MLB Stats

league_per_game_url <- "https://www.baseball-reference.com/leagues/majors/bat.shtml#all_teams_standard_batting_totals"
league_per_game_url_page <- read_html(league_per_game_url)
mlb_season_history <- html_table(league_per_game_url_page)[[1]]

# Remove any row where the value in the first column is "Year"
mlb_season_history <- mlb_season_history %>%
  filter(.[[1]] != "Year")



# Select columns 9 to 31 for faceted graph over all years (Year)
mlb_season_history_for_graph <- mlb_season_history %>%
  select(1, 9:30) %>%
  mutate(across(everything(), as.numeric)) |> 
  select(-"RBI",-"TB")

# For column "SF" replace any value of 0 with NA
mlb_season_history_for_graph$SF <- ifelse(mlb_season_history_for_graph$SF == 0, NA, mlb_season_history_for_graph$SF)

# Define the desired order for the statistics
desired_order <- c("R", "H", "1B", "2B", "3B", "HR", "BB", "IBB", "HBP", "SF", 
                   "SH", "SO", "GDP", "SB", "CS", "BIP", "BA", "OBP", "SLG", "OPS")

# Make faceted graph
mlb_season_history_for_graph %>%
  pivot_longer(cols = -Year, names_to = "Stat", values_to = "Value") %>%
  mutate(Stat = factor(Stat, levels = desired_order)) %>%
  ggplot(aes(x = Year, y = Value)) +
  geom_line() +
  facet_wrap(~Stat, scales = "free_y") +
  geom_smooth(method = "loess", se = FALSE, color = "red") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  labs(title = "MLB Season History, Per Game Averages 1871 to 2024",
       x = "Year",
       y = "Value") +
  My_Theme_WithY()

# Filter mlb_season_history_for_graph all Years to after 1899
mlb_season_history_20th_cent_for_graph <- mlb_season_history_for_graph %>%
  filter(Year > 1899)

# Make faceted graph
mlb_season_history_20th_cent_for_graph %>%
  pivot_longer(cols = -Year, names_to = "Stat", values_to = "Value") %>%
  mutate(Stat = factor(Stat, levels = desired_order)) %>%
  ggplot(aes(x = Year, y = Value)) +
  geom_line() + # Add X axis labels for every 10 years
  scale_x_continuous(breaks = seq(1900, 2020, by = 50)) +
  facet_wrap(~Stat, scales = "free_y") + # add fitted loees curve to graph
  geom_smooth(method = "loess", se = FALSE, color = "red") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  labs(title = "MLB Season History, Per Game Averages 1900 to 2024",
       x = "Year",
       y = "Value",
       caption = paste("Created by Nick Warino. nickwarino.com. Generated on:", Sys.Date())) +
  My_Theme_WithY()

# Install and load libraries
library(baseballr)
# Load the utils package
library(utils)

# URL of the CSV file
url <- "https://raw.githubusercontent.com/Neil-Paine-1/MLB-WAR-data-historical/master/jeffbagwell_war_historical_2024.csv"

# Download the file and read it into a data frame
data <- read.csv(url, stringsAsFactors = FALSE)

# Save file to output_data fold with today's date which shoul dynamically adjust
write.csv(data, paste0(here("output_data"), "/mlb_war_data_", Sys.Date(), ".csv"), row.names = FALSE)

data_filtered <- data |> 
  select(player_name, lg_ID, team_ID, sched, year_ID, bwar162, br_pwar162) |> 
  filter(sched > 100 | year_ID > 2019) |> 
  mutate(twar162 = bwar162 + br_pwar162) |> 
  mutate(label = ifelse(player_name == "Shohei Ohtani" | player_name == "Babe Ruth", 
                        paste(player_name, year_ID), 
                        NA)) |> 
  mutate(bwar162 = round(bwar162, digits=1),
         br_pwar162 = round(br_pwar162, digits=1),
         twar162 = round(twar162, digits=1)) |>   
  arrange(desc(twar162)) |> 
  mutate(rank_twar = row_number()) |> 
  relocate(rank_twar, .before = player_name)

