forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathwindow.py
2607 lines (2142 loc) · 80.1 KB
/
window.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
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
"""
Provide a generic structure to support window functions,
similar to how we have a Groupby object.
"""
from __future__ import division
from collections import defaultdict
from datetime import timedelta
from textwrap import dedent
import warnings
import numpy as np
import pandas._libs.window as libwindow
import pandas.compat as compat
from pandas.compat.numpy import function as nv
from pandas.util._decorators import Appender, Substitution, cache_readonly
from pandas.core.dtypes.common import (
ensure_float64, is_bool, is_float_dtype, is_integer, is_integer_dtype,
is_list_like, is_scalar, is_timedelta64_dtype, needs_i8_conversion)
from pandas.core.dtypes.generic import (
ABCDataFrame, ABCDateOffset, ABCDatetimeIndex, ABCPeriodIndex, ABCSeries,
ABCTimedeltaIndex)
from pandas.core.base import PandasObject, SelectionMixin
import pandas.core.common as com
from pandas.core.generic import _shared_docs
from pandas.core.groupby.base import GroupByMixin
_shared_docs = dict(**_shared_docs)
_doc_template = """
Returns
-------
same type as input
See Also
--------
Series.%(name)s : Series %(name)s.
DataFrame.%(name)s : DataFrame %(name)s.
"""
class _Window(PandasObject, SelectionMixin):
_attributes = ['window', 'min_periods', 'center', 'win_type',
'axis', 'on', 'closed']
exclusions = set()
def __init__(self, obj, window=None, min_periods=None,
center=False, win_type=None, axis=0, on=None, closed=None,
**kwargs):
self.__dict__.update(kwargs)
self.blocks = []
self.obj = obj
self.on = on
self.closed = closed
self.window = window
self.min_periods = min_periods
self.center = center
self.win_type = win_type
self.win_freq = None
self.axis = obj._get_axis_number(axis) if axis is not None else None
self.validate()
@property
def _constructor(self):
return Window
@property
def is_datetimelike(self):
return None
@property
def _on(self):
return None
@property
def is_freq_type(self):
return self.win_type == 'freq'
def validate(self):
if self.center is not None and not is_bool(self.center):
raise ValueError("center must be a boolean")
if (self.min_periods is not None and
not is_integer(self.min_periods)):
raise ValueError("min_periods must be an integer")
if (self.closed is not None and
self.closed not in ['right', 'both', 'left', 'neither']):
raise ValueError("closed must be 'right', 'left', 'both' or "
"'neither'")
def _convert_freq(self):
"""
Resample according to the how, return a new object.
"""
obj = self._selected_obj
index = None
return obj, index
def _create_blocks(self):
"""
Split data into blocks & return conformed data.
"""
obj, index = self._convert_freq()
if index is not None:
index = self._on
# filter out the on from the object
if self.on is not None:
if obj.ndim == 2:
obj = obj.reindex(columns=obj.columns.difference([self.on]),
copy=False)
blocks = obj._to_dict_of_blocks(copy=False).values()
return blocks, obj, index
def _gotitem(self, key, ndim, subset=None):
"""
Sub-classes to define. Return a sliced object.
Parameters
----------
key : str / list of selections
ndim : 1,2
requested ndim of result
subset : object, default None
subset to act on
"""
# create a new object to prevent aliasing
if subset is None:
subset = self.obj
self = self._shallow_copy(subset)
self._reset_cache()
if subset.ndim == 2:
if is_scalar(key) and key in subset or is_list_like(key):
self._selection = key
return self
def __getattr__(self, attr):
if attr in self._internal_names_set:
return object.__getattribute__(self, attr)
if attr in self.obj:
return self[attr]
raise AttributeError("%r object has no attribute %r" %
(type(self).__name__, attr))
def _dir_additions(self):
return self.obj._dir_additions()
def _get_window(self, other=None):
return self.window
@property
def _window_type(self):
return self.__class__.__name__
def __unicode__(self):
"""
Provide a nice str repr of our rolling object.
