iris.R

d = iris
library(caTools)
library(rpart)
library(rpart.plot)
library(caret)

## Loading required package: ggplot2

## Loading required package: lattice

# Splitting
set.seed(20) # Setting the seed
sample =sample.split(d$Species, SplitRatio = .70)
Train=subset(d, sample==TRUE)
Test=subset(d, sample==FALSE)

# Training the decision Tree classifier
Tree <- rpart(Species~., data=Train,cp=0.2)# The dot reps all other variables
# Prediction
Tree.Species.pred = predict(Tree,Test,type = c( "class"))
Tree.Species.pred = predict(Tree,Test,type = c( "class"),
                            na.action = na.pass)

# Confusion matrix to evaluate the model
# confusionMatrix(your predicted test, the actual values)
confusionMatrix(Tree.Species.pred,Test$Species)

## Confusion Matrix and Statistics
## 
##             Reference
## Prediction   setosa versicolor virginica
##   setosa         15          0         0
##   versicolor      0         15         2
##   virginica       0          0        13
## 
## Overall Statistics
##                                           
##                Accuracy : 0.9556          
##                  95% CI : (0.8485, 0.9946)
##     No Information Rate : 0.3333          
##     P-Value [Acc > NIR] : < 2.2e-16       
##                                           
##                   Kappa : 0.9333          
##                                           
##  Mcnemar's Test P-Value : NA              
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            1.0000           0.8667
## Specificity                 1.0000            0.9333           1.0000
## Pos Pred Value              1.0000            0.8824           1.0000
## Neg Pred Value              1.0000            1.0000           0.9375
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3333           0.2889
## Detection Prevalence        0.3333            0.3778           0.2889
## Balanced Accuracy           1.0000            0.9667           0.9333

# Visualizing the decision Tree
rpart.plot(Tree,
           main='using rpart',border.col='purple',
    box.col=c('green','blue','orange'),
    split.box.col='yellow',
    split.border.col='red',
    split.round=1,
    round=T,
    leaf.round = 1,lwd=2)

# Visualizing the decision Tree
prp(Tree,
    main='using prp',border.col='purple',
           box.col=c('green','blue','orange'),
           split.box.col='yellow',
           split.border.col='red',
           split.round=1,
           round=T,
           leaf.round = 1,lwd=2)

rpart.plot(Tree)