update documentation, enable scheduled daily GitHub checks, remove deprecated adjust_cansim_values_by_variable function.

Author: mountainMath

.github/workflows/R-CMD-check.yaml

@@ -13,6 +13,8 @@ on:
     branches:
       - main
       - master
+  schedule:
+    - cron: "15 15 * * *"
 
 name: R-CMD-check
 

CRAN-RELEASE

@@ -1,2 +1,2 @@
-This package was submitted to CRAN on 2021-05-08.
-Once it is accepted, delete this file and tag the release (commit 7ff77e4).
+This package was submitted to CRAN on 2021-05-24.
+Once it is accepted, delete this file and tag the release (commit 3467275).

NAMESPACE

@@ -1,7 +1,6 @@
 # Generated by roxygen2: do not edit by hand
 
 export(add_provincial_abbreviations)
-export(adjust_cansim_values_by_variable)
 export(cansim_old_to_new)
 export(categories_for_level)
 export(collect_and_normalize)

NEWS.md

@@ -1,8 +1,9 @@
 # cansim 0.3.8
 ## Minor changes
-* Exclude vignette from CRAN checks
+* Exclude vignette from automatic CRAN checks to fix problem of CRAN checks failing when StatCan servers are down and lead to the package being removed from CRAN (checks are still active in local environment and when using GitHub action checks)
 * add release date info to cube metadata and cube list calls
 * add auto-refresh option for sqlite tables
+* remove deprecated `adjust_cansim_values_by_variable` function
 
 # cansim 0.3.7
 ## Minor changes

R/cansim.R

@@ -11,7 +11,7 @@
 #' @param timeout (Optional) Timeout in seconds for downloading cansim table to work around scenarios where StatCan servers drop the network connection.
 #  Set to higher values for large tables and slow network connection. (Default is \code{200}).
 #'
-#' @return tibble format data table output
+#' @return A tibble with the StatCan table data
 #'
 #' @examples
 #' \donttest{
@@ -27,17 +27,6 @@ get_cansim_ndm <- function(cansimTableNumber, language="english", refresh=FALSE,
 }
 
 
-#' (Deprecated) Adjust values in a retrieved Statistics Canada data table using a scaling variable
-#'
-#' (Deprecated) Adjust retrieved data table values by a scaled amount; however French does not work, probably due to encoding issues. This function is now deprecated and should not be used.
-#'
-#' @param data A downloaded CANSIM data table
-#' @param var A now deprecated input
-#'
-#' @export
-adjust_cansim_values_by_variable <-function(data, var){
-  normalize_cansim_values(data)
-}
 
 #' Normalize retrieved data table values to appropriate scales
 #'
@@ -206,7 +195,7 @@ normalize_cansim_values <- function(data, replacement_value=NA, normalize_percen
 #'
 #' @param oldCansimTableNumber deprecated style CANSIM table number (e.g. "427-0001")
 #'
-#' @return new-format NDM table number
+#' @return A character string with the new-format NDM table number
 #'
 #' @examples
 #' \donttest{
@@ -240,6 +229,7 @@ cansim_old_to_new <- function(oldCansimTableNumber){
 #' Parse metadata
 #' @param meta the raw metadata table
 #' @param data_path base path to save parsed metadata
+#'
 #' @return NULL
 #' @keywords internal
 parse_metadata <- function(meta,data_path){
@@ -333,10 +323,11 @@ parse_metadata <- function(meta,data_path){
 }
 
 #' Fold in metadata and for selected columns
-#' @param data the data table
+#' @param data A tibble with StatCan table data as e.g. returned by \code{get_cansim}.
 #' @param data_path base path to save parsed metadata
 #' @param column_names the names of the columns
-#' @return data table including the metadata information
+#'
+#' @return A tibble including the metadata information
 #' @keywords internal
 fold_in_metadata_for_columns <- function(data,data_path,column_names){
   cleaned_language <- basename(data_path) %>% gsub("^.+-|\\..+$","",.)
@@ -415,11 +406,12 @@ fold_in_metadata_for_columns <- function(data,data_path,column_names){
 #' @keywords data
 NULL
 
