bayesball

# 2019 statcast data is in data frame sc2019

# collect number of home runs in each game

library(tidyverse)

sc2019 %>%
  group_by(game_pk) %>%
  summarize(HR = sum(events == "home_run",
                     na.rm = TRUE)) -> S

bayesball

# read in SC data from  2019 seasons
# through games of June 23, 2019

library(tidyverse)
library(CalledStrike)

sc2019 <- read_csv("~/Dropbox/2016 WORK/BLOG Baseball R/OTHER/StatcastData/statcast2019.csv")
sc2019_ip <- filter(sc2019, type == "X")

# focus on Statcast 2019 in-play data

bayesball

# load some packages

library(baseballr)
library(tidyverse)
library(CalledStrike)
library(gridExtra)

# scrape data for four pitchers

Aaron <- scrape_statcast_savant(start_date = "2018-03-15",

bayesball

# load in two packages

library(tidyverse)
library(WinProbability)

# assume dataset all2018.csv is in current working
# directory -- these functions compute the runs
# expectancies and WPA values

d2018 <- compute.runs.expectancy(2018)

bayesball

compute.win.probs <- function(d, S){
  # adds variables P.OLD, P.NEW, and WPA
  # to retrosheet data with run expectancies
  invlogit <- function(x) exp(x) / (1 + exp(x))
  
  d %>% 
    mutate(half.inning.row = 2 * INN_CT + BAT_HOME_ID,
          runs0 = ifelse(BAT_HOME_ID == 1,
      HOME_SCORE_CT - AWAY_SCORE_CT + RUNS.STATE,
      HOME_SCORE_CT - AWAY_SCORE_CT - RUNS.STATE)) -> d

bayesball

# 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

bayesball

# read in Statcast data for two seasons

library(tidyverse)
sc <- read_csv("../StatcastData/statcast2018new.csv")
sc17 <- read_csv("../StatcastData/statcast2017.csv")

# erode function will complete individual regression estimates for all
# players who have seen 1000 called pitches

erode <- function(sc){

bayesball

# read in packages and data

library(tidyverse)
library(gridExtra)

sc2018 <- read_csv("../StatcastData/statcast2018new.csv")
sc2017 <- read_csv("../StatcastData/statcast2017.csv")

sc2017ip <- filter(sc2017, type == "X") # 127555 rows
sc2018ip <- filter(sc2018, type == "X") # 126282 rows

bayesball

library(shiny)
library(tidyverse)
sc2018 <- read_csv("sc2018_ip.csv") %>% 
  mutate(Ptype = ifelse(pitch_type %in% c("FC", "FF", "FO", "FS", "FT", "SI"),
                        "fb", "os"))
sc2018 %>% group_by(player_name) %>% summarize(HR = sum(HR)) -> S
plist <- filter(S, HR >= 30) %>% select(player_name) %>% pluck()

ui = fluidPage(
    titlePanel("Locations of 2018 Home Runs: Compare Two 30+ Players"),

bayesball

library(shiny)

# Define UI for application that draws a histogram
ui <- shinyUI(pageWithSidebar(
  
  # Application title
  headerPanel("Offensive Production in Baseball History"),
  
  # Sidebar with controls to select the variable to plot against year