Generation and Evaluation of Synthetic Tabular Datasets

[Up] [Top]

Documentation for package ‘opencesp’ version 0.4.0

Help Pages

opencesp-package opencesp: Generation and Evaluation of Synthetic Tabular Datasets
adaptive_matches_prop Adaptive proportion of matches
ASDED Average squared differences between empirical distributions
avatarize Avatarization of a dataset
CCM_RS Cross-classification metric in the real-synthetic order
CCM_SR Cross-classification metric in the synthetic-real order
cor_F1 Membership F1 metric
CRM_RS Cross-regression metric in the real-synthetic order
CRM_SR Cross-regression metric in the synthetic-real order
dcr Distance to the closest record
dep_order Dependency order in a data set
GCAP Generalized Correct Attribution Probability (GCAP)
get_prec Precision of numeric variables
GTCAP Generalized Targeted Correct Attribution Probability (GTCAP)
hellinger_distance Estimated Hellinger distance
impute_rf Random-forest imputation
ind_blocks Independent blocks of variables
interval_overlap Overlap of confidence intervals
LCM Log-cluster metric
matches_prop Proportion of matches
mean_hellinger Mean Hellinger distance
opencesp opencesp: Generation and Evaluation of Synthetic Tabular Datasets
outlier_coverage Outlier coverage
outlier_learning_factor Outlier learning factor
PCD_cat Pairwise correlation difference adapted for categorical data
PCD_num Pairwise correlation difference
pgb Parallel gradient boosting
pgb_control Controls for PGB fits
pgb_cvh Parallel gradient boosting with cross-validation
pMSE Propensity score mean-squared error
pMSE_cp Heuristics for the complexity parameter of tree-based estimation of propensity scores
predict.pgb Predict method for PGB models
predict_cde_pgb Predict conditional densities from PGB models
predict_cde_pgb_raw Piecewise-constant conditional densities from PGB models
resample Sample conditionally on vector length
round_synth Round synthetic numeric variables to the precision observed in the original data
tsAUC ts-AUC
univ_att_prob Univariate correct attribution probability