Update raw builds (#7)

* Switch from devtools to usethis for `use_data()`. Explicitly set `header` if variable names are present in file. * Re-build Rdas
coatless-rpkg · Jul 18, 2024 · fbc9977 · fbc9977
1 parent 724bc4e
commit fbc9977
Show file tree

Hide file tree

Showing 26 changed files with 42 additions and 36 deletions.
diff --git a/data-raw/abalone_build.R b/data-raw/abalone_build.R
@@ -16,4 +16,4 @@ colnames(abalone) = c("sex",
                       "rings")
 
 # Save dataset
-devtools::use_data(abalone)
+usethis::use_data(abalone, overwrite = TRUE)
diff --git a/data-raw/autoimports_build.R b/data-raw/autoimports_build.R
@@ -44,6 +44,7 @@ var_names_safe = gsub("-", "_", var_names)
 
 colnames(autoimports) = var_names_safe
 
-devtools::use_data(autoimports, overwrite = TRUE)
+usethis::use_data(autoimports, overwrite = TRUE)
+
 
 
diff --git a/data-raw/autompg_build.R b/data-raw/autompg_build.R
@@ -5,9 +5,10 @@ autompg = read.table(
   "http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data",
   quote = "\"",
   comment.char = "",
-  stringsAsFactors = FALSE)
+  stringsAsFactors = FALSE,
+  header = FALSE)
 
 colnames(autompg) = c("mpg", "cylinders", "displacement", "horsepower",
                       "weight", "acceleration", "model_year", "origin", "car_name")
 
-devtools::use_data(autompg)
+usethis::use_data(autompg, overwrite = TRUE)
diff --git a/data-raw/bcw_original_build.R b/data-raw/bcw_original_build.R
@@ -28,4 +28,4 @@ bcw_original = breast_cancer_wis_data
 
 rm(list="breast_cancer_wis_data")
 
-devtools::use_data(bcw_original, overwrite = TRUE)
+usethis::use_data(bcw_original, overwrite = TRUE)
diff --git a/data-raw/bike_sharing_daily_build.R b/data-raw/bike_sharing_daily_build.R
@@ -7,26 +7,28 @@ download.file("http://archive.ics.uci.edu/ml/machine-learning-databases/00275/Bi
 
 # Unzip and load bike sharing data into R
 # Note, data has a header in it!
-bike_sharing_daily = read.csv(unz("data-raw/Bike-Sharing-Dataset.zip",
-                                  "day.csv"),
-                              colClasses = c("character",  # instant
-                                             "Date",       # dteday
-                                             "factor",     # season
-                                             "factor",     # yr
-                                             "factor",     # mnth
-                                             "factor",     # holiday
-                                             "factor",     # weekday
-                                             "factor",     # workingday
-                                             "factor",     # weathersit
-                                             "numeric",    # temp
-                                             "numeric",    # atemp
-                                             "numeric",    # hum
-                                             "numeric",    # windspeed
-                                             "integer",    # casual
-                                             "integer",    # registered
-                                             "integer"     # cnt
-                                             )
-                               )
+bike_sharing_daily = read.csv(
+  unz("data-raw/Bike-Sharing-Dataset.zip", "day.csv"),
+  header = TRUE,
+  colClasses = c(
+    "character",  # instant
+    "Date",       # dteday
+    "factor",     # season
+    "factor",     # yr
+    "factor",     # mnth
+    "factor",     # holiday
+    "factor",     # weekday
+    "factor",     # workingday
+    "factor",     # weathersit
+    "numeric",    # temp
+    "numeric",    # atemp
+    "numeric",    # hum
+    "numeric",    # windspeed
+    "integer",    # casual
+    "integer",    # registered
+    "integer"     # cnt
+  )
+)
 
 # Improve factor labels
 bike_sharing_daily = within(bike_sharing_daily, {
@@ -52,7 +54,7 @@ bike_sharing_daily = within(bike_sharing_daily, {
 # })
 
 # Write the bike_sharing_daily dataset
-devtools::use_data(bike_sharing_daily, overwrite = TRUE)
+usethis::use_data(bike_sharing_daily, overwrite = TRUE)
 
 # Remove the zip + csv after read in.
 file.remove("data-raw/Bike-Sharing-Dataset.zip")
diff --git a/data-raw/bridges_build.R b/data-raw/bridges_build.R
@@ -33,5 +33,5 @@ bridges = within(bridges, {
   lanes = factor(lanes)
 })
 
