-
-
Notifications
You must be signed in to change notification settings - Fork 12.5k
Expand file tree
/
Copy pathcore.py
More file actions
9000 lines (7573 loc) · 285 KB
/
Copy pathcore.py
File metadata and controls
9000 lines (7573 loc) · 285 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
"""
numpy.ma : a package to handle missing or invalid values.
This package was initially written for numarray by Paul F. Dubois
at Lawrence Livermore National Laboratory.
In 2006, the package was completely rewritten by Pierre Gerard-Marchant
(University of Georgia) to make the MaskedArray class a subclass of ndarray,
and to improve support of structured arrays.
Copyright 1999, 2000, 2001 Regents of the University of California.
Released for unlimited redistribution.
* Adapted for numpy_core 2005 by Travis Oliphant and (mainly) Paul Dubois.
* Subclassing of the base `ndarray` 2006 by Pierre Gerard-Marchant
(pgmdevlist_AT_gmail_DOT_com)
* Improvements suggested by Reggie Dugard (reggie_AT_merfinllc_DOT_com)
.. moduleauthor:: Pierre Gerard-Marchant
"""
import builtins
import datetime as dt
import functools
import inspect
import operator
import re
import textwrap
import warnings
import numpy as np
import numpy._core.numerictypes as ntypes
import numpy._core.umath as umath
from numpy import (
_NoValue,
amax,
amin,
angle,
array as narray,
bool_,
expand_dims,
finfo, # noqa: F401
iinfo, # noqa: F401
iscomplexobj,
ndarray,
)
from numpy._core import multiarray as mu
from numpy._core.numeric import normalize_axis_tuple
from numpy._utils import set_module
__all__ = [
'MAError', 'MaskError', 'MaskType', 'MaskedArray', 'abs', 'absolute',
'add', 'all', 'allclose', 'allequal', 'alltrue', 'amax', 'amin',
'angle', 'anom', 'anomalies', 'any', 'append', 'arange', 'arccos',
'arccosh', 'arcsin', 'arcsinh', 'arctan', 'arctan2', 'arctanh',
'argmax', 'argmin', 'argsort', 'around', 'array', 'asanyarray',
'asarray', 'bitwise_and', 'bitwise_or', 'bitwise_xor', 'bool_', 'ceil',
'choose', 'clip', 'common_fill_value', 'compress', 'compressed',
'concatenate', 'conjugate', 'convolve', 'copy', 'correlate', 'cos', 'cosh',
'count', 'cumprod', 'cumsum', 'default_fill_value', 'diag', 'diagonal',
'diff', 'divide', 'empty', 'empty_like', 'equal', 'exp',
'expand_dims', 'fabs', 'filled', 'fix_invalid', 'flatten_mask',
'flatten_structured_array', 'floor', 'floor_divide', 'fmod',
'frombuffer', 'fromflex', 'fromfunction', 'getdata', 'getmask',
'getmaskarray', 'greater', 'greater_equal', 'harden_mask', 'hypot',
'identity', 'ids', 'indices', 'inner', 'innerproduct', 'isMA',
'isMaskedArray', 'is_mask', 'is_masked', 'isarray', 'left_shift',
'less', 'less_equal', 'log', 'log10', 'log2',
'logical_and', 'logical_not', 'logical_or', 'logical_xor', 'make_mask',
'make_mask_descr', 'make_mask_none', 'mask_or', 'masked',
'masked_array', 'masked_equal', 'masked_greater',
'masked_greater_equal', 'masked_inside', 'masked_invalid',
'masked_less', 'masked_less_equal', 'masked_not_equal',
'masked_object', 'masked_outside', 'masked_print_option',
'masked_singleton', 'masked_values', 'masked_where', 'max', 'maximum',
'maximum_fill_value', 'mean', 'min', 'minimum', 'minimum_fill_value',
'mod', 'multiply', 'mvoid', 'ndim', 'negative', 'nomask', 'nonzero',
'not_equal', 'ones', 'ones_like', 'outer', 'outerproduct', 'power', 'prod',
'product', 'ptp', 'put', 'putmask', 'ravel', 'remainder',
'repeat', 'reshape', 'resize', 'right_shift', 'round', 'round_',
'set_fill_value', 'shape', 'sin', 'sinh', 'size', 'soften_mask',
'sometrue', 'sort', 'sqrt', 'squeeze', 'std', 'subtract', 'sum',
'swapaxes', 'take', 'tan', 'tanh', 'trace', 'transpose', 'true_divide',
'var', 'where', 'zeros', 'zeros_like',
]
MaskType = np.bool
nomask = MaskType(0)
class MaskedArrayFutureWarning(FutureWarning):
pass
def _deprecate_argsort_axis(arr):
"""
Adjust the axis passed to argsort, warning if necessary
Parameters
----------
arr
The array which argsort was called on
np.ma.argsort has a long-term bug where the default of the axis argument
is wrong (gh-8701), which now must be kept for backwards compatibility.
