Develop to master

Develop to master

.travis.yml

@@ -6,6 +6,13 @@ warnings_are_errors: true
 env:
   global:
     - NOT_CRAN=false
+addons:
+  apt:
+    packages:
+      - libudunits2-dev
+      - gdal-bin
+      - libgdal1-dev
+      - libproj-dev
 before_install:
   - echo "options(repos = c(CRAN='http://cran.rstudio.com'))" > ~/.Rprofile
 r_github_packages:

DESCRIPTION

@@ -49,11 +49,12 @@ Imports:
     tidyr (>= 1.0),
     tidyselect (>= 0.2.5)
 Suggests:
+    covr,
     extrafont,
     rmarkdown,
+    sf,
     testthat (>= 2.0.0),
-    withr,
-    covr
+    withr
 License: GPL-3
 Encoding: UTF-8
 LazyData: true

R/skim_with.R

@@ -1,10 +1,7 @@
 #' Set or add the summary functions for a particular type of data
 #'
 #' While skim is designed around having an opinionated set of defaults, you
-#' can use these functions to change the summary statistics that it returns.
-#' To do that, provide type you wish to change as an argument to this function,
-#' along with a list of named functions that you want to use instead of the
-#' defaults.
+#' can use this function to change the summary statistics that it returns.
 #'
 #' `skim_with()` is a closure: a function that returns a new function. This
 #' lets you have several skimming functions in a single R session, but it
@@ -14,7 +11,11 @@
 #' You assign values within `skim_with` by using the [sfl()] helper (`skimr`
 #' function list). This helper behaves mostly like [dplyr::funs()], but lets
 #' you also identify which skimming functions you want to remove, by setting
-#' them to `NULL`.
+#' them to `NULL`. Assign an `sfl` to each column type that you wish to modify.
+#' Functions that summarize all data types, and always return the same type
+#' of value, can be assigned to the `base` argument. The default base skimmers
+#' compute the number of missing values `n_missing` and the rate of values being
+#' complete, i.e. not missing.
 #'
 #' When `append = TRUE` and local skimmers have names matching the names of
 #' entries in the default `skim_function_list`, the values in the default list
@@ -68,6 +69,7 @@ skim_with <- function(...,
   local_skimmers <- validate_assignment(...)
 
   function(data, ...) {
+    data_name <- rlang::expr_label(substitute(data))
     if (!is.data.frame(data)) {
       data <- as.data.frame(data)
     }
@@ -110,7 +112,7 @@ skim_with <- function(...,
       class = c("skim_df", "tbl_df", "tbl", "data.frame"),
       data_rows = nrow(data),
       data_cols = ncol(data),
-      df_name = rlang::expr_label(substitute(data)),
+      df_name = data_name,
       groups = dplyr::groups(data),
       base_skimmers = names(base$funs),
       skimmers_used = get_skimmers_used(unique_skimmers)
@@ -193,8 +195,12 @@ get_final_skimmers <- function(column, data, local_skimmers, append) {
 
   if (is.null(locals$funs)) {
     if (defaults$skim_type == "default") {
-      warning("Couldn't find skimmers for class: %s; No user-defined `sfl` ",
-        "provided. Falling back to `character`.",
+      msg <- sprintf(
+        "Couldn't find skimmers for class: %s;",
+        paste(all_classes, collapse = ", ")
+      )
+      warning(msg,
+        " No user-defined `sfl` provided. Falling back to `character`.",
         call. = FALSE
       )
       data[[column]] <- as.character(data[[column]])
@@ -284,47 +290,56 @@ mangle_names <- function(skimmers, base_names) {
 #' mangle the function names. That way, each set of relevant columns begin
 #' with the column name + `_` + our internal delimiter.
 #'
+#' @param mangled_skimmers The `sfl`'s whose function names have been mangled.
+#' @param variable_names The names of columns in the original data, matching a
+#'   data type, that will be summarized.
+#' @param data The original data.
 #' @keywords internal
 #' @noRd
-skim_by_type <- function(mangled, columns, data) {
+skim_by_type <- function(mangled_skimmers, variable_names, data) {
   UseMethod("skim_by_type", data)
 }
 
 #' @export
-skim_by_type.grouped_df <- function(mangled, columns, data) {
+skim_by_type.grouped_df <- function(mangled_skimmers, variable_names, data) {
   group_columns <- dplyr::groups(data)
   grouped <- dplyr::group_by(data, !!!group_columns)
-  skimmed <- dplyr::summarize_at(grouped, columns, mangled$funs)
-  build_results(skimmed, columns, group_columns)
+  skimmed <- dplyr::summarize_at(grouped, variable_names, mangled_skimmers$funs)
+  build_results(skimmed, variable_names, group_columns)
 }
 
