Code for Swing and Miss Study on 10/29/16

ws2016_game3.R

library(pitchRx)
library(dplyr)
library(ggplot2)

# scrape data

ws3 <- scrape("2016-10-28", "2016-10-28")

# choose variables of interest

p <- select(ws3$pitch, des, px, pz, pitch_type, inning_side,
            gameday_link, num, inning)
p <- inner_join(p,
                select(ws3$atbat, pitcher_name,
                        batter_name, gameday_link, num))

# classify pitches as swings and misses

swing_outcomes <- c("Foul", "Foul (Runner Going)",
                    "Foul Bunt", "Foul Tip",                           
                    "In play, no out", "In play, out(s)",          
                    "In play, run(s)", "Swinging Strike",         
                    "Swinging Strike (Blocked)")
miss_outcomes <- c("Swinging Strike",         
                   "Swinging Strike (Blocked)")
p <- mutate(p,
            Swing=ifelse(des %in% swing_outcomes, "yes", "no"),
            Miss=ifelse(des %in% miss_outcomes, "yes", "no"),
            Team=ifelse(inning_side=="bottom", "Cubs", "Tribe"),
            Type=ifelse(pitch_type %in% 
                          c("FC", "FF", "FT", "SI"),
                        "fast", "slow"))

# create a new data frame with only the swings

d_swing <- filter(p, Swing=="yes")

# compute percentages of swings for each team

summarize(group_by(d_swing, Team),
          N=n(), Miss=sum(Miss=="yes"),
          Pct=round(Miss / N * 100))

# break these pcts by pitch type

S <- summarize(group_by(d_swing, Team, Type),
          N=n(), Miss=sum(Miss=="yes"),
          Pct=round(Miss / N * 100))

# code for first graph

TH <- theme(
  plot.title = element_text(
    colour = "red",
    size = 18,
    hjust = 0.5,
    vjust = 0.8,
    angle = 0
  )
)
ggplot(S, aes(Type, Pct)) + geom_point(size=3, color="red")+
  facet_wrap(~ Team, ncol=1) + coord_flip() +
  ggtitle("Percentage of Missed Swings by Type of Pitch") +
  TH

# code for 2nd graph

zone <- function(){
  topKzone <- 3.5
  botKzone <- 1.6
  inKzone <- -0.95
  outKzone <- 0.95
  kZone <- data.frame(
    x=c(inKzone, inKzone, outKzone, outKzone, inKzone),
    y=c(botKzone, topKzone, topKzone, botKzone, botKzone)
  )
  ggplot(aes(x, y), data=kZone)  +
    geom_path(lwd=1.5, col="red") +
    xlim(-2, 2) + ylim(0, 5) +
    coord_fixed(ratio = 1)}

zone() +
  geom_point(data=d_swing, 
             aes(px, pz, color=Type, size=Miss)) +
  facet_wrap(~ Team) +
  ggtitle("Locations of Swung Pitches") +
  TH +
  geom_point(data=d_swing[126, ], 
             aes(px, pz), size=5, color="purple")