插入符包自定义指标

Question

我在我的一个项目中使用插入符函数 "train()"，我想添加 "custom metric" F1 分数。我看了这个 url caret package 但我无法理解如何使用可用参数构建此分数。

自定义指标的示例如下：

## Example with a custom metric
madSummary <- function (data,
lev = NULL,
model = NULL) {
out <- mad(data$obs - data$pred,
na.rm = TRUE)
names(out) <- "MAD"
out
}
robustControl <- trainControl(summaryFunction = madSummary)
marsGrid <- expand.grid(degree = 1, nprune = (1:10) * 2)
earthFit <- train(medv ~ .,
data = BostonHousing,
method = "earth",
tuneGrid = marsGrid,
metric = "MAD",
maximize = FALSE,
trControl = robustControl)

更新：

我试过你的代码，但问题是它不适用于多个类，就像下面的代码一样（显示 F1 分数，但它很奇怪）我不确定，但我认为函数 F1_score 仅适用于二进制类

library(caret)
library(MLmetrics)

set.seed(346)
dat <- iris

## See http://topepo.github.io/caret/training.html#metrics
f1 <- function(data, lev = NULL, model = NULL) {

print(data)
  f1_val <- F1_Score(y_pred = data$pred, y_true = data$obs)
  c(F1 = f1_val)
}

# Split the Data into .75 input
in_train <- createDataPartition(dat$Species, p = .70, list = FALSE)

trainClass <- dat[in_train,]
testClass <- dat[-in_train,]



set.seed(35)
mod <- train(Species ~ ., data = trainClass ,
             method = "rpart",
             metric = "F1",
             trControl = trainControl(summaryFunction = f1, 
                                  classProbs = TRUE))

print(mod)

我也编写了一个手动 F1 分数，其中一个输入是混淆矩阵：（我不确定我们是否可以在 "summaryFunction"

中使用混淆矩阵

F1_score <- function(mat, algoName){

##
## Compute F1-score
##


# Remark: left column = prediction // top = real values
recall <- matrix(1:nrow(mat), ncol = nrow(mat))
precision <- matrix(1:nrow(mat), ncol = nrow(mat))
F1_score <- matrix(1:nrow(mat), ncol = nrow(mat))


for(i in 1:nrow(mat)){
  recall[i] <- mat[i,i]/rowSums(mat)[i]
  precision[i] <- mat[i,i]/colSums(mat)[i]
}

for(i in 1:ncol(recall)){
   F1_score[i] <- 2 * ( precision[i] * recall[i] ) / ( precision[i] + recall[i])
 }

 # We display the matrix labels
 colnames(F1_score) <- colnames(mat)
 rownames(F1_score) <- algoName

 # Display the F1_score for each class
 F1_score

 # Display the average F1_score
 mean(F1_score[1,])
}

Answer 1

您应该查看 The caret Package - Alternate Performance Metrics 了解详细信息。一个工作示例：

library(caret)
library(MLmetrics)

set.seed(346)
dat <- twoClassSim(200)

## See https://topepo.github.io/caret/model-training-and-tuning.html#metrics
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)
}

set.seed(35)
mod <- train(Class ~ ., data = dat,
             method = "rpart",
             tuneLength = 5,
             metric = "F1",
             trControl = trainControl(summaryFunction = f1, 
                                      classProbs = TRUE))

Answer 2

对于两个class的情况，您可以尝试以下方法：

mod <- train(Class ~ ., 
             data = dat,
             method = "rpart",
             tuneLength = 5,
             metric = "F",
             trControl = trainControl(summaryFunction = prSummary, 
                                      classProbs = TRUE))

或定义一个自定义摘要函数，它结合了当前最喜欢的 twoClassSummary 和 prSummary，它提供了以下可能的评估指标 - AUROC、Spec、Sens、AUPRC、Precision、Recall、F - 其中任何一个都可以用作 metric 参数。这也包括我在对已接受答案的评论中提到的特殊情况（F 是 NA）。

comboSummary <- function(data, lev = NULL, model = NULL) {
  out <- c(twoClassSummary(data, lev, model), prSummary(data, lev, model))

  # special case missing value for F
  out$F <- ifelse(is.na(out$F), 0, out$F)  
  names(out) <- gsub("AUC", "AUPRC", names(out))
  names(out) <- gsub("ROC", "AUROC", names(out))
  return(out)
}

mod <- train(Class ~ ., 
             data = dat,
             method = "rpart",
             tuneLength = 5,
             metric = "F",
             trControl = trainControl(summaryFunction = comboSummary, 
                                      classProbs = TRUE))

插入符包自定义指标

Caret package Custom metric

r

r-caret