bn_flag_inference: Bayesian inference for error prediction .

In sdglinkage: Synthetic Data Generation for Linkage Methods Development

Description

bn_flag_inference use the trained Bayesian Network model to predict the errors that may happen in the dataset.

Usage

bn_flag_inference(dataset, fit_model)

Arguments

dataset	A data frame.
fit_model	A bn fit model generated by bn.fit or gen_bn_learn or gen_bn_elicit.

Value

The output is a data frame inferred error flags.

Examples

adult_with_flag <- add_random_error(adult[1:100,], prob = c(0.97, 0.03), "age_missing")
adult_with_flag <- split_data(adult_with_flag, 70)
bn_learn <- gen_bn_learn(adult_with_flag$training_set, "hc")
syn_error_occurrence <- bn_flag_inference(bn_learn$gen_data, bn_learn$fit_model)
syn_error_occurrence

sdglinkage documentation built on April 27, 2020, 5:09 p.m.