forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_take.py
317 lines (252 loc) · 11.6 KB
/
test_take.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
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
from datetime import datetime
import numpy as np
import pytest
from pandas._libs import iNaT
from pandas import array
import pandas._testing as tm
import pandas.core.algorithms as algos
@pytest.fixture(
params=[
(np.int8, np.int16(127), np.int8),
(np.int8, np.int16(128), np.int16),
(np.int32, 1, np.int32),
(np.int32, 2.0, np.float64),
(np.int32, 3.0 + 4.0j, np.complex128),
(np.int32, True, np.object_),
(np.int32, "", np.object_),
(np.float64, 1, np.float64),
(np.float64, 2.0, np.float64),
(np.float64, 3.0 + 4.0j, np.complex128),
(np.float64, True, np.object_),
(np.float64, "", np.object_),
(np.complex128, 1, np.complex128),
(np.complex128, 2.0, np.complex128),
(np.complex128, 3.0 + 4.0j, np.complex128),
(np.complex128, True, np.object_),
(np.complex128, "", np.object_),
(np.bool_, 1, np.object_),
(np.bool_, 2.0, np.object_),
(np.bool_, 3.0 + 4.0j, np.object_),
(np.bool_, True, np.bool_),
(np.bool_, "", np.object_),
]
)
def dtype_fill_out_dtype(request):
return request.param
class TestTake:
def test_1d_fill_nonna(self, dtype_fill_out_dtype):
dtype, fill_value, out_dtype = dtype_fill_out_dtype
data = np.random.default_rng(2).integers(0, 2, 4).astype(dtype)
indexer = [2, 1, 0, -1]
result = algos.take_nd(data, indexer, fill_value=fill_value)
assert (result[[0, 1, 2]] == data[[2, 1, 0]]).all()
assert result[3] == fill_value
assert result.dtype == out_dtype
indexer = [2, 1, 0, 1]
result = algos.take_nd(data, indexer, fill_value=fill_value)
assert (result[[0, 1, 2, 3]] == data[indexer]).all()
assert result.dtype == dtype
def test_2d_fill_nonna(self, dtype_fill_out_dtype):
dtype, fill_value, out_dtype = dtype_fill_out_dtype
data = np.random.default_rng(2).integers(0, 2, (5, 3)).astype(dtype)
indexer = [2, 1, 0, -1]
result = algos.take_nd(data, indexer, axis=0, fill_value=fill_value)
assert (result[[0, 1, 2], :] == data[[2, 1, 0], :]).all()
assert (result[3, :] == fill_value).all()
assert result.dtype == out_dtype
result = algos.take_nd(data, indexer, axis=1, fill_value=fill_value)
assert (result[:, [0, 1, 2]] == data[:, [2, 1, 0]]).all()
assert (result[:, 3] == fill_value).all()
assert result.dtype == out_dtype
indexer = [2, 1, 0, 1]
result = algos.take_nd(data, indexer, axis=0, fill_value=fill_value)
assert (result[[0, 1, 2, 3], :] == data[indexer, :]).all()
assert result.dtype == dtype
result = algos.take_nd(data, indexer, axis=1, fill_value=fill_value)
assert (result[:, [0, 1, 2, 3]] == data[:, indexer]).all()
assert result.dtype == dtype
def test_3d_fill_nonna(self, dtype_fill_out_dtype):
dtype, fill_value, out_dtype = dtype_fill_out_dtype
data = np.random.default_rng(2).integers(0, 2, (5, 4, 3)).astype(dtype)
indexer = [2, 1, 0, -1]
result = algos.take_nd(data, indexer, axis=0, fill_value=fill_value)
assert (result[[0, 1, 2], :, :] == data[[2, 1, 0], :, :]).all()
assert (result[3, :, :] == fill_value).all()
assert result.dtype == out_dtype
result = algos.take_nd(data, indexer, axis=1, fill_value=fill_value)
assert (result[:, [0, 1, 2], :] == data[:, [2, 1, 0], :]).all()
assert (result[:, 3, :] == fill_value).all()
assert result.dtype == out_dtype
result = algos.take_nd(data, indexer, axis=2, fill_value=fill_value)
