use xz compression

Author: mllg

DESCRIPTION

@@ -28,6 +28,7 @@ Suggests:
     mlr3 (>= 0.13.3)
 Encoding: UTF-8
 LazyData: true
+LazyDataCompression: xz
 NeedsCompilation: no
 Roxygen: list(markdown = TRUE)
 RoxygenNote: 7.2.3

data-raw/ames_housing.R

@@ -1,3 +1,3 @@
 url = "https://raw.githubusercontent.com/ja-thomas/extend_ames_housing/main/data/ames_dirty.csv"
 ames_housing = data.table::fread(url, stringsAsFactors = TRUE)
-usethis::use_data(ames_housing, overwrite = TRUE)
+usethis::use_data(ames_housing, overwrite = TRUE, compress = "xz")

data-raw/bike_sharing.R

@@ -5,13 +5,13 @@ download.file("https://archive.ics.uci.edu/ml/machine-learning-databases/00275/B
 bike_sharing = setDT(read.csv(unz(tmp, filename = "hour.csv"), as.is = TRUE))
 bike_sharing = setnames(bike_sharing, c("instant", "date", "season", "year", "month", "hour", "holiday", "weekday",
   "working_day", "weather", "temperature", "apparent_temperature", "humidity", "windspeed", "casual", "registered",
-  "count")) 
+  "count"))
 
 bike_sharing[, holiday := as.logical(holiday)]
 bike_sharing[, working_day := as.logical(working_day)]
 bike_sharing[, season := factor(season, labels = c("winter", "spring", "summer", "fall"))]
-bike_sharing[, weather :=  as.factor(bike_sharing$weather)] 
+bike_sharing[, weather :=  as.factor(bike_sharing$weather)]
 
 bike_sharing = bike_sharing[, .SD, .SDcols = !c("instant", "casual", "registered")]
 
-usethis::use_data(bike_sharing, overwrite = TRUE)
+usethis::use_data(bike_sharing, overwrite = TRUE, compress = "xz")

data-raw/energy_usage.R

@@ -1,3 +1,3 @@
 url = "https://raw.githubusercontent.com/ja-thomas/extend_ames_housing/main/data/energy_usage.csv"
 energy_usage = data.table::fread(url, stringsAsFactors = TRUE)
-usethis::use_data(energy_usage, overwrite = TRUE)
+usethis::use_data(energy_usage, overwrite = TRUE, compress = "xz")

data-raw/ilpd.R

@@ -9,4 +9,4 @@ levels(ilpd$diseased) = c("yes", "no")
 
 data.table::setDF(ilpd)
 
-usethis::use_data(ilpd, overwrite = TRUE)
+usethis::use_data(ilpd, overwrite = TRUE, compress = "xz")

data-raw/kc_housing.R

@@ -10,6 +10,6 @@ kc_housing[, date := anytime::anytime(date)]
 kc_housing[yr_renovated == 0, yr_renovated := NA_integer_]
 kc_housing[sqft_basement == 0, sqft_basement := NA_integer_]
 kc_housing[, waterfront := as.logical(waterfront)]
-setDF(kc_housing)
+data.table::setDF(kc_housing)
 
-usethis::use_data(kc_housing, overwrite = TRUE)
+usethis::use_data(kc_housing, overwrite = TRUE, compress = "xz")

data-raw/moneyball.R

@@ -4,8 +4,8 @@ odata = OMLData$new(41021)
 moneyball = odata$data
 to_integer = c("Year", "RS", "RA", "W")
 moneyball[, (to_integer) := lapply(.SD, as.integer), .SDcols = to_integer]
-setnames(moneyball, new = tolower(colnames(moneyball)))
+data.table::setnames(moneyball, new = tolower(colnames(moneyball)))
 
-setDF(moneyball)
+data.table::setDF(moneyball)
 
-usethis::use_data(moneyball, overwrite = TRUE)
+usethis::use_data(moneyball, overwrite = TRUE, compress = "xz")

data-raw/optdigits.R

@@ -3,7 +3,7 @@ library("mlr3oml")
 odata = OMLData$new(980)
 optdigits = odata$data
 optdigits[, odata$feature_names := lapply(.SD, as.integer), .SDcols = (odata$feature_names)]
-setnames(optdigits, old = "binaryClass", new = "binaryclass")
-setDF(optdigits)
+data.table::setnames(optdigits, old = "binaryClass", new = "binaryclass")
+data.table::setDF(optdigits)
 
-usethis::use_data(optdigits, overwrite = TRUE)
+usethis::use_data(optdigits, overwrite = TRUE, compress = "xz")

data-raw/penguins_simple.R

@@ -10,4 +10,4 @@ task = graph$train(list(task))$output
 penguins_simple = task$data()
 setDF(penguins_simple)
 
-usethis::use_data(penguins_simple, overwrite = TRUE)
+usethis::use_data(penguins_simple, overwrite = TRUE, compress = "xz")

data-raw/titanic.R

@@ -19,4 +19,4 @@ titanic[!nzchar(embarked), embarked := NA_character_]
 titanic[, embarked := as.factor(embarked)]
 setDF(titanic)
 
-usethis::use_data(titanic, overwrite = TRUE)
+usethis::use_data(titanic, overwrite = TRUE, compress = "xz")