From 48b87d10a742f0879158995d5bf8e124ea4e8c20 Mon Sep 17 00:00:00 2001 From: Rob Baker Date: Tue, 16 Jul 2024 08:27:53 -0600 Subject: [PATCH 01/11] add experimental function "document_missing_values" --- R/replace_blanks.R | 84 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) diff --git a/R/replace_blanks.R b/R/replace_blanks.R index 6b9a835..2395d7c 100644 --- a/R/replace_blanks.R +++ b/R/replace_blanks.R @@ -93,3 +93,87 @@ replace_blanks <- function(directory = here::here(), missing_val_code = NA) { } return(invisible()) } + + +#' Handles multiple missing values +#' +#' @description +#' lifecycle::badge("experimental") +#' Given a file name (.csv only) and path, the function will search the +#' columns for any that contain multiple user-specified missing value codes. +#' For any column with multiple missing value codes, all the missing values +#' (including blanks) will be replaced with NA. A new column will be generated +#' and, populated with the given missing value code from the origin column. +#' Values that were not missing will be populated with "not_missing". The +#' newly generate column of categorical variables can be used do describe +#' the various/multiple reasons for why data is absent in the original column. +#' +#' The function will then write the new dataframe to a file, overwriting the +#' original file. If it is important to keep a copy of the original file, make +#' a copy prior to running the function. +#' +#' @details blank cells will be treated as NA. +#' +#' @param file_name String. The name of the file to inspect +#' @param directory String. Location of file to read/write. Defaults to the current working directory. +#' @param colname lifecycle::badge("experimental") String. The columns to inspect. +#' @param missing_val_codes String the missing value code or codes to search for. +#' @param replace_value String. The value (singular) to replace multiple missing values with. Defaults to NA. +#' +#' @return writes a new dataframe to file. Return invisible. +#' @export +#' +#' @examples +#' \dontrun{ +#' # search all columns in "mydata.csv" for any columns that have multiple +#' # missing values (where multiple missing values include, "missing", "blank", +#' # "no data", NA, and a blank cell ("")). Replace those values with NA. Make +#' # a new column with the appropriate missing value codes listed as categorical +#' # variables. +#' document_missing_values(file_name = "mydata.csv", +#' directory = here::here(), +#' colname = NA, +#' missing_val_codes = "missing", "blank", "no data"), +#' replace_value = NA) +#' } +document_missing_values <- function(file_name, + directory = here::here(), + colname = NA, + missing_val_codes = NA, + replace_value = NA) { + + #read in a dataframe: + df <- readr::read_csv(paste0(directory, "/", file_name)) + #generate list of missing values + missing_val_codes <- append(missing_val_codes, NA) + missing_val_codes <- unique(missing_val_codes) + + data_names <- colnames(df) + + if (is.na(colname)) { + y <- ncol(df) + for (i in 1:y) { + #if here are multiple missing value codes in a column: + if (sum(df[[data_names[i]]] %in% missing_val_codes) > + sum(is.na(df[[data_names[i]]]))) { + #generate new column of data: + df$x <- with(df, + ifelse(df[[data_names[i]]] %in% missing_val_codes, + df[[data_names[i]]], "not_missing")) + #replace old missing values with replacement value + df[[data_names[i]]] = ifelse(df[[data_names[i]]] %in% + missing_val_codes, + replace_value, df[[data_names[i]]]) + #rename new column: + names(df)[names(df) == "x"] <- paste0("custom_", + data_names[i], + "_MissingValues") + } + } + } + #write the file back out: + readr::write_csv(df, paste0(directory, "/", file_name)) + + return(invisible) + +} From 5fee42cb0032f78e5d2c1d4722f8fa969e5722b8 Mon Sep 17 00:00:00 2001 From: Rob Baker Date: Tue, 16 Jul 2024 08:37:14 -0600 Subject: [PATCH 02/11] add dependency, lifecycle --- DESCRIPTION | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index 3afc557..cc5a67c 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -49,7 +49,6 @@ Imports: stringr, base, readr, - lifecycle, huxtable, crayon, data.table, @@ -61,7 +60,8 @@ Imports: sp, withr, cli, - purrr + purrr, + lifecycle RoxygenNote: 7.3.1 Suggests: knitr, From 60208489e478ded2528e827f4c070be411dd70a3 Mon Sep 17 00:00:00 2001 From: Rob Baker Date: Tue, 16 Jul 2024 08:37:36 -0600 Subject: [PATCH 03/11] add information about experimental function "document_missing_values()" --- NEWS.