assert (result[:, :, [0, 1, 2]] == data[:, :, [2, 1, 0]]).all()
assert (result[:, :, 3] == fill_value).all()
assert result.dtype == out_dtype
indexer = [2, 1, 0, 1]
result = algos.take_nd(data, indexer, axis=0, fill_value=fill_value)
assert (result[[0, 1, 2, 3], :, :] == data[indexer, :, :]).all()
assert result.dtype == dtype
result = algos.take_nd(data, indexer, axis=1, fill_value=fill_value)
assert (result[:, [0, 1, 2, 3], :] == data[:, indexer, :]).all()
assert result.dtype == dtype
result = algos.take_nd(data, indexer, axis=2, fill_value=fill_value)
assert (result[:, :, [0, 1, 2, 3]] == data[:, :, indexer]).all()
assert result.dtype == dtype
def test_1d_other_dtypes(self):
arr = np.random.default_rng(2).standard_normal(10).astype(np.float32)
indexer = [1, 2, 3, -1]
result = algos.take_nd(arr, indexer)
expected = arr.take(indexer)
expected[-1] = np.nan
tm.assert_almost_equal(result, expected)
def test_2d_other_dtypes(self):
arr = np.random.default_rng(2).standard_normal((10, 5)).astype(np.float32)
indexer = [1, 2, 3, -1]
# axis=0
result = algos.take_nd(arr, indexer, axis=0)
expected = arr.take(indexer, axis=0)
expected[-1] = np.nan
tm.assert_almost_equal(result, expected)
# axis=1
result = algos.take_nd(arr, indexer, axis=1)
expected = arr.take(indexer, axis=1)
expected[:, -1] = np.nan
tm.assert_almost_equal(result, expected)
def test_1d_bool(self):
arr = np.array([0, 1, 0], dtype=bool)
result = algos.take_nd(arr, [0, 2, 2, 1])
expected = arr.take([0, 2, 2, 1])
tm.assert_numpy_array_equal(result, expected)
result = algos.take_nd(arr, [0, 2, -1])
assert result.dtype == np.object_
def test_2d_bool(self):
arr = np.array([[0, 1, 0], [1, 0, 1], [0, 1, 1]], dtype=bool)
result = algos.take_nd(arr, [0, 2, 2, 1])
expected = arr.take([0, 2, 2, 1], axis=0)
tm.assert_numpy_array_equal(result, expected)
result = algos.take_nd(arr, [0, 2, 2, 1], axis=1)
expected = arr.take([0, 2, 2, 1], axis=1)
tm.assert_numpy_array_equal(result, expected)
result = algos.take_nd(arr, [0, 2, -1])
assert result.dtype == np.object_
def test_2d_float32(self):
arr = np.random.default_rng(2).standard_normal((4, 3)).astype(np.float32)
indexer = [0, 2, -1, 1, -1]
# axis=0
result = algos.take_nd(arr, indexer, axis=0)
expected = arr.take(indexer, axis=0)
expected[[2, 4], :] = np.nan
tm.assert_almost_equal(result, expected)
# axis=1
result = algos.take_nd(arr, indexer, axis=1)
expected = arr.take(indexer, axis=1)
expected[:, [2, 4]] = np.nan
tm.assert_almost_equal(result, expected)
def test_2d_datetime64(self):
# 2005/01/01 - 2006/01/01
arr = (
np.random.default_rng(2).integers(11_045_376, 11_360_736, (5, 3))
* 100_000_000_000
)
arr = arr.view(dtype="datetime64[ns]")
indexer = [0, 2, -1, 1, -1]
# axis=0
result = algos.take_nd(arr, indexer, axis=0)
expected = arr.take(indexer, axis=0)
expected.view(np.int64)[[2, 4], :] = iNaT
tm.assert_almost_equal(result, expected)
result = algos.take_nd(arr, indexer, axis=0, fill_value=datetime(2007, 1, 1))
expected = arr.take(indexer, axis=0)
expected[[2, 4], :] = datetime(2007, 1, 1)
tm.assert_almost_equal(result, expected)
# axis=1
result = algos.take_nd(arr, indexer, axis=1)
expected = arr.take(indexer, axis=1)
expected.view(np.int64)[:, [2, 4]] = iNaT
tm.assert_almost_equal(result, expected)
result = algos.take_nd(arr, indexer, axis=1, fill_value=datetime(2007, 1, 1))
expected = arr.take(indexer, axis=1)
