rm(list=ls(all=TRUE))
set.seed(1011)

##################################################
#######           RANDOM FOREST            #######   
##################################################


#install.packages('randomForest')
library(randomForest)

data(iris)
head(iris)

# PLOTING

plot(iris[,3], iris[,4], pch=21, xlab=names(iris)[3], ylab=names(iris)[4],
     bg=c("red", "blue", "green")[as.numeric(factor(iris$Species))],
     main="Iris data")
legend("bottomright", pch=21,legend=levels(iris$Species),pt.bg=c("red", "blue", "green"))



rowsTrain=sample(1:nrow(iris),round(0.75*nrow(iris)))
train = iris[rowsTrain,]
head(train)

iris.rf <- randomForest(train[,-5], train[,5])
iris.rf

pred=predict(iris.rf,iris[-rowsTrain,])
pred

table(pred,iris[-rowsTrain,5])

# And I can tune RF parameters 

fit=randomForest(Species~.,data = iris, subset = rowsTrain, mtry=2, ntree=200)

fit


wVIL <- randomForest(Species ~ ., data = iris, subset = rowsTrain, mtry=2, ntree=200,importance=TRUE)
varImpPlot(wVIL, type=1, pch=19, col="blue", cex=0.7, main="")