will be written to the script file later in the notebook."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create Scoring script ###"
]
},
{
"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 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 yml file for env"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To ensure the consistence the fit results with the training results, the sdk dependence 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.ipynb."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'automl-local-classification'\n",
"\n",
"experiment = Experiment(ws, experiment_name)\n",
"ml_run = AutoMLRun(experiment=experiment, run_id=local_run.id)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"dependencies = ml_run.get_run_sdk_dependencies(iteration=7)"
]
},
{
"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": [
"%%writefile myenv.yml\n",
"name: myenv\n",
"channels:\n",
" - defaults\n",
"dependencies:\n",
" - pip:\n",
" - numpy==1.14.2\n",
" - scikit-learn==0.19.2\n",
" - azureml-sdk[notebooks,automl]==<<azureml-version>> "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Substitute the actual version number in the environment file.\n",
"\n",
"conda_env_file_name = 'myenv.yml'\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-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>>', local_run.model_id))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create Image ###"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.image import Image, ContainerImage\n",
"\n",
"image_config = ContainerImage.image_configuration(runtime= \"python\",\n",
" execution_script = script_file_name,\n",
" conda_file = conda_env_file_name,\n",
" tags = {'area': \"digits\", '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)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Deploy Image as web service on Azure Container Instance ###"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.webservice import AciWebservice\n",
"\n",
"aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1, \n",
" memory_gb = 1, \n",
" tags = {'area': \"digits\", '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-01'\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": [
"### To delete a service ##"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#aci_service.delete()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### To get logs from deployed service ###"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#aci_service.get_logs()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Test Web Service ###"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Randomly select digits and test\n",
"digits = datasets.load_digits()\n",
"X_digits = digits.data[:10, :]\n",
"y_digits = digits.target[:10]\n",
"images = digits.images[:10]\n",
"\n",
"for index in np.random.choice(len(y_digits), 3):\n",
" print(index)\n",
" test_sample = json.dumps({'data':X_digits[index:index + 1].tolist()})\n",
" predicted = aci_service.run(input_data = test_sample)\n",
" label = y_digits[index]\n",
" predictedDict = json.loads(predicted)\n",
" title = \"Label value = %d Predicted value = %s \" % ( label,predictedDict['result'][0])\n",
" fig = plt.figure(1, figsize=(3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap=plt.cm.gray_r, interpolation='nearest')\n",
" plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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
}

575
automl/10.auto-ml-multi-output-example.ipynb
View File

@@ -1,292 +1,287 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 10: Multi-output\n",
"\n",
"This notebook shows how to use AutoML to train multi-output problems by leveraging the correlation between the outputs using indicator vectors."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Transformer Functions\n",
"The transformations of inputs `X` and `y` are happening as follows, e.g. `y = {y_1, y_2}`, then `X` becomes\n",
" \n",
"`X 1 0`\n",
" \n",
"`X 0 1`\n",
"\n",
"and `y` becomes,\n",
"\n",
"`y_1`\n",
"\n",
"`y_2`"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from scipy import sparse\n",
"from scipy import linalg\n",
"\n",
"#Transformer functions\n",
"def multi_output_transform_x_y(X, y):\n",
" X_new = multi_output_transformer_x(X, y.shape[1])\n",
" y_new = multi_output_transform_y(y)\n",
" return X_new, y_new\n",
"\n",
"def multi_output_transformer_x(X, number_of_columns_y):\n",
" indicator_vecs = linalg.block_diag(*([np.ones((X.shape[0], 1))] * number_of_columns_y))\n",
" if sparse.issparse(X):\n",
" X_new = sparse.vstack(np.tile(X, number_of_columns_y))\n",
" indicator_vecs = sparse.coo_matrix(indicator_vecs)\n",
" X_new = sparse.hstack((X_new, indicator_vecs))\n",
" else:\n",
" X_new = np.tile(X, (number_of_columns_y, 1))\n",
" X_new = np.hstack((X_new, indicator_vecs))\n",
" return X_new\n",
"\n",
"def multi_output_transform_y(y):\n",
" return y.reshape(-1, order=\"F\")\n",
"\n",
"def multi_output_inverse_transform_y(y, number_of_columns_y):\n",
" return y.reshape((-1, number_of_columns_y), order = \"F\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## AutoML Experiment Setup"
]
},
{
"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-local-multi-output'\n",
"project_folder = './sample_projects/automl-local-multi-output'\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",
"pd.DataFrame(data = output, index = ['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a Random Dataset for Test Purposes"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"rng = np.random.RandomState(1)\n",
"X_train = np.sort(200 * rng.rand(600, 1) - 100, axis = 0)\n",
"y_train = np.array([np.pi * np.sin(X_train).ravel(), np.pi * np.cos(X_train).ravel()]).T\n",
"y_train += (0.5 - rng.rand(*y_train.shape))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Perform X and y transformation using the transformer function."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"X_train_transformed, y_train_transformed = multi_output_transform_x_y(X_train, y_train)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Configure AutoML using the transformed results."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task = 'regression',\n",
" debug_log = 'automl_errors_multi.log',\n",
" primary_metric = 'r2_score',\n",
" iterations = 10,\n",
" n_cross_validations = 2,\n",
" verbosity = logging.INFO,\n",
" X = X_train_transformed,\n",
" y = y_train_transformed,\n",
" path = project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Fit the Transformed Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output = True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Get the best fit model.\n",
"best_run, fitted_model = local_run.get_output()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Generate random data set for predicting.\n",
"X_test = np.sort(200 * rng.rand(200, 1) - 100, axis = 0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Transform predict data.\n",
"X_test_transformed = multi_output_transformer_x(X_test, y_train.shape[1])\n",
"\n",
"# Predict and inverse transform the prediction.\n",
"y_predict = fitted_model.predict(X_test_transformed)\n",
"y_predict = multi_output_inverse_transform_y(y_predict, y_train.shape[1])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(y_predict)"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 10: Multi output Example for AutoML"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This notebook shows an example to use AutoML to train the multi output problems by leveraging the correlation between the outputs using indicator vectors."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Transformer functions\n",
"The transformation of the input are happening for input X and Y as following, e.g. Y = {y_1, y_2}, then X becomes\n",
" \n",
"X 1 0\n",
" \n",
"X 0 1\n",
"\n",
"and Y becomes,\n",
"\n",
"y_1\n",
"\n",
"y_2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from scipy import sparse\n",
"from scipy import linalg\n",
"\n",
"#Transformer functions\n",
"def multi_output_transform_x_y(X, Y):\n",
" X_new = multi_output_transformer_x(X, Y.shape[1])\n",
" y_new = multi_output_transform_y(Y)\n",
" return X_new, y_new\n",
"\n",
"def multi_output_transformer_x(X, number_of_columns_Y):\n",
" indicator_vecs = linalg.block_diag(*([np.ones((X.shape[0], 1))] * number_of_columns_Y))\n",
" if sparse.issparse(X):\n",
" X_new = sparse.vstack(np.tile(X, number_of_columns_Y))\n",
" indicator_vecs = sparse.coo_matrix(indicator_vecs)\n",
" X_new = sparse.hstack((X_new, indicator_vecs))\n",
" else:\n",
" X_new = np.tile(X, (number_of_columns_Y, 1))\n",
" X_new = np.hstack((X_new, indicator_vecs))\n",
" return X_new\n",
"\n",
"def multi_output_transform_y(Y):\n",
" return Y.reshape(-1, order=\"F\")\n",
" \n",
"def multi_output_inverse_transform_y(y, number_of_columns_y):\n",
" return y.reshape((-1, number_of_columns_y), order=\"F\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## AutoML experiment set up"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ws = Workspace.from_config()\n",
"\n",
"# choose a name for experiment\n",
"experiment_name = 'automl-local-multi-output'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-multi-output'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create a random dataset for the test purpose "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"rng = np.random.RandomState(1)\n",
"X_train = np.sort(200 * rng.rand(600, 1) - 100, axis=0)\n",
"Y_train = np.array([np.pi * np.sin(X_train).ravel(), np.pi * np.cos(X_train).ravel()]).T\n",
"Y_train += (0.5 - rng.rand(*Y_train.shape))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Perform X and Y transformation using transformer function"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"X_train_transformed, y_train_transformed = multi_output_transform_x_y(X_train, Y_train)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"automl_config = AutoMLConfig(task = 'regression',\n",
" debug_log='automl_errors_multi.log',\n",
" primary_metric='r2_score',\n",
" iterations=10,\n",
" n_cross_validations=2,\n",
" verbosity=logging.INFO,\n",
" X=X_train_transformed,\n",
" y=y_train_transformed,\n",
" path=project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Fit the transformed data "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_config, show_output=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Get the best fit model\n",
"best_run, fitted_model = local_run.get_output()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Generate random data set for predicting\n",
"X_predict = np.sort(200 * rng.rand(200, 1) - 100, axis=0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Transform predict data\n",
"X_predict_transformed = multi_output_transformer_x(X_predict, Y_train.shape[1])\n",
"# Predict and inverse transform the prediction\n",
"y_predict = fitted_model.predict(X_predict_transformed)\n",
"Y_predict = multi_output_inverse_transform_y(y_predict, Y_train.shape[1])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(Y_predict)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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
}

