निर्णय वृक्ष: एन्सेम्बल की नींव

tree <- rpart(medv ~ ., data = MASS::Boston, method = 'anova',
              control = rpart.control(minsplit = 5, cp = 0.001))

printcp(tree)

# Identify the CP with minimum cross-validated error
best_cp <- tree$cptable[
  which.min(tree$cptable[, 'xerror']),
  'CP'
]
cat('Best CP:', best_cp)

best_cp <- tree$cptable[
  which.min(tree$cptable[, 'xerror']), 'CP'
]

pruned_tree <- prune(tree, cp = best_cp)

cat('Original tree nodes:', nrow(tree$frame))
cat('Pruned tree nodes:', nrow(pruned_tree$frame))

library(rpart.plot)

tree <- rpart(Species ~ ., data = iris, method = 'class')
pruned <- prune(tree, cp = 0.02)

rpart.plot(
  pruned,
  type   = 4,     # split labels on branches
  extra  = 104,   # show class + probability
  fallen.leaves = TRUE
)

# Deep tree = low bias, high variance (overfits)
deep_tree <- rpart(medv ~ ., data = MASS::Boston,
                   control = rpart.control(minsplit = 2, cp = 0))

# Shallow tree = high bias, low variance (underfits)
shallow_tree <- rpart(medv ~ ., data = MASS::Boston,
                      control = rpart.control(maxdepth = 2))

cat('Deep nodes:', nrow(deep_tree$frame))
cat('Shallow nodes:', nrow(shallow_tree$frame))

set.seed(42)
train_idx <- sample(nrow(MASS::Boston), 400)
train_bos <- MASS::Boston[train_idx, ]
test_bos  <- MASS::Boston[-train_idx, ]

# Fully grown tree
full <- rpart(medv ~ ., data = train_bos,
              control = rpart.control(cp = 0, minsplit = 2))

train_pred <- predict(full, train_bos)
test_pred  <- predict(full, test_bos)

cat('Train RMSE:', sqrt(mean((train_pred - train_bos$medv)^2)))
cat('Test  RMSE:', sqrt(mean((test_pred  - test_bos$medv)^2)))

tree <- rpart(medv ~ ., data = MASS::Boston, method = 'anova')

# Variable importance (sorted)
imp <- sort(tree$variable.importance, decreasing = TRUE)
print(imp)

# Quick barplot
barplot(imp, las = 2, main = 'Variable Importance',
        col = 'steelblue', cex.names = 0.8)

# Demonstrating instability of a single tree
set.seed(1); t1 <- rpart(medv ~ ., data = MASS::Boston[sample(506, 400), ])
set.seed(2); t2 <- rpart(medv ~ ., data = MASS::Boston[sample(506, 400), ])

# Root split may differ between trees
cat('Tree 1 root split:', t1$frame$var[1])
cat('Tree 2 root split:', t2$frame$var[1])

ctrl <- rpart.control(
  cp        = 0.005,  # complexity penalty
  minsplit  = 20,     # min obs to try a split
  minbucket = 7,      # min obs in any leaf
  maxdepth  = 10      # max tree depth
)

tree <- rpart(medv ~ ., data = MASS::Boston,
              method = 'anova', control = ctrl)

printcp(tree)

pruned_tree <- prune(tree, cp = best_cp)

test_pred <- predict(pruned_tree, newdata = test_bos)

rmse <- sqrt(mean((test_pred - test_bos$medv)^2))
ss_res <- sum((test_pred - test_bos$medv)^2)
ss_tot <- sum((test_bos$medv - mean(test_bos$medv))^2)
r2 <- 1 - ss_res / ss_tot

cat('RMSE:', round(rmse, 3))
cat('R2:', round(r2, 3))

# Standard rpart workflow
tree <- rpart(y ~ ., data = train, method = 'anova',
              control = rpart.control(cp = 0.001))

best_cp <- tree$cptable[which.min(tree$cptable[, 'xerror']), 'CP']
pruned  <- prune(tree, cp = best_cp)

test_pred <- predict(pruned, newdata = test)
rmse <- sqrt(mean((test_pred - test$y)^2))
cat('Pruned Tree RMSE:', rmse)