Azure AI ML Py

pip install azure-ai-ml

AZURE_SUBSCRIPTION_ID=<your-subscription-id>  # Required for all auth methods
AZURE_RESOURCE_GROUP=<your-resource-group>  # Required for all auth methods
AZURE_ML_WORKSPACE_NAME=<your-workspace-name>  # Required for all auth methods
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production

from azure.ai.ml import MLClient
from azure.identity import DefaultAzureCredential, ManagedIdentityCredential
import os

# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
credential = DefaultAzureCredential(require_envvar=True)
# Or use a specific credential directly in production:
# See https://learn.microsoft.com/python/api/overview/azure/identity-readme?view=azure-python#credential-classes
# credential = ManagedIdentityCredential()
with MLClient(
    credential=credential,
    subscription_id=os.environ["AZURE_SUBSCRIPTION_ID"],
    resource_group_name=os.environ["AZURE_RESOURCE_GROUP"],
    workspace_name=os.environ["AZURE_ML_WORKSPACE_NAME"]
) as ml_client:
    for ws in ml_client.workspaces.list():
        print(ws.name)

from azure.ai.ml import MLClient
from azure.identity import DefaultAzureCredential

# Uses config.json in current directory or parent
with MLClient.from_config(
    credential=DefaultAzureCredential()
) as ml_client:
    for ws in ml_client.workspaces.list():
        print(ws.name)

from azure.ai.ml.entities import Workspace

ws = Workspace(
    name="my-workspace",
    location="eastus",
    display_name="My Workspace",
    description="ML workspace for experiments",
    tags={"purpose": "demo"}
)

ml_client.workspaces.begin_create(ws).result()

for ws in ml_client.workspaces.list():
    print(f"{ws.name}: {ws.location}")

from azure.ai.ml.entities import Data
from azure.ai.ml.constants import AssetTypes

# Register a file
my_data = Data(
    name="my-dataset",
    version="1",
    path="azureml://datastores/workspaceblobstore/paths/data/train.csv",
    type=AssetTypes.URI_FILE,
    description="Training data"
)

ml_client.data.create_or_update(my_data)

my_data = Data(
    name="my-folder-dataset",
    version="1",
    path="azureml://datastores/workspaceblobstore/paths/data/",
    type=AssetTypes.URI_FOLDER
)

ml_client.data.create_or_update(my_data)

from azure.ai.ml.entities import Model
from azure.ai.ml.constants import AssetTypes

model = Model(
    name="my-model",
    version="1",
    path="./model/",
    type=AssetTypes.CUSTOM_MODEL,
    description="My trained model"
)

ml_client.models.create_or_update(model)

for model in ml_client.models.list(name="my-model"):
    print(f"{model.name} v{model.version}")

from azure.ai.ml.entities import AmlCompute

cluster = AmlCompute(
    name="cpu-cluster",
    type="amlcompute",
    size="Standard_DS3_v2",
    min_instances=0,
    max_instances=4,
    idle_time_before_scale_down=120
)

ml_client.compute.begin_create_or_update(cluster).result()

for compute in ml_client.compute.list():
    print(f"{compute.name}: {compute.type}")

from azure.ai.ml import command, Input

job = command(
    code="./src",
    command="python train.py --data ${{inputs.data}} --lr ${{inputs.learning_rate}}",
    inputs={
        "data": Input(type="uri_folder", path="azureml:my-dataset:1"),
        "learning_rate": 0.01
    },
    environment="AzureML-sklearn-1.0-ubuntu20.04-py38-cpu@latest",
    compute="cpu-cluster",
    display_name="training-job"
)

returned_job = ml_client.jobs.create_or_update(job)
print(f"Job URL: {returned_job.studio_url}")

ml_client.jobs.stream(returned_job.name)

from azure.ai.ml import dsl, Input, Output
from azure.ai.ml.entities import Pipeline

@dsl.pipeline(
    compute="cpu-cluster",
    description="Training pipeline"
)
def training_pipeline(data_input):
    prep_step = prep_component(data=data_input)
    train_step = train_component(
        data=prep_step.outputs.output_data,
        learning_rate=0.01
    )
    return {"model": train_step.outputs.model}

pipeline = training_pipeline(
    data_input=Input(type="uri_folder", path="azureml:my-dataset:1")
)

pipeline_job = ml_client.jobs.create_or_update(pipeline)

from azure.ai.ml.entities import Environment

env = Environment(
    name="my-env",
    version="1",
    image="mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04",
    conda_file="./environment.yml"
)

ml_client.environments.create_or_update(env)

for ds in ml_client.datastores.list():
    print(f"{ds.name}: {ds.type}")

default_ds = ml_client.datastores.get_default()
print(f"Default: {default_ds.name}")