 #' @export
-skim_by_type.data.frame <- function(mangled, columns, data) {
-  skimmed <- dplyr::summarize_at(data, columns, mangled$funs)
-  build_results(skimmed, columns, NULL)
+skim_by_type.data.frame <- function(mangled_skimmers, variable_names, data) {
+  skimmed <- dplyr::summarize_at(data, variable_names, mangled_skimmers$funs)
+  build_results(skimmed, variable_names, NULL)
 }
 
 #' Summarize returns a single row data frame, make it tall.
 #' @noRd
-build_results <- function(skimmed, data_cols, groups) {
-  if (length(data_cols) > 1) {
+build_results <- function(skimmed, variable_names, groups) {
+  if (length(variable_names) > 1) {
     out <- tibble::tibble(
-      skim_variable = data_cols,
-      by_variable = purrr::map(data_cols, reshape_skimmed, skimmed, groups)
+      skim_variable = variable_names,
+      by_variable = purrr::map(variable_names, reshape_skimmed, skimmed, groups)
     )
     tidyr::unnest(out, .data$by_variable)
   } else {
+    out <- dplyr::select(
+      as.data.frame(skimmed),
+      !!!groups,
+      tidyselect::contains(NAME_DELIMETER)
+    )
     tibble::tibble(
-      skim_variable = data_cols,
-      !!!set_clean_names(skimmed)
+      skim_variable = variable_names,
+      !!!set_clean_names(out)
     )
   }
 }
 
 reshape_skimmed <- function(column, skimmed, groups) {
   delim_name <- paste0(column, "_", NAME_DELIMETER)
   out <- dplyr::select(
-    skimmed,
+    as.data.frame(skimmed),
     !!!groups,
     tidyselect::starts_with(delim_name)
   )

R/summary.R

@@ -13,12 +13,12 @@ summary.skim_df <- function(object, ...) {
   if (is.null(object)) {
     stop("dataframe is null.")
   }
-  df_name <- df_name(object)
-  df_name <- ifelse(df_name %in% c("`.`", ".data"), "Piped data", df_name)
-  df_name <- gsub("`", "", df_name)
-  df_name <- ifelse(nchar(df_name) > 25,
-    paste0(substring(df_name, 1, 25), "..."),
-    df_name
+  data_name <- df_name(object)
+  data_name <- ifelse(data_name %in% c("`.`", ".data"), "Piped data", data_name)
+  data_name <- gsub("`", "", data_name)
+  data_name <- ifelse(nchar(data_name) > 25,
+    paste0(substring(data_name, 1, 25), "..."),
+    data_name
   )
 
   duplicated <- duplicated(object$skim_variable)
@@ -32,7 +32,7 @@ summary.skim_df <- function(object, ...) {
   )
 
   summary_object <- c(
-    df_name,
+    data_name,
     data_rows(object),
     data_cols(object),
     " ",

codemeta.json

@@ -162,6 +162,18 @@
     }
   ],
   "softwareSuggestions": [
+    {
+      "@type": "SoftwareApplication",
+      "identifier": "covr",
+      "name": "covr",
+      "provider": {
+        "@id": "https://cran.r-project.org",
+        "@type": "Organization",
+        "name": "Comprehensive R Archive Network (CRAN)",
+        "url": "https://cran.r-project.org"
+      },
+      "sameAs": "https://CRAN.R-project.org/package=covr"
+    },
     {
       "@type": "SoftwareApplication",
       "identifier": "extrafont",
@@ -188,40 +200,40 @@
     },
     {
       "@type": "SoftwareApplication",
-      "identifier": "testthat",
-      "name": "testthat",
-      "version": ">= 2.0.0",
+      "identifier": "sf",
+      "name": "sf",
       "provider": {
         "@id": "https://cran.r-project.org",
         "@type": "Organization",
         "name": "Comprehensive R Archive Network (CRAN)",
         "url": "https://cran.r-project.org"
       },
-      "sameAs": "https://CRAN.R-project.org/package=testthat"
+      "sameAs": "https://CRAN.R-project.org/package=sf"
     },
     {
       "@type": "SoftwareApplication",
-      "identifier": "withr",
-      "name": "withr",
+      "identifier": "testthat",
+      "name": "testthat",
+      "version": ">= 2.0.0",
       "provider": {
         "@id": "https://cran.r-project.org",
         "@type": "Organization",
         "name": "Comprehensive R Archive Network (CRAN)",
         "url": "https://cran.r-project.org"
       },
-      "sameAs": "https://CRAN.R-project.org/package=withr"
+      "sameAs": "https://CRAN.R-project.org/package=testthat"
     },
     {
       "@type": "SoftwareApplication",
-      "identifier": "covr",
-      "name": "covr",
+      "identifier": "withr",
+      "name": "withr",
       "provider": {
         "@id": "https://cran.r-project.org",
         "@type": "Organization",
         "name": "Comprehensive R Archive Network (CRAN)",
         "url": "https://cran.r-project.org"
       },
-      "sameAs": "https://CRAN.R-project.org/package=covr"
+      "sameAs": "https://CRAN.R-project.org/package=withr"
     }
   ],
   "softwareRequirements": [
@@ -391,7 +403,7 @@
   ],
   "releaseNotes": "https://github.com/ropensci/skimr/blob/master/NEWS.md",
   "readme": "https://github.com/ropensci/skimr/blob/master/README.md",
-  "fileSize": "4120.816KB",
+  "fileSize": "3788.726KB",
   "contIntegration": [
     "https://travis-ci.org/ropenscilabs/skimr",
     "https://codecov.io/gh/ropenscilabs/skimr"

