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
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
|
from __future__ import division, print_function, absolute_import
import numpy as np
from numpy.testing import assert_allclose, run_module_suite
from scipy.stats import (binned_statistic, binned_statistic_2d,
binned_statistic_dd)
from scipy._lib.six import u
from common_tests import check_named_results
class TestBinnedStatistic(object):
@classmethod
def setup_class(cls):
np.random.seed(9865)
cls.x = np.random.random(100)
cls.y = np.random.random(100)
cls.v = np.random.random(100)
cls.X = np.random.random((100, 3))
cls.w = np.random.random(100)
def test_1d_count(self):
x = self.x
v = self.v
count1, edges1, bc = binned_statistic(x, v, 'count', bins=10)
count2, edges2 = np.histogram(x, bins=10)
assert_allclose(count1, count2)
assert_allclose(edges1, edges2)
def test_gh5927(self):
# smoke test for gh5927 - binned_statistic was using `is` for string
# comparison
x = self.x
v = self.v
statistics = [u'mean', u'median', u'count', u'sum']
for statistic in statistics:
res = binned_statistic(x, v, statistic, bins=10)
def test_1d_result_attributes(self):
x = self.x
v = self.v
res = binned_statistic(x, v, 'count', bins=10)
attributes = ('statistic', 'bin_edges', 'binnumber')
check_named_results(res, attributes)
def test_1d_sum(self):
x = self.x
v = self.v
sum1, edges1, bc = binned_statistic(x, v, 'sum', bins=10)
sum2, edges2 = np.histogram(x, bins=10, weights=v)
assert_allclose(sum1, sum2)
assert_allclose(edges1, edges2)
def test_1d_mean(self):
x = self.x
v = self.v
stat1, edges1, bc = binned_statistic(x, v, 'mean', bins=10)
stat2, edges2, bc = binned_statistic(x, v, np.mean, bins=10)
assert_allclose(stat1, stat2)
assert_allclose(edges1, edges2)
def test_1d_std(self):
x = self.x
v = self.v
stat1, edges1, bc = binned_statistic(x, v, 'std', bins=10)
stat2, edges2, bc = binned_statistic(x, v, np.std, bins=10)
assert_allclose(stat1, stat2)
assert_allclose(edges1, edges2)
def test_1d_median(self):
x = self.x
v = self.v
stat1, edges1, bc = binned_statistic(x, v, 'median', bins=10)
stat2, edges2, bc = binned_statistic(x, v, np.median, bins=10)
assert_allclose(stat1, stat2)
assert_allclose(edges1, edges2)
def test_1d_bincode(self):
x = self.x[:20]
v = self.v[:20]
count1, edges1, bc = binned_statistic(x, v, 'count', bins=3)
bc2 = np.array([3, 2, 1, 3, 2, 3, 3, 3, 3, 1, 1, 3, 3, 1, 2, 3, 1,
1, 2, 1])
bcount = [(bc == i).sum() for i in np.unique(bc)]
assert_allclose(bc, bc2)
assert_allclose(bcount, count1)
def test_1d_range_keyword(self):
# Regression test for gh-3063, range can be (min, max) or [(min, max)]
np.random.seed(9865)
x = np.arange(30)
data = np.random.random(30)
mean, bins, _ = binned_statistic(x[:15], data[:15])
mean_range, bins_range, _ = binned_statistic(x, data, range=[(0, 14)])
mean_range2, bins_range2, _ = binned_statistic(x, data, range=(0, 14))
assert_allclose(mean, mean_range)
assert_allclose(bins, bins_range)
assert_allclose(mean, mean_range2)
assert_allclose(bins, bins_range2)
def test_1d_multi_values(self):
x = self.x
v = self.v
w = self.w
stat1v, edges1v, bc1v = binned_statistic(x, v, 'mean', bins=10)
