Create deploymentconfig.json

how-to-use-azureml/deploy-to-cloud/README.md

@@ -1,4 +1,5 @@
 # Model Deployment with Azure ML service
+
 You can use Azure Machine Learning to package, debug, validate and deploy inference containers to a variety of compute targets. This process is known as "MLOps" (ML operationalization).
 For more information please check out this article: https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-deploy-and-where
 
@@ -8,5 +9,17 @@ For more information please check out this article: https://docs.microsoft.com/e
 
 ## Deploy to the cloud
 You can deploy to the cloud using the Azure ML CLI or the Azure ML SDK.
-- CLI example: https://aka.ms/azmlcli
+
+### Deploy with the CLI
+```
+az extension add -n azure-cli-ml
+az ml folder attach -w myworkspace -g myresourcegroup
+az ml model register -n sklearn_regression_model.pkl -p sklearn_regression_model.pkl -t model.json
+az ml model deploy -n acicicd -f model.json --ic inferenceConfig.yml --dc deploymentConfig.yml
+```
+
+Here is an [Azure DevOps Pipelines model deployment example](./azure-pipelines-model-deploy.yml)
+[![Build Status](https://aidemos.visualstudio.com/azmlcli/_apis/build/status/Azure.MachineLearningNotebooks?branchName=cli-ga)](https://aidemos.visualstudio.com/azmlcli/_build/latest?definitionId=87&branchName=cli-ga)
+
+### Deploy from a notebook
 - Notebook example: [model-register-and-deploy](./model-register-and-deploy.ipynb).

how-to-use-azureml/deploy-to-cloud/azure-pipelines-model-deploy.yml

@@ -0,0 +1,50 @@
+trigger:
+- master
+
+pool:
+  vmImage: 'Ubuntu-16.04'
+
+steps:
+- task: DownloadSecureFile@1
+  inputs:
+    name: config.json
+    secureFile: config.json
+ 
+- script: cp $(Agent.TempDirectory)/config.json $(Build.SourcesDirectory)
+
+- task: AzureCLI@1
+  displayName: 'Install the CLI'
+  inputs:
+    azureSubscription: 'azmldemows'
+    scriptLocation: inlineScript
+    inlineScript: 'az extension add -n azure-cli-ml'
+
+- task: AzureCLI@1
+  displayName: 'Attach folder to workspace'
+  inputs:
+    azureSubscription: 'azmldemows'
+    scriptLocation: inlineScript
+    inlineScript: 'az ml folder attach'
+
+- task: AzureCLI@1
+  displayName: 'Register model'
+  inputs:
+    azureSubscription: 'azmldemows'
+    scriptLocation: inlineScript
+    inlineScript: 'az ml model register -n sklearn_regression_model.pkl -p sklearn_regression_model.pkl -t model.json'
+    workingDirectory: 'how-to-use-azureml/deploy-to-cloud/'
+
+- task: AzureCLI@1
+  displayName: 'Deploy model'
+  inputs:
+    azureSubscription: 'azmldemows'
+    scriptLocation: inlineScript
+    inlineScript: 'az ml model deploy -n acicicd -f model.json --ic inferenceConfig.yml --dc deploymentConfig.yml'
+    workingDirectory: 'how-to-use-azureml/deploy-to-cloud/'
+
+- task: AzureCLI@1
+  displayName: 'Delete deployed service'
+  inputs:
+    azureSubscription: 'azmldemows'
+    scriptLocation: inlineScript
+    inlineScript: 'az ml service delete -n acicicd'

how-to-use-azureml/deploy-to-cloud/deploymentConfig.yml

@@ -0,0 +1,5 @@
+---
+containerResourceRequirements:
+  cpu: 1
+  memoryInGB: 1
+computeType: ACI

how-to-use-azureml/deploy-to-cloud/deploymentconfig.json

@@ -0,0 +1,7 @@
+{
+   "containerResourceRequirements": {
+      "cpu": 1,
+      "memoryInGB": 1
+   },
+   "computeType": "ACI"
+}

how-to-use-azureml/deploy-to-cloud/inferenceConfig.yml

@@ -0,0 +1,9 @@
+entryScript: score.py
+runtime: python
+condaFile: myenv.yml
+extraDockerfileSteps:
+schemaFile:
+dependencies:
+enableGpu: False
+baseImage:
+baseImageRegistry:

how-to-use-azureml/deploy-to-cloud/inferenceconfig.json

@@ -0,0 +1,11 @@
+{
+   "entryScript": "score.py",
+   "runtime": "python",
+   "condaFile": "myenv.yml",
+   "extraDockerfileSteps": null,
+   "schemaFile": null,
+   "dependencies": null,
+   "enableGpu": false,
+   "baseImage": null,
+   "baseImageRegistry": null
+}

how-to-use-azureml/deploy-to-cloud/mylib.py

@@ -0,0 +1,8 @@
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license.
+
+import numpy as np
+
+def get_alphas():
+    # list of numbers from 0.0 to 1.0 with a 0.05 interval
+    return np.arange(0.0, 1.0, 0.05)

how-to-use-azureml/deploy-to-cloud/train.py

@@ -0,0 +1,45 @@
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license.
+
+from sklearn.datasets import load_diabetes
+from sklearn.linear_model import Ridge
+from sklearn.metrics import mean_squared_error
+from sklearn.model_selection import train_test_split
+from azureml.core.run import Run
+from sklearn.externals import joblib
+import os
+import numpy as np
+import mylib
+
+os.makedirs('./outputs', exist_ok=True)
+
+X, y = load_diabetes(return_X_y=True)
+
+run = Run.get_context()
+
+X_train, X_test, y_train, y_test = train_test_split(X, y,
+                                                    test_size=0.2,
+                                                    random_state=0)
+data = {"train": {"X": X_train, "y": y_train},
+        "test": {"X": X_test, "y": y_test}}
+
+# list of numbers from 0.0 to 1.0 with a 0.05 interval
+alphas = mylib.get_alphas()
+
+for alpha in alphas:
+    # Use Ridge algorithm to create a regression model
+    reg = Ridge(alpha=alpha)
+    reg.fit(data["train"]["X"], data["train"]["y"])
+
+    preds = reg.predict(data["test"]["X"])
+    mse = mean_squared_error(preds, data["test"]["y"])
+    run.log('alpha', alpha)
+    run.log('mse', mse)
+
+    model_file_name = 'ridge_{0:.2f}.pkl'.format(alpha)
+    # save model in the outputs folder so it automatically get uploaded
+    with open(model_file_name, "wb") as file:
+        joblib.dump(value=reg, filename=os.path.join('./outputs/',
+                                                     model_file_name))
+
+    print('alpha is {0:.2f}, and mse is {1:0.2f}'.format(alpha, mse))