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/NEWS.md b/NEWS.md index c631921..cedb49b 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,5 +1,8 @@ # QCkit v0.1.8 (not yet released) +2024-07-16 +* Added experimental function `document_missing_values()`, which searches a file for multiple missing value codes, replaces them all with NA, and generates a new column with the missing value codes so that they can be properly documented in EML. This is a work-around for the fact that there is currently not a good way to get multiple missing value codes in a single column via EMLassemblyline. This function is still under development; expect substantial changes an improvements up to and including removing the function entirely. + 2024-07-09 * Added function `get_user_email()`, which accesses NPS active directory via a powershell function to return the user's email address. Probably won't work for non-NPS users and probably won't work for non-windows users. * Updated rest API from legacy v6 to current v7. From 8c73913ee48dc6c14cd1f4dfac0c6a8e15f4768f Mon Sep 17 00:00:00 2001 From: Rob Baker Date: Tue, 16 Jul 2024 08:38:08 -0600 Subject: [PATCH 04/11] add lifecycle badge "questioning" and fix example in 'document_missing_values()` --- R/replace_blanks.R | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/R/replace_blanks.R b/R/replace_blanks.R index 2395d7c..3163d5a 100644 --- a/R/replace_blanks.R +++ b/R/replace_blanks.R @@ -98,7 +98,8 @@ replace_blanks <- function(directory = here::here(), missing_val_code = NA) { #' Handles multiple missing values #' #' @description -#' lifecycle::badge("experimental") +#' `r lifecycle::badge("experimental")` +#' `r lifecycle::badge("questioning")` #' Given a file name (.csv only) and path, the function will search the #' columns for any that contain multiple user-specified missing value codes. #' For any column with multiple missing value codes, all the missing values @@ -125,15 +126,10 @@ replace_blanks <- function(directory = here::here(), missing_val_code = NA) { #' #' @examples #' \dontrun{ -#' # search all columns in "mydata.csv" for any columns that have multiple -#' # missing values (where multiple missing values include, "missing", "blank", -#' # "no data", NA, and a blank cell ("")). Replace those values with NA. Make -#' # a new column with the appropriate missing value codes listed as categorical -#' # variables. #' document_missing_values(file_name = "mydata.csv", #' directory = here::here(), #' colname = NA, -#' missing_val_codes = "missing", "blank", "no data"), +#' missing_val_codes = c("missing", "blank", "no data"), #' replace_value = NA) #' } document_missing_values <- function(file_name, From be21e3b312366724207f4f7638ff6c245a3b20a4 Mon Sep 17 00:00:00 2001 From: Rob Baker Date: Tue, 16 Jul 2024 08:38:56 -0600 Subject: [PATCH 05/11] autoupdate via usethis::lifecycle, devtools::document and pkgdown::build_site_github_pages --- NAMESPACE | 1 + docs/index.html | 2 +- docs/news/index.html | 1 + docs/pkgdown.yml | 2 +- docs/reference/document_missing_values.html | 172 ++++++++++++++++++ docs/reference/figures/lifecycle-archived.svg | 22 ++- docs/reference/figures/lifecycle-defunct.svg | 22 ++- .../figures/lifecycle-deprecated.svg | 22 ++- .../figures/lifecycle-experimental.svg | 22 ++- docs/reference/figures/lifecycle-maturing.svg | 22 ++- .../figures/lifecycle-questioning.svg | 22 ++- .../figures/lifecycle-soft-deprecated.svg | 21 +++ docs/reference/figures/lifecycle-stable.svg | 30 ++- .../figures/lifecycle-superseded.svg | 22 ++- docs/reference/index.html | 4 + docs/sitemap.xml | 3 + man/document_missing_values.Rd | 56 ++++++ man/figures/lifecycle-archived.svg | 22 ++- man/figures/lifecycle-defunct.svg | 22 ++- man/figures/lifecycle-deprecated.svg | 22 ++- man/figures/lifecycle-experimental.svg | 22 ++- man/figures/lifecycle-maturing.svg | 22 ++- man/figures/lifecycle-questioning.svg | 22 ++- man/figures/lifecycle-soft-deprecated.svg | 21 +++ man/figures/lifecycle-stable.svg | 30 ++- man/figures/lifecycle-superseded.svg | 22 ++- 26 files changed, 633 insertions(+), 18 deletions(-) create mode 100644 docs/reference/document_missing_values.html create mode 100644 docs/reference/figures/lifecycle-soft-deprecated.svg create mode 100644 man/document_missing_values.Rd create mode 100644 man/figures/lifecycle-soft-deprecated.svg diff --git a/NAMESPACE b/NAMESPACE index f63564d..07bc09a 100644 --- a/NAMESPACE +++ b/NAMESPACE @@ -7,6 +7,7 @@ export(convert_datetime_format) export(convert_long_to_utm) export(convert_utm_to_ll) export(create_datastore_script) +export(document_missing_values) export(fix_utc_offset) export(fuzz_location) export(generate_ll_from_utm) diff --git a/docs/index.html b/docs/index.html index 5fb3f58..2573281 100644 --- a/docs/index.html +++ b/docs/index.html @@ -123,7 +123,7 @@

