azureml-automl-core

import os from azureml.core import Workspace, Experiment from azureml.core.compute import AmlCompute, ComputeTarget from azureml.core.dataset import Dataset from azureml.data.datapath import DataPath from azureml.train.automl import AutoMLConfig # NOTE: azureml-automl-core is an internal dependency. # End-users typically interact with AutoML via azureml.train.automl. # This quickstart demonstrates the standard way to run an AutoML experiment. # Authenticate and get workspace # Assumes 'config.json' in current directory or Azure CLI login (az login) ws = Workspace.from_config() print(f"Workspace name: {ws.name}") # Create a compute target (or use an existing one) compute_name = os.environ.get('AML_COMPUTE_CLUSTER_NAME', 'cpu-cluster') # Example name try: compute_target = ComputeTarget(workspace=ws, name=compute_name) print(f'Found existing compute target: {compute_name}') except Exception: print(f'Creating a new compute target: {compute_name}...') config = AmlCompute.provisioning_configuration( vm_size='STANDARD_DS3_V2', max_nodes=4, idle_seconds_before_scaledown=1800 # Scale down after 30 mins idle ) compute_target = ComputeTarget.create(ws, compute_name, config) compute_target.wait_for_completion(show_output=True) # Register a dataset (using sample data for demonstration) # Replace with your actual data source or an already registered dataset # Example: data = Dataset.Tabular.from_delimited_files(path='https://... # Placeholder using dummy data for syntax: from azureml.data.data_reference import DataReference from azureml.data.datastore import Datastore # If you have a datastore and path to a file: # default_datastore = ws.get_default_datastore() # training_data = Dataset.Tabular.from_delimited_files(path=[(default_datastore, 'path/to/your/data.csv')]) # For runnable example without actual data/datastore setup: # Create a dummy dataset reference (won't actually run, but shows API) print("Note: This quickstart uses a dummy dataset reference for demonstration purposes.") print("Replace with your actual data registration for a functional run.") training_data = Dataset.Tabular.from_delimited_files(path=['https://archive.ics.uci.edu/ml/machine-learning-databases/00267/data_banknote_authentication.txt']) training_data = training_data.register(workspace=ws, name='dummy_banknote_data', description='Dummy Banknote Data', create_new_version=True) # Configure AutoML run automl_config = AutoMLConfig( task='classification', primary_metric='accuracy', experiment_timeout_minutes=15, # Max time in minutes for the experiment training_data=training_data, label_column_name='4', # Assuming '4' is the label column in dummy data compute_target=compute_target, n_cross_validations=2, max_concurrent_iterations=2, max_cores_per_iteration=-1, # Use all available cores enable_early_stopping=True, featurization='auto', debug_log='automl_errors.log' ) # Create and submit experiment (commented out to prevent accidental billing) # experiment_name = 'automl-quickstart-exp' # experiment = Experiment(ws, experiment_name) # local_run = experiment.submit(automl_config, show_output=True) # local_run.wait_for_completion(wait_for_completion=True, show_output=True) # print('AutoML run submitted.')