def test_Decomposition(self):
s_map = gpd.read_file(
load_example("Sacramento1").get_path("sacramentot2.shp"))
index1 = Dissim(s_map, 'HISP', 'TOT_POP')
index2 = Dissim(s_map, 'BLACK', 'TOT_POP')
res = DecomposeSegregation(index1,
index2,
counterfactual_approach="composition")
np.testing.assert_almost_equal(res.c_a, -0.16138819842911295)
np.testing.assert_almost_equal(res.c_s, -0.005104643275796905)
res.plot(plot_type='cdfs')
res.plot(plot_type='maps')
res = DecomposeSegregation(index1,
index2,
counterfactual_approach="share")
np.testing.assert_almost_equal(res.c_a, -0.1543828579279878)
np.testing.assert_almost_equal(res.c_s, -0.012109983776922045)
res.plot(plot_type='cdfs')
res.plot(plot_type='maps')
res = DecomposeSegregation(index1,
index2,
counterfactual_approach="dual_composition")
np.testing.assert_almost_equal(res.c_a, -0.16159526946235048)
np.testing.assert_almost_equal(res.c_s, -0.004897572242559378)
res.plot(plot_type='cdfs')
res.plot(plot_type='maps')
def test_Inference(self):
s_map = gpd.read_file(
load_example("Sacramento1").get_path("sacramentot2.shp"))
index1 = Dissim(s_map, 'HISP_', 'TOT_POP')
index2 = Dissim(s_map, 'BLACK_', 'TOT_POP')
groups_list = ['WHITE_', 'BLACK_', 'ASIAN_', 'HISP_']
m_index = MultiDissim(s_map, groups_list)
m_index_1 = MultiDissim(s_map[0:200], groups_list)
m_index_2 = MultiDissim(s_map[200:], groups_list)
# Single Value Tests #
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="systematic",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
0.01603886544282861,
decimal=3)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="bootstrap",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
0.31992467511262773,
decimal=3)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="evenness",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
0.01596295861644252,
decimal=3)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="permutation",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
0.32184656076566864,
decimal=3)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="systematic_permutation",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
0.01603886544282861,
decimal=3)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="even_permutation",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
0.01619436868061094,
decimal=3)
np.random.seed(123)
res = SingleValueTest(m_index,
null_approach="bootstrap",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
0.4143544081847027,
decimal=3)
np.random.seed(123)
res = SingleValueTest(m_index,
null_approach="evenness",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
0.01633979237418177,
decimal=3)
# Two Value Tests #
np.random.seed(123)
res = TwoValueTest(index1,
index2,
null_approach="random_label",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
-0.0031386146371949076,
decimal=3)
np.random.seed(123)
res = TwoValueTest(index1,
index2,
null_approach="counterfactual_composition",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
-0.005032145622504718,
decimal=3)
np.random.seed(123)
res = TwoValueTest(index1,
index2,
null_approach="counterfactual_share",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
-0.034350440515125,
decimal=3)
np.random.seed(123)
res = TwoValueTest(index1,
index2,
null_approach="counterfactual_dual_composition",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
-0.004771386292706747,
decimal=3)
np.random.seed(123)
res = TwoValueTest(m_index_1,
m_index_2,
null_approach="random_label",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
-0.0024327144012562685,
