In arthurgailes/rsegregation: Calculate Empirical Measures of Segregation

knitr::opts_chunk$set(
  collapse = TRUE,
  message = FALSE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

rsegregation

A shortcut package with formulas for several different indices of segregation. rsegregation is designed to fit into the tidyverse framework, particularly dplyr.

Installation

<!-- You can install the released version of rsegregation from CRAN with:

install.packages("rsegregation")

--> The development version from GitHub can be installed with:

``` {r eval=FALSE} # install.packages("devtools") devtools::install_github("arthurgailes/rsegregation")

## Usage

rsegregation depends upon dplyr (>1.0.0), and can be used with it. To return a single divergence score for Bay Area County:

### Divergence and Entropy

#### Calculate the divergence score for the entire dataset

rsegregation can work with base r, or within several dplyr verbs:
```r
library(rsegregation)
library(dplyr)
## included dataset of Bay Area Census tracts
# Using dplyr
bay_divergence <- bay_race %>% 
  summarize(bay_divergence = divergence(white,black,asian, hispanic, all_other,
    population=total_pop, summed = T))

# Using base r
bay_divergence <- divergence(bay_race[c('white','black','asian', 'hispanic', 'all_other')], 
  population=bay_race$total_pop, summed = T)
# or
bay_divergence <- divergence(bay_race$white,bay_race$black,bay_race$asian, 
  bay_race$hispanic, bay_race$all_other, population=bay_race$total_pop, summed = T)
# all return the same result:
bay_divergence

Calculate divergence by group

Using the included Bay Area dataset of 2010 racial groups, divergence can be calculated by county using dplyr::group_by().

#library(dplyr)
group_by(bay_race, county) %>% 
  summarize(bay_divergence = divergence(white,black,asian, hispanic, all_other, 
    population=total_pop, summed = T))

By-observation divergence scores

Divergence and entropy are both calculated rowwise by default (summed = FALSE).

bay_entropy <- bay_race
bay_entropy$entropy <- entropy(bay_race[c('white','black','asian',
  'hispanic','all_other')], population=bay_race$total_pop, summed = F)
head(bay_entropy)

Miscellaneous

Dataframes should be formatted as long on geographic observations (e.g. tracts), but wide on group observations (e.g. races), as in the included dataset of the San Francisco Bay Area.