## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>")

## -----------------------------------------------------------------------------
library(DPSynth)
set.seed(3)
n <- 400
ehr <- data.frame(
  age        = as.integer(pmin(100, pmax(18, round(rnorm(n, 60, 15))))),
  labs       = rnorm(n, 5, 1.5),
  diagnosis  = factor(sample(c("I10", "E11", "J44", "N18"), n,
                             replace = TRUE)),
  readmitted = factor(sample(c("no", "<30d", ">30d"), n,
                             prob = c(.6, .15, .25), replace = TRUE))
)

res <- dp_synthesize(ehr, method = "copula", epsilon = 2, n_synth = 400)
head(res$synthetic_data)
print(res)

# Empirical disclosure risk beyond the theoretical epsilon guarantee
res$risk$membership$risk_score
res$risk$attribute$mean_disclosure_error

## -----------------------------------------------------------------------------
ds <- evaluate_downstream(res$synthetic_data, ehr, target_var = "age")
ds