493
automl/11.auto-ml-sample-weight.ipynb
View File

@@ -1,251 +1,246 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 11: Sample Weight\n",
"\n",
"In this example we use the scikit-learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use sample weight with AutoML. Sample weight is used where some sample values are more important than others.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you will learn how to configure AutoML to use `sample_weight` and you will see the difference sample weight makes to the test results.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create an Experiment\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",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 names for the regular and the sample weight experiments.\n",
"experiment_name = 'non_sample_weight_experiment'\n",
"sample_weight_experiment_name = 'sample_weight_experiment'\n",
"\n",
"project_folder = './sample_projects/automl-local-classification'\n",
"\n",
"experiment = Experiment(ws, experiment_name)\n",
"sample_weight_experiment=Experiment(ws, sample_weight_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",
"pd.DataFrame(data = output, index = ['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Configure AutoML\n",
"\n",
"Instantiate two `AutoMLConfig` objects. One will be used with `sample_weight` and one without."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_train = digits.data[100:,:]\n",
"y_train = digits.target[100:]\n",
"\n",
"# The example makes the sample weight 0.9 for the digit 4 and 0.1 for all other digits.\n",
"# This makes the model more likely to classify as 4 if the image it not clear.\n",
"sample_weight = np.array([(0.9 if x == 4 else 0.01) for x in y_train])\n",
"\n",
"automl_classifier = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 3600,\n",
" iterations = 10,\n",
" n_cross_validations = 2,\n",
" verbosity = logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" path = project_folder)\n",
"\n",
"automl_sample_weight = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 3600,\n",
" iterations = 10,\n",
" n_cross_validations = 2,\n",
" verbosity = logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" sample_weight = sample_weight,\n",
" path = project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train the Models\n",
"\n",
"Call the `submit` method on the experiment objects and pass the run configuration. Execution of local runs is synchronous. Depending on the data and the number of iterations this can run for a while.\n",
"In this example, we specify `show_output = True` to print currently running iterations to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_classifier, show_output = True)\n",
"sample_weight_run = sample_weight_experiment.submit(automl_sample_weight, show_output = True)\n",
"\n",
"best_run, fitted_model = local_run.get_output()\n",
"best_run_sample_weight, fitted_model_sample_weight = sample_weight_run.get_output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Test the Best Fitted Model\n",
"\n",
"#### Load Test Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_test = digits.data[:100, :]\n",
"y_test = digits.target[:100]\n",
"images = digits.images[:100]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Compare the Pipelines\n",
"The prediction from the sample weight model is more likely to correctly predict 4's. However, it is also more likely to predict 4 for some images that are not labelled as 4."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Randomly select digits and test.\n",
"for index in range(0,len(y_test)):\n",
" predicted = fitted_model.predict(X_test[index:index + 1])[0]\n",
" predicted_sample_weight = fitted_model_sample_weight.predict(X_test[index:index + 1])[0]\n",
" label = y_test[index]\n",
" if predicted == 4 or predicted_sample_weight == 4 or label == 4:\n",
" title = \"Label value = %d Predicted value = %d Prediced with sample weight = %d\" % (label, predicted, predicted_sample_weight)\n",
" fig = plt.figure(1, figsize=(3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap = plt.cm.gray_r, interpolation = 'nearest')\n",
" plt.show()"
]
}
],
"metadata": {
"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"
}
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 11: Sample weight\n",
"\n",
"In this example we use the scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html) to showcase how you can use sample weight with the AutoML Classifier.\n",
"Sample weight is used where some sample values are more important than others.\n",
"\n",
"Make sure you have executed the [00.configuration](00.configuration.ipynb) before running this notebook.\n",
"\n",
"In this notebook you would see\n",
"1. How to specifying sample_weight\n",
"2. The difference that it makes to test results\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Experiment\n",
"\n",
"As part of the setup you have already created a <b>Workspace</b>. For AutoML you would need to create an <b>Experiment</b>. An <b>Experiment</b> is a named object in a <b>Workspace</b>, which is used to run experiments."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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 = 'non_sample_weight_experiment'\n",
"sample_weight_experiment_name = 'sample_weight_experiment'\n",
"\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-classification'\n",
"\n",
"experiment=Experiment(ws, experiment_name)\n",
"sample_weight_experiment=Experiment(ws, sample_weight_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",
"pd.DataFrame(data = output, index = ['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiate Auto ML Config\n",
"\n",
"Instantiate two AutoMLConfig Objects. One will be used with sample_weight and one without."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_digits = digits.data[100:,:]\n",
"y_digits = digits.target[100:]\n",
"\n",
"# The example makes the sample weight 0.9 for the digit 4 and 0.1 for all other digits.\n",
"# This makes the model more likely to classify as 4 if the image it not clear.\n",
"sample_weight = np.array([(0.9 if x == 4 else 0.01) for x in y_digits])\n",
"\n",
"automl_classifier = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 3600,\n",
" iterations = 10,\n",
" n_cross_validations = 2,\n",
" verbosity = logging.INFO,\n",
" X = X_digits, \n",
" y = y_digits,\n",
" path=project_folder)\n",
"\n",
"automl_sample_weight = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 3600,\n",
" iterations = 10,\n",
" n_cross_validations = 2,\n",
" verbosity = logging.INFO,\n",
" X = X_digits, \n",
" y = y_digits,\n",
" sample_weight = sample_weight,\n",
" path=project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Training the Models\n",
"\n",
"Call the submit method on the experiment and pass the configuration. For Local runs the execution is synchronous. Depending on the data and number of iterations this can run for while.\n",
"You will see the currently running iterations printing to the console."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"local_run = experiment.submit(automl_classifier, show_output=True)\n",
"sample_weight_run = sample_weight_experiment.submit(automl_sample_weight, show_output=True)\n",
"\n",
"best_run, fitted_model = local_run.get_output()\n",
"best_run_sample_weight, fitted_model_sample_weight = sample_weight_run.get_output()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Testing the Fitted Models\n",
"\n",
"#### Load Test Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_digits = digits.data[:100, :]\n",
"y_digits = digits.target[:100]\n",
"images = digits.images[:100]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Compare the pipelines\n",
"The prediction from the sample weight model is more likely to correctly predict 4's. However, it is also more likely to predict 4 for some images that are not labelled as 4."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Randomly select digits and test\n",
"for index in range(0,len(y_digits)):\n",
" predicted = fitted_model.predict(X_digits[index:index + 1])[0]\n",
" predicted_sample_weight = fitted_model_sample_weight.predict(X_digits[index:index + 1])[0]\n",
" label = y_digits[index]\n",
" if predicted == 4 or predicted_sample_weight == 4 or label == 4:\n",
" title = \"Label value = %d Predicted value = %d Prediced with sample weight = %d\" % ( label,predicted,predicted_sample_weight)\n",
" fig = plt.figure(1, figsize=(3,3))\n",
" ax1 = fig.add_axes((0,0,.8,.8))\n",
" ax1.set_title(title)\n",
" plt.imshow(images[index], cmap=plt.cm.gray_r, interpolation='nearest')\n",
" plt.show()"
]
}
],
"metadata": {
"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"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

478
automl/12.auto-ml-retrieve-the-training-sdk-versions.ipynb
View File

@@ -1,240 +1,242 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AutoML 12: Retrieving Training SDK Versions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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\n",
"from azureml.train.automl.utilities import get_sdk_dependencies"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 1. Retrieve the SDK versions in the current environment"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To retrieve the SDK versions in the current environment, run `get_sdk_dependencies`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"get_sdk_dependencies()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 2. Train model using AutoML"
]
},
{
"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-local-classification'\n",
"project_folder = './sample_projects/automl-local-classification'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_train = digits.data[10:,:]\n",
"y_train = digits.target[10:]\n",
"\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log = 'automl_errors.log',\n",
" primary_metric = 'AUC_weighted',\n",
" iterations = 3,\n",
" n_cross_validations = 2,\n",
" verbosity = logging.INFO,\n",
" X = X_train, \n",
" y = y_train,\n",
" path = project_folder)\n",
"\n",
"local_run = experiment.submit(automl_config, show_output = True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 3. Retrieve the SDK versions from RunHistory"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To get the SDK versions from RunHistory, first the run id needs to be recorded. This can either be done by copying it from the output message or by retrieving it after each run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Use a run id copied from an output message.\n",
"#run_id = 'AutoML_c0585b1f-a0e6-490b-84c7-3a099468b28e'\n",
"\n",
"# Retrieve the run id from a run.\n",
"run_id = local_run.id\n",
"print(run_id)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Initialize a new `AutoMLRun` object."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'automl-local-classification'\n",
"\n",
"experiment = Experiment(ws, experiment_name)\n",
"ml_run = AutoMLRun(experiment = experiment, run_id = run_id)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Get parent training SDK versions."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ml_run.get_run_sdk_dependencies()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Get the traning SDK versions of a specific run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ml_run.get_run_sdk_dependencies(iteration = 2)"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# AutoML 12: Retrieving Training SDK Versions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
"import os\n",
"import random\n",
"\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import numpy as np\n",
"import pandas as pd\n",
"from sklearn import datasets\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\n",
"from azureml.train.automl.utilities import get_sdk_dependencies"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Diagnostics\n",
"\n",
"Opt-in diagnostics for better experience, quality, and security of future releases"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.telemetry import set_diagnostics_collection\n",
"set_diagnostics_collection(send_diagnostics=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 1. Retrieve the SDK versions in the current env"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To retrieve the SDK versions in the current env, simple running get_sdk_dependencies()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"get_sdk_dependencies()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 2. Training Model Using AutoML"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ws = Workspace.from_config()\n",
"\n",
"# choose a name for experiment\n",
"experiment_name = 'automl-local-classification'\n",
"# project folder\n",
"project_folder = './sample_projects/automl-local-classification'\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",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"digits = datasets.load_digits()\n",
"X_digits = digits.data[10:,:]\n",
"y_digits = digits.target[10:]\n",
"\n",
"automl_config = AutoMLConfig(task = 'classification',\n",
" debug_log='automl_errors.log',\n",
" primary_metric='AUC_weighted',\n",
" iterations=3,\n",
" n_cross_validations=2,\n",
" verbosity=logging.INFO,\n",
" X = X_digits, \n",
" y = y_digits,\n",
" path=project_folder)\n",
"\n",
"local_run = experiment.submit(automl_config, show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 3. Retrieve the SDK versions from RunHistory"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To get the SDK versions from RunHistory, first the RunId need to be recorded. This can either be done by copy it from the output message or retieve if after each run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run_id = local_run.id\n",
"print(run_id)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Initialize a new AutoMLRunClass."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'automl-local-classification'\n",
"#run_id = 'AutoML_c0585b1f-a0e6-490b-84c7-3a099468b28e'\n",
"\n",
"experiment = Experiment(ws, experiment_name)\n",
"ml_run = AutoMLRun(experiment=experiment, run_id=run_id)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Get parent training SDK versions."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ml_run.get_run_sdk_dependencies()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Get the traning SDK versions of a specific run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ml_run.get_run_sdk_dependencies(iteration=2)"
]
}
],
"metadata": {
"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
}

