setwd("C:/Users/Steven/Desktop/ACTL ASSINGMENT")

install.packages("ggplot2")
library("ggplot2", lib.loc="~/R/win-library/3.3") #####load ggplot2
install.packages("plotrix")

buildingclaim<-read.csv("file_claim_building.csv",header=TRUE)
buildingpolicy<-read.csv("file_policy_building.csv", header=TRUE)
motorctpclaim<-read.csv("file_claim_motorctp.csv", header=TRUE)
motorctppolicy<-read.csv("file_policy_motorctp.csv", header=TRUE)

combinebuilding <- merge(buildingclaim,buildingpolicy,by="PolicyID") #####combine two dataframes
combinebuilding
View(combinebuilding)

combinebuilding$GeoRisk<-factor(combinebuilding$GeoRisk,levels=c("Low Risk","Normal","High Risk"))
FrequencyVsAge <-qplot(data=combinebuilding,Age, color="red")+ylab("Frequency")
pdf("FrequencyVsAge.pdf")
qplot(data=combinebuilding,Age, color="red")
dev.off()

combinebuilding$GeoRisk<-factor(combinebuilding$GeoRisk,levels=c("Low Risk","Normal","High Risk"))
FrequencyVsGeoRisk <-qplot(data=combinebuilding,GeoRisk, color="red")+ylab("Frequency")
pdf("FrequencyVsGeoRisk.pdf")
qplot(data=combinebuilding,GeoRisk, color="red")
dev.off()

AverageGLBvsAGe<-ggplot(combinebuilding, aes(Age,GrossLossBuilding))
AverageGLBvsAGe + stat_summary_bin(aes(y=GrossLossBuilding),fun.y="mean",geom="bar")+ylab("AverageGrossLossBuilding")

nrow(combinebuilding)/nrow(buildingpolicy)*100 #Gives the percentage of policies that were unclaimed
100 - nrow(combinebuilding)/nrow(buildingpolicy)*100 #Gives the percentage of policies that were claimed

slices<-c(35,15)
lbls<-c("Claimed", "Unclaimed")
pct <- round(slices/sum(slices)*100)
lbls <- paste(lbls, pct) # add percents to labels
lbls <- paste(lbls,"%",sep="") # ad % to labels
pie(slices,labels = lbls, col=rainbow(length(lbls)), main="Percentage of Policies Claimed")