"""
attrs = ["{k}={v}".format(k=k, v=getattr(self, k))
for k in self._attributes
if getattr(self, k, None) is not None]
return "{klass} [{attrs}]".format(klass=self._window_type,
attrs=','.join(attrs))
def __iter__(self):
url = 'https://github.com/pandas-dev/pandas/issues/11704'
raise NotImplementedError('See issue #11704 {url}'.format(url=url))
def _get_index(self, index=None):
"""
Return index as ndarrays.
Returns
-------
tuple of (index, index_as_ndarray)
"""
if self.is_freq_type:
if index is None:
index = self._on
return index, index.asi8
return index, index
def _prep_values(self, values=None, kill_inf=True):
if values is None:
values = getattr(self._selected_obj, 'values', self._selected_obj)
# GH #12373 : rolling functions error on float32 data
# make sure the data is coerced to float64
if is_float_dtype(values.dtype):
values = ensure_float64(values)
elif is_integer_dtype(values.dtype):
values = ensure_float64(values)
elif needs_i8_conversion(values.dtype):
raise NotImplementedError("ops for {action} for this "
"dtype {dtype} are not "
"implemented".format(
action=self._window_type,
dtype=values.dtype))
else:
try:
values = ensure_float64(values)
except (ValueError, TypeError):
raise TypeError("cannot handle this type -> {0}"
"".format(values.dtype))
if kill_inf:
values = values.copy()
values[np.isinf(values)] = np.NaN
return values
def _wrap_result(self, result, block=None, obj=None):
"""
Wrap a single result.
"""
if obj is None:
obj = self._selected_obj
index = obj.index
if isinstance(result, np.ndarray):
# coerce if necessary
if block is not None:
if is_timedelta64_dtype(block.values.dtype):
from pandas import to_timedelta
result = to_timedelta(
result.ravel(), unit='ns').values.reshape(result.shape)
if result.ndim == 1:
from pandas import Series
return Series(result, index, name=obj.name)
return type(obj)(result, index=index, columns=block.columns)
return result
def _wrap_results(self, results, blocks, obj):
"""
Wrap the results.
Parameters
----------
results : list of ndarrays
blocks : list of blocks
obj : conformed data (may be resampled)
"""
from pandas import Series, concat
from pandas.core.index import ensure_index
final = []
for result, block in zip(results, blocks):
result = self._wrap_result(result, block=block, obj=obj)
if result.ndim == 1:
return result
final.append(result)
# if we have an 'on' column
# we want to put it back into the results
# in the same location
columns = self._selected_obj.columns
if self.on is not None and not self._on.equals(obj.index):
name = self._on.name
final.append(Series(self._on, index=obj.index, name=name))
if self._selection is not None:
selection = ensure_index(self._selection)
# need to reorder to include original location of
# the on column (if its not already there)
if name not in selection:
columns = self.obj.columns
indexer = columns.get_indexer(selection.tolist() + [name])
columns = columns.take(sorted(indexer))
if not len(final):
return obj.astype('float64')
return concat(final, axis=1).reindex(columns=columns, copy=False)
def _center_window(self, result, window):
"""
Center the result in the window.
"""
if self.axis > result.ndim - 1:
raise ValueError("Requested axis is larger then no. of argument "
"dimensions")
offset = _offset(window, True)
if offset > 0:
if isinstance(result, (ABCSeries, ABCDataFrame)):
result = result.slice_shift(-offset, axis=self.axis)
else:
lead_indexer = [slice(None)] * result.ndim
lead_indexer[self.axis] = slice(offset, None)
result = np.copy(result[tuple(lead_indexer)])
return result
def aggregate(self, arg, *args, **kwargs):
result, how = self._aggregate(arg, *args, **kwargs)
if result is None:
return self.apply(arg, raw=False, args=args, kwargs=kwargs)
return result
agg = aggregate
_shared_docs['sum'] = dedent("""
Calculate %(name)s sum of given DataFrame or Series.
Parameters
----------
*args, **kwargs
For compatibility with other %(name)s methods. Has no effect
on the computed value.
Returns
-------
Series or DataFrame
Same type as the input, with the same index, containing the
%(name)s sum.
See Also
--------
Series.sum : Reducing sum for Series.
DataFrame.sum : Reducing sum for DataFrame.
