library(rpart)
library(rpart.plot)
data1<-read.csv("file:///C:/Users/LENOVO/Desktop/Missing/decison tree mba.csv", stringsAsFactors = TRUE)
dtm1<-rpart(Specialization~Gender+Previous_Degree,data=data1,
minsplit=100, minbucket=10, maxdepth=4, method = "class")
dtm1
rpart.plot(dtm1, type = 0, cex = 0.5)
#-------------
dtm1<-rpart(Specialization~Gender+Previous_Degree+Percentage_in_10_Class+
Percentage_in_12_Class+Percentage_in_Under_Graduate,
data=data1,
minsplit=100, minbucket=10, maxdepth=4)
dtm1
rpart.plot(dtm1, type = 0, cex = 0.5)
#-------------------------------
dtm1<-rpart(Specialization~Percentage_in_10_Class+
Percentage_in_12_Class+Percentage_in_Under_Graduate,
data=data1,
minsplit=100, minbucket=10, maxdepth=4, parms = list(split = 'gini'))
dtm1
rpart.plot(dtm1, type = 0, cex = 0.5)
#CP= complexity parameter, α be some number between 0 and ∞ which measures the ’cost’ of adding another
# variable to the model
# pruning
dtm1prone<-prune(dtm1, cp=0.01)
rpart.plot(dtm1prone, type = 0, cex = 0.5)
library()
printcp(dtm1)
str(data1)
dtm1<-rpart(Age_in_years~Percentage_in_10_Class+
Percentage_in_12_Class+Percentage_in_Under_Graduate,
data=data1, method = "anova" )
rpart.plot(dtm1, type = 0, cex = 0.5)
predict1<-predict(dtm1, type = "class")
confusionMatrix(predict1, data1$Specialization)
