Expand description
Statistical quality evaluation module.
Provides statistical tests and analyses for validating that generated synthetic data follows expected distributions.
§Modules
- amount_distribution: Log-normal amount distribution analysis
- benford: Benford’s Law compliance testing
- line_item: Line item distribution analysis
- temporal: Temporal pattern analysis
- correlation: Cross-field correlation analysis
- anderson_darling: Anderson-Darling goodness-of-fit test
- chi_squared: Chi-squared goodness-of-fit test
- drift_detection: Drift detection evaluation and ground truth validation
Structs§
- Amount
Distribution Analysis - Results of amount distribution analysis.
- Amount
Distribution Analyzer - Analyzer for amount distributions.
- Anderson
Darling Analysis - Anderson-Darling test results.
- Anderson
Darling Analyzer - Analyzer for Anderson-Darling goodness-of-fit tests.
- Benford
Analysis - Results of Benford’s Law analysis.
- Benford
Analyzer - Analyzer for Benford’s Law compliance.
- BinFrequency
- Bin frequency information.
- ChiSquared
Analysis - Chi-squared test results.
- ChiSquared
Analyzer - Analyzer for chi-squared goodness-of-fit tests.
- Correlation
Analysis - Full correlation matrix analysis results.
- Correlation
Analyzer - Analyzer for correlation analysis.
- Correlation
Check Result - Result of correlation check for a pair of fields.
- Critical
Values - Critical values for Anderson-Darling test at standard significance levels.
- Drift
Detection Analysis - Results from drift detection analysis.
- Drift
Detection Analyzer - Analyzer for drift detection evaluation.
- Drift
Detection Entry - A single data point for drift detection analysis.
- Drift
Detection Metrics - Drift detection performance metrics.
- Expected
Correlation - Expected correlation between two fields.
- Labeled
Drift Event - A labeled drift event from ground truth data.
- Labeled
Event Analysis - Analysis of labeled drift events.
- Line
Item Analysis - Results of line item distribution analysis.
- Line
Item Analyzer - Analyzer for line item distributions.
- Line
Item Entry - Input for line item analysis.
- Statistical
Evaluation - Combined statistical evaluation results.
- Temporal
Analysis - Results of temporal pattern analysis.
- Temporal
Analyzer - Analyzer for temporal patterns.
- Temporal
Entry - Input for temporal analysis.
Enums§
- Benford
Conformity - Conformity level based on Mean Absolute Deviation (MAD).
- Binning
Strategy - Binning strategy for continuous data.
- Detection
Difficulty - Detection difficulty levels.
- Drift
Event Category - Categories of drift events.
- Expected
Distribution - Expected distribution type for comparison.
- Fitted
Parameters - Fitted distribution parameters.
- Target
Distribution - Target distribution types for Anderson-Darling test.
Functions§
- pearson_
correlation - Calculate Pearson correlation coefficient.
- spearman_
correlation - Calculate Spearman rank correlation coefficient.