great-expectations

import great_expectations as gx import pandas as pd import os # 1. Initialize a Data Context (or use an existing one) # For quickstart, a temporary in-memory context is often sufficient # For persistent configuration, run `great_expectations init` in your terminal context = gx.get_context() # 2. Connect to data (using a Pandas DataFrame for simplicity) # This example uses a publicly available CSV dataset # In a real scenario, you'd load your own data, e.g., from a file, database, or API df = pd.read_csv("https://raw.githubusercontent.com/great-expectations/great_expectations/develop/tests/test_sets/taxi_trips.csv") # Add a Pandas Datasource and a Data Asset datasource = context.data_sources.add_pandas("my_pandas_datasource") data_asset = datasource.add_dataframe_asset(name="my_dataframe_asset", dataframe=df) # Get a Validator to create and run Expectations validator = context.get_validator(batch_request=data_asset.build_batch_request()) # 3. Create Expectations # Define assertions about your data validator.expect_column_to_exist("passenger_count") validator.expect_column_values_to_be_between("passenger_count", min_value=1, max_value=6) validator.expect_column_values_to_not_be_null("pickup_datetime") # 4. Save the Expectation Suite validator.save_expectation_suite(discard_failed_expectations=False) # 5. Run validation checkpoint = context.add_or_update_checkpoint( name="my_checkpoint", validator=validator, ) checkpoint_result = checkpoint.run() # 6. Review validation results (e.g., in Data Docs) # To open Data Docs in your browser, uncomment the line below after a successful run # context.build_data_docs() # context.open_data_docs() print("Validation successful:", checkpoint_result.success) if not checkpoint_result.success: print("Validation failed. Check Data Docs for details.")