Get: Fairness Metrics

Computes bias and fairness using metrics like Statistical Parity Difference, Disparate Impact, and Theil Index.

Endpoint:

/eda/fairness_metrics

Input Parameters:

• usecaseVersion (integer, default: 1)
• feature_col1 (string, required – sensitive attribute)
• feature_col2 (string, required – target/outcome)
• graphType (string, required: Statistical Parity Difference, Disparate Impact, Theil Index)

• usecaseId (string, required)

  Output:

  Bias scores and visual output; metrics indicate potential discrimination (values: 0 bias ideal or 1 for parity).