-#' Parse metadata and fold into data table (deprecated)
+#' Parse metadata and fold into tibble (deprecated)
 #' @param data the data table
 #' @param meta the raw metadata table
 #' @param data_path base path to save parsed metadata
-#' @return data table including the metadata information
+#'
+#' @return A tibble including the metadata information
 #' @keywords internal
 parse_and_fold_in_metadata <- function(data,meta,data_path){
   cleaned_language <- ifelse("VALEUR" %in% names(data),"fra","eng")
@@ -555,8 +547,8 @@ parse_and_fold_in_metadata <- function(data,meta,data_path){
 #' @param default_day The default day of the month that should be used when creating Date objects for monthly data (default set to "01")
 #  Set to higher values for large tables and slow network connection. (Default is \code{200}).
 #'
-#' @return tibble format data table output with added Date column with inferred date objects and
-#' a "val_norm" column with normalized VALUE using the supplied scale factor
+#' @return A tibble with StatCan Table data and added \code{Date} column with inferred date objects and
+#' added \code{val_norm} column with normalized value from the \code{VALUE} column.
 #'
 #' @examples
 #' \donttest{
@@ -639,6 +631,8 @@ get_cansim <- function(cansimTableNumber, language="english", refresh=FALSE, tim
 #' @param timeout (Optional) Timeout in seconds for downloading cansim table to work around scenarios where StatCan servers drop the network connection.
 #  Set to higher values for large tables and slow network connection. (Default is \code{200}).
 #'
+#' @return A tibble with the table overview information
+#'
 #' @examples
 #' \donttest{
 #' get_cansim_table_info("34-10-0013")
@@ -663,6 +657,8 @@ get_cansim_table_info <- function(cansimTableNumber, language="english", refresh
 #' @param timeout (Optional) Timeout in seconds for downloading cansim table to work around scenarios where StatCan servers drop the network connection.
 #  Set to higher values for large tables and slow network connection. (Default is \code{200}).
 #'
+#' @return A tibble with the table survey code and name
+#'
 #' @examples
 #' \donttest{
 #' get_cansim_table_survey("34-10-0013")
@@ -686,6 +682,8 @@ get_cansim_table_survey <- function(cansimTableNumber, language="english", refre
 #' @param timeout (Optional) Timeout in seconds for downloading cansim table to work around scenarios where StatCan servers drop the network connection.
 #  Set to higher values for large tables and slow network connection. (Default is \code{200}).
 #'
+#' @return A tibble with the table subject code and name.
+#'
 #' @examples
 #' \donttest{
 #' get_cansim_table_subject("34-10-0013")
@@ -709,6 +707,8 @@ get_cansim_table_subject <- function(cansimTableNumber, language="english", refr
 #' @param timeout (Optional) Timeout in seconds for downloading cansim table to work around scenarios where StatCan servers drop the network connection.
 #  Set to higher values for large tables and slow network connection. (Default is \code{200}).
 #'
+#' @return A tibble with the StatCan Notes for the table
+#'
 #' @examples
 #' \donttest{
 #' get_cansim_table_short_notes("34-10-0013")
@@ -732,6 +732,8 @@ get_cansim_table_short_notes <- function(cansimTableNumber, language="english",
 #' @param timeout (Optional) Timeout in seconds for downloading cansim table to work around scenarios where StatCan servers drop the network connection.
 #  Set to higher values for large tables and slow network connection. (Default is \code{200}).
 #'
+#' @return A tibble listing the column names of the StatCan table.
+#'
 #' @examples
 #' \donttest{
 #' get_cansim_column_list("34-10-0013")
@@ -756,6 +758,8 @@ get_cansim_column_list <- function(cansimTableNumber, language="english", refres
 #' @param timeout (Optional) Timeout in seconds for downloading cansim table to work around scenarios where StatCan servers drop the network connection.
 #  Set to higher values for large tables and slow network connection. (Default is \code{200}).
 #'
+#' @return A tibble with detailed information on StatCan table categories for the specified field
+#'
 #' @examples
 #' \donttest{
 #' get_cansim_column_categories("34-10-0013", "Geography")

