Diversity: Calculate the Diversity of a Dataset

In duncankmckinnon/diversify: Tools For Analyzing Diversity in Data

Description

Calculate the diversity of a dataset by determining the degree to which differentiable groupings in the columns vary from maximum entropy for the number of grouping. If the groupings are uniformly distributed, the entropy is maximized. This functions calculates the ratio of the real distribution of groupings to the maximum entropy distribution to determine the overall diversity represented in the grouped data.

Usage

Diversity(dataset)

Arguments

dataset

A tibble or data.frame type object

Value

A list containing:

• data the distribution dataset of different groupings and the percentage of the total dataset they represent

• entropy the real entropy represented in the dataset

• diversity the percentage of the maximum potential entropy represented by the real data, or the degree to which the dataset is ideally diversified

Examples

Diversity(cars)
t <- data.frame(a = rep(0, 100))
Diversity(t)

duncankmckinnon/diversify documentation built on May 13, 2019, 12:29 a.m.