Repository navigation
Expand file tree
/
Copy path_arraysetops_impl.py
More file actions
1205 lines (979 loc) · 38.5 KB
/
Copy path_arraysetops_impl.py
File metadata and controls
1205 lines (979 loc) · 38.5 KB
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
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""
Set operations for arrays based on sorting.
Notes
-----
For floating point arrays, inaccurate results may appear due to usual round-off
and floating point comparison issues.
Speed could be gained in some operations by an implementation of
`numpy.sort`, that can provide directly the permutation vectors, thus avoiding
calls to `numpy.argsort`.
Original author: Robert Cimrman
"""
import functools
from typing import NamedTuple
import numpy as np
from numpy._core import overrides
from numpy._core._multiarray_umath import _array_converter, _unique_hash
from numpy.lib.array_utils import normalize_axis_index
array_function_dispatch = functools.partial(
overrides.array_function_dispatch, module='numpy')
__all__ = [
"ediff1d", "intersect1d", "isin", "setdiff1d", "setxor1d",
"union1d", "unique", "unique_all", "unique_counts", "unique_inverse",
"unique_values"
]
def _ediff1d_dispatcher(ary, to_end=None, to_begin=None):
return (ary, to_end, to_begin)
@array_function_dispatch(_ediff1d_dispatcher)
def ediff1d(ary, to_end=None, to_begin=None):
"""
The differences between consecutive elements of an array.
Parameters
----------
ary : array_like
If necessary, will be flattened before the differences are taken.
to_end : array_like, optional
Number(s) to append at the end of the returned differences.
to_begin : array_like, optional
Number(s) to prepend at the beginning of the returned differences.
Returns
-------
ediff1d : ndarray
The differences. Loosely, this is ``ary.flat[1:] - ary.flat[:-1]``.
See Also
--------
diff, gradient
Notes
-----
When applied to masked arrays, this function drops the mask information
if the `to_begin` and/or `to_end` parameters are used.
Examples
--------
>>> import numpy as np
>>> x = np.array([1, 2, 4, 7, 0])
>>> np.ediff1d(x)
array([ 1, 2, 3, -7])
>>> np.ediff1d(x, to_begin=-99, to_end=np.array([88, 99]))
array([-99, 1, 2, ..., -7, 88, 99])
The returned array is always 1D.
>>> y = [[1, 2, 4], [1, 6, 24]]
>>> np.ediff1d(y)
array([ 1, 2, -3, 5, 18])
"""
conv = _array_converter(ary)
# Convert to (any) array and ravel:
ary = conv[0].ravel()
# enforce that the dtype of `ary` is used for the output
dtype_req = ary.dtype
# fast track default case
if to_begin is None and to_end is None:
return ary[1:] - ary[:-1]
if to_begin is None:
l_begin = 0
else:
to_begin = np.asanyarray(to_begin)
if not np.can_cast(to_begin, dtype_req, casting="same_kind"):
raise TypeError("dtype of `to_begin` must be compatible "
"with input `ary` under the `same_kind` rule.")
to_begin = to_begin.ravel()
l_begin = len(to_begin)
if to_end is None:
l_end = 0
else:
to_end = np.asanyarray(to_end)
if not np.can_cast(to_end, dtype_req, casting="same_kind"):
raise TypeError("dtype of `to_end` must be compatible "
"with input `ary` under the `same_kind` rule.")
to_end = to_end.ravel()
l_end = len(to_end)
# do the calculation in place and copy to_begin and to_end
l_diff = max(len(ary) - 1, 0)
result = np.empty_like(ary, shape=l_diff + l_begin + l_end)
if l_begin > 0:
result[:l_begin] = to_begin
if l_end > 0:
result[l_begin + l_diff:] = to_end
np.subtract(ary[1:], ary[:-1], result[l_begin:l_begin + l_diff])
return conv.wrap(result)
def _unpack_tuple(x):
""" Unpacks one-element tuples for use as return values """
if len(x) == 1:
return x[0]
else:
return x
def _unique_dispatcher(ar, return_index=None, return_inverse=None,
return_counts=None, axis=None, *, equal_nan=None,
sorted=True):
return (ar,)
@array_function_dispatch(_unique_dispatcher)
def unique(ar, return_index=False, return_inverse=False,
return_counts=False, axis=None, *, equal_nan=True,
sorted=True):
"""
Find the unique elements of an array.
