Decision Trees in R

library(rattle)

## Rattle: A free graphical interface for data science with R.
## Version 5.2.0 Copyright (c) 2006-2018 Togaware Pty Ltd.
## Type 'rattle()' to shake, rattle, and roll your data.

library(rpart.plot)

## Loading required package: rpart

library(rpart)
library(RColorBrewer)
library(MASS)

• low - indicator of whether the birth weight is less than 2.5kg
• age - mother’s age in year
• lwt - mother’s weight in pounds at last menstrual period
• race - mother’s race (1 = white, 2 = black, white = other)
• smoke - smoking status during pregnancy
• ptl - number of previous premature labours
• ht - history of hypertension
• ui - presence of uterine irritability
• ftv - number of physician visits during the first trimester
• bwt - birth weight in grams

head(birthwt)

##    low age lwt race smoke ptl ht ui ftv  bwt
## 85   0  19 182    2     0   0  0  1   0 2523
## 86   0  33 155    3     0   0  0  0   3 2551
## 87   0  20 105    1     1   0  0  0   1 2557
## 88   0  21 108    1     1   0  0  1   2 2594
## 89   0  18 107    1     1   0  0  1   0 2600
## 91   0  21 124    3     0   0  0  0   0 2622

• Quick look at distribution of birth weights

hist(birthwt$bwt)

- This table reads that 130 infants weigh more than 2.5kg and 59 weigh less than 2.5kg.

• Buy guessing using the most common occurences and basic math, your prediction would be 68.78% (130/(130+59))

table(birthwt$low)

## 
##   0   1 
## 130  59

• Converting categorical variables to factor

cols <- c('low', 'race', 'smoke', 'ht', 'ui')
birthwt[cols] <- lapply(birthwt[cols], as.factor)

• Splitting the data sets into a training set and test set

set.seed(1)
train <- sample(1:nrow(birthwt), 0.75 * nrow(birthwt))

• Build the model using rpart() from the rpart package

• Since ‘low’ equals the bodyweight that is less than 2.5kg, it is excluded from the model exclude, and since it is a classification task, we specify method

birthwtTree <- rpart(low ~ . - bwt, data = birthwt[train, ], method = 'class')

• Plotting a simple tree

plot(birthwtTree)
text(birthwtTree, pretty = 0)

• Using fancyRpartPlot() from the rattle package to give it some more pleasent aesthetics

fancyRpartPlot(birthwtTree)

• Checking the accuracy of our new model (75%)

birthwtPred <- predict(birthwtTree, birthwt[-train, ], type = 'class')
table(birthwtPred, birthwt[-train, ]$low)

##            
## birthwtPred  0  1
##           0 31 10
##           1  2  5

• Can further improve accuracy by using bagging and random forests.