{r}
cl<-read.csv("C:\\Users\\SHABANA A T\\Desktop\\Data Science\\claimants.csv")
cl
View(cl)
a<-cl[-1]
a<-na.omit(cl)
View(a)
colnames(a)
attach(a)
summary(a)
str(a)
str(CLMAGE)
str(as.factor(CLMSEX))
m1<-glm(ATTORNEY ~ factor(CLMSEX)+factor(CLMINSUR)+factor(SEATBELT)+CLMAGE+LOSS ,family =binomial,data =a)
#m2<-glm(ATTORNEY~. ,family = binomial,data =a) (Can do in this way also)
coef(m1)
#coef(m2)
summary(m1)
#summary(m2) 
exp(coef(m1))
prob<-predict(m1,cl)
prob
class(prob)
pv<-as.data.frame(prob)
pv
final<-cbind(pv,cl)
final
table(cl$ATTORNEY)
confusion<-table(pv>0.5,cl$ATTORNEY)
confusion
#table(final$prob>0.5)
#table
aggregate<-sum(diag(confusion)/sum(confusion))
aggregate