Random Forest Approach in R Programming

data(iris)
  
str(iris)

## 'data.frame':    150 obs. of  5 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

library(caTools)
library(randomForest)

## randomForest 4.7-1.1

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

split <- sample.split(iris, SplitRatio = 0.7)
split

## [1]  TRUE FALSE  TRUE FALSE  TRUE

train <- subset(iris, split == "TRUE")
test <- subset(iris, split == "FALSE")
  
set.seed(120)  # Setting seed
classifier_RF = randomForest(x = train[-5],
                             y = train$Species,
                             ntree = 500)
  
classifier_RF

## 
## Call:
##  randomForest(x = train[-5], y = train$Species, ntree = 500) 
##                Type of random forest: classification
##                      Number of trees: 500
## No. of variables tried at each split: 2
## 
##         OOB estimate of  error rate: 4.44%
## Confusion matrix:
##            setosa versicolor virginica class.error
## setosa         30          0         0  0.00000000
## versicolor      0         28         2  0.06666667
## virginica       0          2        28  0.06666667

y_pred = predict(classifier_RF, newdata = test[-5])
  
confusion_mtx = table(test[, 5], y_pred)
confusion_mtx

##             y_pred
##              setosa versicolor virginica
##   setosa         20          0         0
##   versicolor      0         19         1
##   virginica       0          3        17

plot(classifier_RF)

importance(classifier_RF)

##              MeanDecreaseGini
## Sepal.Length         5.906138
## Sepal.Width          1.199741
## Petal.Length        29.700240
## Petal.Width         22.501569

varImpPlot(classifier_RF)