1120
automl/13.auto-ml-dataprep.ipynb
View File

File diff suppressed because it is too large Load Diff

118
automl/README.md
View File

@@ -1,52 +1,24 @@
# Table of Contents # Table of Contents
1. [Automated ML Introduction](#introduction) 1. [Auto ML Introduction](#introduction)
1. [Running samples in Azure Notebooks](#jupyter) 2. [Running samples in a Local Conda environment](#localconda)
1. [Running samples in a Local Conda environment](#localconda) 3. [Auto ML SDK Sample Notebooks](#samples)
1. [Automated ML SDK Sample Notebooks](#samples) 4. [Documentation](#documentation)
1. [Documentation](#documentation) 5. [Running using python command](#pythoncommand)
1. [Running using python command](#pythoncommand) 6. [Troubleshooting](#troubleshooting)
1. [Troubleshooting](#troubleshooting)
<a name="introduction"></a>
# Automated ML introduction
Automated machine learning (automated ML) builds high quality machine learning models for you by automating model and hyperparameter selection. Bring a labelled dataset that you want to build a model for, automated ML will give you a high quality machine learning model that you can use for predictions.
# Auto ML Introduction <a name="introduction"></a>
AutoML builds high quality Machine Learning models for you by automating model and hyperparameter selection. Bring a labelled dataset that you want to build a model for, AutoML will give you a high quality machine learning model that you can use for predictions.
If you are new to Data Science, AutoML will help you get jumpstarted by simplifying machine learning model building. It abstracts you from needing to perform model selection, hyperparameter selection and in one step creates a high quality trained model for you to use. If you are new to Data Science, AutoML will help you get jumpstarted by simplifying machine learning model building. It abstracts you from needing to perform model selection, hyperparameter selection and in one step creates a high quality trained model for you to use.
If you are an experienced data scientist, AutoML will help increase your productivity by intelligently performing the model and hyperparameter selection for your training and generates high quality models much quicker than manually specifying several combinations of the parameters and running training jobs. AutoML provides visibility and access to all the training jobs and the performance characteristics of the models to help you further tune the pipeline if you desire. If you are an experienced data scientist, AutoML will help increase your productivity by intelligently performing the model and hyperparameter selection for your training and generates high quality models much quicker than manually specifying several combinations of the parameters and running training jobs. AutoML provides visibility and access to all the training jobs and the performance characteristics of the models to help you further tune the pipeline if you desire.
<a name="jupyter"></a>
## Running samples in Azure Notebooks - Jupyter based notebooks in the Azure cloud
1. [![Azure Notebooks](https://notebooks.azure.com/launch.png)](https://aka.ms/aml-clone-azure-notebooks) # Running samples in a Local Conda environment <a name="localconda"></a>
[Import sample notebooks ](https://aka.ms/aml-clone-azure-notebooks) into Azure Notebooks.
1. Follow the instructions in the [../00.configuration](00.configuration.ipynb) notebook to create and connect to a workspace.
1. Open one of the sample notebooks.
**Make sure the Azure Notebook kernel is set to `Python 3.6`** when you open a notebook.
![set kernel to Python 3.6](../images/python36.png)
<a name="localconda"></a> You can run these notebooks in Azure Notebooks without any extra installation. To run these notebook on your own notebook server, use these installation instructions.
## Running samples in a Local Conda environment
To run these notebook on your own notebook server, use these installation instructions.
The instructions below will install everything you need and then start a Jupyter notebook. To start your Jupyter notebook manually, use:
```
conda activate azure_automl
jupyter notebook
```
or on Mac:
```
source activate azure_automl
jupyter notebook
```
It is best if you create a new conda environment locally to try this SDK, so it doesn't mess up with your existing Python environment.
### 1. Install mini-conda from [here](https://conda.io/miniconda.html), choose Python 3.7 or higher. ### 1. Install mini-conda from [here](https://conda.io/miniconda.html), choose Python 3.7 or higher.
- **Note**: if you already have conda installed, you can keep using it but it should be version 4.4.10 or later (as shown by: conda -V). If you have a previous version installed, you can update it using the command: conda update conda. - **Note**: if you already have conda installed, you can keep using it but it should be version 4.4.10 or later (as shown by: conda -V). If you have a previous version installed, you can update it using the command: conda update conda.
@@ -76,19 +48,19 @@ bash automl_setup_mac.sh
cd to the **automl** folder where the sample notebooks were extracted and then run: cd to the **automl** folder where the sample notebooks were extracted and then run:
``` ```
bash automl_setup_linux.sh automl_setup_linux.sh
``` ```
### 4. Running configuration.ipynb ### 4. Running configuration.ipynb
- Before running any samples you next need to run the configuration notebook. Click on 00.configuration.ipynb notebook - Before running any samples you next need to run the configuration notebook. Click on 00.configuration.ipynb notebook
- Please make sure you use the Python [conda env:azure_automl] kernel when running this notebook.
- Execute the cells in the notebook to Register Machine Learning Services Resource Provider and create a workspace. (*instructions in notebook*) - Execute the cells in the notebook to Register Machine Learning Services Resource Provider and create a workspace. (*instructions in notebook*)
### 5. Running Samples ### 5. Running Samples
- Please make sure you use the Python [conda env:azure_automl] kernel when trying the sample Notebooks. - Please make sure you use the Python [conda env:azure_automl] kernel when trying the sample Notebooks.
- Follow the instructions in the individual notebooks to explore various features in AutoML - Follow the instructions in the individual notebooks to explore various features in AutoML
<a name="samples"></a> # Auto ML SDK Sample Notebooks <a name="samples"></a>
# Automated ML SDK Sample Notebooks
- [00.configuration.ipynb](00.configuration.ipynb) - [00.configuration.ipynb](00.configuration.ipynb)
- Register Machine Learning Services Resource Provider - Register Machine Learning Services Resource Provider
- Create new Azure ML Workspace - Create new Azure ML Workspace
@@ -115,7 +87,7 @@ bash automl_setup_linux.sh
- [03b.auto-ml-remote-batchai.ipynb](03b.auto-ml-remote-batchai.ipynb) - [03b.auto-ml-remote-batchai.ipynb](03b.auto-ml-remote-batchai.ipynb)
- Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits) - Dataset: scikit learn's [digit dataset](http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits)
- Example of using automated ML for classification using a remote Batch AI compute for training - Example of using Auto ML for classification using a remote Batch AI compute for training
- Parallel execution of iterations - Parallel execution of iterations
- Async tracking of progress - Async tracking of progress
- Cancelling individual iterations or entire run - Cancelling individual iterations or entire run
@@ -171,17 +143,20 @@ bash automl_setup_linux.sh
- [13.auto-ml-dataprep.ipynb](13.auto-ml-dataprep.ipynb) - [13.auto-ml-dataprep.ipynb](13.auto-ml-dataprep.ipynb)
- Using DataPrep for reading data - Using DataPrep for reading data
<a name="documentation"></a> - [14a.auto-ml-classification-ensemble.ipynb](14a.auto-ml-classification-ensemble.ipynb)
# Documentation - Classification with ensembling
- [14b.auto-ml-regression-ensemble.ipynb](14b.auto-ml-regression-ensemble.ipynb)
- Regression with ensembling
# Documentation <a name="documentation"></a>
## Table of Contents ## Table of Contents
1. [Automated ML Settings ](#automlsettings) 1. [Auto ML Settings ](#automlsettings)
1. [Cross validation split options](#cvsplits) 2. [Cross validation split options](#cvsplits)
1. [Get Data Syntax](#getdata) 3. [Get Data Syntax](#getdata)
1. [Data pre-processing and featurization](#preprocessing) 4. [Data pre-processing and featurization](#preprocessing)
<a name="automlsettings"></a>
## Automated ML Settings
## Auto ML Settings <a name="automlsettings"></a>
|Property|Description|Default| |Property|Description|Default|
|-|-|-| |-|-|-|
|**primary_metric**|This is the metric that you want to optimize.<br><br> Classification supports the following primary metrics <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i><br><br> 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><br><i>normalized_root_mean_squared_log_error</i>| Classification: accuracy <br><br> Regression: spearman_correlation |**primary_metric**|This is the metric that you want to optimize.<br><br> Classification supports the following primary metrics <br><i>accuracy</i><br><i>AUC_weighted</i><br><i>balanced_accuracy</i><br><i>average_precision_score_weighted</i><br><i>precision_score_weighted</i><br><br> 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><br><i>normalized_root_mean_squared_log_error</i>| Classification: accuracy <br><br> Regression: spearman_correlation
@@ -195,8 +170,7 @@ bash automl_setup_linux.sh
|**exit_score**|*double* value indicating the target for *primary_metric*. <br> Once the target is surpassed the run terminates|None| |**exit_score**|*double* value indicating the target for *primary_metric*. <br> Once the target is surpassed the run terminates|None|
|**blacklist_algos**|*Array* of *strings* indicating pipelines to ignore for Auto ML.<br><br> Allowed values for **Classification**<br><i>LogisticRegression</i><br><i>SGDClassifierWrapper</i><br><i>NBWrapper</i><br><i>BernoulliNB</i><br><i>SVCWrapper</i><br><i>LinearSVMWrapper</i><br><i>KNeighborsClassifier</i><br><i>DecisionTreeClassifier</i><br><i>RandomForestClassifier</i><br><i>ExtraTreesClassifier</i><br><i>gradient boosting</i><br><i>LightGBMClassifier</i><br><br>Allowed values for **Regression**<br><i>ElasticNet</i><br><i>GradientBoostingRegressor</i><br><i>DecisionTreeRegressor</i><br><i>KNeighborsRegressor</i><br><i>LassoLars</i><br><i>SGDRegressor</i><br><i>RandomForestRegressor</i><br><i>ExtraTreesRegressor</i>|None| |**blacklist_algos**|*Array* of *strings* indicating pipelines to ignore for Auto ML.<br><br> Allowed values for **Classification**<br><i>LogisticRegression</i><br><i>SGDClassifierWrapper</i><br><i>NBWrapper</i><br><i>BernoulliNB</i><br><i>SVCWrapper</i><br><i>LinearSVMWrapper</i><br><i>KNeighborsClassifier</i><br><i>DecisionTreeClassifier</i><br><i>RandomForestClassifier</i><br><i>ExtraTreesClassifier</i><br><i>gradient boosting</i><br><i>LightGBMClassifier</i><br><br>Allowed values for **Regression**<br><i>ElasticNet</i><br><i>GradientBoostingRegressor</i><br><i>DecisionTreeRegressor</i><br><i>KNeighborsRegressor</i><br><i>LassoLars</i><br><i>SGDRegressor</i><br><i>RandomForestRegressor</i><br><i>ExtraTreesRegressor</i>|None|
<a name="cvsplits"></a> ## Cross validation split options <a name="cvsplits"></a>
## Cross validation split options
### K-Folds Cross Validation ### K-Folds Cross Validation
Use *n_cross_validations* setting to specify the number of cross validations. The training data set will be randomly split into *n_cross_validations* folds of equal size. During each cross validation round, one of the folds will be used for validation of the model trained on the remaining folds. This process repeats for *n_cross_validations* rounds until each fold is used once as validation set. Finally, the average scores accross all *n_cross_validations* rounds will be reported, and the corresponding model will be retrained on the whole training data set. Use *n_cross_validations* setting to specify the number of cross validations. The training data set will be randomly split into *n_cross_validations* folds of equal size. During each cross validation round, one of the folds will be used for validation of the model trained on the remaining folds. This process repeats for *n_cross_validations* rounds until each fold is used once as validation set. Finally, the average scores accross all *n_cross_validations* rounds will be reported, and the corresponding model will be retrained on the whole training data set.
@@ -206,8 +180,7 @@ Use *validation_size* to specify the percentage of the training data set that sh
### Custom train and validation set ### Custom train and validation set
You can specify seperate train and validation set either through the get_data() or directly to the fit method. You can specify seperate train and validation set either through the get_data() or directly to the fit method.
<a name="getdata"></a> ## get_data() syntax <a name="getdata"></a>
## get_data() syntax
The *get_data()* function can be used to return a dictionary with these values: The *get_data()* function can be used to return a dictionary with these values:
|Key|Type|Dependency|Mutually Exclusive with|Description| |Key|Type|Dependency|Mutually Exclusive with|Description|
@@ -223,23 +196,21 @@ The *get_data()* function can be used to return a dictionary with these values:
|columns|Array of strings|data_train||*Optional* Whitelist of columns to use for features| |columns|Array of strings|data_train||*Optional* Whitelist of columns to use for features|
|cv_splits_indices|Array of integers|data_train||*Optional* List of indexes to split the data for cross validation| |cv_splits_indices|Array of integers|data_train||*Optional* List of indexes to split the data for cross validation|
<a name="preprocessing"></a> ## Data pre-processing and featurization <a name="preprocessing"></a>
## Data pre-processing and featurization If you use "preprocess=True", the following data preprocessing steps are performed automatically for you:
If you use `preprocess=True`, the following data preprocessing steps are performed automatically for you: ### 1. Dropping high cardinality or no variance features
- Features with no useful information are dropped from training and validation sets. These include features with all values missing, same value across all rows or with extremely high cardinality (e.g., hashes, IDs or GUIDs).
### 2. Missing value imputation
- For numerical features, missing values are imputed with average of values in the column.
- For categorical features, missing values are imputed with most frequent value.
### 3. Generating additional features
- For DateTime features: Year, Month, Day, Day of week, Day of year, Quarter, Week of the year, Hour, Minute, Second.
- For Text features: Term frequency based on bi-grams and tri-grams, Count vectorizer.
### 4. Transformations and encodings
- Numeric features with very few unique values are transformed into categorical features.
- Depending on cardinality of categorical features label encoding or (hashing) one-hot encoding is performed.
1. Dropping high cardinality or no variance features # Running using python command <a name="pythoncommand"></a>
- Features with no useful information are dropped from training and validation sets. These include features with all values missing, same value across all rows or with extremely high cardinality (e.g., hashes, IDs or GUIDs).
2. Missing value imputation
- For numerical features, missing values are imputed with average of values in the column.
- For categorical features, missing values are imputed with most frequent value.
3. Generating additional features
- For DateTime features: Year, Month, Day, Day of week, Day of year, Quarter, Week of the year, Hour, Minute, Second.
- For Text features: Term frequency based on bi-grams and tri-grams, Count vectorizer.
4. Transformations and encodings
- Numeric features with very few unique values are transformed into categorical features.
<a name="pythoncommand"></a>
# Running using python command
Jupyter notebook provides a File / Download as / Python (.py) option for saving the notebook as a Python file. Jupyter notebook provides a File / Download as / Python (.py) option for saving the notebook as a Python file.
You can then run this file using the python command. You can then run this file using the python command.
However, on Windows the file needs to be modified before it can be run. However, on Windows the file needs to be modified before it can be run.
@@ -249,8 +220,7 @@ The following condition must be added to the main code in the file:
The main code of the file must be indented so that it is under this condition. The main code of the file must be indented so that it is under this condition.
<a name="troubleshooting"></a> # Troubleshooting <a name="troubleshooting"></a>
# Troubleshooting
## Iterations fail and the log contains "MemoryError" ## Iterations fail and the log contains "MemoryError"
This can be caused by insufficient memory on the DSVM. AutoML loads all training data into memory. So, the available memory should be more than the training data size. This can be caused by insufficient memory on the DSVM. AutoML loads all training data into memory. So, the available memory should be more than the training data size.
If you are using a remote DSVM, memory is needed for each concurrent iteration. The concurrent_iterations setting specifies the maximum concurrent iterations. For example, if the training data size is 8Gb and concurrent_iterations is set to 10, the minimum memory required is at least 80Gb. If you are using a remote DSVM, memory is needed for each concurrent iteration. The concurrent_iterations setting specifies the maximum concurrent iterations. For example, if the training data size is 8Gb and concurrent_iterations is set to 10, the minimum memory required is at least 80Gb.

2
automl/automl_env.yml
View File

@@ -8,7 +8,7 @@ dependencies:
- numpy>=1.11.0,<1.16.0 - numpy>=1.11.0,<1.16.0
- scipy>=0.19.0,<0.20.0 - scipy>=0.19.0,<0.20.0
- scikit-learn>=0.18.0,<=0.19.1 - scikit-learn>=0.18.0,<=0.19.1
- pandas>=0.19.0,<0.23.0 - pandas>=0.22.0,<0.23.0
- pip: - pip:
# Required packages for AzureML execution, history, and data preparation. # Required packages for AzureML execution, history, and data preparation.

