Markdown file to compute random effects estimates of team defenses on ground balls.

AVG_ground_balls.R

---
title: "AVG on Ground Balls"
author: "Jim Albert"
date: "11/2/2021"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE,
                      message = FALSE,
                      warning = FALSE)
```

Read in the necessary packages.
```{r}
library(dplyr)
library(readr)
library(ggplot2)
library(lme4)
library(ggrepel)
```

Couple of helper functions to read in.

```{r}
increasefont <- function (){
    theme(text = element_text(size = 18))
}
centertitle <- function () {
    theme(plot.title = element_text(colour = 
          "blue", size = 18, 
        hjust = 0.5, vjust = 0.8, angle = 0))
}
```

Read in the Statcast data from my hard drive.

```{r}
statcast2021 <- read_csv("~/Dropbox/2021 WORK/Statcast2021/ORIGINAL/data/statcast2021.csv")
```

Data work.  Creating the fielding team and hit variables.  Only considering ground balls.

```{r}
hits <- c("single", "double", "triple",
          "home_run")
statcast2021 %>%
  filter(type == "X") %>%
  mutate(BAT_TEAM = ifelse(inning_topbot == "Top",
                           away_team, home_team),
         FIELD_TEAM = ifelse(inning_topbot == "Top",
                             home_team, away_team),
         H = ifelse(events %in% hits, 1, 0))  %>%
  filter(launch_angle < 10) %>%
  select(game_year, BAT_TEAM,
         FIELD_TEAM, launch_angle, launch_speed,
         H, if_fielding_alignment, stand) -> scip
```

Some minor editing to remove one weird case.

```{r}
filter(scip, if_fielding_alignment != "-0.014") ->
  scip
```

Find AVG for each type of batting side and fielding alignment:

```{r}
scip %>% 
  group_by(stand, if_fielding_alignment) %>% 
  summarize(N = n(), AVG = mean(H)) -> S1
```

Graph these situational AVGs.

```{r}
ggplot(S1, aes(if_fielding_alignment, AVG,
               label = stand,
               color = stand)) +
  geom_text(size = 6,
            fontface = "bold") +
  increasefont() +
  centertitle() +
  ggtitle("2021 Groundball AVG by Fielding Alignment and Stand")
```

Fit random effects model.

```{r}
fit <- glmer(H ~ stand + if_fielding_alignment +
               stand * if_fielding_alignment +
               (1 | FIELD_TEAM),
             family = binomial,
             data = scip)
```

Collect random effects into a data frame.

```{r}
ranef(fit)$FIELD_TEAM -> RE
RE$Team <- row.names(RE)
row.names(RE) <- NULL
names(RE)[1] <- "randeff"

```

Add league info to data frame.

```{r}
RE$League <- c("NL", "NL", "NL", "NL", "AL", "NL", "NL", "NL",
               "AL", "NL", "AL", "NL", "NL", "AL", "AL", "NL",
               "AL", "AL", "AL", "AL", "NL", "NL", "AL", "NL",
               "AL", "AL", "AL", "NL", "AL", "AL")
```

Graph random effects estimates for each league.

```{r}
ggplot(RE, aes(randeff, League, label = Team)) +
  geom_text_repel() +
  increasefont() +
  ggtitle("2021 Team Random Effects") +
  centertitle() +
  xlab("Random Effect")
```

I collected the Fielding Bible team fielding estimates into a csv file -- read this into R and merge with random effects data frame.

```{r}
fb <- read_csv("fieldingbible.csv")
inner_join(RE, fb, by = c("Team" = "T_abb")) -> fb
```

Computing infield FB measurements.

```{r}
fb %>%
  mutate(Infield = X1B + X2B + X3B + XSS) ->
  fb
```

Scatterplot of RE and FB estimates.

```{r}
ggplot(fb, aes(randeff, Infield, 
               label = Team)) +
  geom_text() +
  increasefont() +
  centertitle() +
  ylab("FB Infield") +
  xlab("Random Effect") +
  ggtitle("Scatterplot of Fielding Bible Infield and Random Effects")
```