data_filtered[] <- lapply(data_filtered, function(x) {
  if(is.character(x)) {
    # Convert to UTF-8
    x <- iconv(x, to = "UTF-8", sub = "byte")
    # Optionally, remove non-ASCII characters if they are not needed
    x <- gsub("[^\x01-\x7F]", "", x)
    return(x)
  } else {
    return(x)
  }
})


data_post_integration <- data_filtered |> 
  filter(year_ID > 1944)

seasons_with_2war <- data_filtered |> 
  filter(bwar162 >=2,
         br_pwar162 >=2)  |> 
  select(-label)

seasons_with_1war_post_integration <- data_post_integration |> 
  filter(bwar162 >= 2,
         br_pwar162 >= 2)  |> 
  select(-label)

top_100_ever <- data_filtered |> 
  head(100) |> 
  select(-label)

top_100_post_integration <- data_post_integration |> 
  head(100) |> 
  select(-label)

1 Best Seasons Ever, by WAR per 162 team games

Batting and Pitching WAR per 162 team games by Season (only including seasons with >100 scheduled games)

ggplot(data_filtered,
       aes(x = bwar162,
           y = br_pwar162)) +
  geom_point(aes(size = twar162, fill = twar162), alpha = 0.7, shape = 21, stroke = .5) +
  geom_text_repel(aes(label = label), 
                  size = 5, color = "black", 
                  na.rm = TRUE,
                  max.overlaps = 5) +
  scale_fill_gradient2(low = "blue", mid = "white", high = "red",
                       midpoint = median(data_filtered$twar162, na.rm = TRUE)) +
  labs(title = "WAR By Season, pro-rated to 162 team games",
       subtitle = "Batting and Pitching WAR per 162 team games by Season (only including seasons with >100 scheduled games).\nnickwarino.com, created 2023-08-08",
       caption = "sources: Neil Pain's MLB historical WAR data",
       x = "Batting WAR",
       y = "Pitching WAR",
       fill = "Total WAR") +
  theme(legend.position = c(.9, .9)) +
  My_Theme_WithY()

kable(top_100_ever)