Returns the sorted unique elements of an array. There are three optional
outputs in addition to the unique elements:
* the indices of the input array that give the unique values
* the indices of the unique array that reconstruct the input array
* the number of times each unique value comes up in the input array
Parameters
----------
ar : array_like
Input array. Unless `axis` is specified, this will be flattened if it
is not already 1-D.
return_index : bool, optional
If True, also return the indices of `ar` (along the specified axis,
if provided, or in the flattened array) that result in the unique array.
return_inverse : bool, optional
If True, also return the indices of the unique array (for the specified
axis, if provided) that can be used to reconstruct `ar`.
return_counts : bool, optional
If True, also return the number of times each unique item appears
in `ar`.
axis : int or None, optional
The axis to operate on. If None, `ar` will be flattened. If an integer,
the subarrays indexed by the given axis will be flattened and treated
as the elements of a 1-D array with the dimension of the given axis,
see the notes for more details. Object arrays or structured arrays
that contain objects are not supported if the `axis` kwarg is used. The
default is None.
equal_nan : bool, optional
If True, collapses multiple NaN values in the return array into one.
.. versionadded:: 1.24
sorted : bool, optional
If True, the unique elements are sorted. Elements may be sorted in
practice even if ``sorted=False``, but this could change without
notice.
.. versionadded:: 2.3
Returns
-------
unique : ndarray
The sorted unique values.
unique_indices : ndarray, optional
The indices of the first occurrences of the unique values in the
original array. Only provided if `return_index` is True.
unique_inverse : ndarray, optional
The indices to reconstruct the original array from the
unique array. Only provided if `return_inverse` is True.
unique_counts : ndarray, optional
The number of times each of the unique values comes up in the
original array. Only provided if `return_counts` is True.
See Also
--------
repeat : Repeat elements of an array.
sort : Return a sorted copy of an array.
Notes
-----
When an axis is specified the subarrays indexed by the axis are sorted.
This is done by making the specified axis the first dimension of the array
(move the axis to the first dimension to keep the order of the other axes)
and then flattening the subarrays in C order. The flattened subarrays are
then viewed as a structured type with each element given a label, with the
effect that we end up with a 1-D array of structured types that can be
treated in the same way as any other 1-D array. The result is that the
flattened subarrays are sorted in lexicographic order starting with the
first element.
Like np.sort, NaN will sort to the end of the values.
For complex arrays all NaN values are considered equivalent
(no matter whether the NaN is in the real or imaginary part).
As the representant for the returned array the smallest one in the
lexicographical order is chosen - see np.sort for how the lexicographical
order is defined for complex arrays.
.. versionchanged:: 2.0
For multi-dimensional inputs, ``unique_inverse`` is reshaped
such that the input can be reconstructed using
``np.take(unique, unique_inverse, axis=axis)``. The result is
now not 1-dimensional when ``axis=None``.
Note that in NumPy 2.0.0 a higher dimensional array was returned also
when ``axis`` was not ``None``. This was reverted, but
``inverse.reshape(-1)`` can be used to ensure compatibility with both
versions.
Examples
--------
>>> import numpy as np
>>> np.unique([1, 1, 2, 2, 3, 3])
array([1, 2, 3])
>>> a = np.array([[1, 1], [2, 3]])
>>> np.unique(a)
array([1, 2, 3])
Return the unique rows of a 2D array
>>> a = np.array([[1, 0, 0], [1, 0, 0], [2, 3, 4]])
>>> np.unique(a, axis=0)
array([[1, 0, 0], [2, 3, 4]])
Return the indices of the original array that give the unique values:
>>> a = np.array(['a', 'b', 'b', 'c', 'a'])
>>> u, indices = np.unique(a, return_index=True)
>>> u
array(['a', 'b', 'c'], dtype='<U1')
>>> indices
array([0, 1, 3])
>>> a[indices]
array(['a', 'b', 'c'], dtype='<U1')
Reconstruct the input array from the unique values and inverse:
>>> a = np.array([1, 2, 6, 4, 2, 3, 2])
>>> u, indices = np.unique(a, return_inverse=True)
>>> u
array([1, 2, 3, 4, 6])
>>> indices
array([0, 1, 4, 3, 1, 2, 1])
>>> u[indices]
array([1, 2, 6, 4, 2, 3, 2])
Reconstruct the input values from the unique values and counts:
>>> a = np.array([1, 2, 6, 4, 2, 3, 2])
>>> values, counts = np.unique(a, return_counts=True)
>>> values
array([1, 2, 3, 4, 6])
>>> counts
array([1, 3, 1, 1, 1])
>>> np.repeat(values, counts)
array([1, 2, 2, 2, 3, 4, 6]) # original order not preserved
"""
ar = np.asanyarray(ar)
if axis is None or ar.ndim == 1:
if axis is not None:
normalize_axis_index(axis, ar.ndim)
ret = _unique1d(ar, return_index, return_inverse, return_counts,
equal_nan=equal_nan, inverse_shape=ar.shape, axis=None,
sorted=sorted)
return _unpack_tuple(ret)
# axis was specified and not None
try:
ar = np.moveaxis(ar, axis, 0)
except np.exceptions.AxisError:
# this removes the "axis1" or "axis2" prefix from the error message
raise np.exceptions.AxisError(axis, ar.ndim) from None
inverse_shape = [1] * ar.ndim
inverse_shape[axis] = ar.shape[0]
