## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.width = 7,
  fig.height = 4
)
library(figsr)

## ----load---------------------------------------------------------------------
str(pima_diabetes)

## ----missingness--------------------------------------------------------------
predictors_with_gaps <- c("Glucose", "BloodPressure", "SkinThickness", "Insulin", "BMI")
missing_rate <- vapply(pima_diabetes[predictors_with_gaps], function(x) mean(is.na(x)), numeric(1))
knitr::kable(
  data.frame(predictor = names(missing_rate),
             missing_pct = sprintf("%.1f%%", 100 * missing_rate)),
  row.names = FALSE
)

## ----fit----------------------------------------------------------------------
set.seed(42)
train_idx <- sample(nrow(pima_diabetes), floor(0.75 * nrow(pima_diabetes)))
train <- pima_diabetes[train_idx, ]
test  <- pima_diabetes[-train_idx, ]

fit_omit <- figs(Outcome ~ ., data = train, max_splits = 10, mode = "classification")
fit_mia  <- figs(Outcome ~ ., data = train, max_splits = 10, mode = "classification",
                 na_method = "mia")

cat("training rows used, omit:", length(fit_omit$fitted_values), "of", nrow(train), "\n")
cat("training rows used, mia :", length(fit_mia$fitted_values),  "of", nrow(train), "\n")

test_complete <- complete.cases(test[, predictors_with_gaps])
cat("test patients omit can score at all:", sum(test_complete), "of", nrow(test), "\n")
cat("test patients mia can score        :", nrow(test), "of", nrow(test), "\n")

## ----accuracy-----------------------------------------------------------------
accuracy <- function(predicted, observed) mean(predicted == observed)

pred_omit <- predict(fit_omit, test[test_complete, ], type = "class")$.pred_class
pred_mia  <- predict(fit_mia, test, type = "class")$.pred_class

cat("accuracy, omit, on the", sum(test_complete), "patients it can score:",
    round(accuracy(pred_omit, test$Outcome[test_complete]), 3), "\n")
cat("accuracy, mia, on those same", sum(test_complete), "patients        :",
    round(accuracy(pred_mia[test_complete], test$Outcome[test_complete]), 3), "\n")
cat("accuracy, mia, on all", nrow(test), "test patients                  :",
    round(accuracy(pred_mia, test$Outcome), 3), "\n")

## ----rules--------------------------------------------------------------------
summary(fit_mia)

## ----importance---------------------------------------------------------------
figsr_importance(fit_mia)

## ----plot, fig.width = 8, fig.height = 4.5, fig.alt = "Three trees of the Pima diabetes tree sum, rooted in Glucose, Age and BMI, with positive leaves in green and negative leaves in red."----
fit_plot <- figs(Outcome ~ ., data = train, max_splits = 4, mode = "classification",
                 na_method = "mia")
root_features <- vapply(fit_plot$trees, function(tr) tr[[1]]$feature, character(1))

plot(fit_plot, main = "Pima diabetes: tree sum under na_method = \"mia\"",
     tree_names = paste0("splits first on ", root_features))