CRAN release 0.4.0 (#143)

* update tests

* revert a few test changes

* prepare CRAN submission

* Update NEWS.md

* useful in other functions, but for now, in reshape only

* fix URL

* Delete .DS_Store

* remove png

Co-authored-by: Daniel <[email protected]>

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling
-Version: 0.3.1.9010
+Version: 0.4.0
 Authors@R: c(
     person("Dominique", "Makowski", , "[email protected]", role = "aut",
            comment = c(ORCID = "0000-0001-5375-9967", Twitter = "@Dom_Makowski")),
@@ -25,7 +25,7 @@ BugReports: https://github.com/easystats/datawizard/issues
 Depends:
     R (>= 3.4)
 Imports:
-    insight (>= 0.16.0.5),
+    insight (>= 0.17.0),
     stats,
     utils
 Suggests: 
@@ -46,8 +46,6 @@ Suggests:
     see,
     spelling,
     testthat (>= 3.0.0)
-Remotes:
-    easystats/insight
 VignetteBuilder: 
     knitr
 Config/testthat/edition: 3

NEWS.md

@@ -1,4 +1,4 @@
-# datawizard 0.3.0.9000
+# datawizard 0.4.0
 
 MAJOR CHANGES
 
@@ -17,57 +17,57 @@ MAJOR CHANGES
 
 NEW FUNCTIONS
 
-  * To convert rownames to a column, and *vice versa*: `rownames_as_column()` 
-    and `column_as_rownames()` (@etiennebacher, #80).
+* To convert rownames to a column, and *vice versa*: `rownames_as_column()` 
+  and `column_as_rownames()` (@etiennebacher, #80).
 
-  * `find_columns()` and `get_columns()` to find column names or retrieve
-    subsets of data frames, based on various select-methods (including
-    select-helpers). These function will supersede `data_findcols()` in the
-    future.
+* `find_columns()` and `get_columns()` to find column names or retrieve
+  subsets of data frames, based on various select-methods (including
+  select-helpers). These function will supersede `data_findcols()` in the
+  future.
 
 * `data_filter()` as complement for `data_match()`, which works with logical 
   expressions for filtering rows of data frames.
 
-  * For computing weighted centrality measures and dispersion: `weighted_mean()`,
-    `weighted_median()`, `weighted_sd()` and `weighted_mad()`.
+* For computing weighted centrality measures and dispersion: `weighted_mean()`,
+  `weighted_median()`, `weighted_sd()` and `weighted_mad()`.
 
-  * To replace `NA` in vectors and dataframes: `convert_na_to()` (@etiennebacher, #111).
+* To replace `NA` in vectors and dataframes: `convert_na_to()` (@etiennebacher, #111).
 
 MINOR CHANGES
 
-  * The `select` argument in several functions (like `data_remove()`,
-    `reshape_longer()`, or  `data_extract()`) now allow the use of select-helpers
-    for selecting variables based on specific patterns.
+* The `select` argument in several functions (like `data_remove()`,
+  `reshape_longer()`, or  `data_extract()`) now allows the use of select-helpers
+  for selecting variables based on specific patterns.
 
-  * `data_extract()` gains new arguments to allow type-safe return values,
-    i.e. *always* return a vector *or* a data frame. Thus, `data_extract()`
-    can now be used to select multiple variables or pull a single variable
-    from data frames.
+* `data_extract()` gains new arguments to allow type-safe return values,
+   i.e. *always* return a vector *or* a data frame. Thus, `data_extract()`
+   can now be used to select multiple variables or pull a single variable
+   from data frames.
 
-  * `data_match()` gains a `match` argument, to indicate with which logical
-    operation matching results should be combined.
+* `data_match()` gains a `match` argument, to indicate with which logical
+  operation matching results should be combined.
 
-  * Improved support for *labelled data* for many functions, i.e. returned
-    data frame will preserve value and variable label attributes, where
-    possible and applicable.
+* Improved support for *labelled data* for many functions, i.e. returned
+  data frame will preserve value and variable label attributes, where
+  possible and applicable.
 
-  * `describe_distribution()` now works with lists (@etiennebacher, #105).
+* `describe_distribution()` now works with lists (@etiennebacher, #105).
 
-  * `data_rename()` doesn't use `pattern` anymore to rename the columns if
-    `replacement` is not provided (@etiennebacher, #103).
+* `data_rename()` doesn't use `pattern` anymore to rename the columns if
+  `replacement` is not provided (@etiennebacher, #103).
 
-  * `data_rename()` now adds a suffix to duplicated names in `replacement`
-    (@etiennebacher, #103).
+* `data_rename()` now adds a suffix to duplicated names in `replacement`
+  (@etiennebacher, #103).
 
 BUG FIXES
 
-  * `data_to_numeric()` produced wrong results for factors when
-    `dummy_factors = TRUE` and factor contained missing values.
+* `data_to_numeric()` produced wrong results for factors when
+  `dummy_factors = TRUE` and factor contained missing values.
 
-  * `data_match()` produced wrong results when data contained missing values.
+* `data_match()` produced wrong results when data contained missing values.
 
-  * Fixed CRAN check issues in `data_extract()` when more than one variable
-    was extracted from a data frame.
+* Fixed CRAN check issues in `data_extract()` when more than one variable
+  was extracted from a data frame.
 