3
automl/automl_setup.cmd
View File

@@ -6,7 +6,8 @@ IF "%conda_env_name%"=="" SET conda_env_name="azure_automl"
call conda activate %conda_env_name% 2>nul: call conda activate %conda_env_name% 2>nul:
if not errorlevel 1 ( if not errorlevel 1 (
call conda env update --file automl_env.yml -n %conda_env_name% echo Upgrading azureml-sdk[automl] in existing conda environment %conda_env_name%
call pip install --upgrade azureml-sdk[automl]
if errorlevel 1 goto ErrorExit if errorlevel 1 goto ErrorExit
) else ( ) else (
call conda env create -f automl_env.yml -n %conda_env_name% call conda env create -f automl_env.yml -n %conda_env_name%

3
automl/automl_setup_linux.sh
View File

@@ -9,7 +9,8 @@ fi
if source activate $CONDA_ENV_NAME 2> /dev/null if source activate $CONDA_ENV_NAME 2> /dev/null
then then
conda env update -file automl_env.yml -n $CONDA_ENV_NAME echo "Upgrading azureml-sdk[automl] in existing conda environment" $CONDA_ENV_NAME
pip install --upgrade azureml-sdk[automl]
else else
conda env create -f automl_env.yml -n $CONDA_ENV_NAME && conda env create -f automl_env.yml -n $CONDA_ENV_NAME &&
source activate $CONDA_ENV_NAME && source activate $CONDA_ENV_NAME &&

3
automl/automl_setup_mac.sh
View File

@@ -9,7 +9,8 @@ fi
if source activate $CONDA_ENV_NAME 2> /dev/null if source activate $CONDA_ENV_NAME 2> /dev/null
then then
conda env update -file automl_env.yml -n $CONDA_ENV_NAME echo "Upgrading azureml-sdk[automl] in existing conda environment" $CONDA_ENV_NAME
pip install --upgrade azureml-sdk[automl]
else else
conda env create -f automl_env.yml -n $CONDA_ENV_NAME && conda env create -f automl_env.yml -n $CONDA_ENV_NAME &&
source activate $CONDA_ENV_NAME && source activate $CONDA_ENV_NAME &&

23
onnx/README.md
View File

@@ -1,23 +0,0 @@
# ONNX Runtime on Azure Machine Learning (AML)
These tutorials show how to deploy pretrained [ONNX](http://onnx.ai) models on Azure virtual machines using [ONNX Runtime](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-build-deploy-onnx) for inference. By the end of the tutorial, you will deploy a state-of-the-art deep learning model on a virtual machine in Azure Machine Learning, using ONNX Runtime for Inference. You can ping the model with your own images to be analyzed!
## Tutorials
- [Handwritten Digit Classification (MNIST) using ONNX Runtime on AzureML](https://github.com/Azure/MachineLearningNotebooks/blob/master/onnx/onnx-inference-mnist.ipynb)
- [Facial Expression Recognition using ONNX Runtime on AzureML](https://github.com/Azure/MachineLearningNotebooks/blob/master/onnx/onnx-inference-emotion-recognition.ipynb)
## Documentation
- [ONNX Runtime Python API Documentation](http://aka.ms/onnxruntime-python)
- [Azure Machine Learning API Documentation](http://aka.ms/aml-docs)
## Related Articles
- [Building and Deploying ONNX Runtime Models](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-build-deploy-onnx)
- [Azure AI – Making AI Real for Business](https://aka.ms/aml-blog-overview)
- [What’s new in Azure Machine Learning](https://aka.ms/aml-blog-whats-new)
## License
Copyright (c) Microsoft Corporation. All rights reserved.
Licensed under the MIT License.

1533
onnx/onnx-inference-emotion-recognition.ipynb
View File

File diff suppressed because it is too large Load Diff

1561
onnx/onnx-inference-mnist.ipynb
View File

File diff suppressed because it is too large Load Diff

148
pipeline/00.pipeline-setup.ipynb
View File

@@ -1,76 +1,76 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Packages"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install pandas\n",
"!pip install requests"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Widgets\n",
"Install the following widgets to see the status of each run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!jupyter nbextension install --py --user azureml.train.widgets\n",
"!jupyter nbextension enable --py --user azureml.train.widgets"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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"
}
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# Packages"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install pandas\n",
"!pip install requests"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Widgets\n",
"Install the following widgets to see the status of each run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!jupyter nbextension install --py --user azureml.train.widgets\n",
"!jupyter nbextension enable --py --user azureml.train.widgets"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

1240
pipeline/pipeline-batch-scoring.ipynb
View File

File diff suppressed because it is too large Load Diff

1230
project-brainwave/project-brainwave-custom-weights.ipynb
View File

File diff suppressed because it is too large Load Diff

614
project-brainwave/project-brainwave-quickstart.ipynb
View File

@@ -1,309 +1,309 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Azure ML Hardware Accelerated Models Quickstart"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This tutorial will show you how to deploy an image recognition service based on the ResNet 50 classifier in just a few minutes using the Azure Machine Learning Accelerated AI service. Get more help from our [documentation](https://aka.ms/aml-real-time-ai) or [forum](https://aka.ms/aml-forum).\n",
"\n",
"We will use an accelerated ResNet50 featurizer running on an FPGA. This functionality is powered by Project Brainwave, which handles translating deep neural networks (DNN) into an FPGA program.\n",
"\n",
"## Request Quota\n",
"**IMPORTANT:** You must [request quota](https://aka.ms/aml-real-time-ai-request) and be approved before you can successfully run this notebook. Notebook 00 will show you how to create a workspace which you can use to request quota."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Imports"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import tensorflow as tf"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Image preprocessing\n",
"We'd like our service to accept JPEG images as input. However the input to ResNet50 is a tensor. So we need code that decodes JPEG images and does the preprocessing required by ResNet50. 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 strings) and produces a tensor that is ready to be featurized by ResNet50."
]
},
{
"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.contrib.brainwave.models.utils as utils\n",
"in_images = tf.placeholder(tf.string)\n",
"image_tensors = utils.preprocess_array(in_images)\n",
"print(image_tensors.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Featurizer\n",
"We use ResNet50 as a featurizer. In this step we initialize the model. This downloads a TensorFlow checkpoint of the quantized ResNet50."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.contrib.brainwave.models import QuantizedResnet50, Resnet50\n",
"model_path = os.path.expanduser('~/models')\n",
"model = QuantizedResnet50(model_path, is_frozen = True)\n",
"feature_tensor = model.import_graph_def(image_tensors)\n",
"print(model.version)\n",
"print(feature_tensor.name)\n",
"print(feature_tensor.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Classifier\n",
"The model we downloaded includes a classifier which takes the output of the ResNet50 and identifies an image. This classifier is trained on the ImageNet dataset. We are going to use this classifier for our service. The next [notebook](project-brainwave-trainsfer-learning.ipynb) shows how to train a classifier for a different data set. The input to the classifier is a tensor matching the output of our ResNet50 featurizer."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"classifier_output = model.get_default_classifier(feature_tensor)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Service Definition\n",
"Now that we've definied the image preprocessing, featurizer, and classifier that we will execute on our service we can create a service definition. The service definition is a set of files generated from the model that allow us to deploy to the FPGA service. The service definition consists of a pipeline. The pipeline is a series of stages that are executed in order. We support TensorFlow stages, Keras stages, and BrainWave stages. The stages will be executed in order on the service, with the output of each stage input into the subsequent stage.\n",
"\n",
"To create a TensorFlow stage we specify a session containing the graph (in this case we are using the default graph) and the input and output tensors to this stage. We use this information to save the graph so that we can execute it on the service."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.contrib.brainwave.pipeline import ModelDefinition, TensorflowStage, BrainWaveStage\n",
"\n",
"save_path = os.path.expanduser('~/models/save')\n",
"model_def_path = os.path.join(save_path, 'model_def.zip')\n",
"\n",
"model_def = ModelDefinition()\n",
"with tf.Session() as sess:\n",
" model_def.pipeline.append(TensorflowStage(sess, in_images, image_tensors))\n",
" model_def.pipeline.append(BrainWaveStage(sess, model))\n",
" model_def.pipeline.append(TensorflowStage(sess, classifier_input, classifier_output))\n",
" model_def.save(model_def_path)\n",
" print(model_def_path)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Deploy\n",
"Time to create a service from the service definition. You need a Workspace in the **East US 2** location. In the previous notebooks, you've created this Workspace. The code below will load that Workspace from a configuration file."
]
},
{
"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": [
"Upload the model to the workspace."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.model import Model\n",
"model_name = \"resnet-50-rtai\"\n",
"registered_model = Model.register(ws, model_def_path, model_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Create a service from the model that we registered. If this is a new service then we create it. If you already have a service with this name then the existing service will be updated to use this model."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.webservice import Webservice\n",
"from azureml.exceptions import WebserviceException\n",
"from azureml.contrib.brainwave import BrainwaveWebservice, BrainwaveImage\n",
"service_name = \"imagenet-infer\"\n",
"service = None\n",
"try:\n",
" service = Webservice(ws, service_name)\n",
"except WebserviceException:\n",
" image_config = BrainwaveImage.image_configuration()\n",
" deployment_config = BrainwaveWebservice.deploy_configuration()\n",
" service = Webservice.deploy_from_model(ws, service_name, [registered_model], image_config, deployment_config)\n",
" service.wait_for_deployment(true)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Client\n",
"The service supports gRPC and the TensorFlow Serving \"predict\" API. We provide a client that can call the service to get predictions on aka.ms/rtai. You can also invoke the service like any other web service."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To understand the results we need a mapping to the human readable imagenet classes"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"classes_entries = requests.get(\"https://raw.githubusercontent.com/Lasagne/Recipes/master/examples/resnet50/imagenet_classes.txt\").text.splitlines()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can now send an image to the service and get the predictions. Let's see if it can identify a snow leopard.\n",
"![title](snowleopardgaze.jpg)\n",
"Snow leopard in a zoo. Photo by Peter Bolliger.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"results = service.run('snowleopardgaze.jpg')\n",
"# map results [class_id] => [confidence]\n",
"results = enumerate(results)\n",
"# sort results by confidence\n",
"sorted_results = sorted(results, key=lambda x: x[1], reverse=True)\n",
"# print top 5 results\n",
"for top in sorted_results[:5]:\n",
" print(classes_entries[top[0]], 'confidence:', top[1])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Cleanup\n",
"Run the cell below to delete your service."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"service.delete()\n",
" \n",
"registered_model.delete()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Congratulations! You've just created a service that does predictions using an FPGA. The next [notebook](project-brainwave-trainsfer-learning.ipynb) shows how to customize the service using transfer learning to classify different types of images."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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": "3.5.2"
}
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# Azure ML Hardware Accelerated Models Quickstart"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This tutorial will show you how to deploy an image recognition service based on the ResNet 50 classifier in just a few minutes using the Azure Machine Learning Accelerated AI service. Get more help from our [documentation](https://aka.ms/aml-real-time-ai) or [forum](https://aka.ms/aml-forum).\n",
"\n",
"We will use an accelerated ResNet50 featurizer running on an FPGA. This functionality is powered by Project Brainwave, which handles translating deep neural networks (DNN) into an FPGA program.\n",
"\n",
"## Request Quota\n",
"**IMPORTANT:** You must [request quota](https://aka.ms/aml-real-time-ai-request) and be approved before you can successfully run this notebook. Notebook 00 will show you how to create a workspace which you can use to request quota."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Imports"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import tensorflow as tf"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Image preprocessing\n",
"We'd like our service to accept JPEG images as input. However the input to ResNet50 is a tensor. So we need code that decodes JPEG images and does the preprocessing required by ResNet50. 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 strings) and produces a tensor that is ready to be featurized by ResNet50."
]
},
{
"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.contrib.brainwave.models.utils as utils\n",
"in_images = tf.placeholder(tf.string)\n",
"image_tensors = utils.preprocess_array(in_images)\n",
"print(image_tensors.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Featurizer\n",
"We use ResNet50 as a featurizer. In this step we initialize the model. This downloads a TensorFlow checkpoint of the quantized ResNet50."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.contrib.brainwave.models import QuantizedResnet50, Resnet50\n",
"model_path = os.path.expanduser('~/models')\n",
"model = QuantizedResnet50(model_path, is_frozen = True)\n",
"feature_tensor = model.import_graph_def(image_tensors)\n",
"print(model.version)\n",
"print(feature_tensor.name)\n",
"print(feature_tensor.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Classifier\n",
"The model we downloaded includes a classifier which takes the output of the ResNet50 and identifies an image. This classifier is trained on the ImageNet dataset. We are going to use this classifier for our service. The next [notebook](project-brainwave-trainsfer-learning.ipynb) shows how to train a classifier for a different data set. The input to the classifier is a tensor matching the output of our ResNet50 featurizer."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"classifier_input, classifier_output = Resnet50.get_default_classifier(feature_tensor, model_path)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Service Definition\n",
"Now that we've definied the image preprocessing, featurizer, and classifier that we will execute on our service we can create a service definition. The service definition is a set of files generated from the model that allow us to deploy to the FPGA service. The service definition consists of a pipeline. The pipeline is a series of stages that are executed in order. We support TensorFlow stages, Keras stages, and BrainWave stages. The stages will be executed in order on the service, with the output of each stage input into the subsequent stage.\n",
"\n",
"To create a TensorFlow stage we specify a session containing the graph (in this case we are using the default graph) and the input and output tensors to this stage. We use this information to save the graph so that we can execute it on the service."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.contrib.brainwave.pipeline import ModelDefinition, TensorflowStage, BrainWaveStage\n",
"\n",
"save_path = os.path.expanduser('~/models/save')\n",
"model_def_path = os.path.join(save_path, 'model_def.zip')\n",
"\n",
"model_def = ModelDefinition()\n",
"with tf.Session() as sess:\n",
" model_def.pipeline.append(TensorflowStage(sess, in_images, image_tensors))\n",
" model_def.pipeline.append(BrainWaveStage(sess, model))\n",
" model_def.pipeline.append(TensorflowStage(sess, classifier_input, classifier_output))\n",
" model_def.save(model_def_path)\n",
" print(model_def_path)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Deploy\n",
"Time to create a service from the service definition. You need a Workspace in the **East US 2** location. In the previous notebooks, you've created this Workspace. The code below will load that Workspace from a configuration file."
]
},
{
"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": [
"Upload the model to the workspace."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.model import Model\n",
"model_name = \"resnet-50-rtai\"\n",
"registered_model = Model.register(ws, model_def_path, model_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Create a service from the model that we registered. If this is a new service then we create it. If you already have a service with this name then the existing service will be updated to use this model."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.webservice import Webservice\n",
"from azureml.exceptions import WebserviceException\n",
"from azureml.contrib.brainwave import BrainwaveWebservice, BrainwaveImage\n",
"service_name = \"imagenet-infer\"\n",
"service = None\n",
"try:\n",
" service = Webservice(ws, service_name)\n",
"except WebserviceException:\n",
" image_config = BrainwaveImage.image_configuration()\n",
" deployment_config = BrainwaveWebservice.deploy_configuration()\n",
" service = Webservice.deploy_from_model(ws, service_name, [registered_model], image_config, deployment_config)\n",
" service.wait_for_deployment(true)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Client\n",
"The service supports gRPC and the TensorFlow Serving \"predict\" API. We provide a client that can call the service to get predictions on aka.ms/rtai. You can also invoke the service like any other web service."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To understand the results we need a mapping to the human readable imagenet classes"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"classes_entries = requests.get(\"https://raw.githubusercontent.com/Lasagne/Recipes/master/examples/resnet50/imagenet_classes.txt\").text.splitlines()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can now send an image to the service and get the predictions. Let's see if it can identify a snow leopard.\n",
"![title](snowleopardgaze.jpg)\n",
"Snow leopard in a zoo. Photo by Peter Bolliger.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"results = service.run('snowleopardgaze.jpg')\n",
"# map results [class_id] => [confidence]\n",
"results = enumerate(results)\n",
"# sort results by confidence\n",
"sorted_results = sorted(results, key=lambda x: x[1], reverse=True)\n",
"# print top 5 results\n",
"for top in sorted_results[:5]:\n",
" print(classes_entries[top[0]], 'confidence:', top[1])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Cleanup\n",
"Run the cell below to delete your service."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"service.delete()\n",
" \n",
"registered_model.delete()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Congratulations! You've just created a service that does predictions using an FPGA. The next [notebook](project-brainwave-trainsfer-learning.ipynb) shows how to customize the service using transfer learning to classify different types of images."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