rank_twar	player_name	lg_ID	team_ID	sched	year_ID	bwar162	br_pwar162	twar162
1	Walter Johnson	AL	WSH	155	1913	1.0	15.9	16.9
2	Walter Johnson	AL	WSH	154	1912	1.2	15.0	16.2
3	Babe Ruth	AL	NYY	152	1923	15.4	0.0	15.4
4	Cy Young	AL	BOS	138	1901	0.1	14.6	14.7
5	Walter Johnson	AL	WSH	130	1918	1.2	13.0	14.3
6	Babe Ruth	AL	NYY	153	1921	14.1	-0.3	13.8
7	Joe McGinnity	NL	NYG	142	1903	-0.2	13.9	13.7
8	Grover Alexander	NL	CHC	154	1920	0.7	12.6	13.3
9	Babe Ruth	AL	NYY	155	1927	13.3	0.0	13.3
10	Dwight Gooden	NL	NYM	162	1985	0.9	12.2	13.1
11	Ed Walsh	AL	CHW	158	1912	0.8	12.4	13.1
12	Steve Carlton	NL	PHI	156	1972	0.5	12.5	13.0
13	Babe Ruth	AL	NYY	154	1920	13.1	-0.1	13.0
14	Bullet Rogan	NNL	KCM	101	1921	4.4	8.5	12.9
15	Rogers Hornsby	NL	STL	154	1924	12.8	0.0	12.8
16	Walter Johnson	AL	WSH	157	1914	0.6	12.1	12.8
17	Lou Gehrig	AL	NYY	155	1927	12.7	0.0	12.7
18	Walter Johnson	AL	WSH	155	1915	0.6	12.1	12.7
19	Grover Alexander	NL	PHI	154	1916	1.1	11.5	12.6
20	Hal Newhouser	AL	DET	155	1945	0.8	11.8	12.6
21	Eddie Cicotte	AL	CHW	156	1917	0.2	12.4	12.5
22	Babe Ruth	AL	NYY	153	1924	12.5	0.0	12.5
23	Russ Ford	AL	NYY	156	1910	0.6	11.8	12.4
24	Greg Maddux	NL	ATL	114	1994	0.4	12.1	12.4
25	Christy Mathewson	NL	NYG	142	1903	0.5	11.9	12.4
26	Barry Bonds	NL	SFG	162	2001	12.2	0.0	12.2
27	Barry Bonds	NL	SFG	162	2002	12.2	0.0	12.2
28	Walter Johnson	AL	WSH	142	1919	-0.1	12.3	12.2
29	Christy Mathewson	NL	NYG	157	1908	0.0	12.1	12.2
30	Honus Wagner	NL	PIT	155	1908	12.2	0.0	12.2
31	Roger Clemens	AL	TOR	162	1997	0.1	11.9	12.1
32	Babe Ruth	AL	NYY	155	1926	12.1	0.0	12.1
33	Ed Walsh	AL	CHW	156	1910	0.6	11.6	12.1
34	Ty Cobb	AL	DET	154	1917	12.0	0.0	12.0
35	Stan Coveleski	AL	CLE	129	1918	-0.4	12.4	12.0
36	Mickey Mantle	AL	NYY	154	1956	12.0	0.0	12.0
37	Cy Young	AL	BOS	138	1902	0.1	11.8	12.0
38	Jack Chesbro	AL	NYY	155	1904	0.8	11.1	11.9
39	Mickey Mantle	AL	NYY	154	1957	11.9	0.0	11.9
40	Bob Gibson	NL	STL	162	1968	0.6	11.2	11.8
41	Babe Ruth	AL	BOS	138	1919	10.9	0.9	11.8
42	Smoky Joe Wood	AL	BOS	154	1912	1.1	10.7	11.8
43	Carl Yastrzemski	AL	BOS	162	1967	11.8	0.0	11.8
44	Red Faber	AL	CHW	154	1921	-0.3	12.0	11.7
45	Fergie Jenkins	NL	CHC	162	1971	1.6	10.1	11.7
46	Pedro Martinez	AL	BOS	162	2000	0.0	11.7	11.7
47	Mike Schmidt	NL	PHI	107	1981	11.7	0.0	11.7
48	Ted Williams	AL	BOS	152	1942	11.7	0.0	11.7
49	Grover Alexander	NL	PHI	153	1915	-0.1	11.7	11.6
50	Stan Musial	NL	STL	155	1948	11.6	0.0	11.6
51	Rube Waddell	AL	PHA	137	1902	0.8	10.8	11.6
52	Rogers Hornsby	NL	STL	154	1921	11.5	0.0	11.5
53	Ted Williams	AL	BOS	156	1946	11.5	0.0	11.5
54	Ty Cobb	AL	DET	154	1911	11.4	0.0	11.4
55	Jimmie Foxx	AL	PHA	154	1932	11.4	0.0	11.4
56	Dolf Luque	NL	CIN	154	1923	0.2	11.3	11.4
57	Gaylord Perry	AL	CLE	156	1972	0.2	11.2	11.4
58	Jeff Bagwell	NL	HOU	115	1994	11.3	0.0	11.3
59	Barry Bonds	NL	SFG	162	2004	11.3	0.0	11.3
60	Eddie Cicotte	AL	CHW	140	1919	0.1	11.2	11.3
61	Bob Gibson	NL	STL	162	1969	0.9	10.4	11.3
62	Wes Ferrell	AL	BOS	154	1935	2.6	8.6	11.2
63	Lefty Grove	AL	BOS	155	1936	-0.5	11.7	11.2
64	Rogers Hornsby	NL	CHC	156	1929	11.2	0.0	11.2
65	Walter Johnson	AL	WSH	159	1916	1.0	10.2	11.2
66	Babe Ruth	AL	NYY	154	1930	10.9	0.2	11.2
67	Dizzy Trout	AL	DET	156	1944	1.6	9.6	11.2
68	Ed Walsh	AL	CHW	156	1908	0.5	10.7	11.2
69	Ted Williams	AL	BOS	155	1941	11.2	0.0	11.2
70	Rogers Hornsby	NL	STL	153	1925	11.1	0.0	11.1
71	Cal Ripken Jr.	AL	BAL	162	1991	11.1	0.0	11.1
72	Babe Ruth	AL	NYY	155	1931	11.1	0.0	11.1
73	Tom Seaver	NL	NYM	161	1973	0.4	10.7	11.1
74	Lou Boudreau	AL	CLE	156	1948	11.0	0.0	11.0
75	Walter Johnson	AL	WSH	157	1910	0.2	10.8	11.0
76	Christy Mathewson	NL	NYG	155	1905	1.0	10.1	11.0
77	Joe Morgan	NL	CIN	162	1975	11.0	0.0	11.0
78	Jack Taylor	NL	CHC	143	1902	0.4	10.6	11.0
79	Rube Waddell	AL	PHA	155	1904	-0.8	11.8	11.0
80	Honus Wagner	NL	PIT	155	1905	11.0	0.0	11.0
81	Wilbur Wood	AL	CHW	162	1971	-0.8	11.8	11.0
82	Ty Cobb	AL	DET	155	1910	10.9	0.0	10.9
83	Lou Gehrig	AL	NYY	154	1934	10.9	0.0	10.9
84	Lefty Grove	AL	PHA	154	1930	0.0	10.9	10.9
85	Aaron Judge	AL	NYY	143	2024	10.9	0.0	10.9
86	Greg Maddux	NL	ATL	144	1995	-0.1	10.9	10.9
87	Willie Mays	NL	NYG	154	1954	10.9	0.0	10.9
88	Willie Mays	NL	SFG	163	1965	10.9	0.0	10.9
89	Babe Ruth	AL	NYY	154	1928	10.9	0.0	10.9
90	Tris Speaker	AL	BOS	154	1912	10.9	0.0	10.9
91	Wilbur Wood	AL	CHW	154	1972	-0.4	11.3	10.9
92	Rogers Hornsby	NL	STL	154	1922	10.8	0.0	10.8
93	Rogers Hornsby	NL	NYG	155	1927	10.8	0.0	10.8
94	Aaron Judge	AL	NYY	162	2022	10.8	0.0	10.8
95	Christy Mathewson	NL	NYG	158	1909	0.9	9.9	10.8
96	Willie Mays	NL	SFG	162	1964	10.8	0.0	10.8
97	Tom Seaver	NL	NYM	162	1971	0.6	10.2	10.8
98	Dazzy Vance	NL	BRO	154	1924	-0.2	11.0	10.8
99	Lefty Grove	AL	PHA	153	1931	-0.3	11.0	10.7
100	Dazzy Vance	NL	BRO	155	1928	0.1	10.6	10.7

