You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
312 lines
8.6 KiB
312 lines
8.6 KiB
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"# Data Science in the Cloud: The \"Azure ML SDK\" way \n",
|
|
"\n",
|
|
"## Introduction\n",
|
|
"\n",
|
|
"In this notebook, we will learn how to use the Azure ML SDK to train, deploy and consume a model through Azure ML.\n",
|
|
"\n",
|
|
"Pre-requisites:\n",
|
|
"1. You created an Azure ML workspace.\n",
|
|
"2. You loaded the [Heart Failure dataset](https://www.kaggle.com/andrewmvd/heart-failure-clinical-data) into Azure ML.\n",
|
|
"3. You uploaded this notebook into Azure ML Studio.\n",
|
|
"\n",
|
|
"The next steps are:\n",
|
|
"\n",
|
|
"1. Create an Experiment in an existing Workspace.\n",
|
|
"2. Create a Compute cluster.\n",
|
|
"3. Load the dataset.\n",
|
|
"4. Configure AutoML using AutoMLConfig.\n",
|
|
"5. Run the AutoML experiment.\n",
|
|
"6. Explore the results and get the best model.\n",
|
|
"7. Register the best model.\n",
|
|
"8. Deploy the best model.\n",
|
|
"9. Consume the endpoint.\n",
|
|
"\n",
|
|
"## Azure Machine Learning SDK-specific imports"
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"from azureml.core import Workspace, Experiment\n",
|
|
"from azureml.core.compute import AmlCompute\n",
|
|
"from azureml.train.automl import AutoMLConfig\n",
|
|
"from azureml.widgets import RunDetails\n",
|
|
"from azureml.core.model import InferenceConfig, Model\n",
|
|
"from azureml.core.webservice import AciWebservice"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Initialize Workspace\n",
|
|
"Initialize a workspace object from persisted configuration. Make sure the config file is present at .\\config.json"
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"ws = Workspace.from_config()\n",
|
|
"print(ws.name, ws.resource_group, ws.location, ws.subscription_id, sep = '\\n')"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Create an Azure ML experiment\n",
|
|
"\n",
|
|
"Let's create an experiment named 'aml-experiment' in the workspace we just initialized."
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"experiment_name = 'aml-experiment'\n",
|
|
"experiment = Experiment(ws, experiment_name)\n",
|
|
"experiment"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Create a Compute Cluster\n",
|
|
"You will need to create a [compute target](https://docs.microsoft.com/en-us/azure/machine-learning/concept-azure-machine-learning-architecture#compute-target) for your AutoML run."
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"aml_name = \"heart-f-cluster\"\n",
|
|
"try:\n",
|
|
" aml_compute = AmlCompute(ws, aml_name)\n",
|
|
" print('Found existing AML compute context.')\n",
|
|
"except:\n",
|
|
" print('Creating new AML compute context.')\n",
|
|
" aml_config = AmlCompute.provisioning_configuration(vm_size = \"Standard_D2_v2\", min_nodes=1, max_nodes=3)\n",
|
|
" aml_compute = AmlCompute.create(ws, name = aml_name, provisioning_configuration = aml_config)\n",
|
|
" aml_compute.wait_for_completion(show_output = True)\n",
|
|
"\n",
|
|
"cts = ws.compute_targets\n",
|
|
"compute_target = cts[aml_name]"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Data\n",
|
|
"Make sure you have uploaded the dataset to Azure ML and that the key is the same name as the dataset."
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"key = 'heart-failure-records'\n",
|
|
"dataset = ws.datasets[key]\n",
|
|
"df = dataset.to_pandas_dataframe()\n",
|
|
"df.describe()"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## AutoML Configuration"
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"automl_settings = {\n",
|
|
" \"experiment_timeout_minutes\": 20,\n",
|
|
" \"max_concurrent_iterations\": 3,\n",
|
|
" \"primary_metric\" : 'AUC_weighted'\n",
|
|
"}\n",
|
|
"\n",
|
|
"automl_config = AutoMLConfig(compute_target=compute_target,\n",
|
|
" task = \"classification\",\n",
|
|
" training_data=dataset,\n",
|
|
" label_column_name=\"DEATH_EVENT\",\n",
|
|
" enable_early_stopping= True,\n",
|
|
" featurization= 'auto',\n",
|
|
" debug_log = \"automl_errors.log\",\n",
|
|
" **automl_settings\n",
|
|
" )"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## AutoML Run"
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"remote_run = experiment.submit(automl_config)"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"RunDetails(remote_run).show()"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Save the best model"
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"best_run, fitted_model = remote_run.get_output()"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"best_run.get_properties()"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"model_name = best_run.properties['model_name']\n",
|
|
"script_file_name = 'inference/score.py'\n",
|
|
"best_run.download_file('outputs/scoring_file_v_1_0_0.py', 'inference/score.py')\n",
|
|
"description = \"aml heart failure project sdk\"\n",
|
|
"model = best_run.register_model(model_name = model_name,\n",
|
|
" description = description,\n",
|
|
" tags = None)"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Deploy the Best Model\n",
|
|
"\n",
|
|
"Run the following code to deploy the best model. You can see the state of the deployment in the Azure ML portal. This step can take a few minutes."
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"inference_config = InferenceConfig(entry_script=script_file_name, environment=best_run.get_environment())\n",
|
|
"\n",
|
|
"aciconfig = AciWebservice.deploy_configuration(cpu_cores = 1,\n",
|
|
" memory_gb = 1,\n",
|
|
" tags = {'type': \"automl-heart-failure-prediction\"},\n",
|
|
" description = 'Sample service for AutoML Heart Failure Prediction')\n",
|
|
"\n",
|
|
"aci_service_name = 'automl-hf-sdk'\n",
|
|
"aci_service = Model.deploy(ws, aci_service_name, [model], inference_config, aciconfig)\n",
|
|
"aci_service.wait_for_deployment(True)\n",
|
|
"print(aci_service.state)"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"## Consume the Endpoint\n",
|
|
"You can add inputs to the following input sample. "
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"data = {\n",
|
|
" \"data\":\n",
|
|
" [\n",
|
|
" {\n",
|
|
" 'age': \"60\",\n",
|
|
" 'anaemia': \"false\",\n",
|
|
" 'creatinine_phosphokinase': \"500\",\n",
|
|
" 'diabetes': \"false\",\n",
|
|
" 'ejection_fraction': \"38\",\n",
|
|
" 'high_blood_pressure': \"false\",\n",
|
|
" 'platelets': \"260000\",\n",
|
|
" 'serum_creatinine': \"1.40\",\n",
|
|
" 'serum_sodium': \"137\",\n",
|
|
" 'sex': \"false\",\n",
|
|
" 'smoking': \"false\",\n",
|
|
" 'time': \"130\",\n",
|
|
" },\n",
|
|
" ],\n",
|
|
"}\n",
|
|
"\n",
|
|
"test_sample = str.encode(json.dumps(data))"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"response = aci_service.run(input_data=test_sample)\n",
|
|
"response"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
}
|
|
],
|
|
"metadata": {
|
|
"orig_nbformat": 4,
|
|
"language_info": {
|
|
"name": "python"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
} |