Merge pull request #602 from ropensci/develop

Develop to master
ropensci · Jul 5, 2020 · db89820 · db89820
2 parents b8be860 + 18fa326
commit db89820
Show file tree

Hide file tree

Showing 20 changed files with 230 additions and 108 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: skimr
 Title: Compact and Flexible Summaries of Data
-Version: 2.1.1
+Version: 2.1.2
 Authors@R: 
     c(person(given = "Elin",
              family = "Waring",
@@ -83,8 +83,16 @@ Authors@R:
       person(given = "Daniel",
              family = "Possenriede",
              role = "ctb",
-             email = "possenriede@gmail.com"))
-Description: A simple to use summary function that can be used with pipes
+             email = "possenriede@gmail.com"),
+      person(given = "David",
+             family = "Zimmermann",
+             role = "ctb",
+             email = "david_j_zimmermann@hotmail.com"),
+      person(given = "Kyle", 
+             family = "Butts",
+             role ="ctb",
+             email = ""))
+Description: A simple to use summary function that can be used buttskyle96@gmail.comwith pipes
     and displays nicely in the console. The default summary statistics may
     be modified by the user as can the default formatting.  Support for
     data frames and vectors is included, and users can implement their own
@@ -117,6 +125,7 @@ Imports:
 Suggests:
     covr,
     extrafont,
+    lubridate,
     rmarkdown,
     sf,
     testthat (>= 2.0.0)
@@ -125,7 +134,7 @@ VignetteBuilder:
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.0.2
+RoxygenNote: 7.1.1
 Collate:
     'deprecated.R'
     'dplyr.R'

diff --git a/NAMESPACE b/NAMESPACE
@@ -3,6 +3,7 @@
 S3method(get_skimmers,AsIs)
 S3method(get_skimmers,Date)
 S3method(get_skimmers,POSIXct)
+S3method(get_skimmers,Timespan)
 S3method(get_skimmers,character)
 S3method(get_skimmers,complex)
 S3method(get_skimmers,default)

diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,14 @@
+# skimr 2.1.2
+
+### MINOR IMPROVEMENTS
+
+*   Add support for lubridate Timespan objects.
+*   Improvements to Supporting Additional Objects vignette.
+
+### BUG FIXES
+
+*   Update package to work with new version of `knitr`.
+
 # skimr 2.1.1 (2020-04-15)
 
 ### MINOR IMPROVEMENTS

diff --git a/R/get_skimmers.R b/R/get_skimmers.R
@@ -167,6 +167,13 @@ get_skimmers.difftime <- function(column) {
   modify_default_skimmers("Date", new_skim_type = "difftime")
 }
 
+#' @describeIn get_skimmers Summary functions for `Timespan` columns: [min()],
+#'   [max()], [median()] and [n_unique()].
+#' @export
+get_skimmers.Timespan <- function(column) {
+  modify_default_skimmers("difftime", new_skim_type = "Timespan")
+}
+
 #' @describeIn get_skimmers Summary functions for `ts` columns: [min()],
 #'   [max()], [median()] and [n_unique()].
 #' @export

diff --git a/R/stats.R b/R/stats.R
@@ -39,7 +39,7 @@ complete_rate <- function(x) {
 #'   values using s+ regex.
 #' @export
 n_whitespace <- function(x) {
-  whitespace <- grepl("^\\s+", x)
+  whitespace <- grepl("^\\s+$", x)
   sum(whitespace)
 }
 