decimal=3)
def test_Dissim(self):
s_map = gpd.read_file(
load_example("Sacramento1").get_path("sacramentot2.shp"))
df = s_map[['geometry', 'HISP_', 'TOT_POP']]
index = Dissim(df, 'HISP_', 'TOT_POP')
np.testing.assert_almost_equal(index.statistic, 0.32184656076566864)
def segregationMisc(data_df,zipPolygon):
caseWeekly_unstack=data_df['CasesWeekly'].unstack(level=0)
caseWeekly_columnsReplace_dic={key:"case_"+str(key) for key in caseWeekly_unstack.columns}
caseWeekly_unstack.rename(columns=caseWeekly_columnsReplace_dic,inplace=True)
testWeekly_unstack=data_df['TestsWeekly'].unstack(level=0)
testWeekly_columnsReplace_dic={key:"test_"+str(key) for key in testWeekly_unstack.columns}
testWeekly_unstack.rename(columns=testWeekly_columnsReplace_dic,inplace=True)
zip_codes= gpd.read_file(zipPolygon)
data_df_zipGPD=zip_codes.merge(caseWeekly_unstack,left_on='zip', right_on=caseWeekly_unstack.index)
data_df_zipGPD=data_df_zipGPD.merge(testWeekly_unstack,left_on='zip', right_on=testWeekly_unstack.index)
# print(data_df_zipGPD)
W=ps.lib.weights.Queen(data_df_zipGPD.geometry)
W.transform = 'R'
# weeks=idx_weekNumber=data_df.index.get_level_values('Week Number')
# weeks=np.unique(weeks)
columnsName=list(caseWeekly_columnsReplace_dic.values())+list(testWeekly_columnsReplace_dic.values())
caseColumnsaName=list(caseWeekly_columnsReplace_dic.values())
testColumnsName=list(testWeekly_columnsReplace_dic.values())
# valArray=data_df_zipGPD[weeks].to_numpy()
# valArray_fillNan=bfill(valArray).T
# valArray_fillNan[np.isnan(valArray_fillNan)]=0
# # print(valArray_fillNan,valArray_fillNan.shape)
data_df_zipGPD_bfill=data_df_zipGPD.fillna(method='bfill',axis='columns')
data_df_zipGPD_bfill[columnsName]=data_df_zipGPD_bfill[columnsName].fillna(0)
data_df_zipGPD_bfill[columnsName]=data_df_zipGPD_bfill[columnsName].astype('int32') #'int32' float
#A-aspatial indexes
gdf=data_df_zipGPD_bfill[['case_19','test_19','case_15','test_15','geometry']]
gdf=gdf[~(gdf==0).any(axis=1)]
#01-Dissimilarity
from segregation.aspatial import Dissim
index = Dissim(gdf, 'case_19','test_19')
# print(type(index))
print("dissimilarity:",index.statistic)
#02-Gini
from segregation.aspatial import GiniSeg
index = GiniSeg(gdf, 'case_19','test_19')
# type(index)
print("Gini:",index.statistic)
#03-Entropy
from segregation.aspatial import Entropy
index = Entropy(gdf, 'case_19','test_19')
# type(index)
print("Entropy:",index.statistic)
#04-Atkinson
from segregation.aspatial import Atkinson
index = Atkinson(gdf, 'case_19','test_19', b = 0.5)
# type(index)
print("Atkinson:",index.statistic)
#05-Concentration Profile
from segregation.aspatial import ConProf
index = ConProf(gdf, 'case_19','test_19')
# type(index)
print("Concentration Profile:",index.statistic)
index.plot()
#06-Isolation
from segregation.aspatial import Isolation
index = Isolation(gdf, 'case_19','test_19')
# type(index)
print("Isolation:",index.statistic)
#07-Exposure
from segregation.aspatial import Exposure
index = Exposure(gdf, 'case_19','test_19')
# type(index)
print("Exposure:",index.statistic)
#08-Correlation Ratio
from segregation.aspatial import CorrelationR
index = CorrelationR(gdf, 'case_19','test_19')
# type(index)
print("Correlation Ratio:",index.statistic)
#09-Modified Dissimilarity
from segregation.aspatial import ModifiedDissim
index = ModifiedDissim(gdf, 'case_19','test_19', iterations = 500)
# type(index)
print("Modified Dissimilarity:",index.statistic)
#10-Modified Gini
from segregation.aspatial import ModifiedGiniSeg
index = ModifiedGiniSeg(gdf, 'case_19','test_19', iterations = 500)
