sagemaker-data-insights

import os import sagemaker import boto3 from sagemaker_data_insights.labeling_job.data_insights import LabelingJobDataInsights # Initialize SageMaker session using default boto3 credential chain # Ensure your AWS credentials are configured (e.g., via AWS CLI, environment variables) # The region can be specified if not configured globally. region = os.environ.get('AWS_REGION', 'us-east-1') boto_session = boto3.Session(region_name=region) sagemaker_session = sagemaker.Session(boto_session=boto_session) # Define placeholders for your specific S3 input data and IAM role # Replace with actual S3 URI to your labeling job manifest file input_s3_uri = os.environ.get( 'SAGEMAKER_DATA_INSIGHTS_INPUT_URI', 's3://your-bucket-name/path/to/manifest-file/output.manifest' ) # Replace with the ARN of an IAM role with S3 read/write and SageMaker permissions role_arn = os.environ.get( 'SAGEMAKER_EXECUTION_ROLE_ARN', 'arn:aws:iam::123456789012:role/YourSageMakerExecutionRole' # Placeholder, replace with actual role ) print(f"Analyzing data from: {input_s3_uri}") print(f"Using SageMaker execution role: {role_arn}") try: # Instantiate the insights calculator for a Labeling Job insights_calculator = LabelingJobDataInsights( sagemaker_session=sagemaker_session, s3_input_uri=input_s3_uri, role_arn=role_arn, number_of_samples=10 # Use a small number of samples for quick demo ) # Get insights (this will perform data sampling and analysis) # NOTE: This call requires valid S3 URI, role, and data. # It might take some time to run and will likely fail if placeholders are not replaced. print("Attempting to get insights (this may take a moment)...") insights_result = insights_calculator.get_insights() print("\n--- Data Insights Summary ---") print(f"Total entries analyzed: {insights_result.number_of_samples}") if insights_result.annotation_label_distribution: print("Annotation Label Distribution:") for label, count in insights_result.annotation_label_distribution.items(): print(f" - {label}: {count}") else: print("No annotation label distribution found (check input data/sampling).") except Exception as e: print(f"\nAn error occurred during insights calculation: {e}") print("Please ensure your AWS credentials, S3 input URI, and IAM role are correctly configured and point to valid data.")