kable(seasons_with_2war)

rank_twar	player_name	lg_ID	team_ID	sched	year_ID	bwar162	br_pwar162	twar162
14	Bullet Rogan	NNL	KCM	101	1921	4.4	8.5	12.9
62	Wes Ferrell	AL	BOS	154	1935	2.6	8.6	11.2
144	Shohei Ohtani	AL	LAA	162	2023	6.3	3.9	10.1
158	Lewis Hampton	NNL	ABC	101	1922	3.3	6.7	10.0
199	Shohei Ohtani	AL	LAA	162	2022	3.5	6.2	9.7
276	Babe Ruth	AL	BOS	126	1918	6.3	3.0	9.3
329	Shohei Ohtani	AL	LAA	162	2021	4.9	4.1	9.0
437	Wes Ferrell	AL	CLE	155	1931	2.0	6.5	8.5
2740	Don Drysdale	NL	LAD	162	1965	2.3	3.2	5.6
2974	Don Newcombe	NL	BRO	154	1955	2.4	3.1	5.5

2 Best Seasons Since MLB Integration, by WAR per 162 team games

Batting and Pitching WAR per 162 team games by Season (only including seasons with >100 scheduled games)

ggplot(data_post_integration,
       aes(x = bwar162,
           y = br_pwar162)) +
  geom_point(aes(size = twar162, fill = twar162), alpha = 0.7, shape = 21, stroke = .5) +
  scale_size(range = c(1, 10)) +
  geom_text_repel(aes(label = label), 
                  size = 5, color = "black", 
                  na.rm = TRUE,
                  max.overlaps = 5) +
  scale_fill_gradient2(low = "blue", mid = "white", high = "red",
                       midpoint = median(data_post_integration$twar162, na.rm = TRUE)) +
  labs(title = "WAR By Season (Post-Integrated MLB), pro-rated to 162 team games",
       subtitle = "Batting and Pitching WAR per 162 team games by Season (only including seasons with >100 scheduled games.\nnickwarino.com, created 2023-08-08",
       caption = "sources: Neil Pain's MLB historical WAR data",
       x = "Batting WAR",
       y = "Pitching WAR",
       fill = "Total WAR") +
  theme(legend.position = c(.9, .9)) +
  My_Theme_WithY()

kable(top_100_post_integration)

