Using Random Forest

library(randomForest)

## Warning: package 'randomForest' was built under R version 3.4.4

## randomForest 4.6-14

## Type rfNews() to see new features/changes/bug fixes.

data(iris)
#View(iris)
# Splitting data into training and testing. As the species are in order 
# splitting the data based on species 
iris_setosa <- iris[iris$Species=="setosa",] # 50
iris_versicolor <- iris[iris$Species=="versicolor",] # 50
iris_virginica <- iris[iris$Species=="virginica",] # 50
iris_train <- rbind(iris_setosa[1:35,],iris_versicolor[1:35,],iris_virginica[1:35,])
iris_test <- rbind(iris_setosa[36:50,],iris_versicolor[36:50,],iris_virginica[36:50,])

# Building a random forest model on training data 
#attach(iris_train)
fit.forest <- randomForest(iris_train$Species ~ .,data=iris_train)

predict(fit.forest,iris_test) # 100% accuracy 

##         36         37         38         39         40         41 
##     setosa     setosa     setosa     setosa     setosa     setosa 
##         42         43         44         45         46         47 
##     setosa     setosa     setosa     setosa     setosa     setosa 
##         48         49         50         86         87         88 
##     setosa     setosa     setosa versicolor versicolor versicolor 
##         89         90         91         92         93         94 
## versicolor versicolor versicolor versicolor versicolor versicolor 
##         95         96         97         98         99        100 
## versicolor versicolor versicolor versicolor versicolor versicolor 
##        136        137        138        139        140        141 
##  virginica  virginica  virginica versicolor  virginica  virginica 
##        142        143        144        145        146        147 
##  virginica  virginica  virginica  virginica  virginica  virginica 
##        148        149        150 
##  virginica  virginica  virginica 
## Levels: setosa versicolor virginica

# Training accuracy 
mean(iris_train$Species == predict(fit.forest,iris_train)) # 100% accuracy 

## [1] 1

# Predicting test data 
pred_test <- predict(fit.forest,newdata=iris_test)
mean(pred_test==iris_test$Species) # Accuracy = 100 % 

## [1] 0.9777778