Links

License

diff --git a/docs/news/index.html b/docs/news/index.html index fd274e8..9984134 100644 --- a/docs/news/index.html +++ b/docs/news/index.html @@ -65,6 +65,7 @@

Changelog

QCkit v0.1.8 (not yet released)

+

2024-07-16 * Added experimental function document_missing_values(), which searches a file for multiple missing value codes, replaces them all with NA, and generates a new column with the missing value codes so that they can be properly documented in EML. This is a work-around for the fact that there is currently not a good way to get multiple missing value codes in a single column via EMLassemblyline. This function is still under development; expect substantial changes an improvements up to and including removing the function entirely.

2024-07-09 * Added function get_user_email(), which accesses NPS active directory via a powershell function to return the user’s email address. Probably won’t work for non-NPS users and probably won’t work for non-windows users. * Updated rest API from legacy v6 to current v7.

2024-06-28 * Updated get_park_polygon() to use the new API (had been using a legacy API). Added documentation to specify that the function is getting the convexhull for the park, which may not work particularly well for some parks. 2024-06-27 * bug fixes for generate_ll_from_utm() * add function remove_empty_tables() (and associated unit tests) * update documentation for replace blanks() to indicate it can replace blanks with more than just NA

diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml index 6e19b1b..89ec3e5 100644 --- a/docs/pkgdown.yml +++ b/docs/pkgdown.yml @@ -5,5 +5,5 @@ articles: DRR_Purpose_and_Scope: DRR_Purpose_and_Scope.html Starting-a-DRR: Starting-a-DRR.html Using-the-DRR-Template: Using-the-DRR-Template.html -last_built: 2024-07-09T14:49Z +last_built: 2024-07-16T14:36Z diff --git a/docs/reference/document_missing_values.html b/docs/reference/document_missing_values.html new file mode 100644 index 0000000..ddb9435 --- /dev/null +++ b/docs/reference/document_missing_values.html @@ -0,0 +1,172 @@ + +Handles multiple missing values — document_missing_values • QCkit + + +
+
+ + + +
+
+
+

Handles multiple missing values

+ Source: R/replace_blanks.R + +
+ +
+

[Experimental] +[Questioning] +Given a file name (.csv only) and path, the function will search the +columns for any that contain multiple user-specified missing value codes. +For any column with multiple missing value codes, all the missing values +(including blanks) will be replaced with NA. A new column will be generated +and, populated with the given missing value code from the origin column. +Values that were not missing will be populated with "not_missing". The +newly generate column of categorical variables can be used do describe +the various/multiple reasons for why data is absent in the original column.

+

The function will then write the new dataframe to a file, overwriting the +original file. If it is important to keep a copy of the original file, make +a copy prior to running the function.

+
+ +
+ 
document_missing_values(
+  file_name,
+  directory = here::here(),
+  colname = NA,
+  missing_val_codes = NA,
+  replace_value = NA
+)
+
+ +
+

Arguments

+
file_name
+

String. The name of the file to inspect

+ + +
directory
+

String. Location of file to read/write. Defaults to the current working directory.

+ + +
colname
+

lifecycle::badge("experimental") String. The columns to inspect.

+ + +
missing_val_codes
+

String the missing value code or codes to search for.

+ + +
replace_value
+

String. The value (singular) to replace multiple missing values with. Defaults to NA.

+ +
+
+

Value

+ + +

writes a new dataframe to file. Return invisible.

