Getting Started with Azure AI Machine Learning

Azure AI Machine Learning is a unified platform that accelerates the end‑to‑end machine learning lifecycle. This guide walks you through setting up your first workspace, creating a simple model, and deploying it as a managed endpoint.

1. Create an Azure ML Workspace

Use the Azure portal or Azure CLI to provision a workspace.

az ml workspace create \
    --name my-ml-workspace \
    --resource-group my-resource-group \
    --location eastusCopy

2. Set Up a Compute Instance

A compute instance provides an interactive environment for development.

az ml compute create \
    --name my-compute \
    --type ComputeInstance \
    --size Standard_DS2_v2Copy

3. Build Your First Model

Below is a minimal Python script that trains a scikit‑learn model.

import joblib
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier

data = load_iris()
X, y = data.data, data.target
model = RandomForestClassifier()
model.fit(X, y)

joblib.dump(model, "model.pkl")Copy

4. Register the Model

Upload the trained model to your workspace.

az ml model register \
    --name iris-classifier \
    --path model.pkl \
    --workspace-name my-ml-workspace \
    --resource-group my-resource-groupCopy

5. Deploy as a Real‑Time Endpoint

Create an inference configuration and deploy the model.

az ml endpoint create \
    --name iris-endpoint \
    --model iris-classifier:1 \
    --compute my-compute \
    --workspace-name my-ml-workspace \
    --resource-group my-resource-groupCopy

Next Steps

• Explore automated ML for hyperparameter optimization.
• Integrate with Azure DevOps for CI/CD pipelines.
• Monitor deployed models using Azure Monitor.

For deeper guidance, visit the Resources page.