# Must reshape to a contiguous 2D array for this to work...
orig_shape, orig_dtype = ar.shape, ar.dtype
ar = ar.reshape(orig_shape[0], np.prod(orig_shape[1:], dtype=np.intp))
ar = np.ascontiguousarray(ar)
dtype = [(f'f{i}', ar.dtype) for i in range(ar.shape[1])]
# At this point, `ar` has shape `(n, m)`, and `dtype` is a structured
# data type with `m` fields where each field has the data type of `ar`.
# In the following, we create the array `consolidated`, which has
# shape `(n,)` with data type `dtype`.
try:
if ar.shape[1] > 0:
consolidated = ar.view(dtype)
else:
# If ar.shape[1] == 0, then dtype will be `np.dtype([])`, which is
# a data type with itemsize 0, and the call `ar.view(dtype)` will
# fail. Instead, we'll use `np.empty` to explicitly create the
# array with shape `(len(ar),)`. Because `dtype` in this case has
# itemsize 0, the total size of the result is still 0 bytes.
consolidated = np.empty(len(ar), dtype=dtype)
except TypeError as e:
# There's no good way to do this for object arrays, etc...
msg = 'The axis argument to unique is not supported for dtype {dt}'
raise TypeError(msg.format(dt=ar.dtype)) from e
def reshape_uniq(uniq):
n = len(uniq)
uniq = uniq.view(orig_dtype)
uniq = uniq.reshape(n, *orig_shape[1:])
uniq = np.moveaxis(uniq, 0, axis)
return uniq
output = _unique1d(consolidated, return_index,
return_inverse, return_counts,
equal_nan=equal_nan, inverse_shape=inverse_shape,
axis=axis, sorted=sorted)
output = (reshape_uniq(output[0]),) + output[1:]
return _unpack_tuple(output)
def _unique1d(ar, return_index=False, return_inverse=False,
return_counts=False, *, equal_nan=True, inverse_shape=None,
axis=None, sorted=True):
"""
Find the unique elements of an array, ignoring shape.
Uses a hash table to find the unique elements if possible.
"""
ar = np.asanyarray(ar).flatten()
if len(ar.shape) != 1:
# np.matrix, and maybe some other array subclasses, insist on keeping
# two dimensions for all operations. Coerce to an ndarray in such cases.
ar = np.asarray(ar).flatten()
optional_indices = return_index or return_inverse
# masked arrays are not supported yet.
if not optional_indices and not return_counts and not np.ma.is_masked(ar):
# First we convert the array to a numpy array, later we wrap it back
# in case it was a subclass of numpy.ndarray.
conv = _array_converter(ar)
ar_, = conv
if (hash_unique := _unique_hash(ar_, equal_nan=equal_nan)) \
is not NotImplemented:
if sorted:
hash_unique.sort()
# We wrap the result back in case it was a subclass of numpy.ndarray.
return (conv.wrap(hash_unique),)
# If we don't use the hash map, we use the slower sorting method.
if optional_indices:
perm = ar.argsort(kind='mergesort' if return_index else 'quicksort')
aux = ar[perm]
else:
ar.sort()
aux = ar
mask = np.empty(aux.shape, dtype=np.bool)
