```{r} library(caret) library(klaR) data(iris) #80/20%train split trainIndex<-createDataPartition(iris\(Species,p=0.80,list=FALSE) dataTrain<-iris[trainIndex,] dataTest<-iris[-trainIndex,] #train Naive Bayes fit<-NaiveBayes(Species~.,data=dataTrain) #make predictions predictions<-predict(fit,dataTest[,1:4]) #summarize results confusionMatrix(predictions\)class,dataTest$Species)
library(caret) data(iris) trainControl<-trainControl(method=“boot”,number=100) fit<-train(Species~.,data=iris,trControl=trainControl,method=“nb”) print(fit)
#kfold cross validation 10 fold 3 repeats library(caret) data(iris) trainControl<-trainControl(method=“repeatedcv”,number=10, repeats=3) fit<-train(Species~.,data=iris,trControl=trainControl,method=“nb”) print(fit) #leave one out cross validation library(caret) data(iris) trainControl<-trainControl(method=“LOOCV”) fit<-train(Species~.,data=iris,trControl=trainControl,method=“nb”) print(fit) #GITHUB NAIVE BAYES j brownlee comparing machine learning models library(mlbench) library(caret)
#4/30 trainControl<-trainControl(method=“repeatedcv”,number=10, repeats=3) #cart set.seed(7) fit.cart<-train(diabetes~.,data=PimaIndiansDiabetes, method =“rpart”,trControl=trainControl) library(mlbench) library(caret)
set.seed(7)
trainControl <- trainControl(method = “repeatedcv”, number = 10, repeats = 3)
data(PimaIndiansDiabetes)
fit.cart <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = “rpart”, trControl = trainControl) set.seed(7) # Train LDA model fit.lda <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = “lda”, trControl = trainControl) set.seed(7) # Train SVM model fit.svm <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = “svmRadial”, trControl = trainControl) set.seed(7) # Train KNN model fit.knn <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = “knn”, trControl = trainControl) set.seed(7) # Train RF model fit.rf <- train(diabetes ~ ., data = PimaIndiansDiabetes, method = “rf”, trControl = trainControl) results <- resamples(list(cart = fit.cart, lda = fit.lda, svm = fit.svm, knn = fit.knn, rf = fit.rf)) summary(results) prop.table(table(PimaIndiansDiabetes$diabetes)) scales<-list(x=list(relation=“free”),y=list(relation=“free”)) bwplot(results,scales=scales) splom(results) ```