ป่าสุ่มด้วย ranger

library(ranger)

# Minimal random forest: 500 trees, auto mtry
rf <- ranger(
  medv ~ .,
  data      = MASS::Boston,
  num.trees = 500
)

print(rf)

p <- ncol(MASS::Boston) - 1  # number of predictors

rf_class <- ranger(
  Species ~ ., data = iris,
  num.trees = 500,
  mtry      = floor(sqrt(4))  # sqrt(p) for classification
)

rf_reg <- ranger(
  medv ~ ., data = MASS::Boston,
  num.trees = 500,
  mtry      = floor(p / 3)    # p/3 for regression
)

cat('Classification OOB Error:', rf_class$prediction.error)
cat('Regression OOB RMSE:', sqrt(rf_reg$prediction.error))

rf <- ranger(
  medv ~ ., data = MASS::Boston,
  num.trees = 500,
  mtry      = 4
)

# OOB MSE
cat('OOB MSE:', rf$prediction.error)

# OOB RMSE
cat('OOB RMSE:', sqrt(rf$prediction.error))

# For classification: OOB error rate
rf_cl <- ranger(Species ~ ., data = iris)
cat('OOB Error Rate:', rf_cl$prediction.error)

rf_imp <- ranger(
  medv ~ ., data = MASS::Boston,
  num.trees  = 500,
  importance = 'impurity'
)

# Sorted importance scores
imp <- sort(rf_imp$variable.importance, decreasing = TRUE)
print(imp)

# Quick plot
barplot(imp, las = 2, col = 'steelblue',
        main = 'Random Forest Variable Importance')

set.seed(1)
idx   <- sample(nrow(MASS::Boston), 400)
train <- MASS::Boston[idx, ]
test  <- MASS::Boston[-idx, ]

rf <- ranger(medv ~ ., data = train, num.trees = 500)

pred <- predict(rf, data = test)
test_rmse <- sqrt(mean((pred$predictions - test$medv)^2))
cat('Test RMSE:', round(test_rmse, 3))

rf_cl <- ranger(
  Species ~ ., data = iris,
  num.trees = 500,
  mtry      = 2
)

# OOB confusion matrix
print(rf_cl$confusion.matrix)

# OOB error rate
cat('OOB Error Rate:', rf_cl$prediction.error)

# Manual accuracy on OOB predictions
# (1 - error rate)
cat('OOB Accuracy:', 1 - rf_cl$prediction.error)

mtry_vals <- c(2, 4, 6, 8, 10)
oob_errors <- sapply(mtry_vals, function(m) {
  rf <- ranger(
    medv ~ ., data = MASS::Boston,
    num.trees = 300, mtry = m
  )
  rf$prediction.error
})

best_mtry <- mtry_vals[which.min(oob_errors)]
cat('Best mtry:', best_mtry)
plot(mtry_vals, sqrt(oob_errors), type = 'b',
     xlab = 'mtry', ylab = 'OOB RMSE')

# Ensure the target is a factor
iris$Species <- as.factor(iris$Species)

rf_prob <- ranger(
  Species ~ ., data = iris,
  num.trees   = 300,
  probability = TRUE  # output class probabilities
)

# Predictions are a matrix of probabilities
pred_prob <- predict(rf_prob, data = iris[1:5, ])
print(pred_prob$predictions)

# Use all available cores
rf_fast <- ranger(
  medv ~ ., data = MASS::Boston,
  num.trees  = 1000,
  mtry       = 4,
  num.threads = parallel::detectCores()
)

cat('Trees:', rf_fast$num.trees)
cat('Threads used:', rf_fast$num.threads)
cat('OOB RMSE:', sqrt(rf_fast$prediction.error))

library(parsnip)
library(workflows)

rf_spec <- rand_forest(
  mtry  = tune(),
  trees = 500,
  min_n = tune()
) |>
  set_engine('ranger', importance = 'impurity') |>
  set_mode('regression')

wf <- workflow() |>
  add_recipe(rec) |>
  add_model(rf_spec)

print(wf)

rf <- ranger(
  medv ~ ., data = MASS::Boston,
  num.trees  = 500, mtry = 4,
  importance = 'impurity'
)

# Key output fields
cat('OOB MSE:      ', rf$prediction.error, '\n')
cat('OOB RMSE:     ', sqrt(rf$prediction.error), '\n')
cat('R-squared:    ', rf$r.squared, '\n')
cat('Num trees:    ', rf$num.trees, '\n')
cat('Num features: ', rf$num.independent.variables, '\n')

rf <- ranger(
  medv ~ ., data = MASS::Boston,
  num.trees  = 500,
  mtry       = 4,
  importance = 'impurity',
  num.threads = parallel::detectCores()
)

cat('OOB RMSE:', sqrt(rf$prediction.error))
cat('R2:', rf$r.squared)

print(sort(rf$variable.importance, decreasing = TRUE))