+
+
+

Details

+

blank cells will be treated as NA.

+
+ +
+

Examples

+ 
if (FALSE) {
+document_missing_values(file_name = "mydata.csv",
+                        directory = here::here(),
+                        colname = NA,
+                        missing_val_codes = c("missing", "blank", "no data"),
+                        replace_value = NA)
+                        }
+
+
+
+ +
+ + +
+

Developed by Robert Baker, Judd Patterson, Joe DeVivo, Issac Quevedo, Sarah Wright.

+
+ +
+

Site built with pkgdown 2.0.9.

+
+ +
+ + + + + + + + diff --git a/docs/reference/figures/lifecycle-archived.svg b/docs/reference/figures/lifecycle-archived.svg index 48f72a6..745ab0c 100644 --- a/docs/reference/figures/lifecycle-archived.svg +++ b/docs/reference/figures/lifecycle-archived.svg @@ -1 +1,21 @@ - lifecyclelifecyclearchivedarchived \ No newline at end of file + + lifecycle: archived + + + + + + + + + + + + + + + lifecycle + + archived + + diff --git a/docs/reference/figures/lifecycle-defunct.svg b/docs/reference/figures/lifecycle-defunct.svg index 01452e5..d5c9559 100644 --- a/docs/reference/figures/lifecycle-defunct.svg +++ b/docs/reference/figures/lifecycle-defunct.svg @@ -1 +1,21 @@ -lifecyclelifecycledefunctdefunct \ No newline at end of file + + lifecycle: defunct + + + + + + + + + + + + + + + lifecycle + + defunct + + diff --git a/docs/reference/figures/lifecycle-deprecated.svg b/docs/reference/figures/lifecycle-deprecated.svg index 4baaee0..b61c57c 100644 --- a/docs/reference/figures/lifecycle-deprecated.svg +++ b/docs/reference/figures/lifecycle-deprecated.svg @@ -1 +1,21 @@ -lifecyclelifecycledeprecateddeprecated \ No newline at end of file + + lifecycle: deprecated + + + + + + + + + + + + + + + lifecycle + + deprecated + + diff --git a/docs/reference/figures/lifecycle-experimental.svg b/docs/reference/figures/lifecycle-experimental.svg index d1d060e..5d88fc2 100644 --- a/docs/reference/figures/lifecycle-experimental.svg +++ b/docs/reference/figures/lifecycle-experimental.svg @@ -1 +1,21 @@ -lifecyclelifecycleexperimentalexperimental \ No newline at end of file + + lifecycle: experimental + + + + + + + + + + + + + + + lifecycle + + experimental + + diff --git a/docs/reference/figures/lifecycle-maturing.svg b/docs/reference/figures/lifecycle-maturing.svg index df71310..897370e 100644 --- a/docs/reference/figures/lifecycle-maturing.svg +++ b/docs/reference/figures/lifecycle-maturing.svg @@ -1 +1,21 @@ -lifecyclelifecyclematuringmaturing \ No newline at end of file + + lifecycle: maturing + + + + + + + + + + + + + + + lifecycle + + maturing + + diff --git a/docs/reference/figures/lifecycle-questioning.svg b/docs/reference/figures/lifecycle-questioning.svg index 08ee0c9..7c1721d 100644 --- a/docs/reference/figures/lifecycle-questioning.svg +++ b/docs/reference/figures/lifecycle-questioning.svg @@ -1 +1,21 @@ -lifecyclelifecyclequestioningquestioning \ No newline at end of file + + lifecycle: questioning + + + + + + + + + + + + + + + lifecycle + + questioning + + diff --git a/docs/reference/figures/lifecycle-soft-deprecated.svg b/docs/reference/figures/lifecycle-soft-deprecated.svg new file mode 100644 index 0000000..9c166ff --- /dev/null +++ b/docs/reference/figures/lifecycle-soft-deprecated.svg @@ -0,0 +1,21 @@ + + lifecycle: soft-deprecated + + + + + + + + + + + + + + + lifecycle + + soft-deprecated + + diff --git a/docs/reference/figures/lifecycle-stable.svg b/docs/reference/figures/lifecycle-stable.svg index e015dc8..9bf21e7 100644 --- a/docs/reference/figures/lifecycle-stable.svg +++ b/docs/reference/figures/lifecycle-stable.svg @@ -1 +1,29 @@ -lifecyclelifecyclestablestable \ No newline at end of file + + lifecycle: stable + + + + + + + + + + + + + + + + lifecycle + + + + stable + + + diff --git a/docs/reference/figures/lifecycle-superseded.svg b/docs/reference/figures/lifecycle-superseded.svg index 75f24f5..db8d757 100644 --- a/docs/reference/figures/lifecycle-superseded.svg +++ b/docs/reference/figures/lifecycle-superseded.svg @@ -1 +1,21 @@ - lifecyclelifecyclesupersededsuperseded \ No newline at end of file + + lifecycle: superseded + + + + + + + + + + + + + + + lifecycle + + superseded + + diff --git a/docs/reference/index.html b/docs/reference/index.html index 268af56..b7d29f1 100644 --- a/docs/reference/index.html +++ b/docs/reference/index.html @@ -90,6 +90,10 @@

