Quarto file that collects retrosheet data and compares count rates for two seasons

count_two_seasons.qmd

---
title: "Retrosheet Package - Comparing Count Rates for Two Seasons"
format: html
editor: visual
---

Load packages for this particular run.
```{r}
#| message: FALSE
library(abdwr3edata)
library(tidyr)
library(dplyr)
library(purrr)
library(retrosheet)
library(ggplot2)
```

Function to collect Retrosheet play-by-play files for a particular season. Collects the play files and adds game ids and starting pitchers.

```{r}
get_my_retrosheet <- function(season){
  t <- get_retrosheet("roster", season)
  teams <- names(t)

  one_team_retrieve <- function(team){
    d <- get_retrosheet("play", season, team)
    one_game <- function(j){
      dj <- d[[j]]
      game_id <- unlist(dj$id)[1]
      dj$play |>
        mutate(GAMEID = game_id,
             count = as.character(count))
    }
    NG <- length(d)
    map(1:NG, one_game) |>
      list_rbind()
}
teams |>
  map(one_team_retrieve) |>
  list_rbind() -> DD
}
```

Function will add count variables to a Retrosheet play-by-play data frame and summarize the percentage of plate appearances that will have each possible count.

```{r}
add_count_variables <- function(d){
  d |>
    rename(pitch_seq_tx = pitches) |>
    retrosheet_add_counts() |> 
    summarize(C00 = sum(c00),
            C10 = sum(c10),
            C01 = sum(c01),
            C20 = sum(c20),
            C11 = sum(c11),
            C02 = sum(c02),
            C30 = sum(c30),
            C21 = sum(c21),
            C12 = sum(c12),
            C31 = sum(c31),
            C22 = sum(c22),
            C32 = sum(c32)) |>
    mutate(P10 = 100 * C10 / C00,
         P01 = 100 * C01 / C00,
         P20 = 100 * C20 / C00,
         P11 = 100 * C11 / C00,
         P02 = 100 * C02 / C00,
         P30 = 100 * C30 / C00,
         P21 = 100 * C21 / C00,
         P12 = 100 * C12 / C00,
         P31 = 100 * C31 / C00,
         P22 = 100 * C22 / C00,
         P32 = 100 * C32 / C00) |>
  select(P10, P01, P20, P11, P02,
         P30, P21, P12, P31, P22, P32)
}
```

Collects Retrosheet data for the 1995 and 2023 seasons.

```{r}
d_1995 <- get_my_retrosheet(1995)
d_2023 <- get_my_retrosheet(2023)
```

Here's what this data looks like:

```{r}
head(d_2023)
```

Summarizes the count data for each of the two seasons.

```{r}
(S_2023 <- add_count_variables(d_2023))
(S_1995 <- add_count_variables(d_1995)) 
```

The objective is to compare the count percentages for the two seasons.  Puts data in a different "long" form so we can compare the percentages for the two seasons using logits.

```{r}
logit <- function(y){
  log(y / 100) - log(1 - y / 100)
}
T_1995 <- pivot_longer(S_1995,
             cols = starts_with("P"),
             names_to = "Count",
             values_to = "Pct")
T_2023 <- pivot_longer(S_2023,
                   cols = starts_with("P"),
                   names_to = "Count",
                   values_to = "Pct")

inner_join(T_1995, T_2023, by = "Count") |> 
  mutate(Count = paste(substr(Count, 2, 2),
                       substr(Count, 3, 3),
                       sep = "-"),
         Logit_Change = logit(Pct.y) - logit(Pct.x),
         Count = factor(Count,
                    levels = c("0-1", "1-0",
                               "0-2", "1-1", "2-0",
                               "1-2", "2-1", "3-0",
                               "2-2", "3-1",
                               "3-2"))) -> T12
```

Constructs the graph of the logit differences for all counts.

```{r}
ggplot(T12, aes(Logit_Change, Count)) +
  geom_vline(xintercept = 0, linewidth = 1.5, color = "red") +
  geom_point(size = 4) +
  theme(text=element_text(size=18)) +
  ggtitle("Change in Logits from 1995 to 2023") +
  xlab("Logit 2023 Minus Logit 1985") +
  theme(plot.title = element_text(colour = "blue", size = 18,
              hjust = 0.5, vjust = 0.8, angle = 0))
```