C5.0 Classification Models
In C50: C5.0 Decision Trees and Rule-Based Models

knitr::opts_chunk$set(echo = TRUE)
library(C50)
library(modeldata)

The C50 package contains an interface to the C5.0 classification model. The main two modes for this model are:

a basic tree-based model
a rule-based model

Many of the details of this model can be found in Quinlan (1993) although the model has new features that are described in Kuhn and Johnson (2013). The main public resource on this model comes from the RuleQuest website.

To demonstrate a simple model, we'll use the credit data that can be accessed in the modeldata package:

library(modeldata)
data(credit_data)

The outcome is in a column called Status and, to demonstrate a simple model, the Home and Seniority predictors will be used.

vars <- c("Home", "Seniority")
str(credit_data[, c(vars, "Status")])

# a simple split
set.seed(2411)
in_train <- sample(1:nrow(credit_data), size = 3000)
train_data <- credit_data[ in_train,]
test_data  <- credit_data[-in_train,]

Classification Trees

To fit a simple classification tree model, we can start with the non-formula method:

library(C50)
tree_mod <- C5.0(x = train_data[, vars], y = train_data$Status)
tree_mod

To understand the model, the summary method can be used to get the default C5.0 command-line output:

summary(tree_mod)

A graphical method for examining the model can be generated by the plot method:

plot(tree_mod)

A variety of options are outlines in the documentation for C5.0Control function. Another option that can be used is the trials argument which enables a boosting procedure. This method is model similar to AdaBoost than to more statistical approaches such as stochastic gradient boosting.

For example, using three iterations of boosting:

tree_boost <- C5.0(x = train_data[, vars], y = train_data$Status, trials = 3)
summary(tree_boost)

Note that the counting is zero-based. The plot method can also show a specific tree in the ensemble using the trial option.

Rule-Based Models

C5.0 can create an initial tree model then decompose the tree structure into a set of mutually exclusive rules. These rules can then be pruned and modified into a smaller set of potentially overlapping rules. The rules can be created using the rules option:

rule_mod <- C5.0(x = train_data[, vars], y = train_data$Status, rules = TRUE)
rule_mod
summary(rule_mod)

Note that no pruning was warranted for this model.

There is no plot method for rule-based models.

Predictions

The predict method can be used to get hard class predictions or class probability estimates (aka "confidence values" in documentation).

predict(rule_mod, newdata = test_data[1:3, vars])
predict(tree_boost, newdata = test_data[1:3, vars], type = "prob")

Cost-Sensitive Models

A cost-matrix can also be used to emphasize certain classes over others. For example, to get more of the "bad" samples correct:

cost_mat <- matrix(c(0, 2, 1, 0), nrow = 2)
rownames(cost_mat) <- colnames(cost_mat) <- c("bad", "good")
cost_mat

cost_mod <- C5.0(x = train_data[, vars], y = train_data$Status, 
                 costs = cost_mat)
summary(cost_mod)

# more samples predicted as "bad"
table(predict(cost_mod, test_data[, vars]))

# that previously
table(predict(tree_mod, test_data[, vars]))