在R中使用XGBoost进行基于回归的模型

install.packages("xgboost")
library(xgboost)

# 准备数据
train_index <- sample(1:nrow(data), 0.8 * nrow(data))
train_data <- data[train_index, ]
test_data <- data[-train_index, ]

# 特征和目标变量
train_features <- train_data[, -which(names(train_data) == "target")]
train_target <- train_data$target
test_features <- test_data[, -which(names(test_data) == "target")]

# 转换为DMatrix格式
dtrain <- xgb.DMatrix(data = as.matrix(train_features), label = train_target)
dtest <- xgb.DMatrix(data = as.matrix(test_features))

# 设置参数
params <- list(
  objective = "reg:squarederror",  # 回归任务
  eta = 0.1,
  max_depth = 6,
  subsample = 0.7,
  colsample_bytree = 0.7
)

# 训练模型
bst <- xgb.train(
  params = params,
  data = dtrain,
  nrounds = 100,
  watchlist = list(train = dtrain, test = dtest),
  early_stopping_rounds = 10
)

# 预测
pred <- predict(bst, dtest)

# 评估模型
rmse <- sqrt(mean((test_data$target - pred)^2))
print(paste("RMSE:", rmse))