R/cansim_helpers.R

@@ -180,8 +180,8 @@ short_prov.fr <- purrr::set_names(c(
 
 #' Add provincial abbreviations as factor
 #' @export
-#' @param data code{cansim} package data frame with provincial level data
-#' @return a code{cansim} package data frame with additional factor GEO.abb that contains language-specific provincial abbreviations
+#' @param data A tibble as returned by \code{get_cansim} with provincial level data
+#' @return The input tibble with additional factor GEO.abb that contains language-specific provincial abbreviations
 #'
 #' @examples
 #' \donttest{
@@ -210,7 +210,8 @@ add_provincial_abbreviations <- function(data){
 #' @param code_set the code set to retrieve.
 #' @param refresh Default is \code{FALSE}, repeated calls during the same session will hit the cached data.
 #' To refresh the code list during a running R session set to \code{TRUE}
-#' @return a tibble with english and french labels for the given code set
+#'
+#' @return A tibble with english and french labels for the given code set
 #'
 #' @examples
 #' \donttest{

R/cansim_sql.R

@@ -18,8 +18,7 @@ TIME_FORMAT <- "%Y-%m-%d %H:%M:%S"
 #' in the path specified by `getOption("cansim.cache_path")`, if this is set. Otherwise it will use `tempdir()`.
 #  Set to higher values for large tables and slow network connection. (Default is \code{1000}).
 #'
-#' @return tibble format data table output with added Date column with inferred date objects and
-#' a "val_norm" column with normalized VALUE using the supplied scale factor
+#' @return A database connection to a local SQLite database with the StatCan Table data.
 #'
 #' @examples
 #' \donttest{
@@ -201,7 +200,7 @@ get_cansim_sqlite <- function(cansimTableNumber, language="english", refresh=FAL
   con
 }
 
-#' disconnect from a cansim database connection
+#' Disconnect from a cansim database connection
 #'
 #' @param connection connection to database
 #' @return `NULL``
@@ -216,16 +215,17 @@ disconnect_cansim_sqlite <- function(connection){
   DBI::dbDisconnect(connection$src$con)
 }
 
-#' collect data from connection and normalize cansim table output
+#' Collect data from connection and normalize cansim table output
 #'
-#' @param connection connection to database
+#' @param connection A connection to a local StatCan table SQLite database as returned by \code{get_cansim_sqlite},
+#' possibly with filters or other \code{dbplyr} verbs applied
 #' @param replacement_value (Optional) the name of the column the manipulated value should be returned in. Defaults to adding the `val_norm` value field.
 #' @param normalize_percent (Optional) When \code{true} (the default) normalizes percentages by changing them to rates
 #' @param default_month The default month that should be used when creating Date objects for annual data (default set to "01")
 #' @param default_day The default day of the month that should be used when creating Date objects for monthly data (default set to "01")
 #' @param factors (Optional) Logical value indicating if dimensions should be converted to factors. (Default set to \code{false}).
 #' @param strip_classification_code (strip_classification_code) Logical value indicating if classification code should be stripped from names. (Default set to \code{false}).
-#' @return a tibble with the normalized data
+#' @return A tibble with the collected and normalized data
 #'
 #' @examples
 #' \donttest{
@@ -358,6 +358,7 @@ remove_cansim_sqlite_cached_table <- function(cansimTableNumber,language=NULL,ca
 #' @param connection connection to database
 #' @param table_name sql table name
 #' @param field name of field to index
+#' @return `NULL``
 #' @keywords internal
 create_index <- function(connection,table_name,field){
   field_index=paste0("index_",gsub("[^[:alnum:]]","_",field))
@@ -384,6 +385,8 @@ create_index <- function(connection,table_name,field){
 #' @param na na character strings
 #' @param text_encoding encoding of csv file (default UTF-8)
 #' @param delim (Optional) csv deliminator, default is ","
+#'
+#' @return A database connection
 #' @keywords internal
 csv2sqlite <- function(csv_file, sqlite_file, table_name, transform=NULL,chunk_size=5000000,
                        append=FALSE,col_types=NULL,na=c(NA,"..","","...","F"),

cran-comments.md

@@ -55,6 +55,7 @@ There were no ERRORs or WARNINGs or NOTEs.
 
 # Changes from version 0.3.7
 ## Minor changes
-* Exclude vignette from CRAN checks
+* Exclude vignette from automatic CRAN checks to fix problem of CRAN checks failing when StatCan servers are down and lead to the package being removed from CRAN (checks are still active in local environment and when using GitHub action checks)
 * add release date info to cube metadata and cube list calls
 * add auto-refresh option for sqlite tables
+* remove deprecated `adjust_cansim_values_by_variable` function