mask[:1] = True
# Keep the last element typed so isnan handles StringDType's NA sentinel.
if (equal_nan and aux.shape[0] > 0 and aux.dtype.kind in "cfmMT" and
np.isnan(aux[-1:])[0]):
if aux.dtype.kind in "cT":
# Complex NaNs and StringDType's NaN-like sentinels are equivalent.
aux_firstnan = np.searchsorted(np.isnan(aux), True, side='left')
else:
aux_firstnan = np.searchsorted(aux, aux[-1], side='left')
if aux_firstnan > 0:
mask[1:aux_firstnan] = (
aux[1:aux_firstnan] != aux[:aux_firstnan - 1])
mask[aux_firstnan] = True
mask[aux_firstnan + 1:] = False
else:
mask[1:] = aux[1:] != aux[:-1]
ret = (aux[mask],)
if return_index:
ret += (perm[mask],)
if return_inverse:
imask = np.cumsum(mask) - 1
inv_idx = np.empty(mask.shape, dtype=np.intp)
inv_idx[perm] = imask
ret += (inv_idx.reshape(inverse_shape) if axis is None else inv_idx,)
if return_counts:
idx = np.concatenate(np.nonzero(mask) + ([mask.size],))
ret += (np.diff(idx),)
return ret
# Array API set functions
class UniqueAllResult(NamedTuple):
values: np.ndarray
indices: np.ndarray
inverse_indices: np.ndarray
counts: np.ndarray
class UniqueCountsResult(NamedTuple):
values: np.ndarray
counts: np.ndarray
class UniqueInverseResult(NamedTuple):
values: np.ndarray
inverse_indices: np.ndarray
def _unique_all_dispatcher(x, /):
return (x,)
@array_function_dispatch(_unique_all_dispatcher)
def unique_all(x):
"""
Find the unique elements of an array, and counts, inverse, and indices.
This function is an Array API compatible alternative to::
np.unique(x, return_index=True, return_inverse=True,
return_counts=True, equal_nan=False, sorted=False)
but returns a namedtuple for easier access to each output.
.. note::
This function currently always returns a sorted result, however,
this could change in any NumPy minor release.
Parameters
----------
x : array_like
Input array. It will be flattened if it is not already 1-D.
Returns
-------
out : namedtuple
The result containing:
* values - The unique elements of an input array.
* indices - The first occurring indices for each unique element.
* inverse_indices - The indices from the set of unique elements
that reconstruct `x`.
* counts - The corresponding counts for each unique element.
See Also
--------
unique : Find the unique elements of an array.
Examples
--------
>>> import numpy as np
>>> x = [1, 1, 2]
>>> uniq = np.unique_all(x)
>>> uniq.values
array([1, 2])
>>> uniq.indices
array([0, 2])
>>> uniq.inverse_indices
array([0, 0, 1])
>>> uniq.counts
array([2, 1])
"""
result = unique(
x,
return_index=True,
return_inverse=True,
return_counts=True,
equal_nan=False,
)
return UniqueAllResult(*result)
def _unique_counts_dispatcher(x, /):
return (x,)
@array_function_dispatch(_unique_counts_dispatcher)
def unique_counts(x):
"""
Find the unique elements and counts of an input array `x`.
This function is an Array API compatible alternative to::
np.unique(x, return_counts=True, equal_nan=False, sorted=False)
but returns a namedtuple for easier access to each output.
.. note::
This function currently always returns a sorted result, however,
this could change in any NumPy minor release.
Parameters
----------
x : array_like
Input array. It will be flattened if it is not already 1-D.
Returns
-------
out : namedtuple
The result containing:
* values - The unique elements of an input array.
* counts - The corresponding counts for each unique element.
See Also
--------
unique : Find the unique elements of an array.
Examples
--------
>>> import numpy as np
>>> x = [1, 1, 2]
>>> uniq = np.unique_counts(x)
>>> uniq.values
array([1, 2])
>>> uniq.counts
array([2, 1])
"""
result = unique(
x,
return_index=False,
return_inverse=False,
return_counts=True,
equal_nan=False,
)
return UniqueCountsResult(*result)
def _unique_inverse_dispatcher(x, /):
return (x,)
@array_function_dispatch(_unique_inverse_dispatcher)
def unique_inverse(x):
"""
Find the unique elements of `x` and indices to reconstruct `x`.
This function is an Array API compatible alternative to::
np.unique(x, return_inverse=True, equal_nan=False, sorted=False)
but returns a namedtuple for easier access to each output.
