Twitter post: https://twitter.com/PeteBerryman/status/171181890744976…

…6233

tweets/1711818907449766233/Career WAR by Debut Team.Rmd

@@ -0,0 +1,134 @@
+# Setup
+```{r setup, message = FALSE}
+library(jsonlite)
+library(dplyr)
+library(Lahman)
+library(baseballr)
+library(ggplot2)
+library(ggtext)
+
+player_ids.df <- playerid_lookup(last_name = "", first_name = "")
+```
+
+# Each MLB Player's 1st Team (1871 - 2022)
+```{r}
+# Debut teams
+debut.teams.df <-
+  union(Lahman::Batting %>%
+          filter(stint == 1) %>%
+          select(playerID, yearID, teamID),
+        Lahman::Pitching %>%
+          filter(stint == 1) %>%
+          select(playerID, yearID, teamID)
+  ) %>%
+  group_by(playerID) %>%
+  arrange(yearID) %>%
+  filter(row_number() == 1) %>%
+  left_join(Lahman::Teams %>% select(yearID, teamID, franchID),
+            by = c("yearID" = "yearID", "teamID" = "teamID")) %>%
+  left_join(Lahman::People %>% select(playerID, bbrefID), by = "playerID") %>%
+  left_join(player_ids.df %>% select(bbref_id, fangraphs_id),
+            by = c("bbrefID" = "bbref_id")) %>%
+  ungroup() %>%
+  select(fangraphs_id, franchID)
+debut.teams.df %>% head(10)
+```
+
+# Career fWAR for Each Player
+## Batting
+```{r}
+# Batter Seasons
+base.url <- "https://www.fangraphs.com/api/leaders/major-league/data"
+query.params <- list(age = "", pos = "all", stats = "bat", lg = "al%2Cnl",
+                     qual = "0", season = "2022", season1 = "1871",
+                     startdate = "", enddate = "", month = "0", hand = "",
+                     team = "0", pageitems = "2000000000", pagenum = "1",
+                     ind = "0", rost = "0", players = "", type = "8",
+                     sortdir = "default", sortstat = "WAR")
+sep = "?"
+url <- base.url
+for (param in names(query.params)) {
+  url <- paste(url, sep, param, "=", query.params[[param]], sep = "")
+  sep = "&"
+}
+batter.seasons.df <- fromJSON(url)$data %>%
+  select(Name, WAR) %>%
+  mutate(Type = "Batter")
+batter.seasons.df %>% head(10)
+```
+
+## Pitching
+```{r}
+# Pitcher Seasons
+query.params$stats <- "pit"
+
+sep = "?"
+url <- base.url
+for (param in names(query.params)) {
+  url <- paste(url, sep, param, "=", query.params[[param]], sep = "")
+  sep = "&"
+}
+pitcher.seasons.df <- fromJSON(url)$data %>%
+  select(Name, WAR) %>%
+  mutate(Type = "Pitcher")
+pitcher.seasons.df %>% head(10)
+```
+
+## Combine Batting & Pitching
+```{r}
+war.df <- union(batter.seasons.df, pitcher.seasons.df) %>%
+  mutate(fangraphs_id = as.integer(gsub(".*playerid=(.*)&.*", "\\1", Name)),
+         Name = gsub(".*>(.*)<.*", "\\1", Name)) %>%
+  group_by(fangraphs_id) %>%
+  summarise(Name = first(Name), WAR = sum(WAR)) %>%
+  full_join(debut.teams.df, by = "fangraphs_id") %>%
+  rename(debut_franchise = franchID)
+war.df %>% head(10)
+```
+
+## Data Quality Check
+```{r}
+cat(scales::percent(sum(is.na(war.df$debut_franchise)) /
+                      length(war.df$debut_franchise), accuracy = 0.1),
+    "of player IDs were not mapped successfully")
+war.df %>% filter(is.na(debut_franchise)) %>% arrange(desc(WAR))
+```
+
+# Aggregate fWAR by Franchise
+```{r}
+team.war.df <- war.df %>%
+    group_by(debut_franchise) %>%
+    summarise(WAR = sum(WAR, na.rm = TRUE), players = n()) %>%
+    arrange(WAR) %>%
+    tail(31) %>%
+    mutate(
+      `WAR/player` = WAR / players,
+      logo = ifelse(
+        debut_franchise != "LOU",
+        paste("<img src=\"https://cdn.ssref.net/req/202310031/tlogo/br/",
+              debut_franchise, ".png\" height=\"25\"/>", sep = ""),
+        "<img src=\"https://upload.wikimedia.org/wikipedia/en/4/4a/LouisvilleColonelsLogo.PNG\" height=\"25\"/>"
+      )
+    )
+team.war.df$logo <- factor(team.war.df$logo, levels = team.war.df$logo)
+team.war.df %>% head(10)
+```
+
+# Graph
+```{r}
+team.war.sum.plot <- ggplot(team.war.df, aes(x = reorder(logo, WAR), y = WAR)) +
+  geom_col(fill = "#69b3a2") +
+  geom_text(aes(label = round(WAR, digits = 0)), color = "white", size = 6,
+            hjust = 1.1) +
+  coord_flip() +
+  scale_x_discrete(name = NULL, labels = team.war.df$logo) +
+  ggtitle("Career WAR by Players who Debuted with Each Franchise (1871-2022)") +
+  theme(plot.title = element_text(size = 22),
+        axis.text.x = element_text(size = 14),
+        axis.title.x = element_text(size = 16, face = "bold"),
+        axis.text.y = element_markdown())
+
+ggsave("~/Desktop/peteb206.github.io/tweets/1/team_war_sum.png",
+       plot = team.war.sum.plot, width = 15, height = 12)
+team.war.sum.plot
+```

tweets/1711818907449766233/rsconnect/documents/Career WAR by Debut Team.Rmd/rpubs.com/rpubs/Document.dcf

@@ -0,0 +1,11 @@
+name: Document
+title:
+username:
+account: rpubs
+server: rpubs.com
+hostUrl: rpubs.com
+appId: https://api.rpubs.com/api/v1/document/1096686/2873aea40f2441ca9f415a694b728be4
+bundleId: https://api.rpubs.com/api/v1/document/1096686/2873aea40f2441ca9f415a694b728be4
+url: http://rpubs.com/publish/claim/1096686/cbd69df8f04047b28f18f6bb79887a1f
+when: 1696963013.60974
+lastSyncTime: 1696963013.60975