使用 F1 指标在插入符中训练模型

Question

我正在尝试将随机森林模型拟合到我的数据集，并且我想根据 F1 分数选择最佳模型。我在这里看到一篇文章描述了必要的代码。我尝试复制代码，但收到错误

“{ 中的错误：任务 1 失败 -”找不到函数“F1_Score”

当我运行火车功能时。（仅供参考，我试图预测的变量（“通过”）是一个两类因素“失败”和“通过”）

请参阅下面的代码：

library(MLmetrics)
library(caret)
library(doSNOW)

f1 <- function(data, lev = NULL, model = NULL) {
  f1_val <- F1_Score(y_pred = data$pred, y_true = data$obs, positive = lev[1])
  c(F1 = f1_val)
}



train.control <- trainControl(method = "repeatedcv",
                              number = 10,
                              repeats = 3,
                              classProbs = TRUE,
                              summaryFunction = f1,
                              search = "grid")


tune.grid <- expand.grid(.mtry = seq(from = 1, to = 10, by = 1))


cl <- makeCluster(3, type = "SOCK")
registerDoSNOW(cl)
random.forest.orig <- train(pass ~ manufacturer+meter.type+premise+size+age+avg.winter+totalizer, 
                     data = meter.train,
                     method = "rf",
                     tuneGrid = tune.grid,
                     metric = "F1",
                     weights = model_weights,
                     trControl = train.control)
stopCluster(cl)

Answer 1

我已经重写了 f1 函数，不使用 MLmetrics 库，它似乎可以工作。请参阅下面的创建 f1 分数的工作代码：

f1 <- function (data, lev = NULL, model = NULL) {
  precision <- posPredValue(data$pred, data$obs, positive = "pass")
  recall  <- sensitivity(data$pred, data$obs, postive = "pass")
  f1_val <- (2 * precision * recall) / (precision + recall)
  names(f1_val) <- c("F1")
  f1_val
} 

train.control <- trainControl(method = "repeatedcv",
                          number = 10,
                          repeats = 3,
                          classProbs = TRUE,
                          #sampling = "smote",
                          summaryFunction = f1,
                          search = "grid")


tune.grid <- expand.grid(.mtry = seq(from = 1, to = 10, by = 1))


cl <- makeCluster(3, type = "SOCK")
registerDoSNOW(cl)
random.forest.orig <- train(pass ~ manufacturer+meter.type+premise+size+age+avg.winter+totalizer, 
                 data = meter.train,
                 method = "rf",
                 tuneGrid = tune.grid,
                 metric = "F1",
                 trControl = train.control)
stopCluster(cl)