diff --git a/codemeta.json b/codemeta.json
@@ -5,19 +5,18 @@
   ],
   "@type": "SoftwareSourceCode",
   "identifier": "skimr",
-  "description": "A simple to use summary function that can be used\n    with pipes and displays nicely in the console. The default summary\n    statistics may be modified by the user as can the default formatting.\n    Support for data frames and vectors is included, and users can\n    implement their own skim methods for specific object types as\n    described in a vignette. Default summaries include support for inline\n    spark graphs. Instructions for managing these on specific operating\n    systems are given in the \"Using skimr\" vignette and the README.",
+  "description": "A simple to use summary function that can be used buttskyle96@gmail.comwith pipes\n    and displays nicely in the console. The default summary statistics may\n    be modified by the user as can the default formatting.  Support for\n    data frames and vectors is included, and users can implement their own\n    skim methods for specific object types as described in a vignette.\n    Default summaries include support for inline spark graphs.\n    Instructions for managing these on specific operating systems are\n    given in the \"Using skimr\" vignette and the README.",
   "name": "skimr: Compact and Flexible Summaries of Data",
   "codeRepository": "https://github.com/ropensci/skimr",
   "issueTracker": "https://github.com/ropensci/skimr/issues",
   "license": "https://spdx.org/licenses/GPL-3.0",
-  "version": "2.1",
+  "version": "2.1.2",
   "programmingLanguage": {
     "@type": "ComputerLanguage",
     "name": "R",
-    "version": "3.6.1",
     "url": "https://r-project.org"
   },
-  "runtimePlatform": "R version 3.6.1 (2019-07-05)",
+  "runtimePlatform": "R version 4.0.1 (2020-06-06)",
   "provider": {
     "@id": "https://cran.r-project.org",
     "@type": "Organization",
@@ -145,6 +144,17 @@
       "givenName": "Daniel",
       "familyName": "Possenriede",
       "email": "possenriede@gmail.com"
+    },
+    {
+      "@type": "Person",
+      "givenName": "David",
+      "familyName": "Zimmermann",
+      "email": "david_j_zimmermann@hotmail.com"
+    },
+    {
+      "@type": "Person",
+      "givenName": "Kyle",
+      "familyName": "Butts"
     }
   ],
   "copyrightHolder": [
@@ -186,6 +196,18 @@
       },
       "sameAs": "https://CRAN.R-project.org/package=extrafont"
     },
+    {
+      "@type": "SoftwareApplication",
+      "identifier": "lubridate",
+      "name": "lubridate",
+      "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=lubridate"
+    },
     {
       "@type": "SoftwareApplication",
       "identifier": "rmarkdown",
@@ -415,15 +437,12 @@
   ],
   "releaseNotes": "https://github.com/ropensci/skimr/blob/master/NEWS.md",
   "readme": "https://github.com/ropensci/skimr/blob/master/README.md",
-  "fileSize": "1028.792KB",
-  "contIntegration": [
-    "https://travis-ci.org/ropenscilabs/skimr",
-    "https://codecov.io/gh/ropenscilabs/skimr"
-  ],
+  "fileSize": "364473.922KB",
+  "contIntegration": ["https://travis-ci.org/ropensci/skimr", "https://ci.appveyor.com/project/michaelquinn32/skimr", "https://codecov.io/gh/ropensci/skimr"],
   "review": {
     "@type": "Review",
-    "url": "https://github.com/ropensci/onboarding/issues/175",
-    "provider": "http://ropensci.org"
+    "url": "https://github.com/ropensci/software-review/issues/175",
+    "provider": "https://ropensci.org"
   },
   "keywords": [
     "unconf17",

diff --git a/man/get_skimmers.Rd b/man/get_skimmers.Rd
diff --git a/man/mutate.skim_df.Rd b/man/mutate.skim_df.Rd
diff --git a/man/print.Rd b/man/print.Rd
diff --git a/man/reexports.Rd b/man/reexports.Rd
diff --git a/man/sfl.Rd b/man/sfl.Rd
diff --git a/tests/testthat/print/knit_print-old_knitr.txt b/tests/testthat/print/knit_print-old_knitr.txt
@@ -0,0 +1,31 @@
+
+|                         |     |
+|:------------------------|:----|
+|Name                     |iris |
+|Number of rows           |150  |
+|Number of columns        |5    |
+|_______________________  |     |
+|Column type frequency:   |     |
+|factor                   |1    |
+|numeric                  |4    |
+|________________________ |     |
+|Group variables          |None |
+
+
+**Variable type: factor**
+
+|skim_variable | n_missing| complete_rate|ordered | n_unique|top_counts                |
+|:-------------|---------:|-------------:|:-------|--------:|:-------------------------|
+|Species       |         0|             1|FALSE   |        3|set: 50, ver: 50, vir: 50 |
+
+
+**Variable type: numeric**
+
+|skim_variable | n_missing| complete_rate| mean|   sd|  p0| p25|  p50| p75| p100|hist  |
+|:-------------|---------:|-------------:|----:|----:|---:|---:|----:|---:|----:|:-----|
+|Sepal.Length  |         0|             1| 5.84| 0.83| 4.3| 5.1| 5.80| 6.4|  7.9|▆▇▇▅▂ |
+|Sepal.Width   |         0|             1| 3.06| 0.44| 2.0| 2.8| 3.00| 3.3|  4.4|▁▆▇▂▁ |
+|Petal.Length  |         0|             1| 3.76| 1.77| 1.0| 1.6| 4.35| 5.1|  6.9|▇▁▆▇▂ |
+|Petal.Width   |         0|             1| 1.20| 0.76| 0.1| 0.3| 1.30| 1.8|  2.5|▇▁▇▅▃ |
+
+
diff --git a/tests/testthat/print/knit_print-summary-old_knitr.txt b/tests/testthat/print/knit_print-summary-old_knitr.txt
@@ -0,0 +1,12 @@
+
+|                         |     |
+|:------------------------|:----|
+|Name                     |iris |
+|Number of rows           |150  |
+|Number of columns        |5    |
+|_______________________  |     |
+|Column type frequency:   |     |
+|factor                   |1    |
+|numeric                  |4    |
+|________________________ |     |
+|Group variables          |None |
diff --git a/tests/testthat/print/knit_print-summary.txt b/tests/testthat/print/knit_print-summary.txt
@@ -1,3 +1,5 @@
+Table: Data summary
+
 |                         |     |
 |:------------------------|:----|
 |Name                     |iris |

diff --git a/tests/testthat/print/knit_print.txt b/tests/testthat/print/knit_print.txt
@@ -1,4 +1,6 @@
 