.. note::
This function currently always returns a sorted result, however,
this could change in any NumPy minor release.
Parameters
----------
x : array_like
Input array. It will be flattened if it is not already 1-D.
Returns
-------
out : namedtuple
The result containing:
* values - The unique elements of an input array.
* inverse_indices - The indices from the set of unique elements
that reconstruct `x`.
See Also
--------
unique : Find the unique elements of an array.
Examples
--------
>>> import numpy as np
>>> x = [1, 1, 2]
>>> uniq = np.unique_inverse(x)
>>> uniq.values
array([1, 2])
>>> uniq.inverse_indices
array([0, 0, 1])
"""
result = unique(
x,
return_index=False,
return_inverse=True,
return_counts=False,
equal_nan=False,
)
return UniqueInverseResult(*result)
def _unique_values_dispatcher(x, /):
return (x,)
@array_function_dispatch(_unique_values_dispatcher)
def unique_values(x):
"""
Returns the unique elements of an input array `x`.
This function is an Array API compatible alternative to::
np.unique(x, equal_nan=False, sorted=False)
.. versionchanged:: 2.3
The algorithm was changed to a faster one that does not rely on
sorting, and hence the results are no longer implicitly sorted.
Parameters
----------
x : array_like
Input array. It will be flattened if it is not already 1-D.
Returns
-------
out : ndarray
The unique elements of an input array.
See Also
--------
unique : Find the unique elements of an array.
Examples
--------
>>> import numpy as np
>>> np.unique_values([1, 1, 2])
array([1, 2]) # may vary
"""
return unique(
x,
return_index=False,
return_inverse=False,
return_counts=False,
equal_nan=False,
sorted=False,
)
def _intersect1d_dispatcher(
ar1, ar2, assume_unique=None, return_indices=None):
return (ar1, ar2)
@array_function_dispatch(_intersect1d_dispatcher)
def intersect1d(ar1, ar2, assume_unique=False, return_indices=False):
"""
Find the intersection of two arrays.
Return the sorted, unique values that are in both of the input arrays.
Parameters
----------
ar1, ar2 : array_like
Input arrays. Will be flattened if not already 1D.
assume_unique : bool
If True, the input arrays are both assumed to be unique, which
can speed up the calculation. If True but ``ar1`` or ``ar2`` are not
unique, incorrect results and out-of-bounds indices could result.
Default is False.
return_indices : bool
If True, the indices which correspond to the intersection of the two
arrays are returned. The first instance of a value is used if there are
multiple. Default is False.
Returns
-------
intersect1d : ndarray
Sorted 1D array of common and unique elements.
comm1 : ndarray
The indices of the first occurrences of the common values in `ar1`.
Only provided if `return_indices` is True.
comm2 : ndarray
The indices of the first occurrences of the common values in `ar2`.
Only provided if `return_indices` is True.
Examples
--------
>>> import numpy as np
>>> np.intersect1d([1, 3, 4, 3], [3, 1, 2, 1])
array([1, 3])
To intersect more than two arrays, use functools.reduce:
>>> from functools import reduce
>>> reduce(np.intersect1d, ([1, 3, 4, 3], [3, 1, 2, 1], [6, 3, 4, 2]))
array([3])
To return the indices of the values common to the input arrays
along with the intersected values:
>>> x = np.array([1, 1, 2, 3, 4])
>>> y = np.array([2, 1, 4, 6])
>>> xy, x_ind, y_ind = np.intersect1d(x, y, return_indices=True)
>>> x_ind, y_ind
(array([0, 2, 4]), array([1, 0, 2]))
>>> xy, x[x_ind], y[y_ind]
(array([1, 2, 4]), array([1, 2, 4]), array([1, 2, 4]))
"""
ar1 = np.asanyarray(ar1)
ar2 = np.asanyarray(ar2)
if not assume_unique:
if return_indices:
ar1, ind1 = unique(ar1, return_index=True)
ar2, ind2 = unique(ar2, return_index=True)
else:
ar1 = unique(ar1)
ar2 = unique(ar2)
else:
ar1 = ar1.ravel()
ar2 = ar2.ravel()
aux = np.concatenate((ar1, ar2))
if return_indices:
aux_sort_indices = np.argsort(aux, kind='mergesort')
aux = aux[aux_sort_indices]
else:
aux.sort()
mask = aux[1:] == aux[:-1]
int1d = aux[:-1][mask]
if return_indices:
ar1_indices = aux_sort_indices[:-1][mask]
ar2_indices = aux_sort_indices[1:][mask] - ar1.size
if not assume_unique:
ar1_indices = ind1[ar1_indices]
ar2_indices = ind2[ar2_indices]
return int1d, ar1_indices, ar2_indices
else:
return int1d
def _setxor1d_dispatcher(ar1, ar2, assume_unique=None):
return (ar1, ar2)
@array_function_dispatch(_setxor1d_dispatcher)
def setxor1d(ar1, ar2, assume_unique=False):
"""
Find the set exclusive-or of two arrays.
