purrr.R

# Load packages including ggplot2

library(dplyr)
library(purrr)
library(ggplot2)

# Follow example as at: https://github.com/hadley/purrr/blob/master/README.md

random_group <- function(n, probs) {
  probs <- probs / sum(probs)
  g <- findInterval(seq(0, 1, length = n), c(0, cumsum(probs)),
    rightmost.closed = TRUE)
  names(probs)[sample(g)]
}
partition <- function(df, n, probs) {
  replicate(n, split(df, random_group(nrow(df), probs)), FALSE) %>%
    transpose() %>%
    as_data_frame()
}

msd <- function(x, y) sqrt(mean((x - y) ^ 2))

# Generate 100 random test-training splits
boot <- partition(mtcars, 100, c(training = 0.8, test = 0.2))
boot

boot <- boot %>% 
  mutate(
    # Fit the models
    models = map(training, ~ lm(mpg ~ wt, data = .)),
    # Make predictions on test data
    preds = map2(models, test, predict),
    diffs = map2(preds, test %>% map("mpg"), msd)
  )

# Fails with following error:
# Error in eval(expr, envir, enclos) : invalid term in model formula

# Now detach `ggplot2` and try again

detach("package:ggplot2", unload=TRUE)

boot <- boot %>% 
  dplyr::mutate(
  # Fit the models
  models = map(training, ~ lm(mpg ~ wt, data = .)),
  # Make predictions on test data
  preds = map2(models, test, predict),
  diffs = map2(preds, test %>% map("mpg"), msd)
)

# Works this time...