+Table: Data summary
+
 |                         |     |
 |:------------------------|:----|
 |Name                     |iris |

diff --git a/tests/testthat/test-get_skimmers.R b/tests/testthat/test-get_skimmers.R
@@ -17,7 +17,7 @@ test_that("get_default_skimmer_names() has a correct list of defaults", {
     names(defaults),
     c(
       "AsIs", "character", "complex", "Date", "difftime", "factor", "list",
-      "logical", "numeric", "POSIXct", "ts"
+      "logical", "numeric", "POSIXct", "Timespan", "ts"
     )
   )
   expect_identical(defaults$AsIs, c("n_unique", "min_length", "max_length"))
@@ -27,6 +27,7 @@ test_that("get_default_skimmer_names() has a correct list of defaults", {
   expect_identical(defaults$complex, c("mean"))
   expect_identical(defaults$Date, c("min", "max", "median", "n_unique"))
   expect_identical(defaults$difftime, c("min", "max", "median", "n_unique"))
+  expect_identical(defaults$Timespan, c("min", "max", "median", "n_unique"))
   expect_identical(defaults$factor, c("ordered", "n_unique", "top_counts"))
   expect_identical(defaults$list, c("n_unique", "min_length", "max_length"))
   expect_identical(defaults$logical, c("mean", "count"))

diff --git a/tests/testthat/test-skim.R b/tests/testthat/test-skim.R
@@ -629,6 +629,47 @@ test_that("skim returns expected response for difftime vectors", {
   expect_identical(input$difftime.n_unique, 9L)
 })
 
+test_that("skim returns expected response for lubridate Timespan vectors", {
+  dt <- tibble::tibble(x = lubridate::duration(1))
+  input <- skim(dt)
+
+  # dimensions
+  expect_n_rows(input, 1)
+  expect_n_columns(input, 8)
+
+  # classes
+  expect_is(input, "skim_df")
+  expect_is(input, "tbl_df")
+  expect_is(input, "tbl")
+  expect_is(input, "data.frame")
+  expect_named(input, c(
+    "skim_type", "skim_variable", "n_missing", "complete_rate",
+    "Timespan.min", "Timespan.max", "Timespan.median",
+    "Timespan.n_unique"
+  ))
+
+  # attributes
+  attrs <- attributes(input)
+  expect_equal(attrs$data_rows, 1)
+  expect_equal(attrs$data_cols, 1)
+  expect_equal(attrs$df_name, "`dt`")
+  expect_equal(
+    attrs$skimmers_used,
+    list(Timespan = c("min", "max", "median", "n_unique"))
+  )
+
+  # values
+  expect_identical(input$skim_variable, "x")
+  expect_identical(input$skim_type, "Timespan")
+  expect_identical(input$n_missing, 0L)
+  expect_equal(input$complete_rate, 1, tolerance = .001)
+  expect_identical(input$Timespan.min, 1)
+  expect_identical(input$Timespan.max, 1)
+  expect_identical(input$Timespan.median, lubridate::duration(1))
+  expect_identical(input$Timespan.n_unique, 1L)
+})
+
+
 test_that("skim handles objects with multiple classes", {
   dat <- seq(as.Date("2011-07-01"), by = 1, len = 10)
   dat[2] <- NA

diff --git a/tests/testthat/test-skim_print.R b/tests/testthat/test-skim_print.R
@@ -30,14 +30,23 @@ test_that("knit_print produces expected results", {
   input <- knit_print(skimmed)
   expect_is(input, "knit_asis")
   expect_length(input, 1)
-  expect_matches_file(input, "print/knit_print.txt")
+  if (packageVersion("knitr") <= "1.28") {
+    expect_matches_file(input, "print/knit_print-knitr_old.txt")
+  } else {
+    expect_matches_file(input, "print/knit_print.txt")
+  }
 })
 
 test_that("knit_print works with skim summaries", {
-  skimmed <- skim(iris)
-  summarized <- summary(skimmed)
-  input <- knitr::knit_print(summarized)
+
+    skimmed <- skim(iris)
+    summarized <- summary(skimmed)
+    input <- knitr::knit_print(summarized)
+    if (packageVersion("knitr") <= "1.28") {
+      expect_matches_file(input, "print/knit_print-summary-knitr_old.txt")
+    } else {
   expect_matches_file(input, "print/knit_print-summary.txt")
+  }
 })
 
 test_that("knit_print appropriately falls back to tibble printing", {