Question

我使用了caret个套件train功能，并进行了10次交叉验证。通过在classProbs = TRUE中设置trControl，我也有预测班级的班级概率，如下所示：

myTrainingControl <- trainControl(method = "cv", 
                              number = 10, 
                              savePredictions = TRUE, 
                              classProbs = TRUE, 
                              verboseIter = TRUE)

randomForestFit = train(x = input[3:154], 
                        y = as.factor(input$Target), 
                        method = "rf", 
                        trControl = myTrainingControl, 
                        preProcess = c("center","scale"), 
                        ntree = 50)

我得到的输出预测如下。

  pred obs    0    1 rowIndex mtry Resample

1    0   1 0.52 0.48       28   12   Fold01
2    0   0 0.58 0.42       43   12   Fold01
3    0   1 0.58 0.42       51   12   Fold01
4    0   0 0.68 0.32       55   12   Fold01
5    0   0 0.62 0.38       59   12   Fold01
6    0   1 0.92 0.08       71   12   Fold01

现在我想使用这些数据计算ROC下的ROC和AUC。我怎么做到这一点？

Answer 1

AUC的示例：

rf_output=randomForest(x=predictor_data, y=target, importance = TRUE, ntree = 10001, proximity=TRUE, sampsize=sampsizes)

library(ROCR)
predictions=as.vector(rf_output$votes[,2])
pred=prediction(predictions,target)

perf_AUC=performance(pred,"auc") #Calculate the AUC value
AUC=perf_AUC@y.values[[1]]

perf_ROC=performance(pred,"tpr","fpr") #plot the actual ROC curve
plot(perf_ROC, main="ROC plot")
text(0.5,0.5,paste("AUC = ",format(AUC, digits=5, scientific=FALSE)))

或使用pROC和caret

library(caret)
library(pROC)
data(iris)


iris <- iris[iris$Species == "virginica" | iris$Species == "versicolor", ]
iris$Species <- factor(iris$Species)  # setosa should be removed from factor



samples <- sample(NROW(iris), NROW(iris) * .5)
data.train <- iris[samples, ]
data.test <- iris[-samples, ]
forest.model <- train(Species ~., data.train)

result.predicted.prob <- predict(forest.model, data.test, type="prob") # Prediction

result.roc <- roc(data.test$Species, result.predicted.prob$versicolor) # Draw ROC curve.
plot(result.roc, print.thres="best", print.thres.best.method="closest.topleft")

result.coords <- coords(result.roc, "best", best.method="closest.topleft", ret=c("threshold", "accuracy"))
print(result.coords)#to get threshold and accuracy

Answer 2

Update2019。这是MLeval编写的（https://cran.r-project.org/web/packages/MLeval/index.html），它与Caret训练输出对象配合使用，以制作ROC，PR曲线，校准曲线，并计算指标，例如ROC-AUC，灵敏度，特异性等。它只用一行就可以完成所有这些工作，这对我的分析很有帮助，并且可能会引起人们的兴趣。

library(caret)
library(MLeval)

myTrainingControl <- trainControl(method = "cv", 
                                  number = 10, 
                                  savePredictions = TRUE, 
                                  classProbs = TRUE, 
                                  verboseIter = TRUE)

randomForestFit = train(x = Sonar[,1:60], 
                        y = as.factor(Sonar$Class), 
                        method = "rf", 
                        trControl = myTrainingControl, 
                        preProcess = c("center","scale"), 
                        ntree = 50)

##

x <- evalm(randomForestFit)

## get roc curve plotted in ggplot2

x$roc

## get AUC and other metrics

x$stdres

在R中使用插入符训练后如何计算ROC下的ROC和AUC？

2 个答案: