决策树c5.0算法r语言实现,R C5.0决策树实例转摘

http://www.kaggle.com/c/titanic-gettingStarted/data

.

new_model

C5.0(train[,-2],train$Survived)

levels(train$Cabin)[1] = "missing"

levels(train$Embarked)[1] = "missing"

窗体顶端

窗体底端

library(C50)

test$Survived

combinedData

rbind(train,test)

combinedData$Survived

factor(combinedData$Survived)

# fixing empty character level names

levels(combinedData$Cabin)[1] = "missing"

levels(combinedData$Embarked)[1] = "missing"

new_train

combinedData[1:891,]

new_test

combinedData[892:1309,]

new_model

C5.0(new_train[,-2],new_train$Survived)

new_model_predict

predict(new_model,new_test)

submitC50

data.frame(PassengerId=new_test$PassengerId,

Survived=new_model_predict)

write.csv(submitC50, file="c50dtree.csv",

row.names=FALSE)

summary(new_model)

removeBlankLevelsInDataFrame

function(dataframe) {

for (i in 1:ncol(dataframe))

{

levels

if

(!is.null(levels) && levels[1] ==

"") {

levels(dataframe[,i])[1] = "?"

}

}

dataframe

}

removeBlankLevelsInVector

function(vector) {

levels

levels(vector)

if (!is.null(levels)

&& levels[1] == "") {

levels(vector)[1] = "?"

}

vector

}

trainX = removeBlankLevelsInDataFrame(trainX)

trainY = removeBlankLevelsInVector(trainY)

model = C50::C5.0.default(trainX,trainY)