我正在构建两个不同的分类器来预测二进制输出。然后我想通过使用ROC曲线和它下面的面积(AUC)比较两个模型的结果。R符号外插样本和测试集ROC
我将数据集分为训练集和测试集。在训练集上,我执行一种交叉验证的形式。从交叉验证的保留样本中,我可以为每个模型建立ROC曲线。然后,我使用测试集上的模型并构建另一组ROC曲线。
结果是矛盾的,这使我感到困惑。我不确定哪个结果是正确的,或者我是否做了完全错误的事情。示例ROC曲线显示RF是更好的模型,训练集ROC曲线显示SVM是更好的模型。
分析
library(ggplot2)
library(caret)
library(pROC)
library(ggthemes)
library(plyr)
library(ROCR)
library(reshape2)
library(gridExtra)
my_data <- read.csv("http://www.ats.ucla.edu/stat/data/binary.csv")
str(my_data)
names(my_data)[1] <- "Class"
my_data$Class <- ifelse(my_data$Class == 1, "event", "noevent")
my_data$Class <- factor(emr$Class, levels = c("noevent", "event"), ordered = TRUE)
set.seed(1732)
ind <- createDataPartition(my_data$Class, p = 2/3, list = FALSE)
train <- my_data[ ind,]
test <- my_data[-ind,]
接下来我训练两种模式:随机森林和支持向量机。在这里,我还使用Max Kuhns函数从两个模型的保留样本中获取平均ROC曲线,并将这些结果与曲线的AUC一起保存到另一个数据框架中。
#Train RF
ctrl <- trainControl(method = "repeatedcv",
number = 5,
repeats = 3,
classProbs = TRUE,
savePredictions = TRUE,
summaryFunction = twoClassSummary)
grid <- data.frame(mtry = seq(1,3,1))
set.seed(1537)
rf_mod <- train(Class ~ .,
data = train,
method = "rf",
metric = "ROC",
tuneGrid = grid,
ntree = 1000,
trControl = ctrl)
rfClasses <- predict(rf_mod, test)
#This is the ROC curve from held out samples. Source is from Max Kuhns 2016 UseR! code here: https://github.com/topepo/useR2016
roc_train <- function(object, best_only = TRUE, ...) {
lvs <- object$modelInfo$levels(object$finalModel)
if(best_only) {
object$pred <- merge(object$pred, object$bestTune)
}
## find tuning parameter names
p_names <- as.character(object$modelInfo$parameters$parameter)
p_combos <- object$pred[, p_names, drop = FALSE]
## average probabilities across resamples
object$pred <- plyr::ddply(.data = object$pred,
.variables = c("obs", "rowIndex", p_names),
.fun = function(dat, lvls = lvs) {
out <- mean(dat[, lvls[1]])
names(out) <- lvls[1]
out
})
make_roc <- function(x, lvls = lvs, nms = NULL, ...) {
out <- pROC::roc(response = x$obs,
predictor = x[, lvls[1]],
levels = rev(lvls))
out$model_param <- x[1,nms,drop = FALSE]
out
}
out <- plyr::dlply(.data = object$pred,
.variables = p_names,
.fun = make_roc,
lvls = lvs,
nms = p_names)
if(length(out) == 1) out <- out[[1]]
out
}
temp <- roc_train(rf_mod)
plot_data_ROC <- data.frame(Model='Random Forest', sens = temp$sensitivities, spec=1-temp$specificities)
#This is the AUC of the held-out samples roc curve for RF
auc.1 <- abs(sum(diff(1-temp$specificities) * (head(temp$sensitivities,-1)+tail(temp$sensitivities,-1)))/2)
#Build SVM
set.seed(1537)
svm_mod <- train(Class ~ .,
data = train,
method = "svmRadial",
metric = "ROC",
trControl = ctrl)
svmClasses <- predict(svm_mod, test)
#ROC curve into df
temp <- roc_train(svm_mod)
plot_data_ROC <- rbind(plot_data_ROC, data.frame(Model='Support Vector Machine', sens = temp$sensitivities, spec=1-temp$specificities))
#This is the AUC of the held-out samples roc curve for SVM
auc.2 <- abs(sum(diff(1-temp$specificities) * (head(temp$sensitivities,-1)+tail(temp$sensitivities,-1)))/2)
接下来,我将绘制结果
#Plotting Final
#ROC of held-out samples
q <- ggplot(data=plot_data_ROC, aes(x=spec, y=sens, group = Model, colour = Model))
q <- q + geom_path() + geom_abline(intercept = 0, slope = 1) + xlab("False Positive Rate (1-Specificity)") + ylab("True Positive Rate (Sensitivity)")
q + theme(axis.line = element_line(), axis.text=element_text(color='black'),
axis.title = element_text(colour = 'black'), legend.text=element_text(), legend.title=element_text())
#ROC of testing set
rf.probs <- predict(rf_mod, test,type="prob")
pr <- prediction(rf.probs$event, factor(test$Class, levels = c("noevent", "event"), ordered = TRUE))
pe <- performance(pr, "tpr", "fpr")
roc.data <- data.frame(Model='Random Forest',fpr=unlist([email protected]), tpr=unlist([email protected]))
svm.probs <- predict(svm_mod, test,type="prob")
pr <- prediction(svm.probs$event, factor(test$Class, levels = c("noevent", "event"), ordered = TRUE))
pe <- performance(pr, "tpr", "fpr")
roc.data <- rbind(roc.data, data.frame(Model='Support Vector Machine',fpr=unlist([email protected]), tpr=unlist([email protected])))
q <- ggplot(data=roc.data, aes(x=fpr, y=tpr, group = Model, colour = Model))
q <- q + geom_line() + geom_abline(intercept = 0, slope = 1) + xlab("False Positive Rate (1-Specificity)") + ylab("True Positive Rate (Sensitivity)")
q + theme(axis.line = element_line(), axis.text=element_text(color='black'),
axis.title = element_text(colour = 'black'), legend.text=element_text(), legend.title=element_text())
#AUC of hold out samples
data.frame(Rf = auc.1, Svm = auc.2)
#AUC of testing set. Source is from Max Kuhns 2016 UseR! code here: https://github.com/topepo/useR2016
test_pred <- data.frame(Class = factor(test$Class, levels = c("noevent", "event"), ordered = TRUE))
test_pred$Rf <- predict(rf_mod, test, type = "prob")[, "event"]
test_pred$Svm <- predict(svm_mod, test, type = "prob")[, "event"]
get_auc <- function(pred, ref){
auc(roc(ref, pred, levels = rev(levels(ref))))
}
apply(test_pred[, -1], 2, get_auc, ref = test_pred$Class)
从持有出样品和测试集是完全不同的结果(我知道他们会有所不同,但是通过这么多?)。
Rf Svm
0.656044 0.5983193
Rf Svm
0.6326531 0.6453428
从外挂的样品中选择RF模型,但从测试集中选择SVM模型。
哪一种是选择模型的“正确”或“更好”方式? 我在某个地方犯了一个大错,或者没有正确理解某些东西?
是的我有3个数据集:“培训”,“从培训中拿出样本”和“测试”(我编辑了第二段,因为我在解释这个时犯了一个错误)。我将使用真正的测试集,并摆脱训练集中保留样本制作的ROC曲线。感谢您的答复! – Aerocell