multigroup_aspatial_examples

Multigroup aspatial indexes of segregation

Multigroup aspatial indexes of segregation

This is an example notebook of functionalities for multigroup aspatial indexes of the segregation module. Firstly, we need to import the packages we need:

%%capture

import libpysal
import segregation
import geopandas as gpd

Then it's time to load some data to estimate segregation. We use the data of 2000 Census Tract Data for the metropolitan area of Sacramento, CA, USA.

We use a geopandas dataframe available in PySAL examples repository.

For more information about the data: https://github.com/pysal/libpysal/tree/master/libpysal/examples/sacramento2

input_df = gpd.read_file(libpysal.examples.get_path("sacramentot2.shp"))
input_df.columns

Index(['FIPS', 'MSA', 'TOT_POP', 'POP_16', 'POP_65', 'WHITE_', 'BLACK_',
       'ASIAN_', 'HISP_', 'MULTI_RA', 'MALES', 'FEMALES', 'MALE1664',
       'FEM1664', 'EMPL16', 'EMP_AWAY', 'EMP_HOME', 'EMP_29', 'EMP_30',
       'EMP16_2', 'EMP_MALE', 'EMP_FEM', 'OCC_MAN', 'OCC_OFF1', 'OCC_INFO',
       'HH_INC', 'POV_POP', 'POV_TOT', 'HSG_VAL', 'FIPSNO', 'POLYID',
       'geometry'],
      dtype='object')

The groups of interest are White, Black, Asian and Hispanic population. Therefore, we create an auxiliary list with only the necessary columns for fitting the index.

groups_list = ['WHITE_', 'BLACK_', 'ASIAN_','HISP_']

We also can plot the spatial distribution of the composition of each of these groups over the tracts of Sacramento:

import matplotlib.pyplot as plt

for i in range(len(groups_list)):
    input_df['comp_' + groups_list[i]] = input_df[groups_list[i]] / input_df['TOT_POP']

fig, axes = plt.subplots(ncols = 2, nrows = 2, figsize = (17, 10))


input_df.plot(column = 'comp_' + groups_list[0],
              cmap = 'OrRd',
              legend = True, ax = axes[0,0])
axes[0,0].set_title('Composition of ' + groups_list[0])
axes[0,0].set_xticks([])
axes[0,0].set_yticks([])
axes[0,0].set_facecolor('white')


input_df.plot(column = 'comp_' + groups_list[1],
              cmap = 'OrRd',
              legend = True, ax = axes[0,1])
axes[0,1].set_title('Composition of ' + groups_list[1])
axes[0,1].set_xticks([])
axes[0,1].set_yticks([])
axes[0,1].set_facecolor('white')


input_df.plot(column = 'comp_' + groups_list[2],
              cmap = 'OrRd',
              legend = True, ax = axes[1,0])
axes[1,0].set_title('Composition of ' + groups_list[2])
axes[1,0].set_xticks([])
axes[1,0].set_yticks([])
axes[1,0].set_facecolor('white')

input_df.plot(column = 'comp_' + groups_list[3],
              cmap = 'OrRd',
              legend = True, ax = axes[1,1])
axes[1,1].set_title('Composition of ' + groups_list[3])
axes[1,1].set_xticks([])
axes[1,1].set_yticks([])
axes[1,1].set_facecolor('white')

Multigroup Dissimilarity Index

%%capture
from segregation.aspatial import MultiDissim

index = MultiDissim(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.MultiDissim

index.statistic

0.41340872573177806

Multigroup Gini Index

%%capture
from segregation.aspatial import MultiGiniSeg

index = MultiGiniSeg(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.MultiGiniSeg

index.statistic

0.5456349992598081

Multigroup Normalized Exposure Index

%%capture
from segregation.aspatial import MultiNormalizedExposure

index = MultiNormalizedExposure(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.MultiNormalizedExposure

index.statistic

0.18821879029994157

Multigroup Information Theory Index

%%capture
from segregation.aspatial import MultiInformationTheory

index = MultiInformationTheory(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.MultiInformationTheory

index.statistic

0.1710160297858887

Multigroup Relative Diversity Index

%%capture
from segregation.aspatial import MultiRelativeDiversity

index = MultiRelativeDiversity(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.MultiRelativeDiversity

index.statistic

0.15820019878220337

Multigroup Squared Coefficient of Variation Index

%%capture
from segregation.aspatial import MultiSquaredCoefficientVariation

index = MultiSquaredCoefficientVariation(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.MultiSquaredCoefficientVariation

index.statistic

0.11875484641127525

Multigroup Diversity Index

%%capture
from segregation.aspatial import MultiDiversity

index = MultiDiversity(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.MultiDiversity

index.statistic

0.9733112243997906

# Normalized version of the multigroup diversity index
normalized_index = MultiDiversity(input_df, groups_list, normalized = True)
normalized_index.statistic

0.7020956383415715

Simpson's Concentration Index (lambda)

%%capture
from segregation.aspatial import SimpsonsConcentration

index = SimpsonsConcentration(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.SimpsonsConcentration

index.statistic

0.49182413151957904

Simpson's Interaction Index (I)

%%capture
from segregation.aspatial import SimpsonsInteraction

index = SimpsonsInteraction(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.SimpsonsInteraction

index.statistic

0.508175868480421

Multigroup Divergence Index

%%capture
from segregation.aspatial import MultiDivergence

index = MultiDivergence(input_df, groups_list)
type(index)

segregation.aspatial.multigroup_aspatial_indexes.MultiDivergence

index.statistic

0.16645182134289443

Table of Contents