 # datawizard 0.3.0
 

R/data_reshape.R

@@ -84,6 +84,7 @@ data_to_long <- function(data,
                          values_to = "Value",
                          rows_to = NULL,
                          ignore_case = FALSE,
+                         regex = FALSE,
                          cols = select,
                          ...,
                          names_to = colnames_to) {
@@ -100,7 +101,14 @@ data_to_long <- function(data,
   }
 
   # evaluate arguments
-  cols <- .select_nse(select, data, exclude = NULL, ignore_case, verbose = FALSE)
+  cols <- .select_nse(
+    select,
+    data,
+    exclude = NULL,
+    ignore_case = ignore_case,
+    regex = regex,
+    verbose = FALSE
+  )
 
   # Sanity checks ----------------
 

R/demean.R

@@ -161,7 +161,7 @@
 #'     A description of how to translate the
 #'     formulas described in *Bell et al. 2018* into R using `lmer()`
 #'     from \pkg{lme4} can be found in
-#'     [this vignette](https://easystats.github.io/datawizard/articles/demean.html).
+#'     [this vignette](https://easystats.github.io/parameters/articles/demean.html).
 #'   }
 #'
 #' @references

R/weighted_mean_median_sd_mad.R

@@ -32,7 +32,6 @@ weighted_mean <- function(x, weights = NULL, verbose = TRUE, ...) {
 #' @export
 #' @rdname weighted_mean
 weighted_median <- function(x, weights = NULL, verbose = TRUE, ...) {
-
   if (!.are_weights(weights) || !.validate_weights(weights, verbose)) {
     return(stats::median(x, na.rm = TRUE))
   }
@@ -53,10 +52,11 @@ weighted_median <- function(x, weights = NULL, verbose = TRUE, ...) {
   rw <- cumsum(weights) / sum(weights)
   md.values <- min(which(rw >= p))
 
-  if (rw[md.values] == p)
+  if (rw[md.values] == p) {
     q <- mean(x[md.values:(md.values + 1)])
-  else
+  } else {
     q <- x[md.values]
+  }
 
   q
 }

_pkgdown.yml

@@ -26,8 +26,6 @@ template:
   bslib:
     primary: "#0054AD"
   opengraph:
-    image:
-      src: man/figures/card.png
     twitter:
       creator: "@easystats4u"
       card: summary_large_image

tests/testthat/_snaps/describe_distribution.md

@@ -3,16 +3,16 @@
     Code
       describe_distribution(factor(substring("statistics", 1:10, 1:10)))
     Output
-      Mean | SD | Min | Max | Skewness | Kurtosis |  n | n_Missing
-      ------------------------------------------------------------
-      NA   | NA |   a |   t |    -0.77 |    -0.13 | 10 |         0
+      Mean | SD |  Range | Skewness | Kurtosis |  n | n_Missing
+      ---------------------------------------------------------
+           |    | [a, t] |    -0.77 |    -0.13 | 10 |         0
 
 # describe_distribution - character
 
     Code
       describe_distribution(as.character(ToothGrowth$supp))
     Output
-      Mean | SD | Min | Max | Skewness | Kurtosis |  n | n_Missing
-      ------------------------------------------------------------
-      NA   | NA |  VC |  OJ |        0 |     -2.1 | 60 |         0
+      Mean | SD |    Range | Skewness | Kurtosis |  n | n_Missing
+      -----------------------------------------------------------
+           |    | [VC, OJ] |        0 |    -2.07 | 60 |         0
 

tests/testthat/test-data_reshape.R

@@ -146,17 +146,17 @@ test_that("data_reshape works as expected - complex dataset", {
 })
 
 
-test_that("data_reshape works as expected - simple dataset", {
-  d <- data.frame(
-    age = c(20, 30, 40),
-    sex = c("Female", "Male", "Male"),
-    score_t1 = c(30, 35, 32),
-    score_t2 = c(33, 34, 37),
-    speed_t1 = c(2, 3, 1),
-    speed_t2 = c(3, 4, 5),
-    stringsAsFactors = FALSE
-  )
+d <- data.frame(
+  age = c(20, 30, 40),
+  sex = c("Female", "Male", "Male"),
+  score_t1 = c(30, 35, 32),
+  score_t2 = c(33, 34, 37),
+  speed_t1 = c(2, 3, 1),
+  speed_t2 = c(3, 4, 5),
+  stringsAsFactors = FALSE
+)
 
+test_that("data_reshape works as expected - simple dataset", {
   out <- data_to_long(d, starts_with("score"))
   expect_equal(out$Name, c("score_t1", "score_t2", "score_t1", "score_t2", "score_t1", "score_t2"))
   expect_equal(out$Value, c(d$score_t1, d$score_t2)[c(1, 4, 2, 5, 3, 6)])
@@ -165,3 +165,13 @@ test_that("data_reshape works as expected - simple dataset", {
   expect_equal(out$NewCol, c("score_t2", "speed_t2", "score_t2", "speed_t2", "score_t2", "speed_t2"))
   expect_equal(out$Time, c(33, 3, 34, 4, 37, 5))
 })
+
+
+test_that("data_reshape works as expected - select-helper inside functions, using regex", {
+  test_fun <- function(data, i) {
+    data_to_long(data, select = i, regex = TRUE)
+  }
+  out <- test_fun(d, "^score")
+  expect_equal(out$Name, c("score_t1", "score_t2", "score_t1", "score_t2", "score_t1", "score_t2"))
+  expect_equal(out$Value, c(d$score_t1, d$score_t2)[c(1, 4, 2, 5, 3, 6)])
+})

tests/testthat/test-distributions.R

@@ -3,6 +3,7 @@ test_that("distributions", {
   skip_if_not_installed("bayestestR")
   skip_if_not_installed("parameters")
 
+  set.seed(123)
   x <- bayestestR::distribution_normal(100)
 
   expect_equal(kurtosis(x)$Kurtosis, -0.3204763, tolerance = 0.01)

tests/testthat/test-find_columns.R

@@ -62,7 +62,6 @@ test_that("find_columns works as expected", {
     find_columns(iris, "Width$", regex = TRUE),
     c("Sepal.Width", "Petal.Width")
   )
-
 })