Acquiring Quakes and Storm data with R and baseballr
Oliver d’ Pug
9/4/2022
Get the California League Game Data
First, figure out how to get Cal League data for a single date.
games <- get_game_pks_mlb(date = '2022-09-03',
level_ids = c(14))
games %>%
select(game_pk, gameDate, teams.away.team.name, teams.home.team.name)## ── MLB Game Pks data from MLB.com ─────────────────────────── baseballr 1.2.0 ──## ℹ Data updated: 2022-09-05 13:06:12 PDT## # A tibble: 17 × 4
## game_pk gameDate teams.away.team.name teams.home.team.name
## <int> <chr> <chr> <chr>
## 1 670189 2022-09-03T20:00:00Z Clearwater Threshers Lakeland Flying Tigers
## 2 670190 2022-09-03T20:05:00Z Clearwater Threshers Lakeland Flying Tigers
## 3 670082 2022-09-03T20:00:00Z Dunedin Blue Jays Tampa Tarpons
## 4 669868 2022-09-03T21:00:00Z Columbia Fireflies Carolina Mudcats
## 5 669623 2022-09-03T21:00:00Z Fayetteville Woodpeckers Down East Wood Ducks
## 6 670159 2022-09-03T22:00:00Z Daytona Tortugas Palm Beach Cardinals
## 7 669970 2022-09-03T22:05:00Z Salem Red Sox Augusta GreenJackets
## 8 669823 2022-09-03T22:05:00Z Myrtle Beach Pelicans Charleston RiverDogs
## 9 669577 2022-09-03T22:05:00Z Delmarva Shorebirds Fredericksburg Nation…
## 10 670052 2022-09-03T22:10:00Z Jupiter Hammerheads St. Lucie Mets
## 11 669397 2022-09-03T22:30:00Z Kannapolis Cannon Ballers Lynchburg Hillcats
## 12 670578 2022-09-03T22:30:00Z Fort Myers Mighty Mussels Bradenton Marauders
## 13 671035 2022-09-04T00:05:00Z Visalia Rawhide Lake Elsinore Storm
## 14 669152 2022-09-04T01:50:00Z Modesto Nuts Fresno Grizzlies
## 15 670716 2022-09-04T02:05:00Z San Jose Giants Stockton Ports
## 16 671071 2022-09-04T02:05:00Z Rancho Cucamonga Quakes Inland Empire 66ers
## 17 670006 2022-09-03T22:30:00Z Dunedin Blue Jays Tampa Tarpons games %>%
select(game_pk, gameDate, teams.away.team.name, teams.away.team.id, teams.home.team.name, teams.home.team.id)## ── MLB Game Pks data from MLB.com ─────────────────────────── baseballr 1.2.0 ──
## ℹ Data updated: 2022-09-05 13:06:12 PDT## # A tibble: 17 × 6
## game_pk gameDate teams.away.team.name teams…¹ teams…² teams…³
## <int> <chr> <chr> <int> <chr> <int>
## 1 670189 2022-09-03T20:00:00Z Clearwater Threshers 566 Lakela… 570
## 2 670190 2022-09-03T20:05:00Z Clearwater Threshers 566 Lakela… 570
## 3 670082 2022-09-03T20:00:00Z Dunedin Blue Jays 424 Tampa … 587
## 4 669868 2022-09-03T21:00:00Z Columbia Fireflies 3705 Caroli… 249
## 5 669623 2022-09-03T21:00:00Z Fayetteville Woodpeckers 3712 Down E… 485
## 6 670159 2022-09-03T22:00:00Z Daytona Tortugas 450 Palm B… 279
## 7 669970 2022-09-03T22:05:00Z Salem Red Sox 414 August… 478
## 8 669823 2022-09-03T22:05:00Z Myrtle Beach Pelicans 521 Charle… 233
## 9 669577 2022-09-03T22:05:00Z Delmarva Shorebirds 548 Freder… 436
## 10 670052 2022-09-03T22:10:00Z Jupiter Hammerheads 479 St. Lu… 507
## 11 669397 2022-09-03T22:30:00Z Kannapolis Cannon Balle… 487 Lynchb… 481
## 12 670578 2022-09-03T22:30:00Z Fort Myers Mighty Musse… 509 Braden… 3390
## 13 671035 2022-09-04T00:05:00Z Visalia Rawhide 516 Lake E… 103
## 14 669152 2022-09-04T01:50:00Z Modesto Nuts 515 Fresno… 259
## 15 670716 2022-09-04T02:05:00Z San Jose Giants 476 Stockt… 524
## 16 671071 2022-09-04T02:05:00Z Rancho Cucamonga Quakes 526 Inland… 401
## 17 670006 2022-09-03T22:30:00Z Dunedin Blue Jays 424 Tampa … 587
## # … with abbreviated variable names ¹teams.away.team.id, ²teams.home.team.name,
## # ³teams.home.team.id cal_league_ids <- c(526, 476, 515, 516, 524, 401, 259, 103)
rcquakes_id <- 526
