/
missing.py
609 lines (496 loc) · 16.2 KB
/
missing.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
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
"""
missing types & inference
"""
import numpy as np
from pandas._config import get_option
from pandas._libs import lib
import pandas._libs.missing as libmissing
from pandas._libs.tslibs import NaT, iNaT
from pandas.core.dtypes.common import (
_NS_DTYPE,
_TD_DTYPE,
ensure_object,
is_bool_dtype,
is_complex_dtype,
is_datetime64_dtype,
is_datetime64tz_dtype,
is_datetimelike_v_numeric,
is_dtype_equal,
is_extension_array_dtype,
is_float_dtype,
is_integer_dtype,
is_object_dtype,
is_period_dtype,
is_scalar,
is_string_dtype,
is_string_like_dtype,
is_timedelta64_dtype,
needs_i8_conversion,
pandas_dtype,
)
from pandas.core.dtypes.generic import (
ABCDatetimeArray,
ABCExtensionArray,
ABCGeneric,
ABCIndexClass,
ABCMultiIndex,
ABCSeries,
ABCTimedeltaArray,
)
from pandas.core.dtypes.inference import is_list_like
isposinf_scalar = libmissing.isposinf_scalar
isneginf_scalar = libmissing.isneginf_scalar
def isna(obj):
"""
Detect missing values for an array-like object.
This function takes a scalar or array-like object and indicates
whether values are missing (``NaN`` in numeric arrays, ``None`` or ``NaN``
in object arrays, ``NaT`` in datetimelike).
Parameters
----------
obj : scalar or array-like
Object to check for null or missing values.
Returns
-------
bool or array-like of bool
For scalar input, returns a scalar boolean.
For array input, returns an array of boolean indicating whether each
corresponding element is missing.
See Also
--------
notna : Boolean inverse of pandas.isna.
Series.isna : Detect missing values in a Series.
DataFrame.isna : Detect missing values in a DataFrame.
Index.isna : Detect missing values in an Index.
Examples
--------
Scalar arguments (including strings) result in a scalar boolean.
>>> pd.isna('dog')
False
>>> pd.isna(pd.NA)
True
>>> pd.isna(np.nan)
True
ndarrays result in an ndarray of booleans.
>>> array = np.array([[1, np.nan, 3], [4, 5, np.nan]])
>>> array
array([[ 1., nan, 3.],
[ 4., 5., nan]])
>>> pd.isna(array)
array([[False, True, False],
[False, False, True]])
For indexes, an ndarray of booleans is returned.
>>> index = pd.DatetimeIndex(["2017-07-05", "2017-07-06", None,
... "2017-07-08"])
>>> index
DatetimeIndex(['2017-07-05', '2017-07-06', 'NaT', '2017-07-08'],
dtype='datetime64[ns]', freq=None)
>>> pd.isna(index)
array([False, False, True, False])
For Series and DataFrame, the same type is returned, containing booleans.
>>> df = pd.DataFrame([['ant', 'bee', 'cat'], ['dog', None, 'fly']])
>>> df
0 1 2
0 ant bee cat
1 dog None fly
>>> pd.isna(df)
0 1 2
0 False False False
1 False True False
>>> pd.isna(df[1])
0 False
1 True
Name: 1, dtype: bool
"""
return _isna(obj)
isnull = isna
def _isna_new(obj):
if is_scalar(obj):
return libmissing.checknull(obj)
# hack (for now) because MI registers as ndarray
elif isinstance(obj, ABCMultiIndex):
raise NotImplementedError("isna is not defined for MultiIndex")
elif isinstance(obj, type):
return False
elif isinstance(
obj,
(
ABCSeries,
np.ndarray,
ABCIndexClass,
ABCExtensionArray,
ABCDatetimeArray,
ABCTimedeltaArray,
),
):
return _isna_ndarraylike(obj)
elif isinstance(obj, ABCGeneric):
return obj._constructor(obj._data.isna(func=isna))
elif isinstance(obj, list):
return _isna_ndarraylike(np.asarray(obj, dtype=object))
elif hasattr(obj, "__array__"):
return _isna_ndarraylike(np.asarray(obj))
else:
return obj is None
def _isna_old(obj):
"""
Detect missing values, treating None, NaN, INF, -INF as null.
