adding milb functionality to baseballr

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: baseballr
 Title: Functions for acquiring and analyzing baseball data
-Version: 0.5.0
+Version: 0.6.0
 Author: Bill Petti <billpetti@gmail.com>
 Authors@R: c(
     person("Bill", "Petti", email = "billpetti@gmail.com",

NAMESPACE

@@ -25,6 +25,7 @@ export(get_ncaa_baseball_pbp)
 export(get_ncaa_baseball_roster)
 export(get_ncaa_game_logs)
 export(get_ncaa_schedule_info)
+export(get_pbp_mlb)
 export(get_probables_mlb)
 export(get_retrosheet_data)
 export(ggspraychart)

R/get_game_info_mlb.R

@@ -1,4 +1,4 @@
-#' Retrieve additional game information via the MLB api \url{http://statsapi.mlb.com/api/}
+#' Retrieve additional game information for major and minor league games via the MLB api \url{http://statsapi.mlb.com/api/}
 #'
 #' @param game_pk The unique game_pk identifier for the game
 #' @importFrom jsonlite fromJSON

R/get_game_pks_mlb.R

@@ -1,18 +1,35 @@
-#' Find game_pk values for MLB games via the MLB api \url{http://statsapi.mlb.com/api/}
+#' Find game_pk values for professional baseball games (major and minor leagues)
+#' via the MLB api \url{http://statsapi.mlb.com/api/}
 #'
 #' @param date The date for which you want to find game_pk values for MLB games
+#' @param level_ids A numeric vector with ids for each level where game_pks are
+#' desired. See below for a reference of level ids.
 #' @importFrom jsonlite fromJSON
 #' @return Returns a data frame that includes game_pk values and additional
 #' information for games scheduled or played
 #' requested
+#' @section Level IDs:
+#'
+#' The following IDs can be passed to the level_ids argument:
+#'
+#' 1 = MLB
+#' 11 = Triple-A
+#' 12 = Doubl-A
+#' 13 = Class A Advanced
+#' 14 = Class A
+#' 15 = Class A Short Season
+#' 5442 = Rookie Advanced
+#' 16 = Rookie
+#' 17 = Winter League
 #' @keywords MLB, sabermetrics
 #' @export
 #'
 #' @examples get_game_pks_mlb("2019-04-29")
 
-get_game_pks_mlb <- function(date) {
+get_game_pks_mlb <- function(date,
+                             level_ids = c(1)) {
 
-  api_call <- paste0("http://statsapi.mlb.com/api/v1/schedule?sportId=1&date=", date)
+  api_call <- paste0("http://statsapi.mlb.com/api/v1/schedule?sportId=", paste(level_ids, collapse = ','), "&date=", date)
 
   payload <- jsonlite::fromJSON(api_call, flatten = TRUE)
 

