install.packages("randomForest")

#只有caret包才有混淆矩阵

#set.seed保证每次运行代码获得相同的随机样本

npdata <- read.table("data.txt",header=T)

set.seed(123)

#抽取训练集和测试集

train_sub <- sample(nrow(npdata),0.7*nrow(npdata ))#随机无放回抽取0.7样本

train_data <- npdata[train_sub,]

test_data <- npdata[-train_sub,]

library(randomForest)

#导入数据

#随机森林计算

set.seed(100)

np.rf <- randomForest(npl~.,data=train_data,importance=TRUE,ntree=50)

#使用训练集查看预测精度

np_predict <- predict(np.rf,train_data)

plot(train_data$npl,np_predict,main='训练集', xlab = 'npl',ylab = 'Predict')

abline(1,1)

#使用测试集评估预测性能

np_predict <- predict(np.rf,test_data)

plot(test_data$npl,np_predict,main='预测集', xlab = 'npl',ylab = 'Predict')

abline(1,1)

#查看拟合优度

print(np.rf)

importance(np.rf)

varImpPlot(np.rf,main = "variable importance")

#最优决策树数量

plot(np.rf)

#绘制错误率表,确定变量个数

result = rfcv(train_data[-1],train_data$npl,cv.fold = 10)

result$error.cv

with(result,plot(n.var,error.cv,log="x",type = "o",lwd=2))