Reorder Levels of Qualitative Variables by Frequency — ordonner_variables

This function reorders the levels of all qualitative (factor) variables in a dataset based on their frequency, in descending order. It ensures that the most frequent levels appear first when analyzing or visualizing the data.

ordonner_variables_qualitatives(data)

Arguments

data: A data frame containing the dataset with qualitative variables to reorder.

Value

A data frame with reordered levels for all factor variables. Non-factor variables remain unchanged.

Details

The function applies the following transformations:

Identifies all columns of type factor in the dataset.
Reorders the levels of each factor variable using the forcats::fct_infreq() function, which orders levels by decreasing frequency.

This is particularly useful for preparing datasets for visualization or analysis, where it can be helpful to have the most common levels displayed first.

Examples

# Example usage:
library(dplyr)
library(forcats)
#> Warning: package 'forcats' was built under R version 4.4.3

# Create a sample dataset
data <- data.frame(
  var1 = factor(c("A", "B", "A", "C", "B", "B")),
  var2 = factor(c("X", "Y", "X", "Y", "X", "Z")),
  var3 = c(1, 2, 3, 4, 5, 6)  # Non-factor variable
)

# Reorder qualitative variables by frequency
data <- ordonner_variables_qualitatives(data)

# Check the new order of levels
levels(data$var1) # Output: "B" "A" "C"
#> [1] "B" "A" "C"
levels(data$var2) # Output: "X" "Y" "Z"
#> [1] "X" "Y" "Z"