Examples
--------
>>> s = pd.Series([1, 2, 3, 4, 5])
>>> s
0 1
1 2
2 3
3 4
4 5
dtype: int64
>>> s.rolling(3).sum()
0 NaN
1 NaN
2 6.0
3 9.0
4 12.0
dtype: float64
>>> s.expanding(3).sum()
0 NaN
1 NaN
2 6.0
3 10.0
4 15.0
dtype: float64
>>> s.rolling(3, center=True).sum()
0 NaN
1 6.0
2 9.0
3 12.0
4 NaN
dtype: float64
For DataFrame, each %(name)s sum is computed column-wise.
>>> df = pd.DataFrame({"A": s, "B": s ** 2})
>>> df
A B
0 1 1
1 2 4
2 3 9
3 4 16
4 5 25
>>> df.rolling(3).sum()
A B
0 NaN NaN
1 NaN NaN
2 6.0 14.0
3 9.0 29.0
4 12.0 50.0
""")
_shared_docs['mean'] = dedent("""
Calculate the %(name)s mean of the values.
Parameters
----------
*args
Under Review.
**kwargs
Under Review.
Returns
-------
Series or DataFrame
Returned object type is determined by the caller of the %(name)s
calculation.
See Also
--------
Series.%(name)s : Calling object with Series data.
DataFrame.%(name)s : Calling object with DataFrames.
Series.mean : Equivalent method for Series.
DataFrame.mean : Equivalent method for DataFrame.
Examples
--------
The below examples will show rolling mean calculations with window sizes of
two and three, respectively.
>>> s = pd.Series([1, 2, 3, 4])
>>> s.rolling(2).mean()
0 NaN
1 1.5
2 2.5
3 3.5
dtype: float64
>>> s.rolling(3).mean()
0 NaN
1 NaN
2 2.0
3 3.0
dtype: float64
""")
class Window(_Window):
"""
Provides rolling window calculations.
.. versionadded:: 0.18.0
Parameters
----------
window : int, or offset
Size of the moving window. This is the number of observations used for
calculating the statistic. Each window will be a fixed size.
If its an offset then this will be the time period of each window. Each
window will be a variable sized based on the observations included in
the time-period. This is only valid for datetimelike indexes. This is
new in 0.19.0
min_periods : int, default None
Minimum number of observations in window required to have a value
(otherwise result is NA). For a window that is specified by an offset,
`min_periods` will default to 1. Otherwise, `min_periods` will default
to the size of the window.
center : bool, default False
Set the labels at the center of the window.
win_type : str, default None
Provide a window type. If ``None``, all points are evenly weighted.
See the notes below for further information.
on : str, optional
For a DataFrame, column on which to calculate
the rolling window, rather than the index
axis : int or str, default 0
closed : str, default None
Make the interval closed on the 'right', 'left', 'both' or
'neither' endpoints.
For offset-based windows, it defaults to 'right'.
For fixed windows, defaults to 'both'. Remaining cases not implemented
for fixed windows.
.. versionadded:: 0.20.0
Returns
-------
a Window or Rolling sub-classed for the particular operation
See Also
--------
expanding : Provides expanding transformations.
ewm : Provides exponential weighted functions.
Notes
-----
By default, the result is set to the right edge of the window. This can be
changed to the center of the window by setting ``center=True``.
To learn more about the offsets & frequency strings, please see `this link
<http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases>`__.
The recognized win_types are:
* ``boxcar``
* ``triang``
* ``blackman``
* ``hamming``
* ``bartlett``
* ``parzen``
* ``bohman``
* ``blackmanharris``
* ``nuttall``
* ``barthann``
* ``kaiser`` (needs beta)
* ``gaussian`` (needs std)
* ``general_gaussian`` (needs power, width)
* ``slepian`` (needs width).
If ``win_type=None`` all points are evenly weighted. To learn more about
different window types see `scipy.signal window functions
<https://docs.scipy.org/doc/scipy/reference/signal.html#window-functions>`__.
Examples
--------
>>> df = pd.DataFrame({'B': [0, 1, 2, np.nan, 4]})
>>> df
B
0 0.0
1 1.0
2 2.0
3 NaN
4 4.0
Rolling sum with a window length of 2, using the 'triang'
window type.