All functions create_datastore_script()

Turn a GitHub release into a DataStore Script Reference

+ +

document_missing_values()

+ +

Handles multiple missing values

.get_unit_boundary()

diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 31e79b0..ec11d5b 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -51,6 +51,9 @@ /reference/DC_col_check.html + + /reference/document_missing_values.html + /reference/dot-get_unit_boundary.html diff --git a/man/document_missing_values.Rd b/man/document_missing_values.Rd new file mode 100644 index 0000000..f3d7c72 --- /dev/null +++ b/man/document_missing_values.Rd @@ -0,0 +1,56 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/replace_blanks.R +\name{document_missing_values} +\alias{document_missing_values} +\title{Handles multiple missing values} +\usage{ +document_missing_values( + file_name, + directory = here::here(), + colname = NA, + missing_val_codes = NA, + replace_value = NA +) +} +\arguments{ +\item{file_name}{String. The name of the file to inspect} + +\item{directory}{String. Location of file to read/write. Defaults to the current working directory.} + +\item{colname}{lifecycle::badge("experimental") String. The columns to inspect.} + +\item{missing_val_codes}{String the missing value code or codes to search for.} + +\item{replace_value}{String. The value (singular) to replace multiple missing values with. Defaults to NA.} +} +\value{ +writes a new dataframe to file. Return invisible. +} +\description{ +\ifelse{html}{\href{https://lifecycle.r-lib.org/articles/stages.html#experimental}{\figure{lifecycle-experimental.svg}{options: alt='[Experimental]'}}}{\strong{[Experimental]}} +\ifelse{html}{\href{https://lifecycle.r-lib.org/articles/stages.html#questioning}{\figure{lifecycle-questioning.svg}{options: alt='[Questioning]'}}}{\strong{[Questioning]}} +Given a file name (.csv only) and path, the function will search the +columns for any that contain multiple user-specified missing value codes. +For any column with multiple missing value codes, all the missing values +(including blanks) will be replaced with NA. A new column will be generated +and, populated with the given missing value code from the origin column. +Values that were not missing will be populated with "not_missing". The +newly generate column of categorical variables can be used do describe +the various/multiple reasons for why data is absent in the original column. + +The function will then write the new dataframe to a file, overwriting the +original file. If it is important to keep a copy of the original file, make +a copy prior to running the function. +} +\details{ +blank cells will be treated as NA. +} +\examples{ +\dontrun{ +document_missing_values(file_name = "mydata.csv", + directory = here::here(), + colname = NA, + missing_val_codes = c("missing", "blank", "no data"), + replace_value = NA) + } +} diff --git a/man/figures/lifecycle-archived.svg b/man/figures/lifecycle-archived.svg index 48f72a6..745ab0c 100644 --- a/man/figures/lifecycle-archived.svg +++ b/man/figures/lifecycle-archived.svg @@ -1 +1,21 @@ - lifecyclelifecyclearchivedarchived \ No newline at end of file + + lifecycle: archived + + + + + + + + + + + + + + + lifecycle + + archived + + diff --git a/man/figures/lifecycle-defunct.svg b/man/figures/lifecycle-defunct.svg index 01452e5..d5c9559 100644 --- a/man/figures/lifecycle-defunct.svg +++ b/man/figures/lifecycle-defunct.svg @@ -1 +1,21 @@ -lifecyclelifecycledefunctdefunct \ No newline at end of file + + lifecycle: defunct + + + + + + + + + + + + + + + lifecycle + + defunct + + diff --git a/man/figures/lifecycle-deprecated.svg b/man/figures/lifecycle-deprecated.svg index 4baaee0..b61c57c 100644 --- a/man/figures/lifecycle-deprecated.svg +++ b/man/figures/lifecycle-deprecated.svg @@ -1 +1,21 @@ -lifecyclelifecycledeprecateddeprecated \ No newline at end of file + + lifecycle: deprecated + + + + + + + + + + + + + + + lifecycle + + deprecated + + diff --git a/man/figures/lifecycle-experimental.svg b/man/figures/lifecycle-experimental.svg index d1d060e..5d88fc2 100644 --- a/man/figures/lifecycle-experimental.svg +++ b/man/figures/lifecycle-experimental.svg @@ -1 +1,21 @@ -lifecyclelifecycleexperimentalexperimental \ No newline at end of file + + lifecycle: experimental + + + + + + + + + + + + + + + lifecycle + + experimental + + diff --git a/man/figures/lifecycle-maturing.svg b/man/figures/lifecycle-maturing.svg index df71310..897370e 100644 --- a/man/figures/lifecycle-maturing.svg +++ b/man/figures/lifecycle-maturing.svg @@ -1 +1,21 @@ -lifecyclelifecyclematuringmaturing \ No newline at end of file + + lifecycle: maturing + + + + + + + + + + + + + + + lifecycle + + maturing + + diff --git a/man/figures/lifecycle-questioning.svg b/man/figures/lifecycle-questioning.svg index 08ee0c9..7c1721d 100644 --- a/man/figures/lifecycle-questioning.svg +++ b/man/figures/lifecycle-questioning.svg @@ -1 +1,21 @@ -lifecyclelifecyclequestioningquestioning \ No newline at end of file + + lifecycle: questioning + + + + + + + + + + + + + + + lifecycle + + questioning + + diff --git a/man/figures/lifecycle-soft-deprecated.svg b/man/figures/lifecycle-soft-deprecated.svg new file mode 100644 index 0000000..9c166ff --- /dev/null +++ b/man/figures/lifecycle-soft-deprecated.svg @@ -0,0 +1,21 @@ + + lifecycle: soft-deprecated + + + + + + + + + + + + + + + lifecycle + + soft-deprecated + + diff --git a/man/figures/lifecycle-stable.svg b/man/figures/lifecycle-stable.svg index e015dc8..9bf21e7 100644 --- a/man/figures/lifecycle-stable.svg +++ b/man/figures/lifecycle-stable.svg @@ -1 +1,29 @@ -lifecyclelifecyclestablestable \ No newline at end of file + + lifecycle: stable + + + + + + + + + + + + + + + + lifecycle + + + + stable + + + diff --git a/man/figures/lifecycle-superseded.svg b/man/figures/lifecycle-superseded.svg index 75f24f5..db8d757 100644 --- a/man/figures/lifecycle-superseded.svg +++ b/man/figures/lifecycle-superseded.svg @@ -1 +1,21 @@ - lifecyclelifecyclesupersededsuperseded \ No newline at end of file + + lifecycle: superseded + + + + + + + + + + + + + + + lifecycle + + superseded + + From f1d96f2d72f734708ec4600c5430927a205bd7b2 Mon Sep 17 00:00:00 2001 From: Rob Baker Date: Tue, 16 Jul 2024 08:42:47 -0600 Subject: [PATCH 06/11] update document_missing_values documentation --- R/replace_blanks.R | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/R/replace_blanks.R b/R/replace_blanks.R index 3163d5a..048b785 100644 --- a/R/replace_blanks.R +++ b/R/replace_blanks.R @@ -113,12 +113,12 @@ replace_blanks <- function(directory = here::here(), missing_val_code = NA) { #' original file. If it is important to keep a copy of the original file, make #' a copy prior to running the function. #' -#' @details blank cells will be treated as NA. +#' @details Blank cells will be treated as NA. #' #' @param file_name String. The name of the file to inspect #' @param directory String. Location of file to read/write. Defaults to the current working directory. -#' @param colname lifecycle::badge("experimental") String. The columns to inspect. -#' @param missing_val_codes String the missing value code or codes to search for. +#' @param colname `r lifecycle::badge("experimental")` String. The columns to inspect. CURRENTLY ONLY WORKS AS SET TO DEFAULT "NA". +#' @param missing_val_codes List. A list of strings containing the missing value code or codes to search for. #' @param replace_value String. The value (singular) to replace multiple missing values with. Defaults to NA. #' #' @return writes a new dataframe to file. Return invisible. @@ -128,7 +128,7 @@ replace_blanks <- function(directory = here::here(), missing_val_code = NA) { #' \dontrun{ #' document_missing_values(file_name = "mydata.csv", #' directory = here::here(), -#' colname = NA, +#' colname = NA, #do not change during function development #' missing_val_codes = c("missing", "blank", "no data"), #' replace_value = NA) #' } From 935e6a2804b3f03b5a8b21ecbb1cab15b53cfc4d Mon Sep 17 00:00:00 2001 From: Rob Baker Date: Tue, 16 Jul 2024 08:43:01 -0600 Subject: [PATCH 07/11] updated via devtools::document and pkgdown --- docs/pkgdown.yml | 2 +- docs/reference/document_missing_values.html | 6 +++--- man/document_missing_values.Rd | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml index 89ec3e5..a974cc7 100644 --- a/docs/pkgdown.yml +++ b/docs/pkgdown.yml @@ -5,5 +5,5 @@ articles: DRR_Purpose_and_Scope: DRR_Purpose_and_Scope.html Starting-a-DRR: Starting-a-DRR.html Using-the-DRR-Template: Using-the-DRR-Template.html -last_built: 2024-07-16T14:36Z +last_built: 2024-07-16T14:41Z diff --git a/docs/reference/document_missing_values.html b/docs/reference/document_missing_values.html index ddb9435..0739530 100644 --- a/docs/reference/document_missing_values.html +++ b/docs/reference/document_missing_values.html @@ -113,11 +113,11 @@