rank_twar	player_name	lg_ID	team_ID	sched	year_ID	bwar162	br_pwar162	twar162
10	Dwight Gooden	NL	NYM	162	1985	0.9	12.2	13.1
12	Steve Carlton	NL	PHI	156	1972	0.5	12.5	13.0
20	Hal Newhouser	AL	DET	155	1945	0.8	11.8	12.6
24	Greg Maddux	NL	ATL	114	1994	0.4	12.1	12.4
26	Barry Bonds	NL	SFG	162	2001	12.2	0.0	12.2
27	Barry Bonds	NL	SFG	162	2002	12.2	0.0	12.2
31	Roger Clemens	AL	TOR	162	1997	0.1	11.9	12.1
36	Mickey Mantle	AL	NYY	154	1956	12.0	0.0	12.0
39	Mickey Mantle	AL	NYY	154	1957	11.9	0.0	11.9
40	Bob Gibson	NL	STL	162	1968	0.6	11.2	11.8
43	Carl Yastrzemski	AL	BOS	162	1967	11.8	0.0	11.8
45	Fergie Jenkins	NL	CHC	162	1971	1.6	10.1	11.7
46	Pedro Martinez	AL	BOS	162	2000	0.0	11.7	11.7
47	Mike Schmidt	NL	PHI	107	1981	11.7	0.0	11.7
50	Stan Musial	NL	STL	155	1948	11.6	0.0	11.6
53	Ted Williams	AL	BOS	156	1946	11.5	0.0	11.5
57	Gaylord Perry	AL	CLE	156	1972	0.2	11.2	11.4
58	Jeff Bagwell	NL	HOU	115	1994	11.3	0.0	11.3
59	Barry Bonds	NL	SFG	162	2004	11.3	0.0	11.3
61	Bob Gibson	NL	STL	162	1969	0.9	10.4	11.3
71	Cal Ripken Jr.	AL	BAL	162	1991	11.1	0.0	11.1
73	Tom Seaver	NL	NYM	161	1973	0.4	10.7	11.1
74	Lou Boudreau	AL	CLE	156	1948	11.0	0.0	11.0
77	Joe Morgan	NL	CIN	162	1975	11.0	0.0	11.0
81	Wilbur Wood	AL	CHW	162	1971	-0.8	11.8	11.0
85	Aaron Judge	AL	NYY	143	2024	10.9	0.0	10.9
86	Greg Maddux	NL	ATL	144	1995	-0.1	10.9	10.9
87	Willie Mays	NL	NYG	154	1954	10.9	0.0	10.9
88	Willie Mays	NL	SFG	163	1965	10.9	0.0	10.9
91	Wilbur Wood	AL	CHW	154	1972	-0.4	11.3	10.9
94	Aaron Judge	AL	NYY	162	2022	10.8	0.0	10.8
96	Willie Mays	NL	SFG	162	1964	10.8	0.0	10.8
97	Tom Seaver	NL	NYM	162	1971	0.6	10.2	10.8
101	Andre Dawson	NL	MON	108	1981	10.6	0.0	10.6
103	Randy Johnson	NL	ARI	162	2002	-0.2	10.7	10.5
104	Willie Mays	NL	SFG	154	1958	10.5	0.0	10.5
105	Bobby Witt Jr.	AL	KCR	144	2024	10.5	0.0	10.5
106	Ernie Banks	NL	CHC	155	1959	10.4	0.0	10.4
107	Mookie Betts	AL	BOS	162	2018	10.4	0.0	10.4
108	Roger Clemens	AL	BOS	162	1990	0.0	10.4	10.4
112	Zack Greinke	AL	KCR	162	2009	0.0	10.4	10.4
114	Phil Niekro	NL	ATL	162	1978	0.5	10.0	10.4
118	Mickey Mantle	AL	NYY	163	1961	10.3	0.0	10.3
119	Juan Marichal	NL	SFG	163	1965	0.1	10.2	10.3
120	Willie Mays	NL	SFG	165	1962	10.3	0.0	10.3
121	Robin Roberts	NL	PHI	156	1953	0.1	10.2	10.3
123	Mike Trout	AL	LAA	162	2012	10.3	0.0	10.3
124	Barry Bonds	NL	SFG	162	1993	10.2	0.0	10.2
126	Bob Gibson	NL	STL	162	1970	1.3	8.9	10.2