Thankfully, this only makes a difference when arrays are 2- or more-
dimensional, so we only need a warning then.
"""
if arr.ndim <= 1:
# no warning needed - but switch to -1 anyway, to avoid surprising
# subclasses, which are more likely to implement scalar axes.
return -1
else:
# 2017-04-11, Numpy 1.13.0, gh-8701: warn on axis default
warnings.warn(
"In the future the default for argsort will be axis=-1, not the "
"current None, to match its documentation and np.argsort. "
"Explicitly pass -1 or None to silence this warning.",
MaskedArrayFutureWarning, stacklevel=3)
return None
def doc_note(initialdoc, note):
"""
Adds a Notes section to an existing docstring.
"""
if initialdoc is None:
return
if note is None:
return initialdoc
notesplit = re.split(r'\n\s*?Notes\n\s*?-----', inspect.cleandoc(initialdoc))
notedoc = f"\n\nNotes\n-----\n{inspect.cleandoc(note)}\n"
return ''.join(notesplit[:1] + [notedoc] + notesplit[1:])
###############################################################################
# Exceptions #
###############################################################################
class MAError(Exception):
"""
Class for masked array related errors.
"""
pass
class MaskError(MAError):
"""
Class for mask related errors.
"""
pass
###############################################################################
# Filling options #
###############################################################################
# b: boolean - c: complex - f: floats - i: integer - O: object - S: string
default_filler = {'b': True,
'c': 1.e20 + 0.0j,
'f': 1.e20,
'i': 999999,
'O': '?',
'S': b'N/A',
'u': 999999,
'V': b'???',
'U': 'N/A',
'T': 'N/A'
}
# Add datetime64 and timedelta64 types
for v in ["Y", "M", "W", "D", "h", "m", "s", "ms", "us", "ns", "ps",
"fs", "as"]:
default_filler["M8[" + v + "]"] = np.datetime64("NaT", v)
default_filler["m8[" + v + "]"] = np.timedelta64("NaT", v)
float_types_list = [np.half, np.single, np.double, np.longdouble,
np.csingle, np.cdouble, np.clongdouble]
_minvals: dict[type, int] = {}
_maxvals: dict[type, int] = {}
for sctype in ntypes.sctypeDict.values():
scalar_dtype = np.dtype(sctype)
if scalar_dtype.kind in "Mm":
info = np.iinfo(np.int64)
min_val, max_val = info.min + 1, info.max
elif np.issubdtype(scalar_dtype, np.integer):
info = np.iinfo(sctype)
min_val, max_val = info.min, info.max
elif np.issubdtype(scalar_dtype, np.floating):
info = np.finfo(sctype)
min_val, max_val = info.min, info.max
elif scalar_dtype.kind == "b":
min_val, max_val = 0, 1
else:
min_val, max_val = None, None
_minvals[sctype] = min_val
_maxvals[sctype] = max_val
max_filler = _minvals
max_filler.update([(k, -np.inf) for k in float_types_list[:4]])
max_filler.update([(k, complex(-np.inf, -np.inf)) for k in float_types_list[-3:]])
min_filler = _maxvals
min_filler.update([(k, +np.inf) for k in float_types_list[:4]])
min_filler.update([(k, complex(+np.inf, +np.inf)) for k in float_types_list[-3:]])
del float_types_list
def _recursive_fill_value(dtype, f):
"""
Recursively produce a fill value for `dtype`, calling f on scalar dtypes
"""
if dtype.names is not None:
# We wrap into `array` here, which ensures we use NumPy cast rules
# for integer casts, this allows the use of 99999 as a fill value
# for int8.
vals = []
for name in dtype.names:
field_dtype = dtype[name]
val = _recursive_fill_value(field_dtype, f)
if np.issubdtype(field_dtype, np.datetime64):
if isinstance(val, dt.date):
val = np.datetime64(val)
val = np.array(val)
elif isinstance(val, (int, np.integer)):
val = np.array(val).astype(field_dtype)
else:
val = np.array(val)
else:
val = np.array(val)
vals.append(val)
return np.array(tuple(vals), dtype=dtype)[()] # decay to void scalar from 0d
elif dtype.subdtype:
subtype, shape = dtype.subdtype
subval = _recursive_fill_value(subtype, f)
return np.full(shape, subval)
else:
return f(dtype)
def _get_dtype_of(obj):
""" Convert the argument for *_fill_value into a dtype """
if isinstance(obj, np.dtype):
return obj
elif hasattr(obj, 'dtype'):
return obj.dtype
else:
return np.asanyarray(obj).dtype
def default_fill_value(obj):
"""
Return the default fill value for the argument object.
The default filling value depends on the datatype of the input
array or the type of the input scalar:
=========== ========
datatype default
=========== ========
bool True
int 999999
float 1.e20
complex 1.e20+0j
object '?'
string 'N/A'
StringDType 'N/A'
=========== ========
For structured types, a structured scalar is returned, with each field the
default fill value for its type.
For subarray types, the fill value is an array of the same size containing
the default scalar fill value.
Parameters
----------
obj : ndarray, dtype or scalar
The array data-type or scalar for which the default fill value
is returned.
Returns
-------
fill_value : scalar
The default fill value.
Examples
--------
>>> import numpy as np
>>> np.ma.default_fill_value(1)
999999
>>> np.ma.default_fill_value(np.array([1.1, 2., np.pi]))
1e+20
>>> np.ma.default_fill_value(np.dtype(complex))
(1e+20+0j)
"""
def _scalar_fill_value(dtype):
if dtype.kind in 'Mm':
return default_filler.get(dtype.str[1:], '?')
else:
return default_filler.get(dtype.kind, '?')
dtype = _get_dtype_of(obj)
return _recursive_fill_value(dtype, _scalar_fill_value)
def _extremum_fill_value(obj, extremum, extremum_name):
def _scalar_fill_value(dtype):
try:
return extremum[dtype.type]
except KeyError as e:
raise TypeError(
f"Unsuitable type {dtype} for calculating {extremum_name}."
) from None
dtype = _get_dtype_of(obj)
return _recursive_fill_value(dtype, _scalar_fill_value)
def minimum_fill_value(obj):
"""
Return the maximum value that can be represented by the dtype of an object.
This function is useful for calculating a fill value suitable for
taking the minimum of an array with a given dtype.
Parameters
----------
obj : ndarray, dtype or scalar
An object that can be queried for it's numeric type.
Returns
-------
val : scalar
The maximum representable value.
Raises
------
TypeError
If `obj` isn't a suitable numeric type.
See Also
--------
maximum_fill_value : The inverse function.
set_fill_value : Set the filling value of a masked array.
MaskedArray.fill_value : Return current fill value.
Examples
--------
>>> import numpy as np
>>> import numpy.ma as ma
>>> a = np.int8()
>>> ma.minimum_fill_value(a)
127
>>> a = np.int32()
>>> ma.minimum_fill_value(a)
2147483647
An array of numeric data can also be passed.
>>> a = np.array([1, 2, 3], dtype=np.int8)
>>> ma.minimum_fill_value(a)
127
>>> a = np.array([1, 2, 3], dtype=np.float32)
>>> ma.minimum_fill_value(a)
inf
"""
return _extremum_fill_value(obj, min_filler, "minimum")
def maximum_fill_value(obj):
"""
Return the minimum value that can be represented by the dtype of an object.
