## ----setup, include = FALSE---------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.width = 7,
  fig.height = 5
)

## ----binary-classification----------------------------------------------------
library(evoFE)

data(mtcars)
df <- mtcars
df$am <- as.integer(df$am)   # target: 0 = automatic, 1 = manual

set.seed(42)
res <- evolve_features(
  data      = df,
  target_col = "am",
  task       = "classification",
  evaluator  = "xgboost",
  generations = 5,
  pop_size    = 8,
  cv_folds    = 3,
  early_stopping_rounds = 3,
  verbose     = TRUE
)

## ----binary-inspect-----------------------------------------------------------
# View the winning recipe
cat("Best recipe:", individual_to_recipe_string(res$best_individual), "\n")
cat("Fitness:    ", res$best_individual$fitness, "\n")

## ----binary-predict-features--------------------------------------------------
engineered <- predict(res, df[1:5, ])
head(engineered)

## ----binary-predict-model-----------------------------------------------------
preds <- predict_model(res, df[1:5, ])
preds

## ----regression---------------------------------------------------------------
data(iris)

set.seed(123)
res_reg <- evolve_features(
  data       = iris[, c("Sepal.Length", "Sepal.Width", "Petal.Width", "Petal.Length")],
  target_col = "Petal.Length",
  task       = "regression",
  evaluator  = "xgboost",
  generations = 5,
  pop_size    = 8,
  cv_folds    = 3,
  early_stopping_rounds = 3,
  verbose     = TRUE
)

cat("Best recipe:", individual_to_recipe_string(res_reg$best_individual), "\n")
cat("Fitness (neg RMSE):", res_reg$best_individual$fitness, "\n")

## ----regression-predict-------------------------------------------------------
preds_reg <- predict_model(res_reg, iris[1:10, ])
# Compare predictions to actuals
data.frame(
  actual    = iris$Petal.Length[1:10],
  predicted = round(preds_reg, 2)
)

## ----multiclass---------------------------------------------------------------
iris_mc <- iris
iris_mc$Species <- as.character(iris_mc$Species)

set.seed(99)
res_mc <- evolve_features(
  data       = iris,
  target_col = "Species",
  task       = "multiclass",
  evaluator  = "xgboost",
  generations = 5,
  pop_size    = 8,
  cv_folds    = 3,
  early_stopping_rounds = 3,
  verbose     = TRUE
)

cat("Best recipe:", individual_to_recipe_string(res_mc$best_individual), "\n")

## ----multiclass-predict-------------------------------------------------------
probs <- predict_model(res_mc, iris_mc[c(1, 51, 101), ])
round(probs, 3)

## ----inspect-recipe-----------------------------------------------------------
ind <- res$best_individual

# Human-readable recipe string
cat(individual_to_recipe_string(ind), "\n")

# Number of evolved genes
cat("Evolved genes:", length(ind$genes), "\n")

# Original columns retained
cat("Numeric cols: ", paste(ind$numeric_cols, collapse = ", "), "\n")
cat("Categorical cols:", paste(ind$categorical_cols, collapse = ", "), "\n")

# Individual gene details
for (g in ind$genes) {
  cat(sprintf("  %s(%s) → %s\n",
    g$transformer_name,
    paste(g$input_cols, collapse = ", "),
    g$output_col))
}

## ----reproducibility----------------------------------------------------------
set.seed(42)
r1 <- evolve_features(iris[,1:5], "Petal.Length", task = "regression",
                       generations = 3, pop_size = 5, evaluator = "xgboost",
                       verbose = FALSE)
set.seed(42)
r2 <- evolve_features(iris[,1:5], "Petal.Length", task = "regression",
                       generations = 3, pop_size = 5, evaluator = "xgboost",
                       verbose = FALSE)

identical(r1$best_individual$fitness, r2$best_individual$fitness)
identical(
  individual_to_recipe_string(r1$best_individual),
  individual_to_recipe_string(r2$best_individual)
)

## ----end-to-end---------------------------------------------------------------
data(iris)
set.seed(1)
idx <- sample(nrow(iris), 0.7 * nrow(iris))
train <- iris[idx, ]
test  <- iris[-idx, ]

# Evolve on training data only
set.seed(7)
recipe <- evolve_features(
  data      = train[, 1:4],               # exclude Species
  target_col = "Petal.Length",
  task       = "regression",
  evaluator  = "xgboost",
  generations = 5,
  pop_size    = 8,
  verbose     = FALSE
)

# Predict on held-out test data
test_preds <- predict_model(recipe, test[, 1:4])

# Evaluate
rmse <- sqrt(mean((test$Petal.Length - test_preds)^2))
cat(sprintf("Test RMSE: %.4f\n", rmse))
cat(sprintf("Recipe:    %s\n", individual_to_recipe_string(recipe$best_individual)))

## ----session-info-------------------------------------------------------------
sessionInfo()