129	Mickey Mantle	AL	NYY	154	1955	10.2	0.0	10.2
130	Willie Mays	NL	SFG	162	1963	10.2	0.0	10.2
131	Jose Rijo	NL	CIN	162	1993	1.0	9.2	10.2
133	Ted Williams	AL	BOS	157	1947	10.2	0.0	10.2
134	Ted Williams	AL	BOS	154	1957	10.2	0.0	10.2
137	Steve Carlton	NL	PHI	162	1980	-0.1	10.2	10.1
141	Rickey Henderson	AL	OAK	162	1990	10.1	0.0	10.1
144	Shohei Ohtani	AL	LAA	162	2023	6.3	3.9	10.1
145	Al Rosen	AL	CLE	155	1953	10.1	0.0	10.1
146	Sammy Sosa	NL	CHC	162	2001	10.1	0.0	10.1
149	Robin Yount	AL	MIL	163	1982	10.1	0.0	10.1
154	Dwight Evans	AL	BOS	108	1981	10.0	0.0	10.0
155	Bob Feller	AL	CLE	156	1946	-0.4	10.4	10.0
160	Hal Newhouser	AL	DET	155	1946	-0.2	10.1	10.0
162	Jacob deGrom	NL	NYM	162	2018	0.4	9.5	9.9
164	Dick Ellsworth	NL	CHC	162	1963	-0.3	10.2	9.9
166	Ken Griffey Jr.	AL	SEA	112	1994	9.9	0.0	9.9
167	Rickey Henderson	AL	OAK	109	1981	9.9	0.0	9.9
168	Rickey Henderson	AL	NYY	161	1985	9.9	0.0	9.9
169	Sandy Koufax	NL	LAD	163	1963	-0.7	10.6	9.9
170	Kenny Lofton	AL	CLE	113	1994	9.9	0.0	9.9
171	Juan Marichal	NL	SFG	161	1966	0.7	9.1	9.9
173	Cal Ripken Jr.	AL	BAL	162	1984	9.9	0.0	9.9
174	Alex Rodriguez	AL	SEA	162	2000	9.9	0.0	9.9
175	Warren Spahn	NL	BSN	154	1947	-0.1	10.0	9.9
178	Ted Williams	AL	BOS	155	1949	9.9	0.0	9.9
179	Carl Yastrzemski	AL	BOS	162	1968	9.9	0.0	9.9
182	Barry Bonds	NL	PIT	162	1990	9.8	0.0	9.8
184	Ken Griffey Jr.	AL	SEA	161	1996	9.8	0.0	9.8
188	Pedro Martinez	AL	BOS	162	1999	0.0	9.8	9.8
189	Rico Petrocelli	AL	BOS	162	1969	9.8	0.0	9.8
190	Jackie Robinson	NL	BRO	156	1949	9.8	0.0	9.8
194	Bert Blyleven	AL	MIN	162	1973	0.0	9.7	9.7
195	Barry Bonds	NL	SFG	161	2003	9.7	0.0	9.7
197	David Cone	AL	KCR	115	1994	0.0	9.7	9.7
199	Shohei Ohtani	AL	LAA	162	2022	3.5	6.2	9.7
201	Bret Saberhagen	AL	KCR	162	1989	0.0	9.7	9.7
202	Bobby Shantz	AL	PHA	155	1952	0.4	9.2	9.7
203	Mike Trout	AL	LAA	162	2018	9.7	0.0	9.7
205	Henry Aaron	NL	MLN	155	1961	9.6	0.0	9.6
206	Adrian Beltre	NL	LAD	162	2004	9.6	0.0	9.6
207	Norm Cash	AL	DET	163	1961	9.6	0.0	9.6
209	Mark Fidrych	AL	DET	161	1976	0.0	9.6	9.6
213	Randy Johnson	AL	SEA	145	1995	0.0	9.6	9.6
214	Randy Johnson	NL	ARI	162	2001	-0.5	10.1	9.6
215	Sandy Koufax	NL	LAD	162	1966	-0.6	10.3	9.6
218	Willie Mays	NL	NYG	154	1955	9.6	0.0	9.6
219	Joe Morgan	NL	CIN	162	1976	9.6	0.0	9.6
220	Rick Reuschel	NL	CHC	162	1977	0.2	9.4	9.6
221	Jackie Robinson	NL	BRO	158	1951	9.6	0.0	9.6
222	Ron Santo	NL	CHC	162	1967	9.6	0.0	9.6

