Some Quick Baseball Stats

Lahman

library("gt")
library("Lahman")
library("tidyverse")

df <- Teams |>
  filter(yearID >= 2004) #focusing on the past 18 season

readr::write_csv(df, "baseball_2004_2022.csv")

colnames(df)

 [1] "yearID"         "lgID"           "teamID"         "franchID"      
 [5] "divID"          "Rank"           "G"              "Ghome"         
 [9] "W"              "L"              "DivWin"         "WCWin"         
[13] "LgWin"          "WSWin"          "R"              "AB"            
[17] "H"              "X2B"            "X3B"            "HR"            
[21] "BB"             "SO"             "SB"             "CS"            
[25] "HBP"            "SF"             "RA"             "ER"            
[29] "ERA"            "CG"             "SHO"            "SV"            
[33] "IPouts"         "HA"             "HRA"            "BBA"           
[37] "SOA"            "E"              "DP"             "FP"            
[41] "name"           "park"           "attendance"     "BPF"           
[45] "PPF"            "teamIDBR"       "teamIDlahman45" "teamIDretro"   

df |>
  select(yearID, franchID, HR) |> #select columns to keep
  slice_max(HR, n = 10) |> #finds 10 highest values by numerical variable
  gt() #makes nice tables

yearID	franchID	HR
2019	MIN	307
2019	NYY	306
2019	HOU	288
2019	LAD	279
2018	NYY	267
2021	TOR	262
2005	TEX	260
2010	TOR	257
2019	OAK	257
2019	CHC	256

df |>
  select(yearID, franchID, ERA) |> #select columns to keep
  slice_min(ERA, n = 10) |> #finds 10 loweest values by numerical variable
  gt() #makes nice tables

yearID	franchID	ERA
2022	LAD	2.80
2022	HOU	2.90
2015	STL	2.94
2021	LAD	3.01
2011	PHI	3.02
2020	LAD	3.02
2014	WSN	3.03
2018	HOU	3.11
2016	CHC	3.15
2014	SEA	3.17