Return the sorted, unique values that are in only one (not both) of the
input arrays.
Parameters
----------
ar1, ar2 : array_like
Input arrays.
assume_unique : bool
If True, the input arrays are both assumed to be unique, which
can speed up the calculation. Default is False.
Returns
-------
setxor1d : ndarray
Sorted 1D array of unique values that are in only one of the input
arrays.
Examples
--------
>>> import numpy as np
>>> a = np.array([1, 2, 3, 2, 4])
>>> b = np.array([2, 3, 5, 7, 5])
>>> np.setxor1d(a,b)
array([1, 4, 5, 7])
"""
if not assume_unique:
ar1 = unique(ar1)
ar2 = unique(ar2)
aux = np.concatenate((ar1, ar2), axis=None)
if aux.size == 0:
return aux
aux.sort()
flag = np.concatenate(([True], aux[1:] != aux[:-1], [True]))
return aux[flag[1:] & flag[:-1]]
def _isin(ar1, ar2, assume_unique=False, invert=False, *, kind=None):
# Ravel both arrays, behavior for the first array could be different
ar1 = np.asarray(ar1).ravel()
ar2 = np.asarray(ar2).ravel()
# Ensure that iteration through object arrays yields size-1 arrays
if ar2.dtype == object:
ar2 = ar2.reshape(-1, 1)
if kind not in {None, 'sort', 'table'}:
raise ValueError(
f"Invalid kind: '{kind}'. Please use None, 'sort' or 'table'.")
# Can use the table method if all arrays are integers or boolean:
is_int_arrays = all(ar.dtype.kind in ("u", "i", "b") for ar in (ar1, ar2))
use_table_method = is_int_arrays and kind in {None, 'table'}
if use_table_method:
if ar2.size == 0:
if invert:
return np.ones_like(ar1, dtype=bool)
else:
return np.zeros_like(ar1, dtype=bool)
# Convert booleans to uint8 so we can use the fast integer algorithm
if ar1.dtype == bool:
ar1 = ar1.astype(np.uint8)
if ar2.dtype == bool:
ar2 = ar2.astype(np.uint8)
ar2_min = int(np.min(ar2))
ar2_max = int(np.max(ar2))
ar2_range = ar2_max - ar2_min
# Constraints on whether we can actually use the table method:
# 1. Assert memory usage is not too large
below_memory_constraint = ar2_range <= 6 * (ar1.size + ar2.size)
# 2. Check overflows for (ar2 - ar2_min); dtype=ar2.dtype
range_safe_from_overflow = ar2_range <= np.iinfo(ar2.dtype).max
# Optimal performance is for approximately
# log10(size) > (log10(range) - 2.27) / 0.927.
# However, here we set the requirement that by default
# the intermediate array can only be 6x
# the combined memory allocation of the original
# arrays. See discussion on
# https://github.com/numpy/numpy/pull/12065.
if (
range_safe_from_overflow and
(below_memory_constraint or kind == 'table')
):
if invert:
outgoing_array = np.ones_like(ar1, dtype=bool)
else:
outgoing_array = np.zeros_like(ar1, dtype=bool)
# Make elements 1 where the integer exists in ar2
if invert:
isin_helper_ar = np.ones(ar2_range + 1, dtype=bool)
isin_helper_ar[ar2 - ar2_min] = 0
else:
isin_helper_ar = np.zeros(ar2_range + 1, dtype=bool)
isin_helper_ar[ar2 - ar2_min] = 1
# Mask out elements we know won't work
basic_mask = (ar1 <= ar2_max) & (ar1 >= ar2_min)
in_range_ar1 = ar1[basic_mask]
if in_range_ar1.size == 0:
