sdmetrics

import pandas as pd from sdmetrics import load_demo from sdmetrics.reports.single_table import QualityReport # Load demo data (real, synthetic, and metadata) real_data, synthetic_data, metadata = load_demo(modality='single_table') # Or create your own dataframes and metadata # real_data = pd.DataFrame({'column1': [1, 2, 3], 'column2': ['A', 'B', 'C']}) # synthetic_data = pd.DataFrame({'column1': [1, 2, 2], 'column2': ['A', 'C', 'B']}) # metadata = {'columns': {'column1': {'sdtype': 'numerical'}, 'column2': {'sdtype': 'categorical'}}, 'primary_key': None} # Create a QualityReport report = QualityReport() # Generate the report report.generate(real_data, synthetic_data, metadata) # Print the overall quality score print(f"Overall Quality Score: {report.get_score():.2f}%") # Get a visualization for a specific property (e.g., 'Column Shapes') # fig = report.get_visualization(property_name='Column Shapes') # fig.show() # Save the report # report.save(filepath='demo_data_quality_report.pkl') # To load later: loaded_report = QualityReport.load(filepath='demo_data_quality_report.pkl')