expected[:, [2, 4]] = datetime(2007, 1, 1)
tm.assert_almost_equal(result, expected)
def test_take_axis_0(self):
arr = np.arange(12).reshape(4, 3)
result = algos.take(arr, [0, -1])
expected = np.array([[0, 1, 2], [9, 10, 11]])
tm.assert_numpy_array_equal(result, expected)
# allow_fill=True
result = algos.take(arr, [0, -1], allow_fill=True, fill_value=0)
expected = np.array([[0, 1, 2], [0, 0, 0]])
tm.assert_numpy_array_equal(result, expected)
def test_take_axis_1(self):
arr = np.arange(12).reshape(4, 3)
result = algos.take(arr, [0, -1], axis=1)
expected = np.array([[0, 2], [3, 5], [6, 8], [9, 11]])
tm.assert_numpy_array_equal(result, expected)
# allow_fill=True
result = algos.take(arr, [0, -1], axis=1, allow_fill=True, fill_value=0)
expected = np.array([[0, 0], [3, 0], [6, 0], [9, 0]])
tm.assert_numpy_array_equal(result, expected)
# GH#26976 make sure we validate along the correct axis
with pytest.raises(IndexError, match="indices are out-of-bounds"):
algos.take(arr, [0, 3], axis=1, allow_fill=True, fill_value=0)
def test_take_non_hashable_fill_value(self):
arr = np.array([1, 2, 3])
indexer = np.array([1, -1])
with pytest.raises(ValueError, match="fill_value must be a scalar"):
algos.take(arr, indexer, allow_fill=True, fill_value=[1])
# with object dtype it is allowed
arr = np.array([1, 2, 3], dtype=object)
result = algos.take(arr, indexer, allow_fill=True, fill_value=[1])
expected = np.array([2, [1]], dtype=object)
tm.assert_numpy_array_equal(result, expected)
class TestExtensionTake:
# The take method found in pd.api.extensions
def test_bounds_check_large(self):
arr = np.array([1, 2])
msg = "indices are out-of-bounds"
with pytest.raises(IndexError, match=msg):
algos.take(arr, [2, 3], allow_fill=True)
msg = "index 2 is out of bounds for( axis 0 with)? size 2"
with pytest.raises(IndexError, match=msg):
algos.take(arr, [2, 3], allow_fill=False)
def test_bounds_check_small(self):
arr = np.array([1, 2, 3], dtype=np.int64)
indexer = [0, -1, -2]
msg = r"'indices' contains values less than allowed \(-2 < -1\)"
with pytest.raises(ValueError, match=msg):
algos.take(arr, indexer, allow_fill=True)
result = algos.take(arr, indexer)
expected = np.array([1, 3, 2], dtype=np.int64)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize("allow_fill", [True, False])
def test_take_empty(self, allow_fill):
arr = np.array([], dtype=np.int64)
# empty take is ok
result = algos.take(arr, [], allow_fill=allow_fill)
tm.assert_numpy_array_equal(arr, result)
msg = "|".join(
[
"cannot do a non-empty take from an empty axes.",
"indices are out-of-bounds",
]
)
with pytest.raises(IndexError, match=msg):
algos.take(arr, [0], allow_fill=allow_fill)
def test_take_na_empty(self):
result = algos.take(np.array([]), [-1, -1], allow_fill=True, fill_value=0.0)
expected = np.array([0.0, 0.0])
tm.assert_numpy_array_equal(result, expected)
def test_take_coerces_list(self):
# GH#52981 coercing is deprecated, disabled in 3.0
arr = [1, 2, 3]
msg = (
"pd.api.extensions.take requires a numpy.ndarray, ExtensionArray, "
"Index, Series, or NumpyExtensionArray got list"
)
with pytest.raises(TypeError, match=msg):
algos.take(arr, [0, 0])
def test_take_NumpyExtensionArray(self):
# GH#59177
arr = array([1 + 1j, 2, 3]) # NumpyEADtype('complex128') (NumpyExtensionArray)
assert algos.take(arr, [2]) == 2
arr = array([1, 2, 3]) # Int64Dtype() (ExtensionArray)
assert algos.take(arr, [2]) == 2