1130
project-brainwave/project-brainwave-transfer-learning.ipynb
View File

File diff suppressed because it is too large Load Diff

1516
training/01.train-hyperparameter-tune-deploy-with-pytorch/01.train-hyperparameter-tune-deploy-with-pytorch.ipynb
View File

File diff suppressed because it is too large Load Diff

574
training/02.distributed-pytorch-with-horovod/02.distributed-pytorch-with-horovod.ipynb
View File

@@ -1,289 +1,289 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 02. Distributed PyTorch with Horovod\n",
"In this tutorial, you will train a PyTorch model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using distributed training via [Horovod](https://github.com/uber/horovod)."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-pytorch) on single-node PyTorch training using the SDK"
]
},
{
"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](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 a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\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 = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_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 the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code creates a GPU cluster. If you instead want to create a CPU cluster, 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 cluster 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 = './pytorch-distr-hvd'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `pytorch_horovod_mnist.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('pytorch_horovod_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 PyTorch tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'pytorch-distr-hvd'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a PyTorch estimator\n",
"The AML SDK's PyTorch estimator enables you to easily submit PyTorch training jobs for both single-node and distributed runs. For more information on the PyTorch estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-pytorch)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import PyTorch\n",
"\n",
"estimator = PyTorch(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" entry_script='pytorch_horovod_mnist.py',\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi',\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/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, PyTorch, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `PyTorch` 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.get_details())"
]
},
{
"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."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True) # this provides a verbose log"
]
}
],
"metadata": {
"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"
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# 02. Distributed PyTorch with Horovod\n",
"In this tutorial, you will train a PyTorch model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using distributed training via [Horovod](https://github.com/uber/horovod)."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-pytorch) on single-node PyTorch training using the SDK"
]
},
{
"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](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 a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\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 = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_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 the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code creates a GPU cluster. If you instead want to create a CPU cluster, 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 cluster 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 = './pytorch-distr-hvd'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `pytorch_horovod_mnist.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('pytorch_horovod_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 PyTorch tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'pytorch-distr-hvd'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a PyTorch estimator\n",
"The AML SDK's PyTorch estimator enables you to easily submit PyTorch training jobs for both single-node and distributed runs. For more information on the PyTorch estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-pytorch)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import PyTorch\n",
"\n",
"estimator = PyTorch(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" entry_script='pytorch_horovod_mnist.py',\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi',\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/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, PyTorch, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `PyTorch` 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.get_details())"
]
},
{
"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."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True) # this provides a verbose log"
]
}
],
"metadata": {
"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"
},
"nbformat": 4,
"nbformat_minor": 2
}

3240
training/03.train-hyperparameter-tune-deploy-with-tensorflow/03.train-hyperparameter-tune-deploy-with-tensorflow.ipynb
View File

File diff suppressed because it is too large Load Diff

716
training/04.distributed-tensorflow-with-horovod/04.distributed-tensorflow-with-horovod.ipynb
View File

@@ -1,360 +1,360 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 04. Distributed Tensorflow with Horovod\n",
"In this tutorial, you will train a word2vec model in TensorFlow using distributed training via [Horovod](https://github.com/uber/horovod)."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
]
},
{
"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",
"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 a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\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 = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_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 the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code creates a GPU cluster. If you instead want to create a CPU cluster, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Upload data to datastore\n",
"To make data accessible for remote training, AML provides a convenient way to do so via a [Datastore](https://docs.microsoft.com/azure/machine-learning/service/how-to-access-data). The datastore provides a mechanism for you to upload/download data to Azure Storage, and interact with it from your remote compute targets. \n",
"\n",
"If your data is already stored in Azure, or you download the data as part of your training script, you will not need to do this step. For this tutorial, although you can download the data in your training script, we will demonstrate how to upload the training data to a datastore and access it during training to illustrate the datastore functionality."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, download the training data from [here](http://mattmahoney.net/dc/text8.zip) to your local machine:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import urllib\n",
"\n",
"os.makedirs('./data', exist_ok=True)\n",
"download_url = 'http://mattmahoney.net/dc/text8.zip'\n",
"urllib.request.urlretrieve(download_url, filename='./data/text8.zip')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore. The below code will upload the contents of the data directory to the path `./data` on the default datastore."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds = ws.get_default_datastore()\n",
"print(ds.datastore_type, ds.account_name, ds.container_name)\n",
"\n",
"ds.upload(src_dir='data', target_path='data', overwrite=True, show_progress=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For convenience, let's get a reference to the path on the datastore with the zip file of training data. We can do so using the `path` method. In the next section, we can then pass this reference to our training script's `--input_data` argument. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"path_on_datastore = 'data/text8.zip'\n",
"ds_data = ds.path(path_on_datastore)\n",
"print(ds_data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute"
]
},
{
"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": [
"project_folder = './tf-distr-hvd'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `tf_horovod_word2vec.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('tf_horovod_word2vec.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 TensorFlow tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'tf-distr-hvd'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a TensorFlow estimator\n",
"The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import TensorFlow\n",
"\n",
"script_params={\n",
" '--input_data': ds_data\n",
"}\n",
"\n",
"estimator= TensorFlow(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" script_params=script_params,\n",
" entry_script='tf_horovod_word2vec.py',\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi',\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/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, TensorFlow, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters.\n",
"\n",
"Note that we passed our training data reference `ds_data` to our script's `--input_data` argument. This will 1) mount our datastore on the remote compute and 2) provide the path to the data zip file on our datastore."
]
},
{
"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."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
}
],
"metadata": {
"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"
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# 04. Distributed Tensorflow with Horovod\n",
"In this tutorial, you will train a word2vec model in TensorFlow using distributed training via [Horovod](https://github.com/uber/horovod)."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
]
},
{
"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",
"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 a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\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 = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_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 the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code creates a GPU cluster. If you instead want to create a CPU cluster, provide a different VM size to the `vm_size` parameter, such as `STANDARD_D2_V2`."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Upload data to datastore\n",
"To make data accessible for remote training, AML provides a convenient way to do so via a [Datastore](https://docs.microsoft.com/azure/machine-learning/service/how-to-access-data). The datastore provides a mechanism for you to upload/download data to Azure Storage, and interact with it from your remote compute targets. \n",
"\n",
"If your data is already stored in Azure, or you download the data as part of your training script, you will not need to do this step. For this tutorial, although you can download the data in your training script, we will demonstrate how to upload the training data to a datastore and access it during training to illustrate the datastore functionality."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, download the training data from [here](http://mattmahoney.net/dc/text8.zip) to your local machine:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import urllib\n",
"\n",
"os.makedirs('./data', exist_ok=True)\n",
"download_url = 'http://mattmahoney.net/dc/text8.zip'\n",
"urllib.request.urlretrieve(download_url, filename='./data/text8.zip')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore. The below code will upload the contents of the data directory to the path `./data` on the default datastore."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds = ws.get_default_datastore()\n",
"print(ds.datastore_type, ds.account_name, ds.container_name)\n",
"\n",
"ds.upload(src_dir='data', target_path='data', overwrite=True, show_progress=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For convenience, let's get a reference to the path on the datastore with the zip file of training data. We can do so using the `path` method. In the next section, we can then pass this reference to our training script's `--input_data` argument. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"path_on_datastore = 'data/text8.zip'\n",
"ds_data = ds.path(path_on_datastore)\n",
"print(ds_data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute"
]
},
{
"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": [
"project_folder = './tf-distr-hvd'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `tf_horovod_word2vec.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('tf_horovod_word2vec.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 TensorFlow tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'tf-distr-hvd'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a TensorFlow estimator\n",
"The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import TensorFlow\n",
"\n",
"script_params={\n",
" '--input_data': ds_data\n",
"}\n",
"\n",
"estimator= TensorFlow(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" script_params=script_params,\n",
" entry_script='tf_horovod_word2vec.py',\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi',\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/Horovod, you must provide the argument `distributed_backend='mpi'`. Using this estimator with these settings, TensorFlow, Horovod and their dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` constructor's `pip_packages` or `conda_packages` parameters.\n",
"\n",
"Note that we passed our training data reference `ds_data` to our script's `--input_data` argument. This will 1) mount our datastore on the remote compute and 2) provide the path to the data zip file on our datastore."
]
},
{
"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."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
}
],
"metadata": {
"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"
},
"nbformat": 4,
"nbformat_minor": 2
}

568
training/05.distributed-tensorflow-with-parameter-server/05.distributed-tensorflow-with-parameter-server.ipynb
View File

