library(readr)
library(dplyr)


#
# Load data
#

players <- read_csv("data/nba-players-2013-14.csv")


#
# Histogram
#

# Default histogram
par(las = 1)
hist(players$Ht_inches,
     xlab="inches",
     main="NBA Player Heights")


# Smaller breaks
hist(players$Ht_inches, 
     breaks=seq(65, 90, 1),
     xlab="inches",
     main="NBA Player Heights")

# Vary bin sizes
par(mfrow=c(1,3), mar=c(5,3,3,3))
hist(players$Ht_inches, 
     breaks=seq(65, 90, 1),
     xlab="inches", main="One-inch bins")
hist(players$Ht_inches,
     breaks=seq(65, 90, 3),
     xlab="inches", main="Three-inch bins")
hist(players$Ht_inches,
     breaks=seq(65, 90, 6),
     xlab="inches", main="Six-inch bins")


#
# Comparison between positions
#

ppos <- unique(players$POS)
par(mfrow=c(5,1), mar=c(2,3,3,2), oma=c(2,2,2,2))
for (pos in ppos) {
    curr <- players %>% filter(POS == pos)
    hist(curr$Ht_inches, 
         breaks=seq(65, 90, 1),
         xlab="inches", main=paste0(pos, " Heights"))
}


ppos2 <- c("G", "G/F", "F", "F/C", "C")
par(mfrow=c(5,1))
for (pos in ppos2) {
    curr <- players %>% filter(POS == pos)
    curr_mean <- mean(curr$Ht_inches)
    
    hist(curr$Ht_inches, 
         breaks=seq(65, 90, 1),
         border = "white",
         xlab="inches", 
         main=paste0(pos, " Heights"))
    abline(v = curr_mean, 
           col = "blue", 
           lwd = 2)
}