# type(index)
print("Modified Gini :",index.statistic)
# #11-Bias-Corrected Dissimilarity
# #FloatingPointError: invalid value encountered in true_divide
# from segregation.aspatial import BiasCorrectedDissim
# index = BiasCorrectedDissim(gdf, 'case_19','test_19', B = 500)
# # type(index)
# print("Bias-Corrected Dissimilarity:",index.statistic)
#12-Density-Corrected Dissimilarity
from segregation.aspatial import DensityCorrectedDissim
index = DensityCorrectedDissim(gdf, 'case_19','test_19', xtol = 1e-5)
# type(index)
print("Density-Corrected Dissimilarity:",index.statistic)
#13-Minimum-Maximum Index (MM)
from segregation.aspatial import MinMax
index = MinMax(gdf, 'case_19','test_19')
# type(index)
print("Minimum-Maximum Index (MM):",index.statistic)
#B-Decomposition framework of the PySAL segregation module shapley值法 ref:于伟，张鹏._我国高校生均经费支出省际差异的再分析——基于shapley值分解的方法
gdf["subtotal"]=gdf.case_19+gdf.case_15
G_19=GiniSeg(gdf, 'case_19','subtotal')
gdf_15=gdf[gdf.case_15<gdf.test_15]
G_15=GiniSeg(gdf_15, 'case_15','subtotal')
print("G19_gini:",G_19.statistic)
print("G15_gini:",G_15.statistic)
print("G_19-G_15:",G_19.statistic-G_15.statistic)
# help(DecomposeSegregation)
#14-Composition Approach (default)
#Sergio J. Rey, Renan Cortes, and Elijah Knaap.Comparative Spatial Segregation Analytics[J].5.31.2019
# help(DecomposeSegregation) #Decompose segregation differences into spatial and attribute components.
#Shapley decomposition
DS_composition = DecomposeSegregation(G_15,G_19)
print("Shapley's Spatial Component of the decomposition:",DS_composition.c_s) #Shapley's Spatial Component of the decomposition
print("Shapley's Attribute Component of the decomposition:",DS_composition.c_a) #Shapley's Attribute Component of the decomposition
plt.figure(figsize=(10,10))
DS_composition.plot(plot_type = 'cdfs')
# plt.figure(figsize=(50,50))
DS_composition.plot(plot_type = 'maps')
#15-Share Approach ref: Rey, S. et al "Comparative Spatial Segregation Analytics".
DS_share = DecomposeSegregation(G_19, G_15, counterfactual_approach = 'share')
plt.figure(figsize=(10,10))
DS_share.plot(plot_type = 'cdfs')
plt.figure()
DS_share.plot(plot_type = 'maps')
#16-Dual Composition Approach
DS_dual = DecomposeSegregation(G_19, G_15, counterfactual_approach = 'dual_composition')
plt.figure(figsize=(10,10))
DS_dual.plot(plot_type = 'cdfs')
plt.figure()
DS_dual.plot(plot_type = 'maps')
#17-Inspecting a different index: Relative Concentration
from segregation.spatial import RelativeConcentration
RCO_19 = RelativeConcentration(gdf, 'case_19','subtotal')
RCO_15= RelativeConcentration(gdf_15, 'case_15','subtotal')
print("RCO_19.statistic - RCO_15.statistic",RCO_19.statistic - RCO_15.statistic)
RCO_DS_composition = DecomposeSegregation(RCO_19, RCO_15)
print("RCO_DS_composition.c_s:",RCO_DS_composition.c_s)
print("RCO_DS_composition.c_a:",RCO_DS_composition.c_a)
#C-inference wrappers
# single value
#18-dissimilarity
D= Dissim(gdf, 'case_19','subtotal')
# print(type(index))
print("dissimilarity:",D.statistic)
#evenness
infer_D_eve = SingleValueTest(D, iterations_under_null = 1000, null_approach = "evenness", two_tailed = True)
plt.figure()
infer_D_eve.plot()
print("infer_D_eve.est_sim.mean:",infer_D_eve.est_sim.mean())
print("infer_D_eve.p_value:",infer_D_eve.p_value)
#systematic
infer_D_sys = SingleValueTest(D, iterations_under_null = 5000, null_approach = "systematic", two_tailed = True)
plt.figure()
infer_D_sys.plot()
# print("^"*50)
#ValueError: 'Some estimates resulted in NaN or infinite values for estimations under null hypothesis.