>>> df.rolling(2, win_type='triang').sum()
B
0 NaN
1 1.0
2 2.5
3 NaN
4 NaN
Rolling sum with a window length of 2, min_periods defaults
to the window length.
>>> df.rolling(2).sum()
B
0 NaN
1 1.0
2 3.0
3 NaN
4 NaN
Same as above, but explicitly set the min_periods
>>> df.rolling(2, min_periods=1).sum()
B
0 0.0
1 1.0
2 3.0
3 2.0
4 4.0
A ragged (meaning not-a-regular frequency), time-indexed DataFrame
>>> df = pd.DataFrame({'B': [0, 1, 2, np.nan, 4]},
... index = [pd.Timestamp('20130101 09:00:00'),
... pd.Timestamp('20130101 09:00:02'),
... pd.Timestamp('20130101 09:00:03'),
... pd.Timestamp('20130101 09:00:05'),
... pd.Timestamp('20130101 09:00:06')])
>>> df
B
2013-01-01 09:00:00 0.0
2013-01-01 09:00:02 1.0
2013-01-01 09:00:03 2.0
2013-01-01 09:00:05 NaN
2013-01-01 09:00:06 4.0
Contrasting to an integer rolling window, this will roll a variable
length window corresponding to the time period.
The default for min_periods is 1.
>>> df.rolling('2s').sum()
B
2013-01-01 09:00:00 0.0
2013-01-01 09:00:02 1.0
2013-01-01 09:00:03 3.0
2013-01-01 09:00:05 NaN
2013-01-01 09:00:06 4.0
"""
def validate(self):
super(Window, self).validate()
window = self.window
if isinstance(window, (list, tuple, np.ndarray)):
pass
elif is_integer(window):
if window <= 0:
raise ValueError("window must be > 0 ")
try:
import scipy.signal as sig
except ImportError:
raise ImportError('Please install scipy to generate window '
'weight')
if not isinstance(self.win_type, compat.string_types):
raise ValueError('Invalid win_type {0}'.format(self.win_type))
if getattr(sig, self.win_type, None) is None:
raise ValueError('Invalid win_type {0}'.format(self.win_type))
else:
raise ValueError('Invalid window {0}'.format(window))
def _prep_window(self, **kwargs):
"""
Provide validation for our window type, return the window
we have already been validated.
"""
window = self._get_window()
if isinstance(window, (list, tuple, np.ndarray)):
return com.asarray_tuplesafe(window).astype(float)
elif is_integer(window):
import scipy.signal as sig
# the below may pop from kwargs
def _validate_win_type(win_type, kwargs):
arg_map = {'kaiser': ['beta'],
'gaussian': ['std'],
'general_gaussian': ['power', 'width'],
'slepian': ['width']}
if win_type in arg_map:
return tuple([win_type] + _pop_args(win_type,
arg_map[win_type],
kwargs))
return win_type
def _pop_args(win_type, arg_names, kwargs):
msg = '%s window requires %%s' % win_type
all_args = []
for n in arg_names:
if n not in kwargs:
raise ValueError(msg % n)
all_args.append(kwargs.pop(n))
return all_args
win_type = _validate_win_type(self.win_type, kwargs)
# GH #15662. `False` makes symmetric window, rather than periodic.
return sig.get_window(win_type, window, False).astype(float)
def _apply_window(self, mean=True, **kwargs):
"""
Applies a moving window of type ``window_type`` on the data.
