chaid.R

#SOURCE https://sites.google.com/site/kittipat/rtechniques/usingchaiddecisiontreeinr


#install.packages("CHAID", repos="http://R-Forge.R-project.org") 

library("CHAID")

## Loading required package: partykit

## Loading required package: grid

### fit tree to sub-sample
set.seed(290875)
    data("USvote")
    # 
    # A data frame with 10645 observations on the following 6 variables.
    # 
    # vote3
    # candidate voted for Gore or Bush
    # 
    # gender
    # gender, a factor with levels male and female
    # 
    # ager
    # age group, an ordered factor with levels 18-24 < 25-34 < 35-44 < 45-54 < 55-64 < 65+
    #   
    #   empstat
    # status of employment, a factor with levels yes, no or retired
    # 
    # educr
    # status of education, an ordered factor with levels <HS < HS < >HS < College < Post Coll
    # 
    # marstat
    # status of living situation, a factor with levels married, widowed, divorced or never married
    
    
USvoteS <- USvote[sample(1:nrow(USvote), 1000),]
    
ctrl <- chaid_control(minsplit = 20, minbucket = 5, minprob = 0)
    
chaidUS <- chaid(vote3 ~ ., data = USvoteS, control = ctrl)

print(chaidUS)

## 
## Model formula:
## vote3 ~ gender + ager + empstat + educr + marstat
## 
## Fitted party:
## [1] root
## |   [2] marstat in married
## |   |   [3] educr <HS, HS, >HS: Gore (n = 311, err = 49.5%)
## |   |   [4] educr in College, Post Coll: Bush (n = 249, err = 35.3%)
## |   [5] marstat in widowed, divorced, never married
## |   |   [6] gender in male: Gore (n = 159, err = 47.8%)
## |   |   [7] gender in female
## |   |   |   [8] ager in 18-24, 25-34, 35-44, 45-54: Gore (n = 127, err = 22.0%)
## |   |   |   [9] ager in 55-64, 65+: Gore (n = 115, err = 40.9%)
## 
## Number of inner nodes:    4
## Number of terminal nodes: 5

## Plot the decision tree
    
plot(chaidUS)