R/get_pbp_mlb.R

@@ -0,0 +1,139 @@
+#' Acquire pitch-by-pitch data for Major and Minor League games via the MLB api \url{http://statsapi.mlb.com/api/}
+#'
+#' @param game_pk The date for which you want to find game_pk values for MLB games
+#' @importFrom jsonlite fromJSON
+#' @return Returns a data frame that includes over 100 columns of data provided
+#' by the MLB Stats API at a pitch level.
+#'
+#' Some data will vary depending on the
+#' park and the league level, as most sensor data is not availble in
+#' minor league parks via this API. Note that the column names have mostly
+#' been left as-is and there are likely duplicate columns in terms of the
+#' information they provide. I plan to clean the output up down the road, but
+#' for now I am leaving the majority as-is.
+#'
+#' Both major and minor league pitch-by-pitch data can be pulled with this
+#'  function.
+#' @keywords MLB, sabermetrics
+#' @export
+#'
+#' @examples get_pbp_mlb(575156)
+
+get_pbp_mlb <- function(game_pk) {
+
+  api_call <- paste0("http://statsapi.mlb.com/api/v1.1/game/", game_pk, "/feed/live")
+  payload <- jsonlite::fromJSON(api_call, flatten = TRUE)
+
+  plays <- payload$liveData$plays$allPlays$playEvents %>% bind_rows()
+
+  at_bats <- payload$liveData$plays$allPlays
+
+  current <- payload$liveData$plays$currentPlay
+
+  game_status <- payload$gameData$status$abstractGameState
+
+  home_team <- payload$gameData$teams$home$name
+
+  home_level <- payload$gameData$teams$home$sport
+
+  home_league <- payload$gameData$teams$home$league
+
+  away_team <- payload$gameData$teams$away$name
+
+  away_level <- payload$gameData$teams$away$sport
+
+  away_league <- payload$gameData$teams$away$league
+
+  list_columns <- lapply(at_bats, function(x) class(x)) %>%
+    dplyr::bind_rows(.id = "variable") %>%
+    tidyr::gather(key, value, -variable) %>%
+    dplyr::filter(value == "list") %>%
+    dplyr::pull(key)
+
+  at_bats <- at_bats %>%
+    dplyr::select(-c(one_of(list_columns)))
+
+  pbp <- plays %>%
+    dplyr::left_join(at_bats, by = c("endTime" = "playEndTime"))
+
+  pbp <- pbp %>%
+    tidyr::fill(atBatIndex:matchup.splits.menOnBase, .direction = "up") %>%
+    dplyr::mutate(game_pk = game_pk,
+                  game_date = substr(payload$gameData$datetime$dateTime, 1, 10)) %>%
+    dplyr::select(game_pk, game_date, everything())
+
+  pbp <- pbp %>%
+    dplyr::mutate(matchup.batter.fullName =
+                    factor(matchup.batter.fullName),
+                  matchup.pitcher.fullName =
+                    factor(matchup.pitcher.fullName),
+                  atBatIndex = factor(atBatIndex)
+                  # batted.ball.result = case_when(!result.event %in% c(
+                  #   "Single", "Double", "Triple", "Home Run") ~ "Out/Other",
+                  #   TRUE ~ result.event),
+                  # batted.ball.result = factor(batted.ball.result,
+                  #                             levels = c("Single", "Double", "Triple", "Home Run", "Out/Other"))
+    ) %>%
+    dplyr::mutate(home_team = home_team,
+                  home_level_id = home_level$id,
+                  home_level_name = home_level$name,
+                  home_parentOrg_id = payload$gameData$teams$home$parentOrgId,
+                  home_parentOrg_name = payload$gameData$teams$home$parentOrgName,
+                  home_league_id = home_league$id,
+                  home_league_name = home_league$name,
+                  away_team = away_team,
+                  away_level_id = away_level$id,
+                  away_level_name = away_level$name,
+                  away_parentOrg_id = payload$gameData$teams$away$parentOrgId,
+                  away_parentOrg_name = payload$gameData$teams$away$parentOrgName,
+                  away_league_id = away_league$id,
+                  away_league_name = away_league$name,
+                  batting_team = factor(ifelse(about.halfInning == "bottom",
+                                               home_team,
+                                               away_team)),
+                  fielding_team = factor(ifelse(about.halfInning == "bottom",
+                                                away_team,
+                                                home_team)))
+  pbp <- pbp %>%
+    dplyr::arrange(desc(atBatIndex), desc(pitchNumber))
+
+  pbp <- pbp %>%
+    dplyr::group_by(atBatIndex) %>%
+    dplyr::mutate(last.pitch.of.ab =
+                    ifelse(pitchNumber == max(pitchNumber), "true", "false"),
+                  last.pitch.of.ab = factor(last.pitch.of.ab)) %>%
+    ungroup()
+
+  pbp <- dplyr::bind_rows(stats_api_live_empty_df, pbp)
+
+  check_home_level <- pbp %>%
+    dplyr::distinct(home_level_id) %>%
+    dplyr::pull()
+
+  # this will need to be updated in the future to properly estimate X,Z coordinates at the minor league level
+
+  # if(check_home_level != 1) {
+  #
+  #   pbp <- pbp %>%
+  #     dplyr::mutate(pitchData.coordinates.x = -pitchData.coordinates.x,
+  #                   pitchData.coordinates.y = -pitchData.coordinates.y)
+  #
+  #   pbp <- pbp %>%
+  #     dplyr::mutate(pitchData.coordinates.pX_est = predict(x_model, pbp),
+  #                   pitchData.coordinates.pZ_est = predict(y_model, pbp))
+  #
+  #   pbp <- pbp %>%
+  #     dplyr::mutate(pitchData.coordinates.x = -pitchData.coordinates.x,
+  #                   pitchData.coordinates.y = -pitchData.coordinates.y)
+  # }
+
+  pbp <- pbp %>%
+    dplyr::rename(count.balls.start = count.balls.x,
+                  count.strikes.start = count.strikes.x,
+                  count.outs.start = count.outs.x,
+                  count.balls.end = count.balls.y,
+                  count.strikes.end = count.strikes.y,
+                  count.outs.end = count.outs.y)
+
+  return(pbp)
+}

