#clear the environment 
rm(list=ls()) 
## ------------------------------------------------------------------------
setwd(dirname(rstudioapi::getActiveDocumentContext()$path))
## ------------------------------------------------------------------------

NBAdata=read.csv("Teams_overall.csv", header = T, stringsAsFactors = F, sep = ",")

NBAdata <- na.omit(NBAdata)
NBAdata$FGMISS=NBAdata$FGA-NBAdata$FG
NBAdata$FTMISS=NBAdata$FTA-NBAdata$FT
NBAdata$FGMISS=NBAdata$FGA-NBAdata$FG
NBAdata$FTMISS=NBAdata$FTA-NBAdata$FT
NBAdata$OFGMISS=NBAdata$OFGA-NBAdata$OFG
NBAdata$OFTMISS=NBAdata$OFTA-NBAdata$OFT
NBAdata$MISS=NBAdata$FGMISS+NBAdata$FTMISS
NBAdata$OMISS=NBAdata$OFGMISS+NBAdata$OFTMISS
NBAdata$W.=NBAdata$W/(NBAdata$W+NBAdata$L)
#create employed possessions 
NBAdata$empl_poss=NBAdata$FGA + 0.44*NBAdata$FTA + NBAdata$TOV - NBAdata$ORB
NBAdata$pace=NBAdata$empl_poss/(82*48)
NBAdata$ptsxgame=NBAdata$PTS/NBAdata$G
NBAdata$ptsxposs=NBAdata$PTS/NBAdata$empl_poss

#Golden State Warriors pace over time
Golden_State = subset(NBAdata, Team == "Golden State Warriors", select = Season:pace)

plot(y = Golden_State$pace, x = Golden_State$Season, type = "l",col = "blue",ylim = c(1,3),ylab = "Pace .GSW",
     xlab = "Season",
     main = "Pace over time of GSW")
lines(y = rep(mean(Golden_State$pace), length(Golden_State$pace)), x = Golden_State$Season, col = "red")
lines(y = rep(mean(Golden_State$pace) + 2*sd(Golden_State$pace), length(Golden_State$pace)), x = Golden_State$Season, col = "red", lty = 2)
lines(y = rep(mean(Golden_State$pace) - 2*sd(Golden_State$pace), length(Golden_State$pace)), x = Golden_State$Season, col = "red", lty = 2)

#Chicago Bulls 3 pts share
NBAdata$three_pts_share=NBAdata$X3PA/(NBAdata$X3PA+NBAdata$X2PA)
Chicago_Bulls = subset(NBAdata, Team == "Chicago Bulls", select = Season:three_pts_share)
plot(y = Chicago_Bulls$three_pts_share, x = Chicago_Bulls$Season, type = "l",col = "blue",ylim = c(0,1),ylab = "3pts share .CB",
     xlab = "Season",
     main = "3 pts share over time of CB")
lines(y = rep(mean(Chicago_Bulls$three_pts_share), length(Chicago_Bulls$three_pts_share)), x = Chicago_Bulls$Season, col = "red")
lines(y = rep(mean(Chicago_Bulls$three_pts_share) + 2*sd(Chicago_Bulls$three_pts_share), length(Chicago_Bulls$three_pts_share)), x = Chicago_Bulls$Season, col = "red", lty = 2)
lines(y = rep(mean(Chicago_Bulls$three_pts_share) - 2*sd(Chicago_Bulls$three_pts_share), length(Chicago_Bulls$three_pts_share)), x = Chicago_Bulls$Season, col = "red", lty = 2)

#CB relative efficiency of 3pts and 2pts
NBAdata$three_pts_efficiency=NBAdata$X3P/NBAdata$X3PA
NBAdata$two_pts_efficiency=NBAdata$X2P/NBAdata$X2PA
Chicago_Bulls = subset(NBAdata, Team == "Chicago Bulls", select = Season:two_pts_efficiency)

par(mfrow = c(1, 2))

plot(y = Chicago_Bulls$three_pts_efficiency, x = Chicago_Bulls$Season, type = "l",col = "blue",ylim = c(0,1),ylab = "3pts efficiency .CB",
     xlab = "Season",
     main = "3 pts efficiency over time of CB")

plot(y = Chicago_Bulls$two_pts_efficiency, x = Chicago_Bulls$Season, type = "l",col = "blue",ylim = c(0,1),ylab = "2pts efficiency .CB",
     xlab = "Season",
     main = "2 pts efficiency over time of CB")