@@ -1,286 +1,286 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 05. Distributed TensorFlow with parameter server\n",
"In this tutorial, you will train a TensorFlow model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using native [distributed TensorFlow](https://www.tensorflow.org/deploy/distributed)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
]
},
{
"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",
"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 a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\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 = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_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 the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster 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 = './tf-distr-ps'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `tf_mnist_replica.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('tf_mnist_replica.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 TensorFlow tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'tf-distr-ps'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a TensorFlow estimator\n",
"The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import TensorFlow\n",
"\n",
"script_params={\n",
" '--num_gpus': 1\n",
"}\n",
"\n",
"estimator = TensorFlow(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" script_params=script_params,\n",
" entry_script='tf_mnist_replica.py',\n",
" node_count=2,\n",
" worker_count=2,\n",
" parameter_server_count=1, \n",
" distributed_backend='ps',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code specifies that we will run our training script on `2` nodes, with two workers and one parameter server. In order to execute a native distributed TensorFlow run, you must provide the argument `distributed_backend='ps'`. Using this estimator with these settings, TensorFlow and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` 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.get_details())"
]
},
{
"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."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True) # this provides a verbose log"
]
}
],
"metadata": {
"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"
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# 05. Distributed TensorFlow with parameter server\n",
"In this tutorial, you will train a TensorFlow model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using native [distributed TensorFlow](https://www.tensorflow.org/deploy/distributed)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"* Understand the [architecture and terms](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture) introduced by Azure Machine Learning (AML)\n",
"* Go through the [00.configuration.ipynb](https://github.com/Azure/MachineLearningNotebooks/blob/master/00.configuration.ipynb) notebook to:\n",
" * install the AML SDK\n",
" * create a workspace and its configuration file (`config.json`)\n",
"* Review the [tutorial](https://aka.ms/aml-notebook-hyperdrive) on single-node TensorFlow training using the SDK"
]
},
{
"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",
"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 a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\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 = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_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 the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster 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 = './tf-distr-ps'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `tf_mnist_replica.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('tf_mnist_replica.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 TensorFlow tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'tf-distr-ps'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create a TensorFlow estimator\n",
"The AML SDK's TensorFlow estimator enables you to easily submit TensorFlow training jobs for both single-node and distributed runs. For more information on the TensorFlow estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-tensorflow)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.dnn import TensorFlow\n",
"\n",
"script_params={\n",
" '--num_gpus': 1\n",
"}\n",
"\n",
"estimator = TensorFlow(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" script_params=script_params,\n",
" entry_script='tf_mnist_replica.py',\n",
" node_count=2,\n",
" worker_count=2,\n",
" parameter_server_count=1, \n",
" distributed_backend='ps',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The above code specifies that we will run our training script on `2` nodes, with two workers and one parameter server. In order to execute a native distributed TensorFlow run, you must provide the argument `distributed_backend='ps'`. Using this estimator with these settings, TensorFlow and its dependencies will be installed for you. However, if your script also uses other packages, make sure to install them via the `TensorFlow` 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.get_details())"
]
},
{
"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."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True) # this provides a verbose log"
]
}
],
"metadata": {
"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"
},
"nbformat": 4,
"nbformat_minor": 2
}

724
training/06.distributed-cntk-with-custom-docker/06.distributed-cntk-with-custom-docker.ipynb
View File

@@ -1,364 +1,364 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 06. Distributed CNTK using custom docker images\n",
"In this tutorial, you will train a CNTK model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using a custom docker image and distributed training."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\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",
"* Go through the [00.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": [
"## Initialize workspace\n",
"\n",
"Initialize a [Workspace](https://review.docs.microsoft.com/en-us/azure/machine-learning/service/concept-azure-machine-learning-architecture?branch=release-ignite-aml#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 a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\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 = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_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 the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Upload training data\n",
"For this tutorial, we will be using the MNIST dataset.\n",
"\n",
"First, let's download the dataset. We've included the `install_mnist.py` script to download the data and convert it to a CNTK-supported format. Our data files will get written to a directory named `'mnist'`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import install_mnist\n",
"\n",
"install_mnist.main('mnist')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To make the data accessible for remote training, you will need to upload the data from your local machine to the cloud. AML provides a convenient way to do so via a [Datastore](https://docs.microsoft.com/azure/machine-learning/service/how-to-access-data). The datastore provides a mechanism for you to upload/download data, and interact with it from your remote compute targets. \n",
"\n",
"Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore, which we will then mount on the remote compute for training in the next section."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds = ws.get_default_datastore()\n",
"print(ds.datastore_type, ds.account_name, ds.container_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The following code will upload the training data to the path `./mnist` on the default datastore."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds.upload(src_dir='./mnist', target_path='./mnist')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now let's get a reference to the path on the datastore with the training data. We can do so using the `path` method. In the next section, we can then pass this reference to our training script's `--data_dir` argument. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"path_on_datastore = 'mnist'\n",
"ds_data = ds.path(path_on_datastore)\n",
"print(ds_data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster 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 = './cntk-distr'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `cntk_distr_mnist.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('cntk_distr_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 CNTK tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'cntk-distr'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an Estimator\n",
"The AML SDK's base Estimator enables you to easily submit custom scripts for both single-node and distributed runs. You should this generic estimator for training code using frameworks such as sklearn or CNTK that don't have corresponding custom estimators. For more information on using the generic estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-ml-models)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.estimator import *\n",
"\n",
"script_params = {\n",
" '--num_epochs': 50,\n",
" '--data_dir': ds_data.as_mount(),\n",
" '--output_dir': './outputs'\n",
"}\n",
"\n",
"estimator = Estimator(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" entry_script='cntk_distr_mnist.py',\n",
" script_params=script_params,\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi', \n",
" pip_packages=['cntk-gpu==2.6'],\n",
" custom_docker_base_image='microsoft/mmlspark:gpu-0.12',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We would like to train our model using a [pre-built Docker container](https://hub.docker.com/r/microsoft/mmlspark/). To do so, specify the name of the docker image to the argument `custom_docker_base_image`. You can only provide images available in public docker repositories such as Docker Hub using this argument. To use an image from a private docker repository, use the constructor's `environment_definition` parameter instead. Finally, we provide the `cntk` package to `pip_packages` to install CNTK 2.6 on our custom image.\n",
"\n",
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to run distributed CNTK, which uses MPI, you must provide the argument `distributed_backend='mpi'`."
]
},
{
"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.get_details())"
]
},
{
"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."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
}
],
"metadata": {
"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,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# 06. Distributed CNTK using custom docker images\n",
"In this tutorial, you will train a CNTK model on the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset using a custom docker image and distributed training."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\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",
"* Go through the [00.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": [
"## Initialize workspace\n",
"\n",
"Initialize a [Workspace](https://review.docs.microsoft.com/en-us/azure/machine-learning/service/concept-azure-machine-learning-architecture?branch=release-ignite-aml#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 a remote compute target\n",
"You will need to create a [compute target](https://docs.microsoft.com/azure/machine-learning/service/concept-azure-machine-learning-architecture#compute-target) to execute your training script on. In this tutorial, you create an [Azure Batch AI](https://docs.microsoft.com/azure/batch-ai/overview) cluster as your training compute resource. This code creates a cluster for you if it does not already exist in your workspace.\n",
"\n",
"**Creation of the cluster takes approximately 5 minutes.** If the cluster is already in your workspace this code will skip the cluster creation process."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.compute import ComputeTarget, BatchAiCompute\n",
"from azureml.core.compute_target import ComputeTargetException\n",
"\n",
"# choose a name for your cluster\n",
"cluster_name = \"gpucluster\"\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 = BatchAiCompute.provisioning_configuration(vm_size='STANDARD_NC6', \n",
" autoscale_enabled=True,\n",
" cluster_min_nodes=0, \n",
" cluster_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 the 'status' property to get a detailed status for the current cluster. \n",
" print(compute_target.status.serialize())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Upload training data\n",
"For this tutorial, we will be using the MNIST dataset.\n",
"\n",
"First, let's download the dataset. We've included the `install_mnist.py` script to download the data and convert it to a CNTK-supported format. Our data files will get written to a directory named `'mnist'`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import install_mnist\n",
"\n",
"install_mnist.main('mnist')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To make the data accessible for remote training, you will need to upload the data from your local machine to the cloud. AML provides a convenient way to do so via a [Datastore](https://docs.microsoft.com/azure/machine-learning/service/how-to-access-data). The datastore provides a mechanism for you to upload/download data, and interact with it from your remote compute targets. \n",
"\n",
"Each workspace is associated with a default datastore. In this tutorial, we will upload the training data to this default datastore, which we will then mount on the remote compute for training in the next section."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds = ws.get_default_datastore()\n",
"print(ds.datastore_type, ds.account_name, ds.container_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The following code will upload the training data to the path `./mnist` on the default datastore."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ds.upload(src_dir='./mnist', target_path='./mnist')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now let's get a reference to the path on the datastore with the training data. We can do so using the `path` method. In the next section, we can then pass this reference to our training script's `--data_dir` argument. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"path_on_datastore = 'mnist'\n",
"ds_data = ds.path(path_on_datastore)\n",
"print(ds_data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train model on the remote compute\n",
"Now that we have the cluster 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 = './cntk-distr'\n",
"os.makedirs(project_folder, exist_ok=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Copy the training script `cntk_distr_mnist.py` into this project directory."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import shutil\n",
"shutil.copy('cntk_distr_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 CNTK tutorial. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core import Experiment\n",
"\n",
"experiment_name = 'cntk-distr'\n",
"experiment = Experiment(ws, name=experiment_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create an Estimator\n",
"The AML SDK's base Estimator enables you to easily submit custom scripts for both single-node and distributed runs. You should this generic estimator for training code using frameworks such as sklearn or CNTK that don't have corresponding custom estimators. For more information on using the generic estimator, refer [here](https://docs.microsoft.com/azure/machine-learning/service/how-to-train-ml-models)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.estimator import *\n",
"\n",
"script_params = {\n",
" '--num_epochs': 50,\n",
" '--data_dir': ds_data.as_mount(),\n",
" '--output_dir': './outputs'\n",
"}\n",
"\n",
"estimator = Estimator(source_directory=project_folder,\n",
" compute_target=compute_target,\n",
" entry_script='cntk_distr_mnist.py',\n",
" script_params=script_params,\n",
" node_count=2,\n",
" process_count_per_node=1,\n",
" distributed_backend='mpi', \n",
" pip_packages=['cntk-gpu==2.6'],\n",
" custom_docker_base_image='microsoft/mmlspark:gpu-0.12',\n",
" use_gpu=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We would like to train our model using a [pre-built Docker container](https://hub.docker.com/r/microsoft/mmlspark/). To do so, specify the name of the docker image to the argument `custom_docker_base_image`. You can only provide images available in public docker repositories such as Docker Hub using this argument. To use an image from a private docker repository, use the constructor's `environment_definition` parameter instead. Finally, we provide the `cntk` package to `pip_packages` to install CNTK 2.6 on our custom image.\n",
"\n",
"The above code specifies that we will run our training script on `2` nodes, with one worker per node. In order to run distributed CNTK, which uses MPI, you must provide the argument `distributed_backend='mpi'`."
]
},
{
"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.get_details())"
]
},
{
"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."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Alternatively, you can block until the script has completed training before running more code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"run.wait_for_completion(show_output=True)"
]
}
],
"metadata": {
"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
}

1004
training/07.tensorboard/07.tensorboard.ipynb
View File

File diff suppressed because it is too large Load Diff

482
training/08.export-run-history-to-tensorboard/08.export-run-history-to-tensorboard.ipynb
View File