This function is useful for calculating a fill value suitable for
taking the maximum of an array with a given dtype.
Parameters
----------
obj : ndarray, dtype or scalar
An object that can be queried for it's numeric type.
Returns
-------
val : scalar
The minimum representable value.
Raises
------
TypeError
If `obj` isn't a suitable numeric type.
See Also
--------
minimum_fill_value : The inverse function.
set_fill_value : Set the filling value of a masked array.
MaskedArray.fill_value : Return current fill value.
Examples
--------
>>> import numpy as np
>>> import numpy.ma as ma
>>> a = np.int8()
>>> ma.maximum_fill_value(a)
-128
>>> a = np.int32()
>>> ma.maximum_fill_value(a)
-2147483648
An array of numeric data can also be passed.
>>> a = np.array([1, 2, 3], dtype=np.int8)
>>> ma.maximum_fill_value(a)
-128
>>> a = np.array([1, 2, 3], dtype=np.float32)
>>> ma.maximum_fill_value(a)
-inf
"""
return _extremum_fill_value(obj, max_filler, "maximum")
def _recursive_set_fill_value(fillvalue, dt):
"""
Create a fill value for a structured dtype.
Parameters
----------
fillvalue : scalar or array_like
Scalar or array representing the fill value. If it is of shorter
length than the number of fields in dt, it will be resized.
dt : dtype
The structured dtype for which to create the fill value.
Returns
-------
val : tuple
A tuple of values corresponding to the structured fill value.
"""
fillvalue = np.resize(fillvalue, len(dt.names))
output_value = []
for (fval, name) in zip(fillvalue, dt.names):
cdtype = dt[name]
if cdtype.subdtype:
cdtype = cdtype.subdtype[0]
if cdtype.names is not None:
output_value.append(tuple(_recursive_set_fill_value(fval, cdtype)))
else:
output_value.append(np.array(fval, dtype=cdtype).item())
return tuple(output_value)
def _check_fill_value(fill_value, ndtype):
"""
Private function validating the given `fill_value` for the given dtype.
If fill_value is None, it is set to the default corresponding to the dtype.
If fill_value is not None, its value is forced to the given dtype.
The result is always a 0d array.
"""
ndtype = np.dtype(ndtype)
if fill_value is None:
fill_value = default_fill_value(ndtype)
# TODO: It seems better to always store a valid fill_value, the oddity
# about is that `_fill_value = None` would behave even more
# different then.
# (e.g. this allows arr_uint8.astype(int64) to have the default
# fill value again...)
# The one thing that changed in 2.0/2.1 around cast safety is that the
# default `int(99...)` is not a same-kind cast anymore, so if we
# have a uint, use the default uint.
if ndtype.kind == "u":
fill_value = np.uint(fill_value)
elif ndtype.names is not None:
if isinstance(fill_value, (ndarray, np.void)):
try:
fill_value = np.asarray(fill_value, dtype=ndtype)
except ValueError as e:
err_msg = "Unable to transform %s to dtype %s"
raise ValueError(err_msg % (fill_value, ndtype)) from e
else:
fill_value = np.asarray(fill_value, dtype=object)
fill_value = np.array(_recursive_set_fill_value(fill_value, ndtype),
dtype=ndtype)
elif isinstance(fill_value, str) and (ndtype.char not in 'OSTVU'):
# Note this check doesn't work if fill_value is not a scalar
err_msg = "Cannot set fill value of string with array of dtype %s"
raise TypeError(err_msg % ndtype)
else:
# In case we want to convert 1e20 to int.
# Also in case of converting string arrays.
try:
fill_value = np.asarray(fill_value, dtype=ndtype)
except (OverflowError, ValueError) as e:
# Raise TypeError instead of OverflowError or ValueError.
# OverflowError is seldom used, and the real problem here is
# that the passed fill_value is not compatible with the ndtype.
err_msg = "Cannot convert fill_value %s to dtype %s"
raise TypeError(err_msg % (fill_value, ndtype)) from e
return np.array(fill_value)
def set_fill_value(a, fill_value):
"""
Set the filling value of a, if a is a masked array.