Arguments

colname
-

lifecycle::badge("experimental") String. The columns to inspect.

+

[Experimental] String. The columns to inspect. CURRENTLY ONLY WORKS AS SET TO DEFAULT "NA".

missing_val_codes
-

String the missing value code or codes to search for.

+

List. A list of strings containing the missing value code or codes to search for.

replace_value
@@ -140,7 +140,7 @@

Examples

if (FALSE) {
 document_missing_values(file_name = "mydata.csv",
                         directory = here::here(),
-                        colname = NA,
+                        colname = NA, #do not change during function development
                         missing_val_codes = c("missing", "blank", "no data"),
                         replace_value = NA)
                         }
diff --git a/man/document_missing_values.Rd b/man/document_missing_values.Rd
index f3d7c72..4d2b616 100644
--- a/man/document_missing_values.Rd
+++ b/man/document_missing_values.Rd
@@ -17,9 +17,9 @@ document_missing_values(
 
 \item{directory}{String. Location of file to read/write. Defaults to the current working directory.}
 
-\item{colname}{lifecycle::badge("experimental") String. The columns to inspect.}
+\item{colname}{\ifelse{html}{\href{https://lifecycle.r-lib.org/articles/stages.html#experimental}{\figure{lifecycle-experimental.svg}{options: alt='[Experimental]'}}}{\strong{[Experimental]}} String. The columns to inspect. CURRENTLY ONLY WORKS AS SET TO DEFAULT "NA".}
 
-\item{missing_val_codes}{String the missing value code or codes to search for.}
+\item{missing_val_codes}{List. A list of strings containing the missing value code or codes to search for.}
 
 \item{replace_value}{String. The value (singular) to replace multiple missing values with. Defaults to NA.}
 }
@@ -49,7 +49,7 @@ blank cells will be treated as NA.
 \dontrun{
 document_missing_values(file_name = "mydata.csv",
                         directory = here::here(),
-                        colname = NA,
+                        colname = NA, #do not change during function development
                         missing_val_codes = c("missing", "blank", "no data"),
                         replace_value = NA)
                         }

From 4d26b5ec0a75cf49442a5625703b99067b555570 Mon Sep 17 00:00:00 2001
From: Rob Baker 
Date: Tue, 16 Jul 2024 08:47:48 -0600
Subject: [PATCH 08/11] Update document_missing_values documentation

---
 man/document_missing_values.Rd | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/man/document_missing_values.Rd b/man/document_missing_values.Rd
index 4d2b616..ef1909f 100644
--- a/man/document_missing_values.Rd
+++ b/man/document_missing_values.Rd
@@ -43,7 +43,7 @@ original file. If it is important to keep a copy of the original file, make
 a copy prior to running the function.
 }
 \details{
-blank cells will be treated as NA.
+Blank cells will be treated as NA.
 }
 \examples{
 \dontrun{

From f1b0c77ea7dd9316ca95de1921284ba7025dad0a Mon Sep 17 00:00:00 2001
From: Rob Baker 
Date: Tue, 16 Jul 2024 08:54:27 -0600
Subject: [PATCH 09/11] in document_missing_values, set read_csv to
 show_col_types = FALSE to suppress messages to console.