kable(seasons_with_1war_post_integration)

rank_twar	player_name	lg_ID	team_ID	sched	year_ID	bwar162	br_pwar162	twar162
144	Shohei Ohtani	AL	LAA	162	2023	6.3	3.9	10.1
199	Shohei Ohtani	AL	LAA	162	2022	3.5	6.2	9.7
329	Shohei Ohtani	AL	LAA	162	2021	4.9	4.1	9.0
2740	Don Drysdale	NL	LAD	162	1965	2.3	3.2	5.6
2974	Don Newcombe	NL	BRO	154	1955	2.4	3.1	5.5

3 2024 Hit Data

# Load CSV from raw data
hit_data <- read.csv(here("raw_data", "exit_velocity.csv"), stringsAsFactors = FALSE)
hit_data2 <- read.csv(here("raw_data", "expected_stats.csv"), stringsAsFactors = FALSE)

# Join by player_id
hit_data <- hit_data |> 
  left_join(hit_data2, by = "player_id")

# Rename column 1 to Player
colnames(hit_data)[1] <- "player_name"

hit_data_above_30_attempts <- hit_data |> 
  filter(attempts > 30)

# Plot max_hit_speed and avg_hit_speed by player
ggplot(hit_data_above_30_attempts, aes(x = max_hit_speed, y = avg_hit_speed)) +
  geom_point(aes(size = attempts, fill = max_distance), alpha = 0.7, shape = 21, stroke = .5) +
  geom_text_repel(aes(label = player_name), 
                  size = 5, color = "black", 
                  na.rm = TRUE,
                  max.overlaps = 5) +
  scale_size(range = c(1, 15)) +
  scale_fill_gradient2(low = "blue", mid = "white", high = "red",
                       midpoint = median(hit_data_above_30_attempts$max_distance, na.rm = TRUE)) +
  labs(title = "No one crushes the ball like Ohtani",
       subtitle = "Max Hit Speed, Average Hit Speed, Max Distance, and Average Distance by Player\nnickwarino.com, created 2024-04-25",
       caption = "sources: Statcast",
       x = "Max Hit Speed",
       y = "Average Hit Speed",
       fill = "Max Distance",
       size = "Attempts") +
  theme(legend.position = c(.9, .9)) +
  My_Theme_WithY()

