## ----setup, include = FALSE---------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>", fig.width = 6, fig.height = 4.5)
set.seed(2024)

## ----data---------------------------------------------------------------------
library(glmtree)

## ----tree-data----------------------------------------------------------------
data <- generateData(n = 2000, scenario = "tree")
train <- sample(nrow(data), 1400)
features <- c("x1", "x2", "x3")

## ----tree-fit-----------------------------------------------------------------
fit <- glmtree(
  x = data[train, features], y = data$y[train],
  K = 5, iterations = 100,
  ctree_controls = partykit::ctree_control(alpha = 0.1, minbucket = 80, maxdepth = 4)
)
fit

## ----tree-predict-------------------------------------------------------------
table(true_cluster = data$c[-train], segment = predict(fit, data[-train, features], type = "segment"))
plot(fit@best.tree$tree)

## ----tree-evolution-----------------------------------------------------------
plot(unlist(fit@performance$criterionEvolution), type = "l", xlab = "Iteration", ylab = "-BIC")
abline(v = fit@performance$best_iteration, lty = 2)

## ----tree-compare-------------------------------------------------------------
logit <- glm(y ~ x1 + x2 + x3, data = data[train, ], family = binomial)
mob <- partykit::glmtree(y ~ x2 + x3 | x1 + x2 + x3, data = data[train, ], family = binomial)
c(
  logit = normalizedGini(data$y[-train], predict(logit, data[-train, ], type = "response")),
  mob = normalizedGini(data$y[-train], predict(mob, data[-train, ], type = "response")),
  glmtree = normalizedGini(data$y[-train], predict(fit, data[-train, features]))
)

## ----notree-------------------------------------------------------------------
data <- generateData(n = 2000, scenario = "no tree")
train <- sample(nrow(data), 1400)
fit <- glmtree(
  x = data[train, c("x1", "x2")], y = data$y[train], K = 5, iterations = 100,
  ctree_controls = partykit::ctree_control(alpha = 0.1, minbucket = 80, maxdepth = 4)
)
logit <- glm(y ~ x1 + x2, data = data[train, ], family = binomial)
c(
  logit = normalizedGini(data$y[-train], predict(logit, data[-train, ], type = "response")),
  glmtree = normalizedGini(data$y[-train], predict(fit, data[-train, c("x1", "x2")]))
)

## ----validation, eval = FALSE-------------------------------------------------
# fit <- glmtree(
#   x = data[, features], y = data$y, test = TRUE, validation = TRUE,
#   proportions = c(0.2, 0.2), criterion = "gini", patience = 50
# )

## ----famd, eval = requireNamespace("FactoMineR", quietly = TRUE)--------------
data <- generateData(n = 2000, scenario = "tree")
train <- sample(nrow(data), 1400)
mixed <- FactoMineR::FAMD(data[train, features], graph = FALSE)
cluster <- function(newdata) stats::predict(mixed, newdata)$coord[, "Dim 1"] < 0
segment <- cluster(data[, features])
pred <- numeric(nrow(data))
for (j in c(TRUE, FALSE)) {
  model <- glm(y ~ x1 + x2 + x3, data = data[train, ][segment[train] == j, ], family = binomial)
  pred[segment == j] <- predict(model, data[segment == j, ], type = "response")
}
normalizedGini(data$y[-train], pred[-train])