stat1w, edges1w, bc1w = binned_statistic(x, w, 'mean', bins=10)
stat2, edges2, bc2 = binned_statistic(x, [v, w], 'mean', bins=10)
assert_allclose(stat2[0], stat1v)
assert_allclose(stat2[1], stat1w)
assert_allclose(edges1v, edges2)
assert_allclose(bc1v, bc2)
def test_2d_count(self):
x = self.x
y = self.y
v = self.v
count1, binx1, biny1, bc = binned_statistic_2d(
x, y, v, 'count', bins=5)
count2, binx2, biny2 = np.histogram2d(x, y, bins=5)
assert_allclose(count1, count2)
assert_allclose(binx1, binx2)
assert_allclose(biny1, biny2)
def test_2d_result_attributes(self):
x = self.x
y = self.y
v = self.v
res = binned_statistic_2d(x, y, v, 'count', bins=5)
attributes = ('statistic', 'x_edge', 'y_edge', 'binnumber')
check_named_results(res, attributes)
def test_2d_sum(self):
x = self.x
y = self.y
v = self.v
sum1, binx1, biny1, bc = binned_statistic_2d(x, y, v, 'sum', bins=5)
sum2, binx2, biny2 = np.histogram2d(x, y, bins=5, weights=v)
assert_allclose(sum1, sum2)
assert_allclose(binx1, binx2)
assert_allclose(biny1, biny2)
def test_2d_mean(self):
x = self.x
y = self.y
v = self.v
stat1, binx1, biny1, bc = binned_statistic_2d(x, y, v, 'mean', bins=5)
stat2, binx2, biny2, bc = binned_statistic_2d(x, y, v, np.mean, bins=5)
assert_allclose(stat1, stat2)
assert_allclose(binx1, binx2)
assert_allclose(biny1, biny2)
def test_2d_mean_unicode(self):
x = self.x
y = self.y
v = self.v
stat1, binx1, biny1, bc = binned_statistic_2d(
x, y, v, u('mean'), bins=5)
stat2, binx2, biny2, bc = binned_statistic_2d(x, y, v, np.mean, bins=5)
assert_allclose(stat1, stat2)
assert_allclose(binx1, binx2)
assert_allclose(biny1, biny2)
def test_2d_std(self):
x = self.x
y = self.y
v = self.v
stat1, binx1, biny1, bc = binned_statistic_2d(x, y, v, 'std', bins=5)
stat2, binx2, biny2, bc = binned_statistic_2d(x, y, v, np.std, bins=5)
assert_allclose(stat1, stat2)
assert_allclose(binx1, binx2)
assert_allclose(biny1, biny2)
def test_2d_median(self):
x = self.x
y = self.y
v = self.v
stat1, binx1, biny1, bc = binned_statistic_2d(
x, y, v, 'median', bins=5)
stat2, binx2, biny2, bc = binned_statistic_2d(
x, y, v, np.median, bins=5)
assert_allclose(stat1, stat2)
assert_allclose(binx1, binx2)
assert_allclose(biny1, biny2)
def test_2d_bincode(self):
x = self.x[:20]
y = self.y[:20]
v = self.v[:20]
count1, binx1, biny1, bc = binned_statistic_2d(
x, y, v, 'count', bins=3)
bc2 = np.array([17, 11, 6, 16, 11, 17, 18, 17, 17, 7, 6, 18, 16,
6, 11, 16, 6, 6, 11, 8])
bcount = [(bc == i).sum() for i in np.unique(bc)]
assert_allclose(bc, bc2)
count1adj = count1[count1.nonzero()]
assert_allclose(bcount, count1adj)
def test_2d_multi_values(self):
x = self.x
y = self.y
v = self.v
w = self.w
stat1v, binx1v, biny1v, bc1v = binned_statistic_2d(
x, y, v, 'mean', bins=8)
stat1w, binx1w, biny1w, bc1w = binned_statistic_2d(
x, y, w, 'mean', bins=8)
stat2, binx2, biny2, bc2 = binned_statistic_2d(
x, y, [v, w], 'mean', bins=8)
assert_allclose(stat2[0], stat1v)
assert_allclose(stat2[1], stat1w)
assert_allclose(binx1v, binx2)
assert_allclose(biny1w, biny2)
assert_allclose(bc1v, bc2)
def test_2d_binnumbers_unraveled(self):
x = self.x
y = self.y
v = self.v
