azureml-sdk

import os from azureml.core import Workspace, Experiment, Environment, ScriptRunConfig from azureml.core.compute import ComputeTarget, AmlCompute from azureml.core.compute_target import ComputeTargetException from azureml.core.conda_dependencies import CondaDependencies # Create a dummy script file with open('train_script.py', 'w') as f: f.write(""" import argparse import os import time print("Hello from Azure ML v1 training script!") parser = argparse.ArgumentParser() parser.add_argument('--arg1', type=str, default='default_value') args = parser.parse_args() print(f"Argument 1: {args.arg1}") time.sleep(5) # Simulate work print("Script finished.") """) # Create a dummy conda environment file with open('conda_env.yml', 'w') as f: f.write(""" name: my_env dependencies: - python=3.8 - pip: - azureml-defaults """) # NOTE: For a real scenario, replace placeholder values and ensure a config.json is available # Authenticate and connect to your workspace try: ws = Workspace.from_config(path='./.azureml', _file_name='config.json') # Reads from a local config.json print(f"Connected to workspace {ws.name}") except Exception as e: print(f"Could not load workspace from config. Ensure .azureml/config.json exists or provide details manually: {e}") # Fallback to manual connection (replace with your actual details) subscription_id = os.environ.get('AZURE_SUBSCRIPTION_ID', 'YOUR_SUBSCRIPTION_ID') resource_group = os.environ.get('AZURE_RESOURCE_GROUP', 'YOUR_RESOURCE_GROUP') workspace_name = os.environ.get('AZURE_WORKSPACE_NAME', 'YOUR_WORKSPACE_NAME') ws = Workspace(subscription_id, resource_group, workspace_name) print(f"Connected to workspace {ws.name} via manual details.") experiment_name = "my-first-v1-experiment" experiment = Experiment(workspace=ws, name=experiment_name) # Choose a name for your CPU cluster (or use 'local') compute_name = "cpu-cluster" compute_target = None try: compute_target = ComputeTarget(workspace=ws, name=compute_name) print(f"Found existing compute target: {compute_name}") except ComputeTargetException: print(f"Creating a new compute target: {compute_name}") compute_config = AmlCompute.provisioning_configuration(vm_size='STANDARD_DS1_V2', max_nodes=1) compute_target = ComputeTarget.create(ws, compute_name, compute_config) compute_target.wait_for_completion(show_output=True) # Define the environment env = Environment.from_conda_specification(name='my-custom-env', file_path='conda_env.yml') # Create a ScriptRunConfig src = ScriptRunConfig( source_directory='.', script='train_script.py', compute_target=compute_target, environment=env, arguments=['--arg1', 'hello_from_run'] ) # Submit the run run = experiment.submit(src) print(f"Submitted run: {run.get_portal_url()}") run.wait_for_completion(show_output=True) print(f"Run completed with status: {run.status}")