---
 R/replace_blanks.R | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/R/replace_blanks.R b/R/replace_blanks.R
index 048b785..bdd805f 100644
--- a/R/replace_blanks.R
+++ b/R/replace_blanks.R
@@ -139,7 +139,8 @@ document_missing_values <- function(file_name,
                                              replace_value = NA) {
 
   #read in a dataframe:
-  df <- readr::read_csv(paste0(directory, "/", file_name))
+  df <- readr::read_csv(paste0(directory, "/", file_name),
+                        show_col_types = FALSE)
   #generate list of missing values
   missing_val_codes <- append(missing_val_codes, NA)
   missing_val_codes <- unique(missing_val_codes)

From 247b7c8426825681ed6a81289893b137f9c4b751 Mon Sep 17 00:00:00 2001
From: Rob Baker 
Date: Tue, 16 Jul 2024 09:00:13 -0600
Subject: [PATCH 10/11] Add warning about replacing blanks with NA to
 documentation.

---
 R/replace_blanks.R | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/R/replace_blanks.R b/R/replace_blanks.R
index bdd805f..43f9bc6 100644
--- a/R/replace_blanks.R
+++ b/R/replace_blanks.R
@@ -113,6 +113,8 @@ replace_blanks <- function(directory = here::here(), missing_val_code = NA) {
 #' original file. If it is important to keep a copy of the original file, make
 #' a copy prior to running the function.
 #'
+#' WARNING: this function will replace any blank cells in your data with NA!
+#'
 #' @details Blank cells will be treated as NA.
 #'
 #' @param file_name String. The name of the file to inspect

From 69bc74f4ba260dee95e19e3671ef1416f5a9bfc3 Mon Sep 17 00:00:00 2001
From: Rob Baker 
Date: Tue, 16 Jul 2024 09:02:40 -0600
Subject: [PATCH 11/11] auto update via devtools::document and pkgdown

---
 docs/pkgdown.yml                            | 2 +-
 docs/reference/document_missing_values.html | 6 ++++--
 man/document_missing_values.Rd              | 2 ++
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml
index a974cc7..e07e1b3 100644
--- a/docs/pkgdown.yml
+++ b/docs/pkgdown.yml
@@ -5,5 +5,5 @@ articles:
   DRR_Purpose_and_Scope: DRR_Purpose_and_Scope.html
   Starting-a-DRR: Starting-a-DRR.html
   Using-the-DRR-Template: Using-the-DRR-Template.html
-last_built: 2024-07-16T14:41Z
+last_built: 2024-07-16T15:01Z
 
diff --git a/docs/reference/document_missing_values.html b/docs/reference/document_missing_values.html
index 0739530..c86f3d0 100644
--- a/docs/reference/document_missing_values.html
+++ b/docs/reference/document_missing_values.html
@@ -11,7 +11,8 @@
 the various/multiple reasons for why data is absent in the original column.
 The function will then write the new dataframe to a file, overwriting the
 original file. If it is important to keep a copy of the original file, make
-a copy prior to running the function.'>
@@ -90,6 +91,7 @@ 
Handles multiple missing values

 
The function will then write the new dataframe to a file, overwriting the
 original file. If it is important to keep a copy of the original file, make
 a copy prior to running the function.

+
WARNING: this function will replace any blank cells in your data with NA!
@@ -132,7 +134,7 @@

Value

Details

-

blank cells will be treated as NA.

+

Blank cells will be treated as NA.

diff --git a/man/document_missing_values.Rd b/man/document_missing_values.Rd index ef1909f..62aa6c2 100644 --- a/man/document_missing_values.Rd +++ b/man/document_missing_values.Rd @@ -41,6 +41,8 @@ the various/multiple reasons for why data is absent in the original column. The function will then write the new dataframe to a file, overwriting the original file. If it is important to keep a copy of the original file, make a copy prior to running the function. + +WARNING: this function will replace any blank cells in your data with NA! } \details{ Blank cells will be treated as NA.