r - 使用插入符号中的提升从两种不同的算法绘制 ROC 曲线

Question

我有如下两个模型:

library(mlbench)
data(Sonar)

library(caret)
set.seed(998)

my_data <- Sonar

fitControl <-
  trainControl(
    method = "boot632",
    number = 10,
    classProbs = T,
    savePredictions = "final",
    summaryFunction = twoClassSummary
  )


modelxgb <- train(
  Class ~ .,
  data = my_data,
  method = "xgbTree",
  trControl = fitControl,
  metric = "ROC"
)

library(mlbench)
data(Sonar)

library(caret)
set.seed(998)

my_data <- Sonar

fitControl <-
  trainControl(
    method = "boot632",
    number = 10,
    classProbs = T,
    savePredictions = "final",
    summaryFunction = twoClassSummary
  )


modelsvm <- train(
  Class ~ .,
  data = my_data,
  method = "svmLinear2",
  trControl = fitControl,
  metric = "ROC"
)

我想在一个 ggplot 上绘制两个模型的 ROC 曲线。

我正在执行以下操作来生成曲线的点:

for_lift_xgb = data.frame(Class = modelxgb$pred$obs,  xgbTree = modelxgb$pred$R)

for_lift_svm = data.frame(Class = modelsvm$pred$obs,  svmLinear2 = modelsvm$pred$R)

lift_obj_xgb = lift(Class ~ xgbTree, data = for_lift_xgb, class = "R")
lift_obj_svm = lift(Class ~ svmLinear2, data = for_lift_svm, class = "R")

将这两条曲线绘制在一个图上并用不同颜色绘制的最简单方法是什么。我还想在图中注释各个 AUC 值。

Answer 1

构建模型后，您可以将预测组合到一个数据框中:

for_lift = data.frame(Class = modelxgb$pred$obs,
                      xgbTree = modelxgb$pred$R,
                      svmLinear2 = modelsvm$pred$R)

使用它通过以下方式构建电梯对象:

lift = lift(Class ~ xgbTree + svmLinear2, data = for_lift, class = "R")

并用ggplot作图:

library(ggplot)

ggplot(lift$data)+
  geom_line(aes(1-Sp , Sn, color = liftModelVar))+
  scale_color_discrete(guide = guide_legend(title = "method"))

您可以通过这种方式组合和比较多个模型。

要将 auc 添加到绘图中，您可以创建一个包含模型名称、相应的 auc 和绘图坐标的数据框:

auc_ano <- data.frame(model = c("xgbTree","svmLinear2"),
                      auc = c(pROC::roc(response = for_lift$Class,
                                        predictor = for_lift$xgbTree,
                                        levels=c("M", "R"))$auc,
                              pROC::roc(response = for_lift$Class,
                                        predictor = for_lift$svmLinear2,
                                        levels=c("M", "R"))$auc),
                      y = c(0.95, 0.9))
auc_ano
#output
       model       auc    y
1    xgbTree 0.9000756 0.95
2 svmLinear2 0.5041086 0.90

并将其传递给 geom_text:

ggplot(lift$data)+
  geom_line(aes(1-Sp , Sn, color = liftModelVar))+
  scale_color_discrete(guide = guide_legend(title = "method"))+
  geom_text(data = auc_ano, aes(label = round(auc, 4), color = model, y = y), x = 0.1)