Evaluation

As a final step to your synthetic data project, you can evaluate and visualize the synthetic data against the real data.

from sdv.evaluation.multi_table import run_diagnostic, evaluate_quality
from sdv.evaluation.multi_table import get_column_plot

# 1. perform basic validity checks
diagnostic = run_diagnostic(real_data, synthetic_data, metadata)

# 2. measure the statistical similarity
quality_report = evaluate_quality(real_data, synthetic_data, metadata)

# 3. plot the data
fig = get_column_plot(
    real_data=real_data,
    synthetic_data=synthetic_data,
    metadata=metadata,
    table_name='guests',
    column_name='amenities_fee'
)
    
fig.show()

Explore the functionaliy in more detail below.

Need more evaluation options?

Last updated