# Nothing more to do, since all values are out of range.
return outgoing_array
# Unfortunately, ar2_min can be out of range for `intp` even
# if the calculation result must fit in range (and be positive).
# In that case, use ar2.dtype which must work for all unmasked
# values.
try:
ar2_min = np.array(ar2_min, dtype=np.intp)
dtype = np.intp
except OverflowError:
dtype = ar2.dtype
out = np.empty_like(in_range_ar1, dtype=np.intp)
outgoing_array[basic_mask] = isin_helper_ar[
np.subtract(in_range_ar1, ar2_min, dtype=dtype,
out=out, casting="unsafe")]
return outgoing_array
elif kind == 'table': # not range_safe_from_overflow
raise RuntimeError(
"You have specified kind='table', "
"but the range of values in `ar2` or `ar1` exceed the "
"maximum integer of the datatype. "
"Please set `kind` to None or 'sort'."
)
elif kind == 'table':
raise ValueError(
"The 'table' method is only "
"supported for boolean or integer arrays. "
"Please select 'sort' or None for kind."
)
string_dtype = None
if (ar1.dtype.kind == "T" or ar2.dtype.kind == "T") and (
ar1.dtype.kind in "TU" and ar2.dtype.kind in "TU"):
try:
# promote to the result dtype so we can use the fast hashing path
string_dtype = np.result_type(ar1, ar2)
except TypeError:
# fall back to slow sorting path with e.g. ar1.na_object == None
# and ar2.na_object == np.nan
pass
# Check if one of the arrays may contain arbitrary objects
contains_object = (ar1.dtype.hasobject or ar2.dtype.hasobject) and (
string_dtype is None)
scalar_comparisons_are_faster = len(ar2) < 10 * len(ar1) ** 0.145
result = None
# Remove non-NaN missing values before sorting. Non-string sentinels
# cannot be ordered with strings. String sentinels are sortable, but
# filtering is faster when missing values are common and adds only a
# small overhead otherwise.
if (not scalar_comparisons_are_faster and string_dtype is not None and
string_dtype._has_na and not string_dtype._has_nan_na):
na = np.asarray(string_dtype.na_object, dtype=string_dtype)
missing1, missing2 = ar1 == na, ar2 == na
has_missing2 = missing2.any()
if missing1.any():
result = np.full(
ar1.shape, has_missing2 != invert, dtype=bool)
valid1 = ~missing1
ar1 = ar1[valid1]
if has_missing2:
ar2 = ar2[~missing2]
# Filtering can make scalar comparisons cheaper than sorting.
scalar_comparisons_are_faster = len(ar2) < 10 * len(ar1) ** 0.145
# Use direct comparisons for few candidates or arbitrary objects, which
# cannot be sorted reliably.
if scalar_comparisons_are_faster or contains_object:
if string_dtype is not None:
# StringDType scalars are str or na_object, so ensure iteration
# always produces arrays this could be deleted if StringDType ever
# grew a NumPy scalar type
ar2 = ar2.reshape(-1, 1)
if ar2.dtype.kind == "T" and ar2.dtype._has_nan_na:
na_object = ar2.dtype.na_object
ar2 = (a for a in ar2 if a[0] is not na_object)
if invert:
mask = np.ones(len(ar1), dtype=bool)
for a in ar2:
mask &= (ar1 != a)
else:
mask = np.zeros(len(ar1), dtype=bool)
for a in ar2:
mask |= (ar1 == a)
else:
mask = _isin_sorting(ar1, ar2, assume_unique, invert)
if result is not None:
result[valid1] = mask
return result
return mask
def _isin_sorting(ar1, ar2, assume_unique, invert):
if not assume_unique:
ar1, rev_idx = np.unique(ar1, return_inverse=True)
ar2 = np.unique(ar2)
ar = np.concatenate((ar1, ar2))
# We need this to be a stable sort, so always use 'mergesort'
# here. The values from the first array should always come before
# the values from the second array.
order = ar.argsort(kind='mergesort')
sar = ar[order]
if invert:
bool_ar = (sar[1:] != sar[:-1])
else:
bool_ar = (sar[1:] == sar[:-1])
flag = np.concatenate((bool_ar, [invert]))
ret = np.empty(ar.shape, dtype=bool)
ret[order] = flag
if assume_unique:
return ret[:len(ar1)]
else:
return ret[rev_idx]
def _isin_dispatcher(element, test_elements, assume_unique=None, invert=None,