bayesball

# Main function to get Retrosheet game scores

get_scores <- function(season){
  require(dplyr)
  require(readr)
  load_gamelog <- function(season) {
    glheaders <- read_csv("https://raw.githubusercontent.com/beanumber/baseball_R/master/data/game_log_header.csv")
    remote <- paste0("http://www.retrosheet.org/gamelogs/gl", 
                     season, ".zip")
    local <- paste0("gl", season, ".zip")

bayesball

# reference
# https://billpetti.github.io/baseballr/articles/baseballr.html#follow-the-sportsdataverse-on-twitter-and-star-this-repo

library(baseballr)

# -----------------------------------------------------
# Retrosheet data
# -----------------------------------------------------

# acquire retro play-by-play data for seasons 2020:2022

bayesball

# load in required packages

library(dplyr)
library(ggplot2)
library(CalledStrike)
library(janitor)
library(ShinyBaseball)
library(readr)

# collect mlb ids from two pitchers

bayesball

# load in required packages

library(purrr)
library(ggplot2)
library(tidyr)
library(dplyr)

# read in modeling functions

source("fit_model.R")

bayesball

library(dplyr)
library(ggplot2)
library(geomtextpath)
library(readr)

# datasets are read from a Github respository
fg_batting <- read_csv("https://raw.githubusercontent.com/bayesball/HomeRuns2021/main/fgbatting_complete.csv")
hof <- read_csv("https://raw.githubusercontent.com/bayesball/HomeRuns2021/main/hofdata.csv")
hof_candidates <- read_csv("https://raw.githubusercontent.com/bayesball/HomeRuns2021/main/hofdata_candidates.csv")
hof_cand_batting <- filter(hof_candidates,

bayesball

estimate_batting <- function(retro_final_PA_1990_2020d,
                             season,
                             s_woba = 0.5){
  require(dplyr)
  require(LearnBayes)
  retro_final_PA_1990_2020d %>% 
    filter(YEAR == season) -> retroseason
  retroseason %>% 
    group_by(BAT_ID) %>% 
    summarize(PA = n(),

bayesball

get_hr_data <- function(pred_season,
                        retro_data,
                        n_prev_seasons = 4,
                        mPA = 1000,
                        mPA_season = 200){

  # n_prev_seasons is number of previous seasons
  # mPA is the minimum number of cumulative PA
  # retrodata - Retrosheet data for current season
  # mPA_season - minimum number of PA in both

bayesball

prediction_work <- function(seasons,
                            mPA = 1000,
                            retrodata,
                            mPA_season = 200){

  # seasons is a vector of previous seasons
  # mPA is the minimum number of cumulative PA
  # retrodata - Retrosheet data for current season
  # mPA_season - minimum number of PA in both
  #   halves of current season

bayesball

sac_fly_work <- function(sc, season){

  # load required packages
  require(dplyr)
  require(ggplot2)
  require(metR)
  require(mgcv)
  require(CalledStrike)

  # define location, distance, and spray angle vars

bayesball

# load in Retrosheet pbp data frames
# for seasons 2011 through 2021

library(Lahman)
library(dplyr)
library(ggplot2)

# get Mike Trout's retro id from the People
# data frame in Lahman package