R-k折交叉验证

training <-iris
#抽样方法
#ind<-sample(2,nrow(training),replace=TRUE,prob=c(0.7,0.3)) #对数据分成两部分，70%训练数据，30%检测数据nrow(training)行数
#traindata<- training [ind==1,]  #训练集
#testdata<- training [ind==2,]  #测试集

10-fold cross-validation
就是十折交叉验证，用来测试精度，是常用的精度测试方法。
将数据集分成十分，轮流将其中9份做训练1份做测试，10次的结果的均值作为对算法精度的估计，
一般还需要进行多次10倍交叉验证求均值，例如10次10倍交叉验证，更精确一点。
#使用切分函数-K折交叉验证
library("caret")
folds<-createFolds(y=training$Species,k=10) #根据training的laber-Species把数据集切分成10等份
re<-{}
for(i in 1:10){
traindata<-training[-folds[[i]],]
testdata<-training[folds[[i]],]
rf <- randomForest(Species ~ ., data=training, ntree=100, proximity=TRUE) #Species是因变量
re=c(re,length(training$Species[which(predict(rf)==training$Species)])/length(training$Species))
}
mean(re)#取k折交叉验证结果的均值作为评判模型准确率的结果

现存的方法很多都会自带现成的工具caret
## Not run:

## Do 5 repeats of 10-Fold CV for the iris data. We will fit
## a KNN model that evaluates 12 values of k and set the seed
## at each iteration.

set.seed(123)
seeds <- vector(mode = "list", length = 51)
for(i in 1:50) seeds[[i]] <- sample.int(1000, 22)

## For the last model:
seeds[[51]] <- sample.int(1000, 1)

ctrl <- trainControl(method = "repeatedcv",repeats = 5,seeds = seeds)

set.seed(1)
mod <- train(Species ~ ., data = iris,method = "knn",tuneLength = 12,trControl = ctrl)

ctrl2 <- trainControl(method = "adaptive_cv",repeats = 5,verboseIter = TRUE,seeds = seeds)

set.seed(1)
mod2 <- train(Species ~ ., data = iris,method = "knn",tuneLength = 12,trControl = ctrl2)