This function changes the fill value of the masked array `a` in place.
If `a` is not a masked array, the function returns silently, without
doing anything.
Parameters
----------
a : array_like
Input array.
fill_value : dtype
Filling value. A consistency test is performed to make sure
the value is compatible with the dtype of `a`.
Returns
-------
None
Nothing returned by this function.
See Also
--------
maximum_fill_value : Return the default fill value for a dtype.
MaskedArray.fill_value : Return current fill value.
MaskedArray.set_fill_value : Equivalent method.
Examples
--------
>>> import numpy as np
>>> import numpy.ma as ma
>>> a = np.arange(5)
>>> a
array([0, 1, 2, 3, 4])
>>> a = ma.masked_where(a < 3, a)
>>> a
masked_array(data=[--, --, --, 3, 4],
mask=[ True, True, True, False, False],
fill_value=999999)
>>> ma.set_fill_value(a, -999)
>>> a
masked_array(data=[--, --, --, 3, 4],
mask=[ True, True, True, False, False],
fill_value=-999)
Nothing happens if `a` is not a masked array.
>>> a = list(range(5))
>>> a
[0, 1, 2, 3, 4]
>>> ma.set_fill_value(a, 100)
>>> a
[0, 1, 2, 3, 4]
>>> a = np.arange(5)
>>> a
array([0, 1, 2, 3, 4])
>>> ma.set_fill_value(a, 100)
>>> a
array([0, 1, 2, 3, 4])
"""
if isinstance(a, MaskedArray):
a.set_fill_value(fill_value)
def get_fill_value(a):
"""
Return the filling value of a, if any. Otherwise, returns the
default filling value for that type.
"""
if isinstance(a, MaskedArray):
result = a.fill_value
else:
result = default_fill_value(a)
return result
def common_fill_value(a, b):
"""
Return the common filling value of two masked arrays, if any.
If ``a.fill_value == b.fill_value``, return the fill value,
otherwise return None.
Parameters
----------
a, b : MaskedArray
The masked arrays for which to compare fill values.
Returns
-------
fill_value : scalar or None
The common fill value, or None.
Examples
--------
>>> import numpy as np
>>> x = np.ma.array([0, 1.], fill_value=3)
>>> y = np.ma.array([0, 1.], fill_value=3)
>>> np.ma.common_fill_value(x, y)
3.0
"""
t1 = get_fill_value(a)
t2 = get_fill_value(b)
if t1 == t2:
return t1
return None
def filled(a, fill_value=None):
"""
Return input as an `~numpy.ndarray`, with masked values replaced by
`fill_value`.
If `a` is not a `MaskedArray`, `a` itself is returned.
If `a` is a `MaskedArray` with no masked values, then ``a.data`` is
returned.
If `a` is a `MaskedArray` and `fill_value` is None, `fill_value` is set to
``a.fill_value``.
Parameters
----------
a : MaskedArray or array_like
An input object.
fill_value : array_like, optional.
Can be scalar or non-scalar. If non-scalar, the
resulting filled array should be broadcastable
over input array. Default is None.
Returns
-------
a : ndarray
The filled array.
See Also
--------
compressed
Examples
--------
>>> import numpy as np
>>> import numpy.ma as ma
>>> x = ma.array(np.arange(9).reshape(3, 3), mask=[[1, 0, 0],
... [1, 0, 0],
... [0, 0, 0]])
>>> x.filled()
array([[999999, 1, 2],
[999999, 4, 5],
[ 6, 7, 8]])
>>> x.filled(fill_value=333)
array([[333, 1, 2],
[333, 4, 5],
[ 6, 7, 8]])
>>> x.filled(fill_value=np.arange(3))
array([[0, 1, 2],
[0, 4, 5],
[6, 7, 8]])
"""
if hasattr(a, 'filled'):
return a.filled(fill_value)
elif isinstance(a, ndarray):
# Should we check for contiguity ? and a.flags['CONTIGUOUS']:
return a
elif isinstance(a, dict):
return np.array(a, 'O')
else:
return np.array(a)
def get_masked_subclass(*arrays):
"""
Return the youngest subclass of MaskedArray from a list of (masked) arrays.