Parameters
----------
arr: ndarray or object value
Returns
-------
boolean ndarray or boolean
"""
if is_scalar(obj):
return libmissing.checknull_old(obj)
# hack (for now) because MI registers as ndarray
elif isinstance(obj, ABCMultiIndex):
raise NotImplementedError("isna is not defined for MultiIndex")
elif isinstance(obj, type):
return False
elif isinstance(obj, (ABCSeries, np.ndarray, ABCIndexClass, ABCExtensionArray)):
return _isna_ndarraylike_old(obj)
elif isinstance(obj, ABCGeneric):
return obj._constructor(obj._data.isna(func=_isna_old))
elif isinstance(obj, list):
return _isna_ndarraylike_old(np.asarray(obj, dtype=object))
elif hasattr(obj, "__array__"):
return _isna_ndarraylike_old(np.asarray(obj))
else:
return obj is None
_isna = _isna_new
def _use_inf_as_na(key):
"""
Option change callback for na/inf behaviour.
Choose which replacement for numpy.isnan / -numpy.isfinite is used.
Parameters
----------
flag: bool
True means treat None, NaN, INF, -INF as null (old way),
False means None and NaN are null, but INF, -INF are not null
(new way).
Notes
-----
This approach to setting global module values is discussed and
approved here:
* https://stackoverflow.com/questions/4859217/
programmatically-creating-variables-in-python/4859312#4859312
"""
flag = get_option(key)
if flag:
globals()["_isna"] = _isna_old
else:
globals()["_isna"] = _isna_new
def _isna_ndarraylike(obj):
is_extension = is_extension_array_dtype(obj)
if not is_extension:
# Avoid accessing `.values` on things like
# PeriodIndex, which may be expensive.
values = getattr(obj, "values", obj)
else:
values = obj
dtype = values.dtype
if is_extension:
if isinstance(obj, (ABCIndexClass, ABCSeries)):
values = obj._values
else:
values = obj
result = values.isna()
elif isinstance(obj, ABCDatetimeArray):
return obj.isna()
elif is_string_dtype(dtype):
# Working around NumPy ticket 1542
shape = values.shape
if is_string_like_dtype(dtype):
# object array of strings
result = np.zeros(values.shape, dtype=bool)
else:
# object array of non-strings
result = np.empty(shape, dtype=bool)
vec = libmissing.isnaobj(values.ravel())
result[...] = vec.reshape(shape)
elif needs_i8_conversion(dtype):
# this is the NaT pattern
result = values.view("i8") == iNaT
else:
result = np.isnan(values)
# box
if isinstance(obj, ABCSeries):
result = obj._constructor(result, index=obj.index, name=obj.name, copy=False)
return result
def _isna_ndarraylike_old(obj):
values = getattr(obj, "values", obj)
dtype = values.dtype
if is_string_dtype(dtype):
# Working around NumPy ticket 1542
shape = values.shape
if is_string_like_dtype(dtype):
result = np.zeros(values.shape, dtype=bool)
else:
result = np.empty(shape, dtype=bool)
vec = libmissing.isnaobj_old(values.ravel())
result[:] = vec.reshape(shape)
elif is_datetime64_dtype(dtype):
# this is the NaT pattern
result = values.view("i8") == iNaT
else:
result = ~np.isfinite(values)
# box
if isinstance(obj, ABCSeries):
result = obj._constructor(result, index=obj.index, name=obj.name, copy=False)
return result
def notna(obj):
"""
Detect non-missing values for an array-like object.
