Merge pull request #38 from vbfelix/calc_perc

closes #37

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: relper
 Title: Miscellaneous Functions for Data Preparation, Cleaning, and Visualization
-Version: 3.10.1
+Version: 3.11.2
 Authors@R: person("Vinícius", "Félix", email = "vinicius1b7f@gmail.com", role = c("aut", "cre"))
 Description: A collection of functions to help with data preparation, cleaning, and visualization. relper offers functions to: transform and format data (e.g., easily apply the percentage), compute metrics (e.g., coefficient of variation), check conditions (e.g., determine if a number is even or odd), supply lovely and varied color palettes (e.g., palettes inspired by TV series and movies), complement ggplot2 (e.g., add an identity line to a scatter plot), manipulate strings (e.g., keep only a type of character). The package's ultimate purpose is to simplify data analysis by providing functions that will shorten some steps.
 Depends: R (>= 3.6.0)

NAMESPACE

@@ -2,7 +2,6 @@
 
 export("%>%")
 export(as_num)
-export(as_perc)
 export(calc_acf)
 export(calc_association)
 export(calc_auc)
@@ -15,6 +14,7 @@ export(calc_mean)
 export(calc_modality)
 export(calc_mode)
 export(calc_peak_density)
+export(calc_perc)
 export(calc_skewness)
 export(cut_by_quantile)
 export(dttm_diff)

NEWS.md

@@ -4,6 +4,16 @@
 >
 > *These additions transform the package into a comprehensive "Data Insight Toolbox," empowering users to gain deeper insights and perform advanced analyses on their datasets. Additionally, some functions have been renamed for better clarity and consistency.*
 
+## relper 3.11.2
+
+**Additions**
+
+-   calc_perc
+
+**Removals**
+
+-   as_perc
+
 ## relper 3.10.1
 
 **Additions**

R/calc_perc.r

@@ -0,0 +1,49 @@
+#' Compute a percentage
+#'
+#' @description Compute  the percentage based on one or multiple variables.
+#'
+#' @eval arg_df("df")
+#' @param grp_var The grouping variable(s) based on which the percentages will be computed
+#' @param main_var An optional variable, when provided, will be utilized to compute the percentage for each of its own levels
+#'
+#' @return A data.frame summarizing the counts and percentages within groups. The output is arranged in descending order of counts within each group.
+#'
+#' @export
+#'
+#' @examples
+#'
+#' #without main_var
+#' calc_perc(mtcars,grp_var = c(cyl,vs))
+#'
+#' #main_var within grp_var
+#' calc_perc(mtcars,grp_var = c(cyl,vs),main_var = vs)
+#'
+#' #main_var not within grp_var
+#' calc_perc(mtcars,grp_var = c(cyl),main_var = vs)
+
+calc_perc <- function(df,grp_var, main_var = NULL){
+
+  stopifnot(is.data.frame(df))
+
+  if(is.null(substitute(main_var))){
+    output <-
+      df %>%
+      dplyr::group_by(dplyr::across({{grp_var}})) %>%
+      dplyr::summarise(n = dplyr::n(),.groups = 'drop') %>%
+      dplyr::ungroup() %>%
+      dplyr::mutate(perc = 100*n/sum(n,na.rm = TRUE)) %>%
+      dplyr::arrange(-n)
+
+  }else {
+    output <-
+      df %>%
+      dplyr::group_by({{main_var}},across({{grp_var}})) %>%
+      dplyr::summarise(n = dplyr::n(),.groups = 'drop') %>%
+      dplyr::group_by({{main_var}}) %>%
+      dplyr::mutate(perc = 100*n/sum(n,na.rm = TRUE)) %>%
+      dplyr::arrange({{main_var}},-n)
+  }
+
+  return(output)
+
+}

tests/testthat/test-calc_perc.R

@@ -0,0 +1,56 @@
+data_calc_perc <-
+  data.frame(
+    grp1 = c("a","b","a","b","c","c"),
+    grp2 = c("1","2","1","2","1","2")
+  )
+
+grp1 <-
+  structure(list(grp1 = c("a", "b", "c"),
+                 n = c(2L, 2L, 2L),
+                 perc = c(33.3333333333333,33.3333333333333, 33.3333333333333)),
+            row.names = c(NA, -3L), class = c("tbl_df","tbl", "data.frame"))
+
+grp2 <-
+structure(list(grp2 = c("1", "1", "2", "2"),
+               grp1 = c("a", "c","b", "c"),
+               n = c(2L, 1L, 2L, 1L),
+               perc = c(66.6666666666667, 33.3333333333333, 66.6666666666667, 33.3333333333333)),
+          class = c("grouped_df",  "tbl_df", "tbl", "data.frame"),
+          row.names = c(NA, -4L),
+          groups = structure(list(
+            grp2 = c("1", "2"), .rows = structure(list(1:2, 3:4), ptype = integer(0),
+                                                  class = c("vctrs_list_of","vctrs_vctr", "list"))),
+            row.names = c(NA, -2L), .drop = TRUE, class = c("tbl_df","tbl", "data.frame")))
+
+test_that("Expected equal", {
+
+  expect_equal(object = calc_perc(mtcars,vs),expected =  calc_perc(mtcars,"vs"))
+
+  expect_equal(
+    object = calc_perc(data_calc_perc,grp1),
+    expected =  grp1
+    )
+
+  expect_equal(
+    object = calc_perc(data_calc_perc,grp1,grp2),
+    expected =  grp2
+  )
+
+
+  expect_equal(
+    object = calc_perc(data_calc_perc,c(grp1,grp2),grp2),
+    expected =  grp2
+  )
+
+})
+
+test_that("Wrong type", {
+
+  expect_error(calc_perc(df = "a"))
+
+  expect_error(calc_perc(df = 1))
+
+  expect_error(calc_perc(df = mtcars,grp_var = jojo))
+
+})
+

vignettes/functions_as.Rmd

@@ -29,17 +29,6 @@ The goal of `as_num` is to be a more generalized version of `as.numeric`, where
 as_num("123.456,78")
 ```
 
-# as_perc
-
-The goal of `as_perc` is to convert a number to a percentage. By default, the function simply multiplies values by 100.
-
-```{r as_perc}
-mtcars %>% 
-  count(vs,am) %>% 
-  mutate(prop = n/sum(n)) %>% 
-  mutate(perc = as_perc(prop))
-```
-
 If you set the argument `sum` to `TRUE` the function will divide the values by their total and multiply by 100.
 
 ```{r as_perc-sum}

vignettes/functions_calc.Rmd

@@ -553,6 +553,23 @@ pd_plot+
 
 ```
 
+# calc_perc
+
+The goal of `calc_perc` is to compute the percentage.
+
+```{r calc_perc}
+
+#without main_var
+calc_perc(mtcars,grp_var = c(cyl,vs))
+
+#main_var within grp_var
+calc_perc(mtcars,grp_var = c(cyl,vs),main_var = vs)
+
+#main_var not within grp_var
+calc_perc(mtcars,grp_var = c(cyl),main_var = vs)
+
+```
+
 # calc_skewness
 
 The goal of `calc_skewness` is to compute a skewness coefficient.