Predicting with Trees, Random Forests and Predictive Models

Example Iris Data

data(iris); library(ggplot2)
names(iris)

## [1] "Sepal.Length" "Sepal.Width"  "Petal.Length" "Petal.Width" 
## [5] "Species"

table(iris$Species)

## 
##     setosa versicolor  virginica 
##         50         50         50

Create training and test sets

inTrain <- createDataPartition(y=iris$Species, p=0.7, list=FALSE)
training <- iris[inTrain,]
testing <- iris[-inTrain,]
dim(training); dim(testing)

## [1] 105   5

## [1] 45  5

ris petal widths/sepal width

qplot(Petal.Width,Sepal.Width,colour=Species,data=training)

Iris petal widths/sepal width

library(caret)
modFit <- train(Species ~ .,method="rpart",data=training)
print(modFit$finalModel)

## n= 105 
## 
## node), split, n, loss, yval, (yprob)
##       * denotes terminal node
## 
## 1) root 105 70 setosa (0.3333333 0.3333333 0.3333333)  
##   2) Petal.Length< 2.6 35  0 setosa (1.0000000 0.0000000 0.0000000) *
##   3) Petal.Length>=2.6 70 35 versicolor (0.0000000 0.5000000 0.5000000)  
##     6) Petal.Width< 1.65 38  4 versicolor (0.0000000 0.8947368 0.1052632) *
##     7) Petal.Width>=1.65 32  1 virginica (0.0000000 0.0312500 0.9687500) *

Plot tree

plot(modFit$finalModel, uniform=TRUE, 
      main="Classification Tree")
text(modFit$finalModel, use.n=TRUE, all=TRUE, cex=.8)

Prettier plots

library(rattle)

## Rattle: A free graphical interface for data science with R.
## Version 5.1.0 Copyright (c) 2006-2017 Togaware Pty Ltd.
## Type 'rattle()' to shake, rattle, and roll your data.

fancyRpartPlot(modFit$finalModel)

Predicting new values

predict(modFit,newdata=testing)

##  [1] setosa     setosa     setosa     setosa     setosa     setosa    
##  [7] setosa     setosa     setosa     setosa     setosa     setosa    
## [13] setosa     setosa     setosa     versicolor versicolor versicolor
## [19] versicolor versicolor versicolor versicolor versicolor virginica 
## [25] versicolor versicolor versicolor versicolor versicolor versicolor
## [31] virginica  virginica  virginica  virginica  virginica  virginica 
## [37] virginica  virginica  virginica  virginica  virginica  virginica 
## [43] virginica  virginica  virginica 
## Levels: setosa versicolor virginica