Skip to content

Commit

Permalink
Update data using new source data directory structure
Browse files Browse the repository at this point in the history
  • Loading branch information
cdalzell committed Apr 4, 2022
1 parent 20712f3 commit d317d4e
Show file tree
Hide file tree
Showing 33 changed files with 8 additions and 12 deletions.
Binary file modified data/AllstarFull.RData
Binary file not shown.
Binary file modified data/Appearances.RData
Binary file not shown.
Binary file modified data/AwardsManagers.RData
Binary file not shown.
Binary file modified data/AwardsPlayers.RData
Binary file not shown.
Binary file modified data/AwardsShareManagers.RData
Binary file not shown.
Binary file modified data/AwardsSharePlayers.RData
Binary file not shown.
Binary file modified data/Batting.RData
Binary file not shown.
Binary file modified data/BattingPost.RData
Binary file not shown.
Binary file modified data/CollegePlaying.RData
Binary file not shown.
Binary file modified data/Fielding.RData
Binary file not shown.
Binary file modified data/FieldingOF.RData
Binary file not shown.
Binary file modified data/FieldingOFsplit.RData
Binary file not shown.
Binary file modified data/FieldingPost.RData
Binary file not shown.
Binary file modified data/HallOfFame.RData
Binary file not shown.
Binary file modified data/HomeGames.RData
Binary file not shown.
Binary file modified data/LahmanData.RData
Binary file not shown.
Binary file modified data/Managers.RData
Binary file not shown.
Binary file modified data/ManagersHalf.RData
Binary file not shown.
Binary file modified data/Master.RData
Binary file not shown.
Binary file modified data/Parks.RData
Binary file not shown.
Binary file modified data/People.RData
Binary file not shown.
Binary file modified data/Pitching.RData
Binary file not shown.
Binary file modified data/PitchingPost.RData
Binary file not shown.
Binary file modified data/Salaries.RData
Binary file not shown.
Binary file modified data/Schools.RData
Binary file not shown.
Binary file modified data/SeriesPost.RData
Binary file not shown.
Binary file modified data/Teams.RData
Binary file not shown.
Binary file modified data/TeamsFranchises.RData
Binary file not shown.
Binary file modified data/TeamsHalf.RData
Binary file not shown.
Binary file modified data/battingLabels.RData
Binary file not shown.
Binary file modified data/fieldingLabels.RData
Binary file not shown.
Binary file modified data/pitchingLabels.RData
Binary file not shown.
20 changes: 8 additions & 12 deletions inst/scripts/readLahman.R
Original file line number Diff line number Diff line change
Expand Up @@ -23,11 +23,12 @@ unzip(dataFile, exdir=indir)
#Batting <- read.csv(file="Batting.csv", header=TRUE, stringsAsFactors=FALSE, na.strings="")
#Master <- read.csv(file="Master.csv", header=TRUE, stringsAsFactors=FALSE)

# set indir to the directories the csv are extracted to
indir <- paste0(indir, "/baseballdatabank-2022.2/core")

indir <- paste0(indir, "/baseballdatabank-2022.2")
setwd(indir)

(files <- list.files(path=getwd(), pattern="csv"))
directoryList = c(paste0(getwd(), "/core"), paste0(getwd(), "/contrib"))
(files <- list.files(directoryList, pattern="csv", full.names=TRUE))

for (i in 1:length(files)) {
inp <- read.csv(file=files[i], header=TRUE, stringsAsFactors=FALSE, na.strings="")
Expand All @@ -45,12 +46,8 @@ for (i in 1:length(files)) {
if("teamIDwinner" %in% names(inp)) inp$teamIDwinner <- factor(inp$teamIDwinner)
if("teamIDloser" %in% names(inp)) inp$teamIDloser <- factor(inp$teamIDloser)

cname <- name <- sub(".csv", "", files[i])
assign( name, inp)

# these will be saved below after being compressed
#save(inp, file=paste(cname, ".RData", sep=""))
#promptData(inp, name=cname)
name <- sub(".csv", "", basename(files[i]))
assign(name, inp)
}

# fix column names or perform any needed data cleanup here
Expand Down Expand Up @@ -87,7 +84,7 @@ People <- within(People, {
# 'named Guillermo VelC!zquez' in object 'Master'
# 'Martmn Magdaleno Dihigo (Llanos)' in object 'Master'

tools:::showNonASCII(paste0(indir, 'People.csv'))
tools:::showNonASCII(paste0(indir, '/core/People.csv'))

# then, fix manually, because I don't know an R way ...

Expand Down Expand Up @@ -151,8 +148,7 @@ if (FALSE) {
promptData(HallOfFame, filename="HallOfFame.Rd")
promptData(HOFold, filename="HOFold.Rd")
promptData(Managers, filename="Managers.Rd")
promptData(ManagersHalf, filename="ManagersHalf.Rd")
promptData(Master, filename="Master.Rd")
promptData(ManagersHalf, filename="ManagersHalf.Rd")
promptData(Pitching, filename="Pitching.Rd")
promptData(PitchingPost, filename="PitchingPost.Rd")
promptData(Salaries, filename="Salaries.Rd")
Expand Down

0 comments on commit d317d4e

Please sign in to comment.