This function takes a scalar or array-like object and indicates
whether values are valid (not missing, which is ``NaN`` in numeric
arrays, ``None`` or ``NaN`` in object arrays, ``NaT`` in datetimelike).
Parameters
----------
obj : array-like or object value
Object to check for *not* null or *non*-missing values.
Returns
-------
bool or array-like of bool
For scalar input, returns a scalar boolean.
For array input, returns an array of boolean indicating whether each
corresponding element is valid.
See Also
--------
isna : Boolean inverse of pandas.notna.
Series.notna : Detect valid values in a Series.
DataFrame.notna : Detect valid values in a DataFrame.
Index.notna : Detect valid values in an Index.
Examples
--------
Scalar arguments (including strings) result in a scalar boolean.
>>> pd.notna('dog')
True
>>> pd.notna(pd.NA)
False
>>> pd.notna(np.nan)
False
ndarrays result in an ndarray of booleans.
>>> array = np.array([[1, np.nan, 3], [4, 5, np.nan]])
>>> array
array([[ 1., nan, 3.],
[ 4., 5., nan]])
>>> pd.notna(array)
array([[ True, False, True],
[ True, True, False]])
For indexes, an ndarray of booleans is returned.
>>> index = pd.DatetimeIndex(["2017-07-05", "2017-07-06", None,
... "2017-07-08"])
>>> index
DatetimeIndex(['2017-07-05', '2017-07-06', 'NaT', '2017-07-08'],
dtype='datetime64[ns]', freq=None)
>>> pd.notna(index)
array([ True, True, False, True])
For Series and DataFrame, the same type is returned, containing booleans.
>>> df = pd.DataFrame([['ant', 'bee', 'cat'], ['dog', None, 'fly']])
>>> df
0 1 2
0 ant bee cat
1 dog None fly
>>> pd.notna(df)
0 1 2
0 True True True
1 True False True
>>> pd.notna(df[1])
0 True
1 False
Name: 1, dtype: bool
"""
res = isna(obj)
if is_scalar(res):
return not res
return ~res
notnull = notna
def _isna_compat(arr, fill_value=np.nan) -> bool:
"""
Parameters
----------
arr: a numpy array
fill_value: fill value, default to np.nan
Returns
-------
True if we can fill using this fill_value
"""
dtype = arr.dtype
if isna(fill_value):
return not (is_bool_dtype(dtype) or is_integer_dtype(dtype))
return True
def array_equivalent(left, right, strict_nan: bool = False) -> bool:
"""
True if two arrays, left and right, have equal non-NaN elements, and NaNs
in corresponding locations. False otherwise. It is assumed that left and
right are NumPy arrays of the same dtype. The behavior of this function
(particularly with respect to NaNs) is not defined if the dtypes are
different.
Parameters
----------
left, right : ndarrays
strict_nan : bool, default False
If True, consider NaN and None to be different.
Returns
-------
b : bool
Returns True if the arrays are equivalent.
Examples
--------
>>> array_equivalent(
... np.array([1, 2, np.nan]),
... np.array([1, 2, np.nan]))
True
>>> array_equivalent(
... np.array([1, np.nan, 2]),
... np.array([1, 2, np.nan]))
False
"""
left, right = np.asarray(left), np.asarray(right)
# shape compat
if left.shape != right.shape:
return False
# Object arrays can contain None, NaN and NaT.
# string dtypes must be come to this path for NumPy 1.7.1 compat
if is_string_dtype(left) or is_string_dtype(right):
if not strict_nan:
# isna considers NaN and None to be equivalent.
return lib.array_equivalent_object(
ensure_object(left.ravel()), ensure_object(right.ravel())
)
for left_value, right_value in zip(left, right):
if left_value is NaT and right_value is not NaT:
return False
elif left_value is libmissing.NA and right_value is not libmissing.NA:
return False
elif isinstance(left_value, float) and np.isnan(left_value):
if not isinstance(right_value, float) or not np.isnan(right_value):
return False
else:
try:
if np.any(np.asarray(left_value != right_value)):
return False
except TypeError as err:
if "Cannot compare tz-naive" in str(err):
# tzawareness compat failure, see GH#28507
return False
elif "boolean value of NA is ambiguous" in str(err):
