plot_conditional_distribution: Plot conditional distribution

In johnaclouse/eeda: Univariate and bivariate exploratory data analysis, but extra

Plot conditional distribution

Description

A visualization showing values from the eda_var separated in two sets based on the target_var. A histogram format chosen to accommodate discontinuities in data. The number of bins is determined based on the data in eda_var. Conditional views of histograms will involve different binwidths. This compromise was made in recognition of the need to see a more accurate view of the distribuion rather than attempt to compare counts at a given position on the x-axis. The default confidence_level was chosen at 0.01 to address concerns of multiple search. A more supportable value should be considered based on the data.

Usage

plot_conditional_distribution(
  df,
  eda_var = NULL,
  target_var = NULL,
  confidence_level = 0.99,
  width = 300,
  height = 450
)

Arguments

df	data frame
eda_var	character
target_var	character name of column for conditional analysis
confidence_level	numeric confidence level
width	numeric width of plot in pixels
height	numeric height of plot in pixels

Value

NULL. Function called for side effect of rendering exploratory data anlysis visualization

Examples

# plot_conditional_distribution()

johnaclouse/eeda documentation built on July 22, 2022, 12:16 a.m.