azureml-train-automl

import os import pandas as pd from azureml.core.workspace import Workspace from azureml.core.experiment import Experiment from azureml.core.dataset import Dataset from azureml.train.automl import AutoMLConfig # NOTE: Replace with your actual workspace details or ensure config.json is present try: ws = Workspace.from_config() print(f"Workspace loaded: {ws.name}") except Exception as e: print(f"Could not load workspace from config. Attempting environment variables. Error: {e}") subscription_id = os.environ.get("AZUREML_SUBSCRIPTION_ID", "YOUR_SUBSCRIPTION_ID") resource_group = os.environ.get("AZUREML_RESOURCE_GROUP", "YOUR_RESOURCE_GROUP") workspace_name = os.environ.get("AZUREML_WORKSPACE_NAME", "YOUR_WORKSPACE_NAME") if "YOUR_" in subscription_id + resource_group + workspace_name: raise ValueError("Please configure your Azure ML Workspace details via config.json or environment variables.") ws = Workspace.get(name=workspace_name, subscription_id=subscription_id, resource_group=resource_group) print(f"Workspace loaded from env: {ws.name}") experiment_name = "automl-quickstart-exp" experiment = Experiment(ws, experiment_name) # Load sample data (replace with your own Dataset registration or data path) data_url = "https://automlsamplenotebookdata.blob.core.windows.net/automl-sample-notebook-data/creditcard.csv" df = pd.read_csv(data_url) # For simplicity, create a dummy Dataset. In a real scenario, you'd register your data. # Or use a registered dataset: Dataset.get_by_name(ws, name='my_dataset') from azureml.data.tabulardataset import TabularDataset training_data = TabularDataset.from_pandas_dataframe(df, target=(ws.get_default_datastore(), 'automl_creditcard.csv')) # Configure AutoML automl_config = AutoMLConfig( task='classification', primary_metric='accuracy', training_data=training_data, label_column_name='Class', compute_target='local', experiment_timeout_minutes=15, max_concurrent_iterations=1, n_cross_validations=2, iterations=5, verbosity=logging.INFO ) # Submit the AutoML run # NOTE: 'local' compute target runs on the current environment, may require many local dependencies. # For remote compute, configure an AmlCompute target and specify it in AutoMLConfig. print("Submitting AutoML experiment...") # run = experiment.submit(automl_config, show_output=True) # print(f"AutoML experiment submitted: {run.id}") # print("NOTE: Uncomment the submit line and ensure compute target is configured for actual execution.") import logging # Ensure logging is imported for verbosity