Merge pull request #9 from inbo/7-new-function-colcompare

7 new function colcompare

DESCRIPTION

@@ -9,3 +9,7 @@ License: MIT + file LICENSE
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
 RoxygenNote: 7.3.1
+Imports: 
+    dplyr (>= 1.1.4),
+    magrittr (>= 2.0.3),
+    rlang (>= 1.1.3)

NAMESPACE

@@ -1,2 +1,3 @@
 # Generated by roxygen2: do not edit by hand
 
+importFrom(magrittr,"%>%")

R/check.R

@@ -0,0 +1,19 @@
+#' Check
+#'
+#' @author Sander Devisscher
+#'
+#' @description
+#' Helper script to determine existence in environment panel
+#'
+#' @param x environment object
+#'
+#' @details
+#' This doesn't work with functions which will yield a 0 by default.
+#'
+#'
+#' @returns
+#' 1 = object exists in environment
+#' 0 = object doesn't exist in environment
+
+
+check <- function(x){tryCatch(if(!is.logical(class(x)) && ifelse(is.function(x), stop(), 0)) 1 else 1, error=function(e) 0)}

R/colcompare.R

@@ -0,0 +1,85 @@
+#' Columnname comparison
+#'
+#' @author Sander Devisscher
+#'
+#' @description
+#' A simple function to list the difference in column names in 2 datasets.
+#'
+#' @param x dataframe 1
+#' @param y dataframe 2
+#'
+#' @return
+#' a list of columns present in x but not in y and a list of columns
+#' present in y and not in x.
+#'
+#' @examples
+#' \dontrun{
+#' # create example dataframes
+#' super_sleepers <- data.frame(rating=1:4,
+#' animal=c('koala', 'hedgehog', 'sloth', 'panda'),
+#' country=c('Australia', 'Italy', 'Peru', 'China'),
+#' avg_sleep_hours=c(21, 18, 17, 10))
+#'
+#' super_actives <- data.frame(rating=1:4,
+#' animal=c('kangeroo', 'wolf', 'jaguar', 'tiger'),
+#' country=c('Australia', 'Italy', 'Peru', 'China'),
+#' avg_active_hours=c(16, 15, 8, 10))
+#'
+#' colcompare(super_sleepers, super_actives)
+#' }
+#'
+#' @importFrom magrittr %>%
+
+colcompare <- function(x, y){
+
+  test_xiny <- subset(colnames(x), !colnames(x) %in% colnames(y))
+  test_xiny <- as.data.frame(test_xiny) %>%
+    dplyr::mutate(lower = tolower(test_xiny))
+  test_yinx <- subset(colnames(y), !colnames(y) %in% colnames(x))
+  test_yinx <- as.data.frame(test_yinx) %>%
+    dplyr::mutate(lower = tolower(test_yinx))
+
+  combined <- test_xiny %>%
+    dplyr::full_join(test_yinx, by = "lower")
+
+  # Typos (x en y) ####
+  test_xANDy <- combined %>%
+    dplyr::filter(!is.na(test_xiny) & !is.na(test_yinx)) %>%
+    dplyr::mutate(test_xANDy = paste0("X: ", test_xiny, " <==> ", test_yinx, " :Y \n"))
+  test_xANDy <- test_xANDy$test_xANDy
+
+  if(check(test_xANDy) == 1){
+    if(!rlang::is_empty(test_xANDy)){
+      error <- paste0("Kolommen met verschillende schrijfwijze: \n",
+                     test_xANDy)
+      writeLines(error)
+      print("=====================================================================")
+    }
+  }
+  # Only X ####
+  test_xiny <- combined %>%
+    dplyr::filter(is.na(test_yinx))
+  test_xiny <- test_xiny$test_xiny
+
+  if(check(test_xiny)==1){
+    if(!rlang::is_empty(test_xiny)){
+      test_xiny <- paste(test_xiny, collapse = ", \n")
+      error <- paste0("Kolommen uit x die niet in y voorkomen: \n", test_xiny)
+      writeLines(error)
+      print("=====================================================================")
+    }
+  }
+
+  # Only y ####
+  test_yinx <- combined %>%
+    dplyr::filter(is.na(test_xiny))
+  test_yinx <- test_yinx$test_yinx
+
+  if(check(test_yinx)==1){
+    if(!rlang::is_empty(test_yinx)){
+      test_yinx <- paste(test_yinx, collapse = ", \n")
+      error <- paste0("Kolommen uit y die niet in x voorkomen: ", test_yinx)
+      writeLines(error)
+    }
+  }
+}