Parameters
----------
mean : bool, default True
If True computes weighted mean, else weighted sum
Returns
-------
y : same type as input argument
"""
window = self._prep_window(**kwargs)
center = self.center
blocks, obj, index = self._create_blocks()
results = []
for b in blocks:
try:
values = self._prep_values(b.values)
except TypeError:
results.append(b.values.copy())
continue
if values.size == 0:
results.append(values.copy())
continue
offset = _offset(window, center)
additional_nans = np.array([np.NaN] * offset)
def f(arg, *args, **kwargs):
minp = _use_window(self.min_periods, len(window))
return libwindow.roll_window(np.concatenate((arg,
additional_nans))
if center else arg, window, minp,
avg=mean)
result = np.apply_along_axis(f, self.axis, values)
if center:
result = self._center_window(result, window)
results.append(result)
return self._wrap_results(results, blocks, obj)
_agg_doc = dedent("""
Examples
--------
>>> df = pd.DataFrame(np.random.randn(10, 3), columns=['A', 'B', 'C'])
>>> df
A B C
0 -2.385977 -0.102758 0.438822
1 -1.004295 0.905829 -0.954544
2 0.735167 -0.165272 -1.619346
3 -0.702657 -1.340923 -0.706334
4 -0.246845 0.211596 -0.901819
5 2.463718 3.157577 -1.380906
6 -1.142255 2.340594 -0.039875
7 1.396598 -1.647453 1.677227
8 -0.543425 1.761277 -0.220481
9 -0.640505 0.289374 -1.550670
>>> df.rolling(3, win_type='boxcar').agg('mean')
A B C
0 NaN NaN NaN
1 NaN NaN NaN
2 -0.885035 0.212600 -0.711689
3 -0.323928 -0.200122 -1.093408
4 -0.071445 -0.431533 -1.075833
5 0.504739 0.676083 -0.996353
6 0.358206 1.903256 -0.774200
7 0.906020 1.283573 0.085482
8 -0.096361 0.818139 0.472290
9 0.070889 0.134399 -0.031308
See Also
--------
pandas.DataFrame.rolling.aggregate
pandas.DataFrame.aggregate
""")
@Appender(_agg_doc)
@Appender(_shared_docs['aggregate'] % dict(
versionadded='',
klass='Series/DataFrame',
axis=''))
def aggregate(self, arg, *args, **kwargs):
result, how = self._aggregate(arg, *args, **kwargs)
if result is None:
# these must apply directly
result = arg(self)
return result
agg = aggregate
@Substitution(name='window')
@Appender(_shared_docs['sum'])
def sum(self, *args, **kwargs):
nv.validate_window_func('sum', args, kwargs)
return self._apply_window(mean=False, **kwargs)
@Substitution(name='window')
@Appender(_shared_docs['mean'])
def mean(self, *args, **kwargs):
nv.validate_window_func('mean', args, kwargs)
return self._apply_window(mean=True, **kwargs)
class _GroupByMixin(GroupByMixin):
"""
Provide the groupby facilities.
"""
def __init__(self, obj, *args, **kwargs):
parent = kwargs.pop('parent', None) # noqa
groupby = kwargs.pop('groupby', None)
if groupby is None:
groupby, obj = obj, obj.obj
self._groupby = groupby
self._groupby.mutated = True
self._groupby.grouper.mutated = True
super(GroupByMixin, self).__init__(obj, *args, **kwargs)
count = GroupByMixin._dispatch('count')
corr = GroupByMixin._dispatch('corr', other=None, pairwise=None)
cov = GroupByMixin._dispatch('cov', other=None, pairwise=None)
def _apply(self, func, name, window=None, center=None,
check_minp=None, **kwargs):
"""
Dispatch to apply; we are stripping all of the _apply kwargs and
performing the original function call on the grouped object.
"""
def f(x, name=name, *args):
x = self._shallow_copy(x)
if isinstance(name, compat.string_types):
return getattr(x, name)(*args, **kwargs)
return x.apply(name, *args, **kwargs)
return self._groupby.apply(f)
class _Rolling(_Window):
@property
def _constructor(self):
return Rolling
def _apply(self, func, name=None, window=None, center=None,
check_minp=None, **kwargs):
"""
Rolling statistical measure using supplied function.
Designed to be used with passed-in Cython array-based functions.