In case of siblings, the first listed takes over.
"""
if len(arrays) == 1:
arr = arrays[0]
if isinstance(arr, MaskedArray):
rcls = type(arr)
else:
rcls = MaskedArray
else:
arrcls = [type(a) for a in arrays]
rcls = arrcls[0]
if not issubclass(rcls, MaskedArray):
rcls = MaskedArray
for cls in arrcls[1:]:
if issubclass(cls, rcls):
rcls = cls
# Don't return MaskedConstant as result: revert to MaskedArray
if rcls.__name__ == 'MaskedConstant':
return MaskedArray
return rcls
def getdata(a, subok=True):
"""
Return the data of a masked array as an ndarray.
Return the data of `a` (if any) as an ndarray if `a` is a ``MaskedArray``,
else return `a` as an ndarray or subclass (depending on `subok`) if not.
Parameters
----------
a : array_like
Input ``MaskedArray``, alternatively an ndarray or a subclass thereof.
subok : bool
Whether to force the output to be a `pure` ndarray (False) or to
return a subclass of ndarray if appropriate (True, default).
See Also
--------
getmask : Return the mask of a masked array, or nomask.
getmaskarray : Return the mask of a masked array, or full array of False.
Examples
--------
>>> import numpy as np
>>> import numpy.ma as ma
>>> a = ma.masked_equal([[1,2],[3,4]], 2)
>>> a
masked_array(
data=[[1, --],
[3, 4]],
mask=[[False, True],
[False, False]],
fill_value=2)
>>> ma.getdata(a)
array([[1, 2],
[3, 4]])
Equivalently use the ``MaskedArray`` `data` attribute.
>>> a.data
array([[1, 2],
[3, 4]])
"""
try:
data = a._data
except AttributeError:
data = np.array(a, copy=None, subok=subok)
if not subok:
return data.view(ndarray)
return data
get_data = getdata
def fix_invalid(a, mask=nomask, copy=True, fill_value=None):
"""
Return input with invalid data masked and replaced by a fill value.
Invalid data means values of `nan`, `inf`, etc.
Parameters
----------
a : array_like
Input array, a (subclass of) ndarray.
mask : sequence, optional
Mask. Must be convertible to an array of booleans with the same
shape as `data`. True indicates a masked (i.e. invalid) data.
copy : bool, optional
Whether to use a copy of `a` (True) or to fix `a` in place (False).
Default is True.
fill_value : scalar, optional
Value used for fixing invalid data. Default is None, in which case
the ``a.fill_value`` is used.
Returns
-------
b : MaskedArray
The input array with invalid entries fixed.
Notes
-----
A copy is performed by default.
Examples
--------
>>> import numpy as np
>>> x = np.ma.array([1., -1, np.nan, np.inf], mask=[1] + [0]*3)
>>> x
masked_array(data=[--, -1.0, nan, inf],
mask=[ True, False, False, False],
fill_value=1e+20)
>>> np.ma.fix_invalid(x)
masked_array(data=[--, -1.0, --, --],
mask=[ True, False, True, True],
fill_value=1e+20)
>>> fixed = np.ma.fix_invalid(x)
>>> fixed.data
array([ 1.e+00, -1.e+00, 1.e+20, 1.e+20])
>>> x.data
array([ 1., -1., nan, inf])
"""
a = masked_array(a, copy=copy, mask=mask, subok=True)
invalid = np.logical_not(np.isfinite(a._data))
if not invalid.any():
return a
a._mask |= invalid
if fill_value is None:
fill_value = a.fill_value
a._data[invalid] = fill_value
return a
def is_string_or_list_of_strings(val):
return (isinstance(val, str) or
(isinstance(val, list) and val and
builtins.all(isinstance(s, str) for s in val)))
###############################################################################
# Ufuncs #
###############################################################################
ufunc_domain = {}
ufunc_fills = {}
class _DomainCheckInterval:
"""
Define a valid interval, so that :
``domain_check_interval(a,b)(x) == True`` where
``x < a`` or ``x > b``.
