library(openxlsx) wine = read.xlsx("E:/時間趨勢/winequality-red-2.xlsx") #將數據集分為訓練集和測試集,比例為7:3 train_sub = sample(nrow(wine),7/10*nrow(wine)) train_data = wine[train_sub,] test_data = wine[-train_sub,] library(pROC) #繪制ROC曲線 library(randomForest) #數據預處理 train_data$Yield = as.factor(train_data$Yield) test_data$Yield = as.factor(test_data$Yield) wine_randomforest <- randomForest(Yield ~ Tmax+Tmin+AVRH+AVGT+SD+CWDI+P,data = train_data,ntree =500,mtry=3,importance=TRUE ,proximity=TRUE) #查看變量的重要性 wine_randomforest$importance varImpPlot(wine_randomforest, main = "variable importance",font = 2,lwd = 5,col = "red",col.axis = "blue",font.axis = 2,cex = 1,cex.axis = 5,pch = 16,cex.lab = 0.7,font.lab = 2)#對測試集進行預測 pre_ran <- predict(wine_randomforest,newdata=test_data) #將真實值和預測值整合到一起 obs_p_ran = data.frame(prob=pre_ran,obs=test_data$Yield) #輸出混淆矩陣 table(test_data$Yield,pre_ran,dnn=c("真實值","預測值")) #繪制ROC曲線 ran_roc <- roc(test_data$Yield,as.numeric(pre_ran)) plot(ran_roc, print.auc=TRUE, auc.polygon=TRUE, grid=c(0.1, 0.2),grid.col=c("green", "red"), max.auc.polygon=TRUE,auc.polygon.col="skyblue", print.thres=TRUE,main='隨機森林模型ROC曲線,mtry=3,ntree=500')

總結

以上是生活随笔為你收集整理的随机森林重要性排序-R的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。