# Analysis of foul data
library(tidyverse)

allfouls <- read_csv("data/foulsonly.csv")

## Plots
# histogram of fouls as a function of corrected score margin
png('figures/foul_histogram-all.png')
ggplot(allfouls, aes(x=SCOREMARGIN_CORR)) +
    geom_histogram(binwidth=1, fill="black") +
    theme_bw() +
    scale_y_log10() +
    xlab("Score Margin") + ylab("N Fouls")

dev.off()

# histogram of fouls as a function of corrected score margin,
# ignoring overtime and the final minute of regular play
earlyfouls <- filter(allfouls,
                     PERIOD <= 4,
                     !(PERIOD == 4 & PCTIMESTRING < "00:01:00"))

png('figures/foul_histogram-regular_nofinalmin.png')
ggplot(earlyfouls, aes(x=SCOREMARGIN_CORR)) +
    geom_histogram(binwidth=1, fill="red", alpha=0.5) +
    theme_bw() +
    scale_y_log10() +
    xlab("Score Margin") + ylab("N Fouls") +
    geom_histogram(data=allfouls, binwidth=1, fill="green", alpha=0.5)
dev.off()

# hexbin plots of fouls as a function of total score and corrected score
# margin, separated by home and away teams
png('figures/fouls_totalscore-hexbin.png', height=600, width=1200)
ggplot(allfouls, aes(SCOREMARGIN_CORR, TOTALSCORE)) +
    geom_hex() +
    scale_fill_viridis_c() +
    theme_bw() +
    facet_wrap(vars(FOULTEAM))
dev.off()