Package index • rsdv

Metadata

add_constraint(): Add a constraint to metadata
equality_constraint(): Constraint: two columns must be equal row-wise
inequality_constraint(): Constraint: col_a must be less than / greater than col_b
fixed_combinations_constraint(): Constraint: only observed column combinations are valid
custom_constraint(): Constraint: arbitrary row-wise predicate
check_constraint(): Check a single constraint against each row of a data frame
check_constraints(): Check all constraints in metadata against a data frame
print(<equality_constraint>): Print method for an equality_constraint
print(<inequality_constraint>): Print method for an inequality_constraint
print(<fixed_combinations_constraint>): Print method for a fixed_combinations_constraint
print(<custom_constraint>): Print method for a custom_constraint

gaussian_copula_synthesizer(): Create a Gaussian Copula synthesizer
reexports fit: Objects exported from other packages
sample(): Sample synthetic rows from a fitted synthesizer
sample_conditions(): Sample synthetic rows that match fixed column values (conditional sampling)
is_fitted(): Check whether a synthesizer has been fitted
validate_data(): Validate that a data frame is compatible with metadata

quality_report(): Generate a quality report comparing real and synthetic data
print(<rsdv_quality_report>): Print method for rsdv_quality_report
autoplot(<rsdv_quality_report>): Plot a quality report
diagnostic_report(): Generate a diagnostic (validity) report for synthetic data
print(<rsdv_diagnostic_report>): Print method for rsdv_diagnostic_report
autoplot(<rsdv_diagnostic_report>): Plot a diagnostic report
privacy_report(): Generate a privacy report comparing real and synthetic data
print(<rsdv_privacy_report>): Print method for rsdv_privacy_report
autoplot(<rsdv_privacy_report>): Plot a privacy report
ks_similarity(): Kolmogorov-Smirnov similarity score per numerical column
tvd_similarity(): Total variation distance similarity score per categorical column
correlation_similarity(): Correlation similarity between real and synthetic numerical column pairs
contingency_similarity(): Contingency similarity between real and synthetic categorical column pairs
ml_efficacy(): ML efficacy: train-on-synthetic / test-on-real accuracy ratio (TSTR)
nndr(): Nearest-Neighbor Distance Ratio privacy score
attribute_disclosure_risk(): Attribute disclosure risk