elsinore_id <- 103
games %>%
filter(teams.away.team.id %in% cal_league_ids | teams.home.team.id %in% cal_league_ids)## ── MLB Game Pks data from MLB.com ─────────────────────────── baseballr 1.2.0 ──
## ℹ Data updated: 2022-09-05 13:06:12 PDT## # A tibble: 4 × 61
## game_pk link gameT…¹ season gameD…² offic…³ resum…⁴ isTie gameN…⁵ publi…⁶
## <int> <chr> <chr> <chr> <chr> <chr> <chr> <lgl> <int> <lgl>
## 1 671035 /api/v1.… R 2022 2022-0… 2022-0… <NA> FALSE 1 TRUE
## 2 669152 /api/v1.… R 2022 2022-0… 2022-0… <NA> FALSE 1 TRUE
## 3 670716 /api/v1.… R 2022 2022-0… 2022-0… <NA> FALSE 1 TRUE
## 4 671071 /api/v1.… R 2022 2022-0… 2022-0… <NA> FALSE 1 TRUE
## # … with 51 more variables: doubleHeader <chr>, gamedayType <chr>,
## # tiebreaker <chr>, calendarEventID <chr>, seasonDisplay <chr>,
## # dayNight <chr>, scheduledInnings <int>, reverseHomeAwayStatus <lgl>,
## # inningBreakLength <int>, gamesInSeries <int>, seriesGameNumber <int>,
## # seriesDescription <chr>, recordSource <chr>, ifNecessary <chr>,
## # ifNecessaryDescription <chr>, rescheduledFrom <chr>,
## # rescheduledFromDate <chr>, description <chr>, resumedFrom <chr>, …Now grab the data for a bunch of dates.
### Create a sequence of gamedays
game_dates <- seq(ymd('2022-04-08'), ymd('2022-09-03'), by='day') ### Requires lubridate for ymd
### Get game data for each date. "Invalid arguments" will be returned for non-game dates --- Mondays
Sys.time()## [1] "2022-09-05 13:06:13 PDT" games <- map_df(.x = game_dates,
~get_game_pks_mlb(.x, level_ids=c(14))
) %>%
filter(teams.away.team.id %in% cal_league_ids | teams.home.team.id %in% cal_league_ids)## 2022-09-05 13:06:14: Invalid arguments provided## 2022-09-05 13:06:15: Invalid arguments provided## 2022-09-05 13:06:17: Invalid arguments provided## 2022-09-05 13:06:19: Invalid arguments provided## 2022-09-05 13:06:21: Invalid arguments provided## 2022-09-05 13:06:22: Invalid arguments provided## 2022-09-05 13:06:24: Invalid arguments provided## 2022-09-05 13:06:27: Invalid arguments provided## 2022-09-05 13:06:29: Invalid arguments provided## 2022-09-05 13:06:31: Invalid arguments provided## 2022-09-05 13:06:32: Invalid arguments provided## 2022-09-05 13:06:34: Invalid arguments provided## 2022-09-05 13:06:36: Invalid arguments provided## 2022-09-05 13:06:38: Invalid arguments provided
## 2022-09-05 13:06:38: Invalid arguments provided## 2022-09-05 13:06:39: Invalid arguments provided
## 2022-09-05 13:06:39: Invalid arguments provided## 2022-09-05 13:06:40: Invalid arguments provided## 2022-09-05 13:06:41: Invalid arguments provided## 2022-09-05 13:06:43: Invalid arguments provided## 2022-09-05 13:06:45: Invalid arguments provided## 2022-09-05 13:06:47: Invalid arguments provided## 2022-09-05 13:06:48: Invalid arguments provided Sys.time()## [1] "2022-09-05 13:06:50 PDT" ### Look at the first 10 games to make sure that they are Cal League
games %>%
select(game_pk, gameDate, teams.away.team.name, teams.away.team.id, teams.home.team.name, teams.home.team.id) %>%
head(10)## ── MLB Game Pks data from MLB.com ─────────────────────────── baseballr 1.2.0 ──## ℹ Data updated: 2022-09-05 13:06:13 PDT## # A tibble: 10 × 6