@@ -1,243 +1,243 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 41. Export Run History as Tensorboard logs\n",
"\n",
"1. Run some training and log some metrics into Run History\n",
"2. Export the run history to some directory as Tensorboard logs\n",
"3. Launch a local Tensorboard to view the run history"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.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": {},
"outputs": [],
"source": [
"from azureml.core import Workspace, Run, Experiment\n",
"\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": [
"## Set experiment name and start the run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'export-to-tensorboard'\n",
"exp = Experiment(ws, experiment_name)\n",
"root_run = exp.start_logging()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load diabetes dataset, a well-known built-in small dataset that comes with scikit-learn\n",
"from sklearn.datasets import load_diabetes\n",
"from sklearn.linear_model import Ridge\n",
"from sklearn.metrics import mean_squared_error\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"X, y = load_diabetes(return_X_y=True)\n",
"\n",
"columns = ['age', 'gender', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']\n",
"\n",
"x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n",
"data = {\n",
" \"train\":{\"x\":x_train, \"y\":y_train}, \n",
" \"test\":{\"x\":x_test, \"y\":y_test}\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Example experiment\n",
"from tqdm import tqdm\n",
"\n",
"alphas = [.1, .2, .3, .4, .5, .6 , .7]\n",
"\n",
"# try a bunch of alpha values in a Linear Regression (Ridge) model\n",
"for alpha in tqdm(alphas):\n",
" # create a bunch of child runs\n",
" with root_run.child_run(\"alpha\" + str(alpha)) as run:\n",
" # More data science stuff\n",
" reg = Ridge(alpha=alpha)\n",
" reg.fit(data[\"train\"][\"x\"], data[\"train\"][\"y\"])\n",
" # TODO save model\n",
" preds = reg.predict(data[\"test\"][\"x\"])\n",
" mse = mean_squared_error(preds, data[\"test\"][\"y\"])\n",
" # End train and eval\n",
"\n",
" # log alpha, mean_squared_error and feature names in run history\n",
" root_run.log(\"alpha\", alpha)\n",
" root_run.log(\"mse\", mse)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Export Run History to Tensorboard logs"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Export Run History to Tensorboard logs\n",
"from azureml.contrib.tensorboard.export import export_to_tensorboard\n",
"import os\n",
"import tensorflow as tf\n",
"\n",
"logdir = 'exportedTBlogs'\n",
"log_path = os.path.join(os.getcwd(), logdir)\n",
"try:\n",
" os.stat(log_path)\n",
"except os.error:\n",
" os.mkdir(log_path)\n",
"print(logdir)\n",
"\n",
"# export run history for the project\n",
"export_to_tensorboard(root_run, logdir)\n",
"\n",
"# or export a particular run\n",
"# export_to_tensorboard(run, logdir)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"root_run.complete()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Start Tensorboard\n",
"\n",
"Or you can start the Tensorboard outside this notebook to view the result"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.contrib.tensorboard import Tensorboard\n",
"\n",
"# The Tensorboard constructor takes an array of runs, so be sure and pass it in as a single-element array here\n",
"tb = Tensorboard([], local_root=logdir, port=6006)\n",
"\n",
"# If successful, start() returns a string with the URI of the instance.\n",
"tb.start()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Stop Tensorboard\n",
"\n",
"When you're done, make sure to call the `stop()` method of the Tensorboard object."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tb.stop()"
]
}
],
"metadata": {
"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"
}
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# 41. Export Run History as Tensorboard logs\n",
"\n",
"1. Run some training and log some metrics into Run History\n",
"2. Export the run history to some directory as Tensorboard logs\n",
"3. Launch a local Tensorboard to view the run history"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequisites\n",
"Make sure you go through the [00. Installation and Configuration](00.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": {},
"outputs": [],
"source": [
"from azureml.core import Workspace, Run, Experiment\n",
"\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": [
"## Set experiment name and start the run"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"experiment_name = 'export-to-tensorboard'\n",
"exp = Experiment(ws, experiment_name)\n",
"root_run = exp.start_logging()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load diabetes dataset, a well-known built-in small dataset that comes with scikit-learn\n",
"from sklearn.datasets import load_diabetes\n",
"from sklearn.linear_model import Ridge\n",
"from sklearn.metrics import mean_squared_error\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"X, y = load_diabetes(return_X_y=True)\n",
"\n",
"columns = ['age', 'gender', 'bmi', 'bp', 's1', 's2', 's3', 's4', 's5', 's6']\n",
"\n",
"x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n",
"data = {\n",
" \"train\":{\"x\":x_train, \"y\":y_train}, \n",
" \"test\":{\"x\":x_test, \"y\":y_test}\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Example experiment\n",
"from tqdm import tqdm\n",
"\n",
"alphas = [.1, .2, .3, .4, .5, .6 , .7]\n",
"\n",
"# try a bunch of alpha values in a Linear Regression (Ridge) model\n",
"for alpha in tqdm(alphas):\n",
" # create a bunch of child runs\n",
" with root_run.child_run(\"alpha\" + str(alpha)) as run:\n",
" # More data science stuff\n",
" reg = Ridge(alpha=alpha)\n",
" reg.fit(data[\"train\"][\"x\"], data[\"train\"][\"y\"])\n",
" # TODO save model\n",
" preds = reg.predict(data[\"test\"][\"x\"])\n",
" mse = mean_squared_error(preds, data[\"test\"][\"y\"])\n",
" # End train and eval\n",
"\n",
" # log alpha, mean_squared_error and feature names in run history\n",
" root_run.log(\"alpha\", alpha)\n",
" root_run.log(\"mse\", mse)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Export Run History to Tensorboard logs"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Export Run History to Tensorboard logs\n",
"from azureml.contrib.tensorboard.export import export_to_tensorboard\n",
"import os\n",
"import tensorflow as tf\n",
"\n",
"logdir = 'exportedTBlogs'\n",
"log_path = os.path.join(os.getcwd(), logdir)\n",
"try:\n",
" os.stat(log_path)\n",
"except os.error:\n",
" os.mkdir(log_path)\n",
"print(logdir)\n",
"\n",
"# export run history for the project\n",
"export_to_tensorboard(root_run, logdir)\n",
"\n",
"# or export a particular run\n",
"# export_to_tensorboard(run, logdir)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"root_run.complete()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Start Tensorboard\n",
"\n",
"Or you can start the Tensorboard outside this notebook to view the result"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.contrib.tensorboard import Tensorboard\n",
"\n",
"# The Tensorboard constructor takes an array of runs, so be sure and pass it in as a single-element array here\n",
"tb = Tensorboard([], local_root=logdir, port=6006)\n",
"\n",
"# If successful, start() returns a string with the URI of the instance.\n",
"tb.start()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Stop Tensorboard\n",
"\n",
"When you're done, make sure to call the `stop()` method of the Tensorboard object."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"tb.stop()"
]
}
],
"metadata": {
"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"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

