StringsAsFactors

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: git2rdata
 Title: Store and Retrieve Data.frames in a Git Repository
-Version: 0.2.0
+Version: 0.2.1
 Authors@R: c(
   person(
     "Thierry", "Onkelinx", role = c("aut", "cre"), 

NEWS.md

@@ -1,3 +1,13 @@
+git2rdata 0.2.1 (2020-02-03)
+=================================
+
+### Bugfixes
+
+  * Explicitly use the `stringsAsFactors` of `data.frame()` in the examples and
+  unit tests if the dataframe contains characters. The upcoming change in 
+  default value of `stringsAsFactors` requires this change. See
+  https://developer.r-project.org/Blog/public/2020/02/16/stringsasfactors/index.html
+
 git2rdata 0.2.0 (2019-11-08)
 =================================
 

R/relabel.R

@@ -27,7 +27,11 @@
 #' # Create a dataframe and store it as an optimized git2rdata object.
 #' # Note that write_vc() uses optimization by default.
 #' # Stage and commit the git2rdata object.
-#' ds <- ds <- data.frame(a = c("a1", "a2"), b = c("b2", "b1"))
+#' ds <- data.frame(
+#'   a = c("a1", "a2"),
+#'   b = c("b2", "b1"),
+#'   stringsAsFactors = TRUE
+#' )
 #' junk <- write_vc(ds, "relabel", repo, sorting = "b", stage = TRUE)
 #' cm <- commit(repo, "initial commit")
 #' # check that the workspace is clean
@@ -49,7 +53,8 @@
 #' change <- data.frame(
 #'   factor = c("a", "a", "b"),
 #'   old = c("a3", "a1", "b2"),
-#'   new = c("c2", "c1", "b3")
+#'   new = c("c2", "c1", "b3"),
+#'   stringsAsFactors = TRUE
 #' )
 #' relabel("relabel", repo, change)
 #' # check the changes

codemeta.json

@@ -14,14 +14,14 @@
   ],
   "issueTracker": "https://github.com/ropensci/git2rdata/issues",
   "license": "https://spdx.org/licenses/GPL-3.0",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "programmingLanguage": {
     "@type": "ComputerLanguage",
     "name": "R",
-    "version": "3.6.1",
+    "version": "3.6.2",
     "url": "https://r-project.org"
   },
-  "runtimePlatform": "R version 3.6.1 (2019-07-05)",
+  "runtimePlatform": "R version 3.6.2 (2019-12-12)",
   "author": [
     {
       "@type": "Person",
@@ -203,7 +203,7 @@
   ],
   "releaseNotes": "https://github.com/ropensci/git2rdata/blob/master/NEWS.md",
   "readme": "https://github.com/ropensci/git2rdata/blob/master/README.md",
-  "fileSize": "341.663KB",
+  "fileSize": "341.883KB",
   "contIntegration": [
     "https://travis-ci.org/inbo/git2rdata",
     "https://ci.appveyor.com/project/ThierryO/git2rdata/branch/master",

tests/testthat/test_b_update.R

@@ -56,7 +56,7 @@ test_that("updates to numeric", {
 test_that("updates to character", {
   write_vc(original, "character", root, sorting = "test_logical")
   updated <- matrix("xyz", ncol = ncol(original), dimnames = dimnames(original))
-  updated <- as.data.frame(updated)
+  updated <- as.data.frame(updated, stringsAsFactor = FALSE)
   expect_is(
     suppressWarnings(
       fn <- write_vc(updated, "character", root, strict = FALSE)

tests/testthat/test_d_relabel.R

@@ -1,7 +1,7 @@
 context("relabel")
 root <- tempfile("git2rdata-relabel")
 dir.create(root)
-ds <- data.frame(a = c("a1", "a2"), b = c("b2", "b1"))
+ds <- data.frame(a = c("a1", "a2"), b = c("b2", "b1"), stringsAsFactors = TRUE)
 write_vc(ds, "relabel", root, sorting = "b")
 new_labels <- list(a = list(a2 = "a3"))
 test_that("relabel handles a list of changes", {

tests/testthat/test_e_empty_label.R

@@ -56,7 +56,9 @@ test_that("write_vc handles empty labels", {
 })
 
 test_that("relabel handles empty labels", {
-  change <- data.frame(factor = "var", old = "", new = "something")
+  change <- data.frame(
+    factor = "var", old = "", new = "something", stringsAsFactors = TRUE
+  )
 
   # "" is first level
   mydf <- data.frame(

vignettes/version_control.Rmd

@@ -217,15 +217,18 @@ print_file("column_order.tsv", root, n = 5)
 We take this even a bit further: what happens if new data arrives and we need an extra factor level? 
 
 ```{r factor}
-old <- data.frame(color = c("red", "blue"))
+old <- data.frame(color = c("red", "blue"), stringsAsFactors = TRUE)
 write_vc(old, "factor", root, sorting = "color")
 print_file("factor.yml", root)
 ```
 
 Let's add an observation with a new factor level. If we store the updated dataframe in a new file, we see that the indices are different. The factor level `"blue"` remains unchanged, but `"red"` becomes the third level and get index `3` instead of index `2`. This could lead to a large diff whereas the potential semantics (and thus the information content) are not changed.
 
 ```{r factor2}
-updated <- data.frame(color = c("red", "green", "blue"))
+updated <- data.frame(
+  color = c("red", "green", "blue"), 
+  stringsAsFactors = TRUE
+)
 write_vc(updated, "factor2", root, sorting = "color")
 print_file("factor2.yml", root)
 ```
@@ -239,12 +242,13 @@ print_file("factor.yml", root)
 ```
 
 The next example removes the `"blue"` level and switches the order of the remaining levels. 
-Notice that the medatadata retains the existing indices. 
+Notice that the meta data retains the existing indices. 
 The order of the labels and indices reflects their new ordering.
 
 ```{r factor_deleted}
 deleted <- data.frame(
-  color = factor(c("red", "green"), levels = c("red", "green")))
+  color = factor(c("red", "green"), levels = c("red", "green"))
+)
 write_vc(deleted, "factor", root, sorting = "color", strict = FALSE)
 print_file("factor.yml", root)
 ```
@@ -253,7 +257,8 @@ Changing a factor to an ordered factor or _vice versa_ will also keep existing l
 
 ```{r factor_ordered}
 ordered <- data.frame(
-  color = factor(c("red", "green"), levels = c("red", "green"), ordered = TRUE))
+  color = factor(c("red", "green"), levels = c("red", "green"), ordered = TRUE)
+)
 write_vc(ordered, "factor", root, sorting = "color", strict = FALSE)
 print_file("factor.yml", root)
 ```
@@ -285,8 +290,12 @@ The dataframe format requires a `factor`, `old` and `new` variable with one row
 write_vc(old, "relabel", root, sorting = "color")
 relabel("relabel", root, change = list(color = c(red = "rood", blue = "blauw")))
 print_file("relabel.yml", root)
-relabel("relabel", root, 
-        change = data.frame(factor = "color", old = "blauw", new = "blue"))
+relabel(
+  "relabel", root, 
+  change = data.frame(
+    factor = "color", old = "blauw", new = "blue", stringsAsFactors = TRUE
+  )
+)
 print_file("relabel.yml", root)
 ```