"""
def __init__(self, a, b):
"domain_check_interval(a,b)(x) = true where x < a or y > b"
if a > b:
(a, b) = (b, a)
self.a = a
self.b = b
def __call__(self, x):
"Execute the call behavior."
# nans at masked positions cause RuntimeWarnings, even though
# they are masked. To avoid this we suppress warnings.
with np.errstate(invalid='ignore'):
return umath.logical_or(umath.greater(x, self.b),
umath.less(x, self.a))
class _DomainTan:
"""
Define a valid interval for the `tan` function, so that:
``domain_tan(eps) = True`` where ``abs(cos(x)) < eps``
"""
def __init__(self, eps):
"domain_tan(eps) = true where abs(cos(x)) < eps)"
self.eps = eps
def __call__(self, x):
"Executes the call behavior."
with np.errstate(invalid='ignore'):
return umath.less(umath.absolute(umath.cos(x)), self.eps)
class _DomainSafeDivide:
"""
Define a domain for safe division.
"""
def __init__(self, tolerance=None):
self.tolerance = tolerance
def __call__(self, a, b):
# Delay the selection of the tolerance to here in order to reduce numpy
# import times. The calculation of these parameters is a substantial
# component of numpy's import time.
if self.tolerance is None:
self.tolerance = np.finfo(float).tiny
# don't call ma ufuncs from __array_wrap__ which would fail for scalars
a, b = np.asarray(a), np.asarray(b)
with np.errstate(all='ignore'):
return umath.absolute(a) * self.tolerance >= umath.absolute(b)
class _DomainGreater:
"""
DomainGreater(v)(x) is True where x <= v.
"""
def __init__(self, critical_value):
"DomainGreater(v)(x) = true where x <= v"
self.critical_value = critical_value
def __call__(self, x):
"Executes the call behavior."
with np.errstate(invalid='ignore'):
return umath.less_equal(x, self.critical_value)
class _DomainGreaterEqual:
"""
DomainGreaterEqual(v)(x) is True where x < v.
"""
def __init__(self, critical_value):
"DomainGreaterEqual(v)(x) = true where x < v"
self.critical_value = critical_value
def __call__(self, x):
"Executes the call behavior."
with np.errstate(invalid='ignore'):
return umath.less(x, self.critical_value)
class _MaskedUFunc:
def __init__(self, ufunc):
self.f = ufunc
self.__doc__ = ufunc.__doc__
self.__name__ = ufunc.__name__
self.__qualname__ = ufunc.__qualname__
def __str__(self):
return f"Masked version of {self.f}"
class _MaskedUnaryOperation(_MaskedUFunc):
"""
Defines masked version of unary operations, where invalid values are
pre-masked.
Parameters
----------
mufunc : callable
The function for which to define a masked version. Made available
as ``_MaskedUnaryOperation.f``.
fill : scalar, optional
Filling value, default is 0.
domain : class instance
Domain for the function. Should be one of the ``_Domain*``
classes. Default is None.
"""
def __init__(self, mufunc, fill=0, domain=None):
super().__init__(mufunc)
self.fill = fill
self.domain = domain
ufunc_domain[mufunc] = domain
ufunc_fills[mufunc] = fill
def __call__(self, a, *args, **kwargs):
"""
Execute the call behavior.
"""
d = getdata(a)
# Deal with domain
if self.domain is not None:
# Case 1.1. : Domained function
# nans at masked positions cause RuntimeWarnings, even though
# they are masked. To avoid this we suppress warnings.
with np.errstate(divide='ignore', invalid='ignore'):
result = self.f(d, *args, **kwargs)
# Make a mask
m = ~umath.isfinite(result)
m |= self.domain(d)
m |= getmask(a)
else:
# Case 1.2. : Function without a domain
# Get the result and the mask
with np.errstate(divide='ignore', invalid='ignore'):