使用R语言C5.0构建决策树无输出的问题排查

问题背景 #

使用R语言的C50包构建决策树，数据集为14行3列的jogging数据，目标变量为CLASSIFICATION。执行代码后未生成预期的2节点决策树，无树结构输出。

数据集详情 #

WEATHER   JOGGED_YESTERDAY   CLASSIFICATION
C          N                  +
W          Y                  -
Y          Y                  -
C          Y                  -
Y          N                  -
W          Y                  -
C          N                  -
W          N                  +
C          Y                  -
W          Y                  +
W          N                  +
C          N                  +
Y          N                  -
W          Y                  -

dput结构：

structure(list(WEATHER = c("C", "W", "Y", "C", "Y", "W", "C", 
"W", "C", "W", "W", "C", "Y", "W"), JOGGED_YESTERDAY = c("N", 
"Y", "Y", "Y", "N", "Y", "N", "N", "Y", "Y", "N", "N", "N", "Y"
), CLASSIFICATION = c("+", "-", "-", "-", "-", "-", "-", "+", 
"-", "+", "+", "+", "-", "-")), class = "data.frame", row.names = c(NA, 
-14L))

执行代码 #

jogging <- read.csv("Jogging.csv")

jogging           #training data

library(C50)
jogging$CLASSIFICATION <- as.factor(jogging$CLASSIFICATION)
jogging_model <- C5.0(jogging[-3], jogging$CLASSIFICATION)       

jogging_model
summary(jogging_model)
plot(jogging_model)

问题原因 #

C5.0()函数默认会根据数据复杂度自动选择生成规则集还是决策树。当算法判定规则集比决策树更简洁时，会输出规则而非树结构，这就导致你看不到预期的决策树节点。

另外需确认数据读取是否正确：若你的Jogging.csv是用空格分隔而非逗号，read.csv()会错误合并列，导致模型输入异常。但从你提供的dput结构看，数据格式是正确的，所以核心原因是算法自动选择了规则集。

解决方法 #

强制C5.0()生成决策树，只需在函数中添加rules = FALSE参数：

library(C50)
# 确保目标变量是因子类型
jogging$CLASSIFICATION <- as.factor(jogging$CLASSIFICATION)
# 强制生成决策树
jogging_model <- C5.0(jogging[-3], jogging$CLASSIFICATION, rules = FALSE)

# 查看树结构
jogging_model
summary(jogging_model)
plot(jogging_model)

执行修改后的代码后，就能生成并查看决策树结构了。

内容的提问来源于stack exchange，提问作者kang yep sng