FakeDataR: Getting started"

In FakeDataR: Privacy-Preserving Synthetic Data for 'LLM' Workflows

knitr::opts_chunk$set(collapse = TRUE, comment = "#>", message = FALSE, warning = FALSE)
set.seed(1)  # ensure RNG is initialized for clean vignette sessions
library(FakeDataR)

This vignette shows how to mirror the structure of real data with fully synthetic values, verify the structure, and produce an LLM-ready bundle.

Quick start

# tiny input with a few likely sensitive fields
df <- data.frame(
  id = sprintf("id%03d", 1:10),
  email = paste0("a", 1:10, "@x.com"),
  Progress = paste0(sample(80:100, 10, TRUE), "%"),
  check.names = FALSE
)

orig <- prepare_input_data(df)

fake_priv <- generate_fake_with_privacy(
  data = orig, n = 10, level = "low", seed = 1,
  sensitive = c("id", "email"),
  sensitive_detect = TRUE,
  sensitive_strategy = "fake",
  normalize = TRUE
)

# quick validation sample
head(validate_fake(orig, fake_priv), 5)

library(FakeDataR)

# Basic fake from a data.frame
fake_mtc <- generate_fake_data(mtcars, n = 200, seed = 1)
validate_fake(mtcars, fake_mtc)

Factors, characters, and numerics

fake_co2 <- generate_fake_data(as.data.frame(CO2), n = 200, seed = 2)
validate_fake(as.data.frame(CO2), fake_co2)

fake_tg <- generate_fake_data(ToothGrowth, n = 120, seed = 3)
validate_fake(ToothGrowth, fake_tg)

Dates and POSIXct (time zones preserved)

df_date <- data.frame(d = seq(as.Date("2020-01-01"), by = "day", length.out = 50))
fake_date <- generate_fake_data(df_date, n = 80, seed = 4)
str(fake_date$d)

dt <- data.frame(
  when = seq.POSIXt(as.POSIXct("2023-05-01 00:00:00", tz = "America/New_York"),
                    by = "hour", length.out = 200)
)
fake_dt <- generate_fake_data(dt, n = 50, seed = 5)
str(fake_dt$when)
range(fake_dt$when)

Public datasets - wrap in guards, trim sizes

These chunks run only if the packages are installed.

if (requireNamespace("nycflights13", quietly = TRUE)) {
  fl <- nycflights13::flights
  set.seed(10)
  fl_small <- fl[sample.int(nrow(fl), 2000), ]  # smaller
  fake_fl <- generate_fake_data(
    fl_small, n = 500, seed = 10,
    numeric_mode = "distribution"
  )
  head(validate_fake(fl_small, fake_fl), 5)
} else {
  message("nycflights13 not installed - skipping.")
}

if (requireNamespace("palmerpenguins", quietly = TRUE)) {
  peng <- na.omit(palmerpenguins::penguins[, c("species","island","bill_length_mm","sex")])
  fake_peng <- generate_fake_data(
    peng, n = 400, seed = 11,
    category_mode = "preserve"
  )
  head(validate_fake(peng, fake_peng), 5)
} else {
  message("palmerpenguins not installed - skipping.")
}

Gapminder demo

# Optional package; make the chunk robust
if (requireNamespace("gapminder", quietly = TRUE)) {
  set.seed(21)
  gm <- gapminder::gapminder
  # Keep it light if you want: gm <- gm[sample.int(nrow(gm), 2000), ]

  fake_gm <- generate_fake_data(
    gm, n = 800, seed = 21,
    numeric_mode = "distribution",  # nicer numeric spread
    category_mode = "preserve"      # keep factor levels
  )

  validate_fake(gm, fake_gm)
} else {
  message("gapminder not installed; skipping demo.")
}

Sensitive columns: fake vs drop

set.seed(12)
df_pii <- data.frame(
  id    = 1:100,
  email = sprintf("[e-mail]", 1:100),
  phone = sprintf("(415) 555-%04d", 1:100),
  spend = runif(100, 10, 500)
)

fake_keep <- generate_fake_data(
  df_pii, n = 120,
  sensitive_detect   = TRUE,
  sensitive_strategy = "fake"
)
fake_drop <- generate_fake_data(
  df_pii, n = 120,
  sensitive_detect   = TRUE,
  sensitive_strategy = "drop"
)

names(fake_keep)        # expect id/email/phone present but synthetic
names(fake_drop)        # expect only "spend"

LLM bundle: data + schema + README (+ optional ZIP)

b1 <- llm_bundle(
  data = ToothGrowth, n = 150, level = "high", seed = 10,
  formats = c("csv","rds"),
  path = tempdir(), filename = "toothgrowth_fake",
  write_prompt = TRUE, zip = TRUE
)
b1$schema_path
b1$readme_path
b1$zip_path

Parquet export (optional)

if (requireNamespace("arrow", quietly = TRUE)) {
  fake_air <- generate_fake_data(airquality, n = 400, seed = 20)
  export_fake(fake_air, file.path(tempdir(), "air.parquet"))
} else {
  message("arrow not installed - skipping Parquet export.")
}

Reproducibility

a1 <- generate_fake_data(CO2, n = 123, seed = 42)
a2 <- generate_fake_data(CO2, n = 123, seed = 42)
identical(a1, a2)

big <- data.frame(
  a = runif(2e5),
  b = sample(letters, 2e5, TRUE),
  c = as.Date("2020-01-01") + sample.int(3000, 2e5, TRUE)
)
system.time({
  fake_big <- generate_fake_data(big, n = 2e5, seed = 99)
})

FakeDataR documentation built on Nov. 6, 2025, 1:15 a.m.