Parameters
----------
func : str/callable to apply
name : str, optional
name of this function
window : int/array, default to _get_window()
center : bool, default to self.center
check_minp : function, default to _use_window
Returns
-------
y : type of input
"""
if center is None:
center = self.center
if window is None:
window = self._get_window()
if check_minp is None:
check_minp = _use_window
blocks, obj, index = self._create_blocks()
index, indexi = self._get_index(index=index)
results = []
for b in blocks:
values = self._prep_values(b.values)
if values.size == 0:
results.append(values.copy())
continue
# if we have a string function name, wrap it
if isinstance(func, compat.string_types):
cfunc = getattr(libwindow, func, None)
if cfunc is None:
raise ValueError("we do not support this function "
"in libwindow.{func}".format(func=func))
def func(arg, window, min_periods=None, closed=None):
minp = check_minp(min_periods, window)
# ensure we are only rolling on floats
arg = ensure_float64(arg)
return cfunc(arg,
window, minp, indexi, closed, **kwargs)
# calculation function
if center:
offset = _offset(window, center)
additional_nans = np.array([np.NaN] * offset)
def calc(x):
return func(np.concatenate((x, additional_nans)),
window, min_periods=self.min_periods,
closed=self.closed)
else:
def calc(x):
return func(x, window, min_periods=self.min_periods,
closed=self.closed)
with np.errstate(all='ignore'):
if values.ndim > 1:
result = np.apply_along_axis(calc, self.axis, values)
else:
result = calc(values)
if center:
result = self._center_window(result, window)
results.append(result)
return self._wrap_results(results, blocks, obj)
class _Rolling_and_Expanding(_Rolling):
_shared_docs['count'] = dedent(r"""
The %(name)s count of any non-NaN observations inside the window.
Returns
-------
Series or DataFrame
Returned object type is determined by the caller of the %(name)s
calculation.
See Also
--------
pandas.Series.%(name)s : Calling object with Series data.
pandas.DataFrame.%(name)s : Calling object with DataFrames.
pandas.DataFrame.count : Count of the full DataFrame.
Examples
--------
>>> s = pd.Series([2, 3, np.nan, 10])
>>> s.rolling(2).count()
0 1.0
1 2.0
2 1.0
3 1.0
dtype: float64
>>> s.rolling(3).count()
0 1.0
1 2.0
2 2.0
3 2.0
dtype: float64
>>> s.rolling(4).count()
0 1.0
1 2.0
2 2.0
3 3.0
dtype: float64
""")
def count(self):
blocks, obj, index = self._create_blocks()
# Validate the index
self._get_index(index=index)
window = self._get_window()
window = min(window, len(obj)) if not self.center else window
results = []
for b in blocks:
result = b.notna().astype(int)
result = self._constructor(result, window=window, min_periods=0,
center=self.center,
closed=self.closed).sum()
results.append(result)
return self._wrap_results(results, blocks, obj)
_shared_docs['apply'] = dedent(r"""
The %(name)s function apply.
Parameters
----------
func : function
Must produce a single value from an ndarray input if ``raw=True``
or a Series if ``raw=False``.
raw : bool, default None
* ``False`` : passes each row or column as a Series to the
function.
* ``True`` or ``None`` : the passed function will receive ndarray
objects instead.
If you are just applying a NumPy reduction function this will
achieve much better performance.
The `raw` parameter is required and will show a FutureWarning if
not passed. In the future `raw` will default to False.
.. versionadded:: 0.23.0
*args, **kwargs :
Passed to the function for compatibility with other %(name)s
methods.""")
def apply(self, func, raw=None, args=(), kwargs={}):
from pandas import Series
# TODO: _level is unused?
_level = kwargs.pop('_level', None) # noqa
window = self._get_window()
offset = _offset(window, self.center)
index, indexi = self._get_index()
# TODO: default is for backward compat
# change to False in the future
if raw is None:
warnings.warn(
"Currently, 'apply' passes the values as ndarrays to the "
"applied function. In the future, this will change to passing "
"it as Series objects. You need to specify 'raw=True' to keep "
"the current behaviour, and you can pass 'raw=False' to "
"silence this warning", FutureWarning, stacklevel=3)
raw = True
def f(arg, window, min_periods, closed):
minp = _use_window(min_periods, window)
if not raw:
arg = Series(arg, index=self.obj.index)
return libwindow.roll_generic(
arg, window, minp, indexi,
closed, offset, func, raw, args, kwargs)
return self._apply(f, func, args=args, kwargs=kwargs,
center=False, raw=raw)