README.Rmd

@@ -20,23 +20,41 @@ knitr::opts_chunk$set(
 
 # baseballr
 
-# `baseballr` 0.3.4
-**(latest version released 2018-05-29)**
+# `baseballr` 0.6.0
 
-`baseballr` is a package written for R focused on baseball analysis. It includes functions for scraping various data from websites, such as FanGraphs.com, Baseball-Reference.com, and baseballsavant.com. It also includes functions for calculating metrics, such as wOBA, FIP, and team-level consistency over custom time frames.
+**(latest version released 2020-01-07)**
 
-You can read more about some of the functions and how to use them at its [official site](http://billpetti.github.io/baseballr/) as well as this [Hardball Times article](http://www.hardballtimes.com/developing-the-baseballr-package-for-r/).
+`baseballr` is a package written for R focused on baseball analysis. It
+includes functions for scraping various data from websites, such as
+FanGraphs.com, Baseball-Reference.com, and baseballsavant.com. It also
+includes functions for calculating metrics, such as wOBA, FIP, and
+team-level consistency over custom time frames.
 
+You can read more about some of the functions and how to use them at its
+[official site](http://billpetti.github.io/baseballr/) as well as this
+[Hardball Times
+article](http://www.hardballtimes.com/developing-the-baseballr-package-for-r/).
 
 ## Installation
 
 You can install `baseballr` from github with:
 
-```{r gh-installation, eval = FALSE}
+``` r
 # install.packages("devtools")
 devtools::install_github("BillPetti/baseballr")
 ```
 
+For experimental functions in development, you can install the [development branch](https://github.com/BillPetti/baseballr/tree/development_branch):
+
+``` r
+# install.packages("devtools")
+devtools::install_github("BillPetti/baseballr", ref = "development_branch")
+```
+
+## Pull Requests
+
+Pull request are welcome, but I cannot guarantee that they will be accepted or accepted quickly. Please make all pull requests to the [development branch](https://github.com/BillPetti/baseballr/tree/development_branch) for review.
+
 ## Functionality
 
 The package consists of two main sets of functions: data acquisition and metric calculation.
@@ -77,11 +95,8 @@ data %>%
   head()
 ```
 
-
 You can also generate these wOBA-based stats, as well as FIP, for pitchers using the `fip_plus()` function:
 
-
-
 ```{r}
 daily_pitcher_bref("2015-04-05", "2015-04-30") %>% 
   fip_plus() %>% 

README.md

@@ -9,9 +9,9 @@ status](https://travis-ci.org/BillPetti/baseballr.svg?branch=master)](https://tr
 
 # baseballr
 
-# `baseballr` 0.5.0
+# `baseballr` 0.6.0
 
-**(latest version released 2019-06-25)**
+**(latest version released 2020-01-07)**
 
 `baseballr` is a package written for R focused on baseball analysis. It
 includes functions for scraping various data from websites, such as
@@ -33,7 +33,9 @@ You can install `baseballr` from github with:
 devtools::install_github("BillPetti/baseballr")
 ```
 
-For experimental functions in development, you can install the [development branch](https://github.com/BillPetti/baseballr/tree/development_branch):
+For experimental functions in development, you can install the
+[development
+branch](https://github.com/BillPetti/baseballr/tree/development_branch):
 
 ``` r
 # install.packages("devtools")
@@ -42,7 +44,11 @@ devtools::install_github("BillPetti/baseballr", ref = "development_branch")
 
 ## Pull Requests
 
-Pull request are welcome, but I cannot guarantee that they will be accepted or accepted quickly. Please make all pull requests to the [development branch](https://github.com/BillPetti/baseballr/tree/development_branch) for review.
+Pull request are welcome, but I cannot guarantee that they will be
+accepted or accepted quickly. Please make all pull requests to the
+[development
+branch](https://github.com/BillPetti/baseballr/tree/development_branch)
+for review.
 
 ## Functionality