-devtools::use_data(bridges, overwrite = TRUE)
+usethis::use_data(bridges, overwrite = TRUE)
 
diff --git a/data-raw/car_eval_build.R b/data-raw/car_eval_build.R
@@ -13,4 +13,4 @@ colnames(car_eval) = c("buying",
                        "safety",
                        "class_value")
 
-devtools::use_data(car_eval, overwrite = TRUE)
+usethis::use_data(car_eval, overwrite = TRUE)
diff --git a/data-raw/forest_fires_build.R b/data-raw/forest_fires_build.R
@@ -5,4 +5,4 @@ url_forest_fires = "https://archive.ics.uci.edu/ml/machine-learning-databases/fo
 
 forest_fires = read.csv(url_forest_fires, header = TRUE)
 
-devtools::use_data(forest_fires, overwrite = TRUE)
+usethis::use_data(forest_fires, overwrite = TRUE)
diff --git a/data-raw/glass_build.R b/data-raw/glass_build.R
@@ -36,4 +36,4 @@ glass = within(glass, {
 })
 
 # Save dataset
-devtools::use_data(glass, overwrite = TRUE)
+usethis::use_data(glass, overwrite = TRUE)
diff --git a/data-raw/hepatitis_build.R b/data-raw/hepatitis_build.R
@@ -3,8 +3,10 @@
 
 url_hepatitis = "http://archive.ics.uci.edu/ml/machine-learning-databases/hepatitis/hepatitis.data"
 
-hepatitis = read.csv(url_hepatitis,
-                   header = FALSE, na.strings = "?")
+hepatitis = read.csv(
+  url_hepatitis,
+  header = FALSE, na.strings = "?"
+)
 
 # Columns taken verbatim from ML page
 # Regex search with: [0-9]{1,2}\. (.*):.*
@@ -46,7 +48,7 @@ hepatitis = within(hepatitis,{
   sex   = factor(sex, labels = c("Male", "Female"))
 })
 
-devtools::use_data(hepatitis, overwrite = TRUE)
+usethis::use_data(hepatitis, overwrite = TRUE)
 
 ## output colnames
 cat(paste0(colnames(hepatitis),"\n"), sep="")
diff --git a/data-raw/wine_build.R b/data-raw/wine_build.R
@@ -6,8 +6,8 @@ red_wine_url   = "http://archive.ics.uci.edu/ml/machine-learning-databases/wine-
 white_wine_url = "http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv"
 
 # Note the .csv uses a `;` as the separater. Not `,`
-red_wine_data   = read.csv(red_wine_url, sep = ";")
-white_wine_data = read.csv(white_wine_url, sep = ";")
+red_wine_data   = read.csv(red_wine_url, sep = ";", header = TRUE)
+white_wine_data = read.csv(white_wine_url, sep = ";", header = TRUE)
 
 # Load in Red vs. White Data
 red_wine_data$color   = "Red"
@@ -22,4 +22,4 @@ wine$color = as.factor(wine$color)
 # Remove periods
 colnames(wine) = gsub("\\.", "_", colnames(wine))
 
-devtools::use_data(wine)
+usethis::use_data(wine, overwrite = TRUE)
diff --git a/data/abalone.rda b/data/abalone.rda
diff --git a/data/autoimports.rda b/data/autoimports.rda
diff --git a/data/autompg.rda b/data/autompg.rda
diff --git a/data/bcw_original.rda b/data/bcw_original.rda
diff --git a/data/bike_sharing_daily.rda b/data/bike_sharing_daily.rda
diff --git a/data/bridges.rda b/data/bridges.rda
diff --git a/data/car_eval.rda b/data/car_eval.rda
diff --git a/data/forest_fires.rda b/data/forest_fires.rda
diff --git a/data/glass.rda b/data/glass.rda
diff --git a/data/heart_disease_ch.rda b/data/heart_disease_ch.rda
diff --git a/data/heart_disease_cl.rda b/data/heart_disease_cl.rda
diff --git a/data/heart_disease_hu.rda b/data/heart_disease_hu.rda
diff --git a/data/heart_disease_va.rda b/data/heart_disease_va.rda
diff --git a/data/hepatitis.rda b/data/hepatitis.rda
diff --git a/data/wine.rda b/data/wine.rda