1416
tutorials/01.train-models.ipynb
View File

File diff suppressed because it is too large Load Diff

1216
tutorials/02.deploy-models.ipynb
View File

File diff suppressed because it is too large Load Diff

821
tutorials/03.auto-train-models.ipynb
View File

@@ -1,403 +1,422 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Copyright (c) Microsoft Corporation. All rights reserved.\n", "Copyright (c) Microsoft Corporation. All rights reserved.\n",
"\n", "\n",
"Licensed under the MIT License." "Licensed under the MIT License."
] ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Tutorial: Train a classification model with automated machine learning\n",
"\n",
"In this tutorial, you'll learn how to generate a machine learning model using automated machine learning (automated ML). Azure Machine Learning can perform data preprocessing, algorithm selection and hyperparameter selection in an automated way for you. The final model can then be deployed following the workflow in the [Deploy a model](02.deploy-models.ipynb) tutorial.\n",
"\n",
"[flow diagram](./imgs/flow2.png)\n",
"\n",
"Similar to the [train models tutorial](01.train-models.ipynb), this tutorial classifies handwritten images of digits (0-9) from the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset. But this time you don't to specify an algorithm or tune hyperparameters. The automated ML technique iterates over many combinations of algorithms and hyperparameters until it finds the best model based on your criterion.\n",
"\n",
"You'll learn how to:\n",
"\n",
"> * Set up your development environment\n",
"> * Access and examine the data\n",
"> * Train using an automated classifier locally with custom parameters\n",
"> * Explore the results\n",
"> * Review training results\n",
"> * Register the best model\n",
"\n",
"## Prerequisites\n",
"\n",
"Use [these instructions](https://aka.ms/aml-how-to-configure-environment) to: \n",
"* Create a workspace and its configuration file (**config.json**) \n",
"* Upload your **config.json** to the same folder as this notebook"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Start a notebook\n",
"\n",
"To follow along, start a new notebook from the same directory as **config.json** and copy the code from the sections below.\n",
"\n",
"\n",
"## Set up your development environment\n",
"\n",
"All the setup for your development work can be accomplished in the Python notebook. Setup includes:\n",
"\n",
"* Import Python packages\n",
"* Configure a workspace to enable communication between your local computer and remote resources\n",
"* Create a directory to store training scripts\n",
"\n",
"### Import packages\n",
"Import Python packages you need in this tutorial."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import azureml.core\n",
"import pandas as pd\n",
"from azureml.core.workspace import Workspace\n",
"from azureml.train.automl.run import AutoMLRun\n",
"import time\n",
"import logging\n",
"from sklearn import datasets\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import random\n",
"import numpy as np"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Configure workspace\n",
"\n",
"Create a workspace object from the existing workspace. `Workspace.from_config()` reads the file **aml_config/config.json** and loads the details into an object named `ws`. `ws` is used throughout the rest of the code in this tutorial.\n",
"\n",
"Once you have a workspace object, specify a name for the experiment and create and register a local directory with the workspace. The history of all runs is recorded under the specified experiment."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ws = Workspace.from_config()\n",
"# choose a name for the run history container in the workspace\n",
"experiment_name = 'automl-classifier'\n",
"# project folder\n",
"project_folder = './automl-classifier'\n",
"\n",
"import os\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",
"pd.set_option('display.max_colwidth', -1)\n",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore data\n",
"\n",
"The initial training tutorial used a high-resolution version of the MNIST dataset (28x28 pixels). Since auto training requires many iterations, this tutorial uses a smaller resolution version of the images (8x8 pixels) to demonstrate the concepts while speeding up the time needed for each iteration."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn import datasets\n",
"\n",
"digits = datasets.load_digits()\n",
"\n",
"# Exclude the first 100 rows from training so that they can be used for test.\n",
"X_digits = digits.data[100:,:]\n",
"y_digits = digits.target[100:]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Display some sample images\n",
"\n",
"Load the data into `numpy` arrays. Then use `matplotlib` to plot 30 random images from the dataset with their labels above them."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"count = 0\n",
"sample_size = 30\n",
"plt.figure(figsize = (16, 6))\n",
"for i in np.random.permutation(X_digits.shape[0])[:sample_size]:\n",
" count = count + 1\n",
" plt.subplot(1, sample_size, count)\n",
" plt.axhline('')\n",
" plt.axvline('')\n",
" plt.text(x = 2, y = -2, s = y_digits[i], fontsize = 18)\n",
" plt.imshow(X_digits[i].reshape(8, 8), cmap = plt.cm.Greys)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You now have the necessary packages and data ready for auto training for your model. \n",
"\n",
"## Auto train a model \n",
"\n",
"To auto train a model, first define settings for autogeneration and tuning and then run the automatic classifier.\n",
"\n",
"\n",
"### Define settings for autogeneration and tuning\n",
"\n",
"Define the experiment parameters and models settings for autogeneration and tuning. \n",
"\n",
"\n",
"|Property| Value in this tutorial |Description|\n",
"|----|----|---|\n",
"|**primary_metric**|AUC Weighted | Metric that you want to optimize.|\n",
"|**max_time_sec**|12,000|Time limit in seconds for each iteration|\n",
"|**iterations**|20|Number of iterations. In each iteration, the model trains with the data with a specific pipeline|\n",
"|**n_cross_validations**|3|Number of cross validation splits|\n",
"|**preprocess**|False| *True/False* Enables experiment to perform preprocessing on the input. Preprocessing handles *missing data*, and performs some common *feature extraction*|\n",
"|**exit_score**|0.995|*double* value indicating the target for *primary_metric*. Once the target is surpassed the run terminates|\n",
"|**blacklist_algos**|['kNN','LinearSVM']|*Array* of *strings* indicating algorithms to ignore.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"configure automl"
]
},
"outputs": [],
"source": [
"from azureml.train.automl import AutoMLConfig\n",
"\n",
"##Local compute \n",
"Automl_config = AutoMLConfig(task = 'classification',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 12000,\n",
" iterations = 20,\n",
" n_cross_validations = 3,\n",
" preprocess = False,\n",
" exit_score = 0.9985,\n",
" blacklist_algos = ['kNN','LinearSVM'],\n",
" X = X_digits,\n",
" y = y_digits,\n",
" path=project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Run the automatic classifier\n",
"\n",
"Start the experiment to run locally. Define the compute target as local and set the output to true to view progress on the experiment."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"local submitted run",
"automl"
]
},
"outputs": [],
"source": [
"from azureml.core.experiment import Experiment\n",
"experiment=Experiment(ws, experiment_name)\n",
"local_run = experiment.submit(Automl_config, show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore the results\n",
"\n",
"Explore the results of automatic training with a Jupyter widget or by examining the experiment history.\n",
"\n",
"### Jupyter widget\n",
"\n",
"Use the Jupyter notebook widget to see a graph and a table of all results."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"use notebook widget"
]
},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(local_run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Retrieve all iterations\n",
"\n",
"View the experiment history and see individual metrics for each iteration run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"get metrics",
"query history"
]
},
"outputs": [],
"source": [
"children = list(local_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",
"import pandas as pd\n",
"rundata = pd.DataFrame(metricslist).sort_index(1)\n",
"rundata"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Register the best model \n",
"\n",
"Use the `local_run` object to get the best model and register it into the workspace. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"query history",
"register model from history"
]
},
"outputs": [],
"source": [
"# find the run with the highest accuracy value.\n",
"best_run, fitted_model = local_run.get_output()\n",
"\n",
"# register model in workspace\n",
"description = 'Automated Machine Learning Model'\n",
"tags = None\n",
"local_run.register_model(description=description, tags=tags)\n",
"local_run.model_id # Use this id to deploy the model as a web service in Azure"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Test the best model\n",
"\n",
"Use the model to predict a few random digits. Display the predicted and the image. Red font and inverse image (white on black) is used to highlight the misclassified samples.\n",
"\n",
"Since the model accuracy is high, you might have to run the following code a few times before you can see a misclassified sample."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# find 30 random samples from test set\n",
"n = 30\n",
"sample_indices = np.random.permutation(X_digits.shape[0])[0:n]\n",
"test_samples = X_digits[sample_indices]\n",
"\n",
"\n",
"# predict using the model\n",
"result = fitted_model.predict(test_samples)\n",
"\n",
"# compare actual value vs. the predicted values:\n",
"i = 0\n",
"plt.figure(figsize = (20, 1))\n",
"\n",
"for s in sample_indices:\n",
" plt.subplot(1, n, i + 1)\n",
" plt.axhline('')\n",
" plt.axvline('')\n",
" \n",
" # use different color for misclassified sample\n",
" font_color = 'red' if y_digits[s] != result[i] else 'black'\n",
" clr_map = plt.cm.gray if y_digits[s] != result[i] else plt.cm.Greys\n",
" \n",
" plt.text(x = 2, y = -2, s = result[i], fontsize = 18, color = font_color)\n",
" plt.imshow(X_digits[s].reshape(8, 8), cmap = clr_map)\n",
" \n",
" i = i + 1\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Next steps\n",
"\n",
"In this Azure Machine Learning tutorial, you used Python to:\n",
"\n",
"> * Set up your development environment\n",
"> * Access and examine the data\n",
"> * Train using an automated classifier locally with custom parameters\n",
"> * Explore the results\n",
"> * Review training results\n",
"> * Register the best model\n",
"\n",
"Learn more about [how to configure settings for automatic training]() or [how to use automatic training on a remote resource]()."
]
}
],
"metadata": {
"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": "sgilley"
}, },
{ "nbformat": 4,
"cell_type": "markdown", "nbformat_minor": 2
"metadata": {}, }
"source": [
"# Tutorial: Train a classification model with automated machine learning\n",
"\n",
"In this tutorial, you'll learn how to generate a machine learning model using automated machine learning (automated ML). Azure Machine Learning can perform data preprocessing, algorithm selection and hyperparameter selection in an automated way for you. The final model can then be deployed following the workflow in the [Deploy a model](02.deploy-models.ipynb) tutorial.\n",
"\n",
"[flow diagram](./imgs/flow2.png)\n",
"\n",
"Similar to the [train models tutorial](01.train-models.ipynb), this tutorial classifies handwritten images of digits (0-9) from the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset. But this time you don't to specify an algorithm or tune hyperparameters. The automated ML technique iterates over many combinations of algorithms and hyperparameters until it finds the best model based on your criterion.\n",
"\n",
"You'll learn how to:\n",
"\n",
"> * Set up your development environment\n",
"> * Access and examine the data\n",
"> * Train using an automated classifier locally with custom parameters\n",
"> * Explore the results\n",
"> * Review training results\n",
"> * Register the best model\n",
"\n",
"## Prerequisites\n",
"\n",
"Use [these instructions](https://aka.ms/aml-how-to-configure-environment) to: \n",
"* Create a workspace and its configuration file (**config.json**) \n",
"* Upload your **config.json** to the same folder as this notebook"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Start a notebook\n",
"\n",
"To follow along, start a new notebook from the same directory as **config.json** and copy the code from the sections below.\n",
"\n",
"\n",
"## Set up your development environment\n",
"\n",
"All the setup for your development work can be accomplished in the Python notebook. Setup includes:\n",
"\n",
"* Import Python packages\n",
"* Configure a workspace to enable communication between your local computer and remote resources\n",
"* Create a directory to store training scripts\n",
"\n",
"### Import packages\n",
"Import Python packages you need in this tutorial."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import azureml.core\n",
"import pandas as pd\n",
"from azureml.core.workspace import Workspace\n",
"from azureml.train.automl.run import AutoMLRun\n",
"import time\n",
"import logging\n",
"from sklearn import datasets\n",
"from matplotlib import pyplot as plt\n",
"from matplotlib.pyplot import imshow\n",
"import random\n",
"import numpy as np"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Configure workspace\n",
"\n",
"Create a workspace object from the existing workspace. `Workspace.from_config()` reads the file **aml_config/config.json** and loads the details into an object named `ws`. `ws` is used throughout the rest of the code in this tutorial.\n",
"\n",
"Once you have a workspace object, specify a name for the experiment and create and register a local directory with the workspace. The history of all runs is recorded under the specified experiment."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"ws = Workspace.from_config()\n",
"# choose a name for the run history container in the workspace\n",
"experiment_name = 'automl-classifier'\n",
"# project folder\n",
"project_folder = './automl-classifier'\n",
"\n",
"import os\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",
"pd.set_option('display.max_colwidth', -1)\n",
"pd.DataFrame(data=output, index=['']).T"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore data\n",
"\n",
"The initial training tutorial used a high-resolution version of the MNIST dataset (28x28 pixels). Since auto training requires many iterations, this tutorial uses a smaller resolution version of the images (8x8 pixels) to demonstrate the concepts while speeding up the time needed for each iteration."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn import datasets\n",
"\n",
"digits = datasets.load_digits()\n",
"\n",
"# only take the first 100 rows if you want the training steps to run faster\n",
"X_digits = digits.data[:100,:]\n",
"y_digits = digits.target[:100]\n",
"\n",
"# use full dataset\n",
"#X_digits = digits.data\n",
"#y_digits = digits.target"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Display some sample images\n",
"\n",
"Load the data into `numpy` arrays. Then use `matplotlib` to plot 30 random images from the dataset with their labels above them."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"count = 0\n",
"sample_size = 30\n",
"plt.figure(figsize = (16, 6))\n",
"for i in np.random.permutation(X_digits.shape[0])[:sample_size]:\n",
" count = count + 1\n",
" plt.subplot(1, sample_size, count)\n",
" plt.axhline('')\n",
" plt.axvline('')\n",
" plt.text(x = 2, y = -2, s = y_digits[i], fontsize = 18)\n",
" plt.imshow(X_digits[i].reshape(8, 8), cmap = plt.cm.Greys)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You now have the necessary packages and data ready for auto training for your model. \n",
"\n",
"## Auto train a model \n",
"\n",
"To auto train a model, first define settings for autogeneration and tuning and then run the automatic classifier.\n",
"\n",
"\n",
"### Define settings for autogeneration and tuning\n",
"\n",
"Define the experiment parameters and models settings for autogeneration and tuning. \n",
"\n",
"\n",
"|Property| Value in this tutorial |Description|\n",
"|----|----|---|\n",
"|**primary_metric**|AUC Weighted | Metric that you want to optimize.|\n",
"|**max_time_sec**|12,000|Time limit in seconds for each iteration|\n",
"|**iterations**|20|Number of iterations. In each iteration, the model trains with the data with a specific pipeline|\n",
"|**n_cross_validations**|3|Number of cross validation splits|\n",
"|**preprocess**|False| *True/False* Enables experiment to perform preprocessing on the input. Preprocessing handles *missing data*, and performs some common *feature extraction*|\n",
"|**exit_score**|0.995|*double* value indicating the target for *primary_metric*. Once the target is surpassed the run terminates|\n",
"|**blacklist_algos**|['kNN','LinearSVM']|*Array* of *strings* indicating algorithms to ignore.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.automl import AutoMLConfig\n",
"\n",
"##Local compute \n",
"Automl_config = AutoMLConfig(task = 'classification',\n",
" primary_metric = 'AUC_weighted',\n",
" max_time_sec = 12000,\n",
" iterations = 20,\n",
" n_cross_validations = 3,\n",
" preprocess = False,\n",
" exit_score = 0.995,\n",
" blacklist_algos = ['kNN','LinearSVM'],\n",
" X = X_digits,\n",
" y = y_digits,\n",
" path=project_folder)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Run the automatic classifier\n",
"\n",
"Start the experiment to run locally. Define the compute target as local and set the output to true to view progress on the experiment."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.core.experiment import Experiment\n",
"experiment=Experiment(ws, experiment_name)\n",
"local_run = experiment.submit(Automl_config, show_output=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore the results\n",
"\n",
"Explore the results of automatic training with a Jupyter widget or by examining the experiment history.\n",
"\n",
"### Jupyter widget\n",
"\n",
"Use the Jupyter notebook widget to see a graph and a table of all results."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azureml.train.widgets import RunDetails\n",
"RunDetails(local_run).show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Retrieve all iterations\n",
"\n",
"View the experiment history and see individual metrics for each iteration run."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"children = list(local_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",
"import pandas as pd\n",
"rundata = pd.DataFrame(metricslist).sort_index(1)\n",
"rundata"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Register the best model \n",
"\n",
"Use the `local_run` object to get the best model and register it into the workspace. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# find the run with the highest accuracy value.\n",
"best_run, fitted_model = local_run.get_output()\n",
"\n",
"# register model in workspace\n",
"description = 'Automated Machine Learning Model'\n",
"tags = None\n",
"local_run.register_model(description=description, tags=tags)\n",
"local_run.model_id # Use this id to deploy the model as a web service in Azure"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Test the best model\n",
"\n",
"Use the model to predict a few random digits. Display the predicted and the image. Red font and inverse image (white on black) is used to highlight the misclassified samples.\n",
"\n",
"Since the model accuracy is high, you might have to run the following code a few times before you can see a misclassified sample."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# find 30 random samples from test set\n",
"n = 30\n",
"sample_indices = np.random.permutation(X_digits.shape[0])[0:n]\n",
"test_samples = X_digits[sample_indices]\n",
"\n",
"\n",
"# predict using the model\n",
"result = fitted_model.predict(test_samples)\n",
"\n",
"# compare actual value vs. the predicted values:\n",
"i = 0\n",
"plt.figure(figsize = (20, 1))\n",
"\n",
"for s in sample_indices:\n",
" plt.subplot(1, n, i + 1)\n",
" plt.axhline('')\n",
" plt.axvline('')\n",
" \n",
" # use different color for misclassified sample\n",
" font_color = 'red' if y_digits[s] != result[i] else 'black'\n",
" clr_map = plt.cm.gray if y_digits[s] != result[i] else plt.cm.Greys\n",
" \n",
" plt.text(x = 2, y = -2, s = result[i], fontsize = 18, color = font_color)\n",
" plt.imshow(X_digits[s].reshape(8, 8), cmap = clr_map)\n",
" \n",
" i = i + 1\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Next steps\n",
"\n",
"In this Azure Machine Learning tutorial, you used Python to:\n",
"\n",
"> * Set up your development environment\n",
"> * Access and examine the data\n",
"> * Train using an automated classifier locally with custom parameters\n",
"> * Explore the results\n",
"> * Review training results\n",
"> * Register the best model\n",
"\n",
"Learn more about [how to configure settings for automatic training](https://aka.ms/aml-how-configure-auto) or [how to use automatic training on a remote resource](https://aka.ms/aml-how-to-auto-remote)."
]
}
],
"metadata": {
"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": "sgilley"
},
"nbformat": 4,
"nbformat_minor": 2
}