tests/testthat/helper-expectations.R

@@ -30,14 +30,15 @@ expect_NA <- function(object) {
 
 expect_print_matches_file <- function(object,
                                       filename,
-                                      skip_on_windows = TRUE) {
+                                      skip_on_windows = TRUE,
+                                      width = 100) {
   if (skip_on_windows) testthat::skip_on_os("windows")
-  withr::with_options(list(crayon.enabled = FALSE), {
+  withr::with_options(list(crayon.enabled = FALSE, width = width), {
     testthat::expect_known_output(
       print(object),
       filename,
       update = FALSE,
-      width = 100
+      width = width
     )
   })
 }

tests/testthat/print/smaller.txt

@@ -10,13 +10,20 @@ Column type frequency:
 ________________________         
 Group variables            None  
 
-── Variable type: factor ───────────────────────────────────────────────────────────────────────────
-  skim_variable n_missing complete_rate ordered n_unique top_counts               
-1 Species               0             1 FALSE          3 set: 50, ver: 50, vir: 50
+── Variable type: factor ─────────────────────────
+  skim_variable n_missing complete_rate ordered
+1 Species               0             1 FALSE  
+  n_unique top_counts               
+1        3 set: 50, ver: 50, vir: 50
 
-── Variable type: numeric ──────────────────────────────────────────────────────────────────────────
-  skim_variable n_missing complete_rate  mean    sd    p0   p25   p50   p75  p100 hist 
-1 Sepal.Length          0             1  5.84 0.828   4.3   5.1  5.8    6.4   7.9 ▆▇▇▅▂
-2 Sepal.Width           0             1  3.06 0.436   2     2.8  3      3.3   4.4 ▁▆▇▂▁
-3 Petal.Length          0             1  3.76 1.77    1     1.6  4.35   5.1   6.9 ▇▁▆▇▂
-4 Petal.Width           0             1  1.20 0.762   0.1   0.3  1.3    1.8   2.5 ▇▁▇▅▃
+── Variable type: numeric ────────────────────────
+  skim_variable n_missing complete_rate  mean
+1 Sepal.Length          0             1  5.84
+2 Sepal.Width           0             1  3.06
+3 Petal.Length          0             1  3.76
+4 Petal.Width           0             1  1.20
+     sd    p0   p25   p50   p75  p100 hist 
+1 0.828   4.3   5.1  5.8    6.4   7.9 ▆▇▇▅▂
+2 0.436   2     2.8  3      3.3   4.4 ▁▆▇▂▁
+3 1.77    1     1.6  4.35   5.1   6.9 ▇▁▆▇▂
+4 0.762   0.1   0.3  1.3    1.8   2.5 ▇▁▇▅▃

tests/testthat/test-skim_print.R

@@ -86,10 +86,8 @@ test_that("Print focused objects appropriately", {
 })
 
 test_that("Metadata is stripped from smaller consoles", {
-  withr::with_options(list(width = 50), {
-    skimmed <- skim(iris)
-    expect_print_matches_file(skimmed, "print/smaller.txt")
-  })
+  skimmed <- skim(iris)
+  expect_print_matches_file(skimmed, "print/smaller.txt", width = 50)
 })
 
 test_that("Crayon is supported", {