# Plot max_hit_speed and avg_hit_speed by player
ggplot(hit_data_above_30_attempts, aes(x = max_hit_speed, y = max_distance)) +
  geom_point(aes(size = attempts, fill = avg_hit_speed), alpha = 0.7, shape = 21, stroke = .5) +
  geom_text_repel(aes(label = player_name), 
                  size = 5, color = "black", 
                  na.rm = TRUE,
                  max.overlaps = 5) +
  scale_size(range = c(1, 15)) +
  scale_fill_gradient2(low = "blue", mid = "white", high = "red",
                       midpoint = median(hit_data_above_30_attempts$avg_hit_speed, na.rm = TRUE)) +
  labs(title = "No one crushes the ball like Ohtani",
       subtitle = "Max Hit Speed, Average Hit Speed, Max Distance, and Average Distance by Player\nnickwarino.com, created 2024-04-25",
       caption = "sources: Statcast",
       x = "Max Hit Speed",
       y = "Max Distance",
       fill = "Average Hit Speed",
       size = "Attempts") +
  theme(legend.position = c(.9, .9)) +
  My_Theme_WithY()

# Plot max_hit_speed and avg_hit_speed by player
ggplot(hit_data_above_30_attempts, aes(x = max_hit_speed, y = max_distance)) +
  geom_point(aes(size = attempts, fill = est_woba), alpha = 0.7, shape = 21, stroke = .5) +
  geom_text_repel(aes(label = player_name), 
                  size = 5, color = "black", 
                  na.rm = TRUE,
                  max.overlaps = 5) +
  scale_size(range = c(1, 15)) +
  scale_fill_gradient2(low = "blue", mid = "white", high = "red",
                       midpoint = median(hit_data_above_30_attempts$est_woba, na.rm = TRUE)) +
  labs(title = "No one crushes the ball like Ohtani",
       subtitle = "Max Hit Speed, Max Distance, and Expected wOBA by Player\nnickwarino.com, created 2024-04-25",
       caption = "sources: Statcast",
       x = "Max Hit Speed",
       y = "Max Distance",
       fill = "Expected wOBA",
       size = "Attempts") +
  theme(legend.position = c(.9, .9)) +
  My_Theme_WithY()

4 Fuck the Yankees: Team Payroll History

# Load "output_data/team_salaries_2024-05-02.csv"
team_salaries <- read.csv(here("output_data", "team_salaries_2024-05-02.csv"), stringsAsFactors = FALSE)

# Calculate new column that is total league payroll grouped by Year, and then another new column that is the percentage of the league payroll that each team is spending
team_salaries <- team_salaries |> 
  group_by(Year) |> 
  mutate(league_payroll = sum(Payroll), 
         pct_of_league_payroll = round((Payroll / league_payroll)*100, 2))

library(tidyverse)

# Assuming team_salaries is your dataset
highlighted_teams <- c("Yankees", "Dodgers", "Red Sox", "Giants")  # Define highlighted teams

team_salaries %>%
  ggplot(aes(x = Year, y = pct_of_league_payroll, group = TeamName,
             color = ifelse(TeamName %in% highlighted_teams, TeamName, "Other"))) +
  geom_line(aes(size = ifelse(TeamName %in% highlighted_teams, 2, 0.5))) +  # Adjust this line for line sizes
  scale_size_identity() +  # Ensure that sizes are used as is
  scale_y_continuous(limits = c(0, 10)) +
  scale_color_manual(values = c(
    "Yankees" = "black",
    "Dodgers" = "blue",
    "Red Sox" = "red",
    "Giants" = "orange",
    "Other" = "lightgrey"  # Light grey for all other teams
  )) +
  labs(title = "Fuck the Yankees: Team Payroll as a Percentage of League Payroll (1985-2024)",
       x = "Year",
       y = "Percentage of League Payroll",
       caption = "Source: Baseball-Reference, Lahman package. Created by Nick Warino on 2024-05-02") +
  guides(color = guide_legend(title = "Team Name"), size = FALSE) +  # Disable size legend
  My_Theme_WithY() +  # Assuming this is your custom theme function
  theme(legend.position = "top")  # Move legend to top