stat, edgesx, bcx = binned_statistic(x, v, 'mean', bins=10)
stat, edgesy, bcy = binned_statistic(y, v, 'mean', bins=10)
stat2, edgesx2, edgesy2, bc2 = binned_statistic_2d(
x, y, v, 'mean', bins=10, expand_binnumbers=True)
bcx3 = np.searchsorted(edgesx, x, side='right')
bcy3 = np.searchsorted(edgesy, y, side='right')
# `numpy.searchsorted` is non-inclusive on right-edge, compensate
bcx3[x == x.max()] -= 1
bcy3[y == y.max()] -= 1
assert_allclose(bcx, bc2[0])
assert_allclose(bcy, bc2[1])
assert_allclose(bcx3, bc2[0])
assert_allclose(bcy3, bc2[1])
def test_dd_count(self):
X = self.X
v = self.v
count1, edges1, bc = binned_statistic_dd(X, v, 'count', bins=3)
count2, edges2 = np.histogramdd(X, bins=3)
assert_allclose(count1, count2)
assert_allclose(edges1, edges2)
def test_dd_result_attributes(self):
X = self.X
v = self.v
res = binned_statistic_dd(X, v, 'count', bins=3)
attributes = ('statistic', 'bin_edges', 'binnumber')
check_named_results(res, attributes)
def test_dd_sum(self):
X = self.X
v = self.v
sum1, edges1, bc = binned_statistic_dd(X, v, 'sum', bins=3)
sum2, edges2 = np.histogramdd(X, bins=3, weights=v)
assert_allclose(sum1, sum2)
assert_allclose(edges1, edges2)
def test_dd_mean(self):
X = self.X
v = self.v
stat1, edges1, bc = binned_statistic_dd(X, v, 'mean', bins=3)
stat2, edges2, bc = binned_statistic_dd(X, v, np.mean, bins=3)
assert_allclose(stat1, stat2)
assert_allclose(edges1, edges2)
def test_dd_std(self):
X = self.X
v = self.v
stat1, edges1, bc = binned_statistic_dd(X, v, 'std', bins=3)
stat2, edges2, bc = binned_statistic_dd(X, v, np.std, bins=3)
assert_allclose(stat1, stat2)
assert_allclose(edges1, edges2)
def test_dd_median(self):
X = self.X
v = self.v
stat1, edges1, bc = binned_statistic_dd(X, v, 'median', bins=3)
stat2, edges2, bc = binned_statistic_dd(X, v, np.median, bins=3)
assert_allclose(stat1, stat2)
assert_allclose(edges1, edges2)
def test_dd_bincode(self):
X = self.X[:20]
v = self.v[:20]
count1, edges1, bc = binned_statistic_dd(X, v, 'count', bins=3)
bc2 = np.array([63, 33, 86, 83, 88, 67, 57, 33, 42, 41, 82, 83, 92,
32, 36, 91, 43, 87, 81, 81])
bcount = [(bc == i).sum() for i in np.unique(bc)]
assert_allclose(bc, bc2)
count1adj = count1[count1.nonzero()]
assert_allclose(bcount, count1adj)
def test_dd_multi_values(self):
X = self.X
v = self.v
w = self.w
stat1v, edges1v, bc1v = binned_statistic_dd(X, v, np.std, bins=8)
stat1w, edges1w, bc1w = binned_statistic_dd(X, w, np.std, bins=8)
stat2, edges2, bc2 = binned_statistic_dd(X, [v, w], np.std, bins=8)
assert_allclose(stat2[0], stat1v)
assert_allclose(stat2[1], stat1w)
assert_allclose(edges1v, edges2)
assert_allclose(edges1w, edges2)
assert_allclose(bc1v, bc2)
def test_dd_binnumbers_unraveled(self):
X = self.X
v = self.v
stat, edgesx, bcx = binned_statistic(X[:, 0], v, 'mean', bins=10)
stat, edgesy, bcy = binned_statistic(X[:, 1], v, 'mean', bins=10)
stat, edgesz, bcz = binned_statistic(X[:, 2], v, 'mean', bins=10)
stat2, edges2, bc2 = binned_statistic_dd(
X, v, 'mean', bins=10, expand_binnumbers=True)
assert_allclose(bcx, bc2[0])
assert_allclose(bcy, bc2[1])
assert_allclose(bcz, bc2[2])
if __name__ == "__main__":
run_module_suite()
|
