-
Notifications
You must be signed in to change notification settings - Fork 54
/
test_diversity.py
228 lines (207 loc) · 7.64 KB
/
test_diversity.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
import geopandas as gpd
import momepy as mm
import numpy as np
import pytest
from momepy import sw_high
from pytest import approx
class TestDiversity:
def setup_method(self):
test_file_path = mm.datasets.get_path("bubenec")
self.df_buildings = gpd.read_file(test_file_path, layer="buildings")
self.df_streets = gpd.read_file(test_file_path, layer="streets")
self.df_tessellation = gpd.read_file(test_file_path, layer="tessellation")
self.df_buildings["height"] = np.linspace(10.0, 30.0, 144)
self.df_tessellation["area"] = mm.Area(self.df_tessellation).series
self.sw = sw_high(k=3, gdf=self.df_tessellation, ids="uID")
self.sw.neighbors[100] = []
self.sw_drop = sw_high(k=3, gdf=self.df_tessellation[2:], ids="uID")
def test_Range(self):
full_sw = mm.Range(self.df_tessellation, "area", self.sw, "uID").series
assert full_sw[0] == approx(8255.372, rel=1e-3)
area = self.df_tessellation["area"]
full2 = mm.Range(self.df_tessellation, area, self.sw, "uID").series
assert full2[0] == approx(8255.372, rel=1e-3)
limit = mm.Range(
self.df_tessellation, "area", self.sw, "uID", rng=(10, 90)
).series
assert limit[0] == approx(4122.139, rel=1e-3)
assert (
mm.Range(self.df_tessellation, "area", self.sw_drop, "uID")
.series.isna()
.any()
)
def test_Theil(self):
full_sw = mm.Theil(self.df_tessellation, "area", self.sw, "uID").series
assert full_sw[0] == approx(0.25744684)
limit = mm.Theil(
self.df_tessellation,
self.df_tessellation.area,
self.sw,
"uID",
rng=(10, 90),
).series
assert limit[0] == approx(0.1330295)
zeros = mm.Theil(
self.df_tessellation, np.zeros(len(self.df_tessellation)), self.sw, "uID"
).series
assert zeros[0] == 0
assert (
mm.Theil(self.df_tessellation, "area", self.sw_drop, "uID")
.series.isna()
.any()
)
def test_Simpson(self):
ht_sw = mm.Simpson(self.df_tessellation, "area", self.sw, "uID").series
assert ht_sw[0] == 0.385
quan_sw = mm.Simpson(
self.df_tessellation,
self.df_tessellation.area,
self.sw,
"uID",
binning="quantiles",
k=3,
).series
assert quan_sw[0] == 0.395
with pytest.raises(ValueError):
ht_sw = mm.Simpson(
self.df_tessellation, "area", self.sw, "uID", binning="nonexistent"
)
assert (
mm.Simpson(self.df_tessellation, "area", self.sw_drop, "uID")
.series.isna()
.any()
)
gs = mm.Simpson(
self.df_tessellation, "area", self.sw, "uID", gini_simpson=True
).series
assert gs[0] == 1 - 0.385
inv = mm.Simpson(
self.df_tessellation, "area", self.sw, "uID", inverse=True
).series
assert inv[0] == 1 / 0.385
self.df_tessellation["cat"] = list(range(8)) * 18
cat = mm.Simpson(
self.df_tessellation, "cat", self.sw, "uID", categorical=True
).series
assert cat[0] == pytest.approx(0.15)
cat2 = mm.Simpson(
self.df_tessellation,
"cat",
self.sw,
"uID",
categorical=True,
categories=range(15),
).series
assert cat2[0] == pytest.approx(0.15)
def test_Gini(self):
full_sw = mm.Gini(self.df_tessellation, "area", self.sw, "uID").series
assert full_sw[0] == approx(0.3945388)
limit = mm.Gini(
self.df_tessellation, "area", self.sw, "uID", rng=(10, 90)
).series
assert limit[0] == approx(0.28532814)
self.df_tessellation["negative"] = (
self.df_tessellation.area - self.df_tessellation.area.mean()
)
with pytest.raises(ValueError):
mm.Gini(self.df_tessellation, "negative", self.sw, "uID").series
assert (
mm.Gini(self.df_tessellation, "area", self.sw_drop, "uID")
.series.isna()
.any()
)
def test_Shannon(self):
ht_sw = mm.Shannon(self.df_tessellation, "area", self.sw, "uID").series
assert ht_sw[0] == 1.094056456831614
quan_sw = mm.Shannon(
self.df_tessellation,
self.df_tessellation.area,
self.sw,
"uID",
binning="quantiles",
k=3,
).series
assert quan_sw[0] == 0.9985793315873921
with pytest.raises(ValueError):
ht_sw = mm.Shannon(
self.df_tessellation, "area", self.sw, "uID", binning="nonexistent"
)
assert (
mm.Shannon(self.df_tessellation, "area", self.sw_drop, "uID")
.series.isna()
.any()
)
self.df_tessellation["cat"] = list(range(8)) * 18
cat = mm.Shannon(
self.df_tessellation, "cat", self.sw, "uID", categorical=True
).series
assert cat[0] == pytest.approx(1.973)
cat2 = mm.Shannon(
self.df_tessellation,
"cat",
self.sw,
"uID",
categorical=True,
categories=range(15),
).series
assert cat2[0] == pytest.approx(1.973)
def test_Unique(self):
self.df_tessellation["cat"] = list(range(8)) * 18
un = mm.Unique(self.df_tessellation, "cat", self.sw, "uID").series
assert un[0] == 8
un = mm.Unique(self.df_tessellation, list(range(8)) * 18, self.sw, "uID").series
assert un[0] == 8
un = mm.Unique(self.df_tessellation, "cat", self.sw_drop, "uID").series
assert un.isna().any()
assert un[5] == 8
self.df_tessellation.loc[0, "cat"] = np.nan
un = mm.Unique(self.df_tessellation, "cat", self.sw, "uID", dropna=False).series
assert un[0] == 9
un = mm.Unique(self.df_tessellation, "cat", self.sw, "uID", dropna=True).series
assert un[0] == 8
def test_Percentile(self):
perc = mm.Percentiles(self.df_tessellation, "area", self.sw, "uID").frame
assert np.all(
perc.loc[0].values - np.array([1085.11492833, 2623.9962661, 4115.47168328])
< 0.00001
)
perc = mm.Percentiles(
self.df_tessellation, list(range(8)) * 18, self.sw, "uID"
).frame
assert np.all(perc.loc[0].values == np.array([1.0, 3.5, 6.0]))
perc = mm.Percentiles(
self.df_tessellation, "area", self.sw, "uID", percentiles=[30, 70]
).frame
assert np.all(
perc.loc[0].values - np.array([1218.98841575, 3951.35531166]) < 0.00001
)
perc = mm.Percentiles(
self.df_tessellation,
"area",
self.sw,
"uID",
weighted="linear",
).frame
assert np.all(
perc.loc[0].values - np.array([997.8086922, 2598.84036762, 4107.14201011])
< 0.00001
)
perc = mm.Percentiles(
self.df_tessellation,
"area",
self.sw,
"uID",
percentiles=[30, 70],
weighted="linear",
).frame
assert np.all(
perc.loc[0].values - np.array([1211.83227008, 3839.99083097]) < 0.00001
)
with pytest.raises(ValueError, match="'nonsense' is not a valid"):
mm.Percentiles(
self.df_tessellation,
"area",
self.sw,
"uID",
weighted="nonsense",
)