## game_pk gameDate teams.away.team.name teams.…¹ teams…² teams…³
## <int> <chr> <chr> <int> <chr> <int>
## 1 670707 2022-04-09T01:45:00Z Rancho Cucamonga Quakes 526 Visali… 516
## 2 671522 2022-04-09T01:50:00Z Stockton Ports 524 Fresno… 259
## 3 671220 2022-04-09T02:05:00Z Lake Elsinore Storm 103 Inland… 401
## 4 671037 2022-04-09T02:05:00Z San Jose Giants 476 Modest… 515
## 5 671036 2022-04-10T01:05:00Z San Jose Giants 476 Modest… 515
## 6 670708 2022-04-10T01:30:00Z Rancho Cucamonga Quakes 526 Visali… 516
## 7 671524 2022-04-10T01:50:00Z Stockton Ports 524 Fresno… 259
## 8 671217 2022-04-10T02:05:00Z Lake Elsinore Storm 103 Inland… 401
## 9 670712 2022-04-10T20:00:00Z Rancho Cucamonga Quakes 526 Visali… 516
## 10 671519 2022-04-10T20:05:00Z Stockton Ports 524 Fresno… 259
## # … with abbreviated variable names ¹teams.away.team.id, ²teams.home.team.name,
## # ³teams.home.team.id ### Now get additional game info. We use the game_pk variable to retrieve the information.
Sys.time()## [1] "2022-09-05 13:06:50 PDT" game_info <- map_df(.x = games$game_pk,
~get_game_info_mlb(.x)
)
Sys.time()## [1] "2022-09-05 13:11:55 PDT" ### Join the two tibbles on game_pk
Sys.time()## [1] "2022-09-05 13:11:55 PDT" games_2022 <- games %>%
left_join(game_info, by="game_pk")
Sys.time()## [1] "2022-09-05 13:11:55 PDT" dim(games)## [1] 503 70 dim(game_info)## [1] 503 18 dim(games_2022)## [1] 509 87 ### Determine home fields for Elsinore and the Quakes
games_2022 %>%
filter(teams.home.team.id %in% c(elsinore_id, rcquakes_id)) %>%
count(venue.id, venue_name)## ── MLB Game Pks data from MLB.com ─────────────────────────── baseballr 1.2.0 ──
## ℹ Data updated: 2022-09-05 13:06:13 PDT## # A tibble: 2 × 3
## venue.id venue_name n
## <int> <chr> <int>
## 1 2516 The Diamond 68
## 2 2854 LoanMart Field 60Histograms of Run Distribution
Look at the distribution of runs by the different teams. We only really care about the Storm and the Quakes at Loanmart Field.
games_2022 %>%
ggplot(aes(x=teams.home.score)) +
geom_histogram(binwidth = 1) +
facet_wrap(~venue_name) +
labs(title = 'Home Team Score at Home',
subtitle = '2022 Season') ## Warning: Removed 4 rows containing non-finite values (stat_bin).
games_2022 %>%
filter(teams.home.team.id == rcquakes_id) %>%
ggplot(aes(x=teams.home.score)) +
geom_histogram(binwidth = 1) +
facet_grid(rows = vars(teams.away.team.name)) +
labs(title = 'Quakes Score vs Away Team',
subtitle = '2022 Season')
games_2022 %>%
filter(teams.home.team.id == rcquakes_id) %>%
ggplot(aes(x=teams.away.score)) +
geom_histogram(binwidth = 1) +
facet_grid(rows = vars(teams.away.team.name)) +
labs(title = 'Away Team Score vs Quakes',
subtitle = '2022 Season')
Compare Scores at Loanmart Field
temp <- games_2022 %>%
filter(teams.home.team.id == rcquakes_id) %>%
group_by(teams.away.score, teams.home.score) %>%
count(teams.away.score, teams.home.score)
head(temp,10)## # A tibble: 10 × 3
## # Groups: teams.away.score, teams.home.score [10]
## teams.away.score teams.home.score n
## <int> <int> <int>
## 1 0 8 1
## 2 1 2 1
## 3 1 3 1
## 4 1 4 1
## 5 1 7 1
## 6 1 10 1
## 7 1 18 1
## 8 2 1 1
## 9 2 5 1
## 10 2 6 1 temp %>% ggplot(aes(x=teams.away.score, y=teams.home.score, fill=n)) +
geom_raster(interpolate = FALSE) +
scale_fill_distiller(palette = "Spectral")## Warning: Raster pixels are placed at uneven vertical intervals and will be
## shifted. Consider using geom_tile() instead.
temp <- games_2022 %>%
group_by(venue_name, teams.away.score, teams.home.score) %>%
count(venue_name, teams.away.score, teams.home.score)
temp %>% ggplot(aes(x=teams.away.score, y=teams.home.score, fill=n)) +
geom_tile() +
scale_fill_gradient(low = "red", high = "green") +
facet_wrap("venue_name")## Warning: Removed 2 rows containing missing values (geom_tile).
temp <- games_2022 %>%
filter(teams.home.team.id == rcquakes_id)
temp <- table(temp[,c("teams.home.score","teams.away.score")])
### Or, use the tabluated values
melted_z_counts <- melt(temp)
head(melted_z_counts)## teams.home.score teams.away.score value
## 1 1 0 0
## 2 2 0 0
## 3 3 0 0
## 4 4 0 0
## 5 5 0 0
## 6 6 0 0 names(melted_z_counts) <- c("Quakes_Runs","Away_Runs","Count")
ggplot(data = melted_z_counts, aes(x=Quakes_Runs, y=Away_Runs, fill=Count)) +
geom_tile() + scale_fill_gradient(low = "red", high = "green")
ggplot(data = melted_z_counts, aes(x=Quakes_Runs, y=Away_Runs, z=Count)) +
geom_contour_filled()