return False
raise
return True
# NaNs can occur in float and complex arrays.
if is_float_dtype(left) or is_complex_dtype(left):
# empty
if not (np.prod(left.shape) and np.prod(right.shape)):
return True
return ((left == right) | (isna(left) & isna(right))).all()
elif is_datetimelike_v_numeric(left, right):
# GH#29553 avoid numpy deprecation warning
return False
elif needs_i8_conversion(left) or needs_i8_conversion(right):
# datetime64, timedelta64, Period
if not is_dtype_equal(left.dtype, right.dtype):
return False
left = left.view("i8")
right = right.view("i8")
# if we have structured dtypes, compare first
if left.dtype.type is np.void or right.dtype.type is np.void:
if left.dtype != right.dtype:
return False
return np.array_equal(left, right)
def _infer_fill_value(val):
"""
infer the fill value for the nan/NaT from the provided
scalar/ndarray/list-like if we are a NaT, return the correct dtyped
element to provide proper block construction
"""
if not is_list_like(val):
val = [val]
val = np.array(val, copy=False)
if needs_i8_conversion(val):
return np.array("NaT", dtype=val.dtype)
elif is_object_dtype(val.dtype):
dtype = lib.infer_dtype(ensure_object(val), skipna=False)
if dtype in ["datetime", "datetime64"]:
return np.array("NaT", dtype=_NS_DTYPE)
elif dtype in ["timedelta", "timedelta64"]:
return np.array("NaT", dtype=_TD_DTYPE)
return np.nan
def _maybe_fill(arr, fill_value=np.nan):
"""
if we have a compatible fill_value and arr dtype, then fill
"""
if _isna_compat(arr, fill_value):
arr.fill(fill_value)
return arr
def na_value_for_dtype(dtype, compat: bool = True):
"""
Return a dtype compat na value
Parameters
----------
dtype : string / dtype
compat : bool, default True
Returns
-------
np.dtype or a pandas dtype
Examples
--------
>>> na_value_for_dtype(np.dtype('int64'))
0
>>> na_value_for_dtype(np.dtype('int64'), compat=False)
nan
>>> na_value_for_dtype(np.dtype('float64'))
nan
>>> na_value_for_dtype(np.dtype('bool'))
False
>>> na_value_for_dtype(np.dtype('datetime64[ns]'))
NaT
"""
dtype = pandas_dtype(dtype)
if is_extension_array_dtype(dtype):
return dtype.na_value
if (
is_datetime64_dtype(dtype)
or is_datetime64tz_dtype(dtype)
or is_timedelta64_dtype(dtype)
or is_period_dtype(dtype)
):
return NaT
elif is_float_dtype(dtype):
return np.nan
elif is_integer_dtype(dtype):
if compat:
return 0
return np.nan
elif is_bool_dtype(dtype):
return False
return np.nan
def remove_na_arraylike(arr):
"""
Return array-like containing only true/non-NaN values, possibly empty.
"""
if is_extension_array_dtype(arr):
return arr[notna(arr)]
else:
return arr[notna(lib.values_from_object(arr))]
def is_valid_nat_for_dtype(obj, dtype) -> bool:
"""
isna check that excludes incompatible dtypes
Parameters
----------
obj : object
dtype : np.datetime64, np.timedelta64, DatetimeTZDtype, or PeriodDtype
Returns
-------
bool
"""
if not lib.is_scalar(obj) or not isna(obj):
return False
if dtype.kind == "M":
return not isinstance(obj, np.timedelta64)
if dtype.kind == "m":
return not isinstance(obj, np.datetime64)
# must be PeriodDType
return not isinstance(obj, (np.datetime64, np.timedelta64))