## ----setup, include = FALSE---------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>")
library(rolescry)
set.seed(1)

## ----example------------------------------------------------------------------
set.seed(1)
pre  <- rnorm(100, 10, 2)          # a measurement, before ...
d <- data.frame(
  arm  = rep(c("control", "treatment"), each = 50),  # a balanced 2-level grouping
  pre  = pre,
  post = pre + rnorm(100, 1, 1)                       # ... and again after (paired with pre)
)

res <- detect_roles(d)
res
summary(res)

## ----blind--------------------------------------------------------------------
d_blind <- setNames(d, paste0("col_", seq_along(d)))
pos <- function(r, dat) match(r$roles$paired_pairs$columns, names(dat))
identical(pos(detect_roles(d), d), pos(detect_roles(d_blind), d_blind))

## ----breakdown----------------------------------------------------------------
res$roles$paired_pairs$components[[1]]

## ----nmi----------------------------------------------------------------------
set.seed(2)
g <- sample(c("A", "B", "C"), 300, replace = TRUE)
y <- ifelse(g == "A", "event", sample(c("event", "none"), 300, replace = TRUE))
compute_nmi(g, y)          # > 0: g informs y
compute_nmi(g, sample(g))  # ~ 0: shuffled -> independent

## ----namebonus----------------------------------------------------------------
set.seed(4)
clin <- data.frame(
  site    = rep(c("north", "south"), length.out = 160),  # perfectly balanced (the math pick)
  treated = sample(c("no", "yes"), 160, replace = TRUE, prob = c(0.62, 0.38))
)
detect_roles(clin)$roles$group_var$columns                                  # data alone -> "site"
detect_roles(clin, name_bonus = rolescry_default_name_bonus())$roles$group_var$columns  # name nudge -> "treated"