#19-relative concentration
# RCO = RelativeConcentration(gdf, 'case_19','subtotal')
# RCO=RCO_15
# print(RCO)
#permutation
# infer_RCO_per = SingleValueTest(RCO, iterations_under_null = 1000, null_approach = "permutation", two_tailed = True)
# plt.figure()
# infer_RCO_per.plot()
# print("infer_RCO_per.p_value:",infer_RCO_per.p_value)
# #even_permutation
# infer_RCO_eve_per = SingleValueTest(RCO, iterations_under_null = 1000, null_approach = "even_permutation", two_tailed = True)
# plt.figure()
# infer_RCO_eve_per.plot()
#20-relative centralization
#ValueError: It not possible to determine the center distance for, at least, one unit. This is probably due to the magnitude of the number of the centroids. We recommend to reproject the geopandas DataFrame.
# print(gdf.crs)
# RCE = RelativeCentralization(gdf.to_crs(communityArea_CRS), 'case_19','test_19')
# infer_RCE_per = SingleValueTest(RCE, iterations_under_null = 1000, null_approach = "permutation", two_tailed = True)
# plt.figure()
# infer_RCE_per.plot()
#D-comparative inference
#21-compararive dissimilarity
D_19=Dissim(gdf, 'case_19','subtotal')
D_15=Dissim(gdf_15, 'case_15','subtotal')
print("D_19-D_15:",D_19.statistic-D_15.statistic)
compare_D_fit = TwoValueTest(D_19, D_15, iterations_under_null = 1000, null_approach = "random_label")
plt.figure()
compare_D_fit.plot()
print("compare_D_fit.p_value:",compare_D_fit.p_value)
#22-comparative Gini
G_19=GiniSeg(gdf, 'case_19','subtotal')
gdf_15=gdf[gdf.case_15<gdf.test_15]
G_15=GiniSeg(gdf_15, 'case_15','subtotal')
compare_G_fit = TwoValueTest(G_19, G_15, iterations_under_null = 1000, null_approach = "random_label")
plt.figure()
compare_G_fit.plot()
#23-comparative spatial dissimilarity
SD_19 = SpatialDissim(gdf, 'case_19','subtotal')
SD_15 = SpatialDissim(gdf_15, 'case_15','subtotal')
compare_SD_fit = TwoValueTest(SD_19, SD_15, iterations_under_null = 500, null_approach = "counterfactual_composition")
plt.figure()
compare_SD_fit.plot()
def test_Inference(self):
s_map = gpd.read_file(libpysal.examples.get_path("sacramentot2.shp"))
index1 = Dissim(s_map, 'HISP_', 'TOT_POP')
index2 = Dissim(s_map, 'BLACK_', 'TOT_POP')
# Single Value Tests #
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="systematic",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(), 0.01603886544282861)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="bootstrap",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(), 0.31992467511262773)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="evenness",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(), 0.01596295861644252)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="permutation",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(), 0.32184656076566864)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="systematic_permutation",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(), 0.01603886544282861)
np.random.seed(123)
res = SingleValueTest(index1,
null_approach="even_permutation",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(), 0.01619436868061094)
# Two Value Tests #
np.random.seed(123)
res = TwoValueTest(index1,
index2,
null_approach="random_label",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
-0.0013532591859387643)
np.random.seed(123)
res = TwoValueTest(index1,
index2,
null_approach="counterfactual_composition",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
-0.005032145622504718)
np.random.seed(123)
res = TwoValueTest(index1,
index2,
null_approach="counterfactual_share",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(), -0.034350440515125)
np.random.seed(123)
res = TwoValueTest(index1,
index2,
null_approach="counterfactual_dual_composition",
iterations_under_null=50)
np.testing.assert_almost_equal(res.est_sim.mean(),
-0.004771386292706747)