Created
January 1, 2019 18:28
-
-
Save bayesball/39d493fe1b4897d6065b6f68a8285811 to your computer and use it in GitHub Desktop.
Explores impact of length of plate appearance using 2018 Retrosheet data
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Load tidyverse packages and read in the Retrosheet data | |
library(tidyverse) | |
load("~/Dropbox/Google Drive/Retrosheet/pbp.2018.Rdata") | |
# if you have trouble getting the 2018 Retrosheet data, you can | |
# use several complete Retrosheet datasets from previous seasons | |
# see http://www-math.bgsu.edu/~albert/retrosheet/ | |
# Create new variables: pseq containing only the pitch | |
# results, pseq_length gives the length of the PA, and | |
# Count records the ball strike count | |
d2018 %>% | |
mutate(pseq = str_remove_all(PITCH_SEQ_TX, | |
"[.>123N+*]"), | |
pseq_length = str_length(pseq), | |
Count = paste(BALLS_CT, STRIKES_CT, sep="-")) -> d2018 | |
# Only want to consider PA's where the PA is completed | |
end_of_pa_code <- c(2, 3, 5, 13:24) | |
d2018 %>% filter(pseq_length > 0, | |
EVENT_CD %in% end_of_pa_code) -> d2018a | |
# Find Brandon Belt's long PA in 2018 | |
library(Lahman) | |
d2018a %>% filter(pseq_length == max(pseq_length)) %>% | |
inner_join(select(Master, nameFirst, nameLast, retroID), | |
by = c("BAT_ID" = "retroID")) %>% | |
select(GAME_ID, nameFirst, nameLast, pseq, pseq_length, EVENT_CD) | |
# For each possible length of PA, find the number of PAs, the | |
# mean run value and the standard deviation of the run values | |
d2018a %>% group_by(pseq_length) %>% | |
summarize(N = n(), | |
M = mean(RUNS.VALUE), | |
S = sd(RUNS.VALUE)) -> S_count | |
# Plot of mean value of PA as function of number of pitches | |
ggplot(filter(S_count, pseq_length <= 9), | |
aes(pseq_length, M)) + | |
geom_point(size = 2) + | |
geom_hline(yintercept = 0, color = "red") + | |
scale_x_continuous(breaks=1:9) + | |
xlab("Number of Pitches") + | |
ylab("Mean Run Value") + | |
theme(plot.title = element_text(colour = "blue", | |
size = 18, hjust = 0.5)) + | |
ggtitle("Value of Plate Appearance\nas Function of Number of Pitches") | |
# Plot of standard deviation of value | |
ggplot(filter(S_count, pseq_length <= 9), | |
aes(pseq_length, S)) + | |
geom_point() + | |
xlab("Number of Pitches") + | |
ylab("SD Run Value") + | |
ggtitle("Value of Plate Appearance as Function of Number of Pitches") | |
######### Summarize for each PA length and Count | |
d2018a %>% group_by(pseq_length, Count) %>% | |
summarize(N = n(), | |
M = mean(RUNS.VALUE), | |
S = sd(RUNS.VALUE)) %>% | |
filter(N >= 10) -> | |
new_summ | |
## This adds the count info to the previous plot | |
ggplot(filter(new_summ, pseq_length <= 9), | |
aes(pseq_length, M, label = Count)) + | |
geom_label(color = "blue", size = 5) + | |
geom_hline(yintercept = 0, color = "red") + | |
scale_x_continuous(breaks=1:9) + | |
xlab("Number of Pitches") + | |
ylab("Mean Run Value") + | |
theme(plot.title = element_text(colour = "blue", | |
size = 18, hjust = 0.5)) + | |
ggtitle("Value of Plate Appearance\nas Function of # of Pitches and Count") | |
# Find the HR rate for each length of PA and count | |
d2018a %>% | |
group_by(pseq_length, Count) %>% | |
summarize(N = n(), | |
HR = sum(EVENT_CD == 23), | |
HR_Rate = mean(EVENT_CD == 23)) -> HR | |
# graph the HR rates against PA length | |
ggplot(filter(HR, pseq_length <= 9, HR > 9), | |
aes(pseq_length, HR_Rate, | |
label = Count)) + | |
geom_label(color = "blue", size = 5) + | |
scale_x_continuous(breaks=1:9) + | |
xlab("Number of Pitches") + | |
ylab("Home Run Rate") + | |
theme(plot.title = element_text(colour = "blue", | |
size = 18, hjust = 0.5)) + | |
ggtitle("Home Run Rate\nas Function of Number of Pitches") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment