forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdatetimes.py
2884 lines (2464 loc) · 91.7 KB
/
datetimes.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
from __future__ import annotations
from datetime import (
datetime,
timedelta,
tzinfo,
)
from typing import (
TYPE_CHECKING,
TypeVar,
cast,
overload,
)
import warnings
import numpy as np
from pandas._config.config import get_option
from pandas._libs import (
lib,
tslib,
)
from pandas._libs.tslibs import (
BaseOffset,
NaT,
NaTType,
Resolution,
Timestamp,
astype_overflowsafe,
fields,
get_resolution,
get_supported_dtype,
get_unit_from_dtype,
ints_to_pydatetime,
is_date_array_normalized,
is_supported_dtype,
is_unitless,
normalize_i8_timestamps,
timezones,
to_offset,
tz_convert_from_utc,
tzconversion,
)
from pandas._libs.tslibs.dtypes import abbrev_to_npy_unit
from pandas.errors import PerformanceWarning
from pandas.util._exceptions import find_stack_level
from pandas.util._validators import validate_inclusive
from pandas.core.dtypes.common import (
DT64NS_DTYPE,
INT64_DTYPE,
is_bool_dtype,
is_float_dtype,
is_string_dtype,
pandas_dtype,
)
from pandas.core.dtypes.dtypes import (
DatetimeTZDtype,
ExtensionDtype,
PeriodDtype,
)
from pandas.core.dtypes.missing import isna
from pandas.core.arrays import datetimelike as dtl
from pandas.core.arrays._ranges import generate_regular_range
import pandas.core.common as com
from pandas.tseries.frequencies import get_period_alias
from pandas.tseries.offsets import (
Day,
Tick,
)
if TYPE_CHECKING:
from collections.abc import (
Generator,
Iterator,
)
from pandas._typing import (
ArrayLike,
DateTimeErrorChoices,
DtypeObj,
IntervalClosedType,
Self,
TimeAmbiguous,
TimeNonexistent,
npt,
)
from pandas import (
DataFrame,
Timedelta,
)
from pandas.core.arrays import PeriodArray
_TimestampNoneT1 = TypeVar("_TimestampNoneT1", Timestamp, None)
_TimestampNoneT2 = TypeVar("_TimestampNoneT2", Timestamp, None)
_ITER_CHUNKSIZE = 10_000
@overload
def tz_to_dtype(tz: tzinfo, unit: str = ...) -> DatetimeTZDtype: ...
@overload
def tz_to_dtype(tz: None, unit: str = ...) -> np.dtype[np.datetime64]: ...
def tz_to_dtype(
tz: tzinfo | None, unit: str = "ns"
) -> np.dtype[np.datetime64] | DatetimeTZDtype:
"""
Return a datetime64[ns] dtype appropriate for the given timezone.
Parameters
----------
tz : tzinfo or None
unit : str, default "ns"
Returns
-------
np.dtype or Datetime64TZDType
"""
if tz is None:
return np.dtype(f"M8[{unit}]")
else:
return DatetimeTZDtype(tz=tz, unit=unit)
def _field_accessor(name: str, field: str, docstring: str | None = None):
def f(self):
values = self._local_timestamps()
if field in self._bool_ops:
result: np.ndarray
if field.endswith(("start", "end")):
freq = self.freq
month_kw = 12
if freq:
kwds = freq.kwds
month_kw = kwds.get("startingMonth", kwds.get("month", 12))
result = fields.get_start_end_field(
values, field, self.freqstr, month_kw, reso=self._creso
)
else:
result = fields.get_date_field(values, field, reso=self._creso)
# these return a boolean by-definition
return result
if field in self._object_ops:
result = fields.get_date_name_field(values, field, reso=self._creso)
result = self._maybe_mask_results(result, fill_value=None)
else:
result = fields.get_date_field(values, field, reso=self._creso)
result = self._maybe_mask_results(
result, fill_value=None, convert="float64"
)
return result
f.__name__ = name
f.__doc__ = docstring
return property(f)
# error: Definition of "_concat_same_type" in base class "NDArrayBacked" is
# incompatible with definition in base class "ExtensionArray"
class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps): # type: ignore[misc]
"""
Pandas ExtensionArray for tz-naive or tz-aware datetime data.
.. warning::
DatetimeArray is currently experimental, and its API may change
without warning. In particular, :attr:`DatetimeArray.dtype` is
expected to change to always be an instance of an ``ExtensionDtype``
subclass.
Parameters
----------
data : Series, Index, DatetimeArray, ndarray
The datetime data.
For DatetimeArray `values` (or a Series or Index boxing one),
`dtype` and `freq` will be extracted from `values`.
dtype : numpy.dtype or DatetimeTZDtype
Note that the only NumPy dtype allowed is 'datetime64[ns]'.
freq : str or Offset, optional
The frequency.
copy : bool, default False
Whether to copy the underlying array of values.
Attributes
----------
None
Methods
-------
None
Examples
--------
>>> pd.arrays.DatetimeArray._from_sequence(
... pd.DatetimeIndex(["2023-01-01", "2023-01-02"], freq="D")
... )
<DatetimeArray>
['2023-01-01 00:00:00', '2023-01-02 00:00:00']
Length: 2, dtype: datetime64[ns]
"""
_typ = "datetimearray"
_internal_fill_value = np.datetime64("NaT", "ns")
_recognized_scalars = (datetime, np.datetime64)
_is_recognized_dtype = lambda x: lib.is_np_dtype(x, "M") or isinstance(
x, DatetimeTZDtype
)
_infer_matches = ("datetime", "datetime64", "date")
@property
def _scalar_type(self) -> type[Timestamp]:
return Timestamp
# define my properties & methods for delegation
_bool_ops: list[str] = [
"is_month_start",
"is_month_end",
"is_quarter_start",
"is_quarter_end",
"is_year_start",
"is_year_end",
"is_leap_year",
]
_object_ops: list[str] = ["freq", "tz"]
_field_ops: list[str] = [
"year",
"month",
"day",
"hour",
"minute",
"second",
"weekday",
"dayofweek",
"day_of_week",
"dayofyear",
"day_of_year",
"quarter",
"days_in_month",
"daysinmonth",
"microsecond",
"nanosecond",
]
_other_ops: list[str] = ["date", "time", "timetz"]
_datetimelike_ops: list[str] = (
_field_ops + _object_ops + _bool_ops + _other_ops + ["unit"]
)
_datetimelike_methods: list[str] = [
"to_period",
"tz_localize",
"tz_convert",
"normalize",
"strftime",
"round",
"floor",
"ceil",
"month_name",
"day_name",
"as_unit",
]
# ndim is inherited from ExtensionArray, must exist to ensure
# Timestamp.__richcmp__(DateTimeArray) operates pointwise
# ensure that operations with numpy arrays defer to our implementation
__array_priority__ = 1000
# -----------------------------------------------------------------
# Constructors
_dtype: np.dtype[np.datetime64] | DatetimeTZDtype
_freq: BaseOffset | None = None
@classmethod
def _from_scalars(cls, scalars, *, dtype: DtypeObj) -> Self:
if lib.infer_dtype(scalars, skipna=True) not in ["datetime", "datetime64"]:
# TODO: require any NAs be valid-for-DTA
# TODO: if dtype is passed, check for tzawareness compat?
raise ValueError
return cls._from_sequence(scalars, dtype=dtype)
@classmethod
def _validate_dtype(cls, values, dtype):
# used in TimeLikeOps.__init__
dtype = _validate_dt64_dtype(dtype)
_validate_dt64_dtype(values.dtype)
if isinstance(dtype, np.dtype):
if values.dtype != dtype:
raise ValueError("Values resolution does not match dtype.")
else:
vunit = np.datetime_data(values.dtype)[0]
if vunit != dtype.unit:
raise ValueError("Values resolution does not match dtype.")
return dtype
# error: Signature of "_simple_new" incompatible with supertype "NDArrayBacked"
@classmethod
def _simple_new( # type: ignore[override]
cls,
values: npt.NDArray[np.datetime64],
freq: BaseOffset | None = None,
dtype: np.dtype[np.datetime64] | DatetimeTZDtype = DT64NS_DTYPE,
) -> Self:
assert isinstance(values, np.ndarray)
assert dtype.kind == "M"
if isinstance(dtype, np.dtype):
assert dtype == values.dtype
assert not is_unitless(dtype)
else:
# DatetimeTZDtype. If we have e.g. DatetimeTZDtype[us, UTC],
# then values.dtype should be M8[us].
assert dtype._creso == get_unit_from_dtype(values.dtype)
result = super()._simple_new(values, dtype)
result._freq = freq
return result
@classmethod
def _from_sequence(cls, scalars, *, dtype=None, copy: bool = False) -> Self:
return cls._from_sequence_not_strict(scalars, dtype=dtype, copy=copy)
@classmethod
def _from_sequence_not_strict(
cls,
data,
*,
dtype=None,
copy: bool = False,
tz=lib.no_default,
freq: str | BaseOffset | lib.NoDefault | None = lib.no_default,
dayfirst: bool = False,
yearfirst: bool = False,
ambiguous: TimeAmbiguous = "raise",
) -> Self:
"""
A non-strict version of _from_sequence, called from DatetimeIndex.__new__.
"""
# if the user either explicitly passes tz=None or a tz-naive dtype, we
# disallows inferring a tz.
explicit_tz_none = tz is None
if tz is lib.no_default:
tz = None
else:
tz = timezones.maybe_get_tz(tz)
dtype = _validate_dt64_dtype(dtype)
# if dtype has an embedded tz, capture it
tz = _validate_tz_from_dtype(dtype, tz, explicit_tz_none)
unit = None
if dtype is not None:
unit = dtl.dtype_to_unit(dtype)
data, copy = dtl.ensure_arraylike_for_datetimelike(
data, copy, cls_name="DatetimeArray"
)
inferred_freq = None
if isinstance(data, DatetimeArray):
inferred_freq = data.freq
subarr, tz = _sequence_to_dt64(
data,
copy=copy,
tz=tz,
dayfirst=dayfirst,
yearfirst=yearfirst,
ambiguous=ambiguous,
out_unit=unit,
)
# We have to call this again after possibly inferring a tz above
_validate_tz_from_dtype(dtype, tz, explicit_tz_none)
if tz is not None and explicit_tz_none:
raise ValueError(
"Passed data is timezone-aware, incompatible with 'tz=None'. "
"Use obj.tz_localize(None) instead."
)
data_unit = np.datetime_data(subarr.dtype)[0]
data_dtype = tz_to_dtype(tz, data_unit)
result = cls._simple_new(subarr, freq=inferred_freq, dtype=data_dtype)
if unit is not None and unit != result.unit:
# If unit was specified in user-passed dtype, cast to it here
result = result.as_unit(unit)
validate_kwds = {"ambiguous": ambiguous}
result._maybe_pin_freq(freq, validate_kwds)
return result
@classmethod
def _generate_range(
cls,
start,
end,
periods: int | None,
freq,
tz=None,
normalize: bool = False,
ambiguous: TimeAmbiguous = "raise",
nonexistent: TimeNonexistent = "raise",
inclusive: IntervalClosedType = "both",
*,
unit: str | None = None,
) -> Self:
periods = dtl.validate_periods(periods)
if freq is None and any(x is None for x in [periods, start, end]):
raise ValueError("Must provide freq argument if no data is supplied")
if com.count_not_none(start, end, periods, freq) != 3:
raise ValueError(
"Of the four parameters: start, end, periods, "
"and freq, exactly three must be specified"
)
freq = to_offset(freq)
if start is not None:
start = Timestamp(start)
if end is not None:
end = Timestamp(end)
if start is NaT or end is NaT:
raise ValueError("Neither `start` nor `end` can be NaT")
if unit is not None:
if unit not in ["s", "ms", "us", "ns"]:
raise ValueError("'unit' must be one of 's', 'ms', 'us', 'ns'")
else:
unit = "ns"
if start is not None:
start = start.as_unit(unit, round_ok=False)
if end is not None:
end = end.as_unit(unit, round_ok=False)
left_inclusive, right_inclusive = validate_inclusive(inclusive)
start, end = _maybe_normalize_endpoints(start, end, normalize)
tz = _infer_tz_from_endpoints(start, end, tz)
if tz is not None:
# Localize the start and end arguments
start = _maybe_localize_point(start, freq, tz, ambiguous, nonexistent)
end = _maybe_localize_point(end, freq, tz, ambiguous, nonexistent)
if freq is not None:
# We break Day arithmetic (fixed 24 hour) here and opt for
# Day to mean calendar day (23/24/25 hour). Therefore, strip
# tz info from start and day to avoid DST arithmetic
if isinstance(freq, Day):
if start is not None:
start = start.tz_localize(None)
if end is not None:
end = end.tz_localize(None)
if isinstance(freq, Tick):
i8values = generate_regular_range(start, end, periods, freq, unit=unit)
else:
xdr = _generate_range(
start=start, end=end, periods=periods, offset=freq, unit=unit
)
i8values = np.array([x._value for x in xdr], dtype=np.int64)
endpoint_tz = start.tz if start is not None else end.tz
if tz is not None and endpoint_tz is None:
if not timezones.is_utc(tz):
# short-circuit tz_localize_to_utc which would make
# an unnecessary copy with UTC but be a no-op.
creso = abbrev_to_npy_unit(unit)
i8values = tzconversion.tz_localize_to_utc(
i8values,
tz,
ambiguous=ambiguous,
nonexistent=nonexistent,
creso=creso,
)
# i8values is localized datetime64 array -> have to convert
# start/end as well to compare
if start is not None:
start = start.tz_localize(tz, ambiguous, nonexistent)
if end is not None:
end = end.tz_localize(tz, ambiguous, nonexistent)
else:
# Create a linearly spaced date_range in local time
# Nanosecond-granularity timestamps aren't always correctly
# representable with doubles, so we limit the range that we
# pass to np.linspace as much as possible
periods = cast(int, periods)
i8values = (
np.linspace(0, end._value - start._value, periods, dtype="int64")
+ start._value
)
if i8values.dtype != "i8":
# 2022-01-09 I (brock) am not sure if it is possible for this
# to overflow and cast to e.g. f8, but if it does we need to cast
i8values = i8values.astype("i8")
if start == end:
if not left_inclusive and not right_inclusive:
i8values = i8values[1:-1]
else:
start_i8 = Timestamp(start)._value
end_i8 = Timestamp(end)._value
if not left_inclusive or not right_inclusive:
if not left_inclusive and len(i8values) and i8values[0] == start_i8:
i8values = i8values[1:]
if not right_inclusive and len(i8values) and i8values[-1] == end_i8:
i8values = i8values[:-1]
dt64_values = i8values.view(f"datetime64[{unit}]")
dtype = tz_to_dtype(tz, unit=unit)
return cls._simple_new(dt64_values, freq=freq, dtype=dtype)
# -----------------------------------------------------------------
# DatetimeLike Interface
def _unbox_scalar(self, value) -> np.datetime64:
if not isinstance(value, self._scalar_type) and value is not NaT:
raise ValueError("'value' should be a Timestamp.")
self._check_compatible_with(value)
if value is NaT:
return np.datetime64(value._value, self.unit)
else:
return value.as_unit(self.unit).asm8
def _scalar_from_string(self, value) -> Timestamp | NaTType:
return Timestamp(value, tz=self.tz)
def _check_compatible_with(self, other) -> None:
if other is NaT:
return
self._assert_tzawareness_compat(other)
# -----------------------------------------------------------------
# Descriptive Properties
def _box_func(self, x: np.datetime64) -> Timestamp | NaTType:
# GH#42228
value = x.view("i8")
ts = Timestamp._from_value_and_reso(value, reso=self._creso, tz=self.tz)
return ts
@property
# error: Return type "Union[dtype, DatetimeTZDtype]" of "dtype"
# incompatible with return type "ExtensionDtype" in supertype
# "ExtensionArray"
def dtype(self) -> np.dtype[np.datetime64] | DatetimeTZDtype: # type: ignore[override]
"""
The dtype for the DatetimeArray.
.. warning::
A future version of pandas will change dtype to never be a
``numpy.dtype``. Instead, :attr:`DatetimeArray.dtype` will
always be an instance of an ``ExtensionDtype`` subclass.
Returns
-------
numpy.dtype or DatetimeTZDtype
If the values are tz-naive, then ``np.dtype('datetime64[ns]')``
is returned.
If the values are tz-aware, then the ``DatetimeTZDtype``
is returned.
"""
return self._dtype
@property
def tz(self) -> tzinfo | None:
"""
Return the timezone.
Returns
-------
datetime.tzinfo, pytz.tzinfo.BaseTZInfo, dateutil.tz.tz.tzfile, or None
Returns None when the array is tz-naive.
Examples
--------
For Series:
>>> s = pd.Series(["1/1/2020 10:00:00+00:00", "2/1/2020 11:00:00+00:00"])
>>> s = pd.to_datetime(s)
>>> s
0 2020-01-01 10:00:00+00:00
1 2020-02-01 11:00:00+00:00
dtype: datetime64[ns, UTC]
>>> s.dt.tz
datetime.timezone.utc
For DatetimeIndex:
>>> idx = pd.DatetimeIndex(
... ["1/1/2020 10:00:00+00:00", "2/1/2020 11:00:00+00:00"]
... )
>>> idx.tz
datetime.timezone.utc
"""
# GH 18595
return getattr(self.dtype, "tz", None)
@tz.setter
def tz(self, value):
# GH 3746: Prevent localizing or converting the index by setting tz
raise AttributeError(
"Cannot directly set timezone. Use tz_localize() "
"or tz_convert() as appropriate"
)
@property
def tzinfo(self) -> tzinfo | None:
"""
Alias for tz attribute
"""
return self.tz
@property # NB: override with cache_readonly in immutable subclasses
def is_normalized(self) -> bool:
"""
Returns True if all of the dates are at midnight ("no time")
"""
return is_date_array_normalized(self.asi8, self.tz, reso=self._creso)
@property # NB: override with cache_readonly in immutable subclasses
def _resolution_obj(self) -> Resolution:
return get_resolution(self.asi8, self.tz, reso=self._creso)
# ----------------------------------------------------------------
# Array-Like / EA-Interface Methods
def __array__(self, dtype=None, copy=None) -> np.ndarray:
if dtype is None and self.tz:
# The default for tz-aware is object, to preserve tz info
dtype = object
return super().__array__(dtype=dtype, copy=copy)
def __iter__(self) -> Iterator:
"""
Return an iterator over the boxed values
Yields
------
tstamp : Timestamp
"""
if self.ndim > 1:
for i in range(len(self)):
yield self[i]
else:
# convert in chunks of 10k for efficiency
data = self.asi8
length = len(self)
chunksize = _ITER_CHUNKSIZE
chunks = (length // chunksize) + 1
for i in range(chunks):
start_i = i * chunksize
end_i = min((i + 1) * chunksize, length)
converted = ints_to_pydatetime(
data[start_i:end_i],
tz=self.tz,
box="timestamp",
reso=self._creso,
)
yield from converted
def astype(self, dtype, copy: bool = True):
# We handle
# --> datetime
# --> period
# DatetimeLikeArrayMixin Super handles the rest.
dtype = pandas_dtype(dtype)
if dtype == self.dtype:
if copy:
return self.copy()
return self
elif isinstance(dtype, ExtensionDtype):
if not isinstance(dtype, DatetimeTZDtype):
# e.g. Sparse[datetime64[ns]]
return super().astype(dtype, copy=copy)
elif self.tz is None:
# pre-2.0 this did self.tz_localize(dtype.tz), which did not match
# the Series behavior which did
# values.tz_localize("UTC").tz_convert(dtype.tz)
raise TypeError(
"Cannot use .astype to convert from timezone-naive dtype to "
"timezone-aware dtype. Use obj.tz_localize instead or "
"series.dt.tz_localize instead"
)
else:
# tzaware unit conversion e.g. datetime64[s, UTC]
np_dtype = np.dtype(dtype.str)
res_values = astype_overflowsafe(self._ndarray, np_dtype, copy=copy)
return type(self)._simple_new(res_values, dtype=dtype, freq=self.freq)
elif (
self.tz is None
and lib.is_np_dtype(dtype, "M")
and not is_unitless(dtype)
and is_supported_dtype(dtype)
):
# unit conversion e.g. datetime64[s]
res_values = astype_overflowsafe(self._ndarray, dtype, copy=True)
return type(self)._simple_new(res_values, dtype=res_values.dtype)
# TODO: preserve freq?
elif self.tz is not None and lib.is_np_dtype(dtype, "M"):
# pre-2.0 behavior for DTA/DTI was
# values.tz_convert("UTC").tz_localize(None), which did not match
# the Series behavior
raise TypeError(
"Cannot use .astype to convert from timezone-aware dtype to "
"timezone-naive dtype. Use obj.tz_localize(None) or "
"obj.tz_convert('UTC').tz_localize(None) instead."
)
elif (
self.tz is None
and lib.is_np_dtype(dtype, "M")
and dtype != self.dtype
and is_unitless(dtype)
):
raise TypeError(
"Casting to unit-less dtype 'datetime64' is not supported. "
"Pass e.g. 'datetime64[ns]' instead."
)
elif isinstance(dtype, PeriodDtype):
return self.to_period(freq=dtype.freq)
return dtl.DatetimeLikeArrayMixin.astype(self, dtype, copy)
# -----------------------------------------------------------------
# Rendering Methods
def _format_native_types(
self, *, na_rep: str | float = "NaT", date_format=None, **kwargs
) -> npt.NDArray[np.object_]:
if date_format is None and self._is_dates_only:
# Only dates and no timezone: provide a default format
date_format = "%Y-%m-%d"
return tslib.format_array_from_datetime(
self.asi8, tz=self.tz, format=date_format, na_rep=na_rep, reso=self._creso
)
# -----------------------------------------------------------------
# Comparison Methods
def _assert_tzawareness_compat(self, other) -> None:
# adapted from _Timestamp._assert_tzawareness_compat
other_tz = getattr(other, "tzinfo", None)
other_dtype = getattr(other, "dtype", None)
if isinstance(other_dtype, DatetimeTZDtype):
# Get tzinfo from Series dtype
other_tz = other.dtype.tz
if other is NaT:
# pd.NaT quacks both aware and naive
pass
elif self.tz is None:
if other_tz is not None:
raise TypeError(
"Cannot compare tz-naive and tz-aware datetime-like objects."
)
elif other_tz is None:
raise TypeError(
"Cannot compare tz-naive and tz-aware datetime-like objects"
)
# -----------------------------------------------------------------
# Arithmetic Methods
def _add_offset(self, offset: BaseOffset) -> Self:
assert not isinstance(offset, Tick)
if self.tz is not None:
values = self.tz_localize(None)
else:
values = self
try:
res_values = offset._apply_array(values._ndarray)
if res_values.dtype.kind == "i":
# error: Argument 1 to "view" of "ndarray" has incompatible type
# "dtype[datetime64] | DatetimeTZDtype"; expected
# "dtype[Any] | type[Any] | _SupportsDType[dtype[Any]]"
res_values = res_values.view(values.dtype) # type: ignore[arg-type]
except NotImplementedError:
if get_option("performance_warnings"):
warnings.warn(
"Non-vectorized DateOffset being applied to Series or "
"DatetimeIndex.",
PerformanceWarning,
stacklevel=find_stack_level(),
)
res_values = self.astype("O") + offset
# TODO(GH#55564): as_unit will be unnecessary
result = type(self)._from_sequence(res_values).as_unit(self.unit)
if not len(self):
# GH#30336 _from_sequence won't be able to infer self.tz
return result.tz_localize(self.tz)
else:
result = type(self)._simple_new(res_values, dtype=res_values.dtype)
if offset.normalize:
result = result.normalize()
result._freq = None
if self.tz is not None:
result = result.tz_localize(self.tz)
return result
# -----------------------------------------------------------------
# Timezone Conversion and Localization Methods
def _local_timestamps(self) -> npt.NDArray[np.int64]:
"""
Convert to an i8 (unix-like nanosecond timestamp) representation
while keeping the local timezone and not using UTC.
This is used to calculate time-of-day information as if the timestamps
were timezone-naive.
"""
if self.tz is None or timezones.is_utc(self.tz):
# Avoid the copy that would be made in tzconversion
return self.asi8
return tz_convert_from_utc(self.asi8, self.tz, reso=self._creso)
def tz_convert(self, tz) -> Self:
"""
Convert tz-aware Datetime Array/Index from one time zone to another.
Parameters
----------
tz : str, pytz.timezone, dateutil.tz.tzfile, datetime.tzinfo or None
Time zone for time. Corresponding timestamps would be converted
to this time zone of the Datetime Array/Index. A `tz` of None will
convert to UTC and remove the timezone information.
Returns
-------
Array or Index
Raises
------
TypeError
If Datetime Array/Index is tz-naive.
See Also
--------
DatetimeIndex.tz : A timezone that has a variable offset from UTC.
DatetimeIndex.tz_localize : Localize tz-naive DatetimeIndex to a
given time zone, or remove timezone from a tz-aware DatetimeIndex.
Examples
--------
With the `tz` parameter, we can change the DatetimeIndex
to other time zones:
>>> dti = pd.date_range(
... start="2014-08-01 09:00", freq="h", periods=3, tz="Europe/Berlin"
... )
>>> dti
DatetimeIndex(['2014-08-01 09:00:00+02:00',
'2014-08-01 10:00:00+02:00',
'2014-08-01 11:00:00+02:00'],
dtype='datetime64[ns, Europe/Berlin]', freq='h')
>>> dti.tz_convert("US/Central")
DatetimeIndex(['2014-08-01 02:00:00-05:00',
'2014-08-01 03:00:00-05:00',
'2014-08-01 04:00:00-05:00'],
dtype='datetime64[ns, US/Central]', freq='h')
With the ``tz=None``, we can remove the timezone (after converting
to UTC if necessary):
>>> dti = pd.date_range(
... start="2014-08-01 09:00", freq="h", periods=3, tz="Europe/Berlin"
... )
>>> dti
DatetimeIndex(['2014-08-01 09:00:00+02:00',
'2014-08-01 10:00:00+02:00',
'2014-08-01 11:00:00+02:00'],
dtype='datetime64[ns, Europe/Berlin]', freq='h')
>>> dti.tz_convert(None)
DatetimeIndex(['2014-08-01 07:00:00',
'2014-08-01 08:00:00',
'2014-08-01 09:00:00'],
dtype='datetime64[ns]', freq='h')
"""
tz = timezones.maybe_get_tz(tz)
if self.tz is None:
# tz naive, use tz_localize
raise TypeError(
"Cannot convert tz-naive timestamps, use tz_localize to localize"
)
# No conversion since timestamps are all UTC to begin with
dtype = tz_to_dtype(tz, unit=self.unit)
return self._simple_new(self._ndarray, dtype=dtype, freq=self.freq)
@dtl.ravel_compat
def tz_localize(
self,
tz,
ambiguous: TimeAmbiguous = "raise",
nonexistent: TimeNonexistent = "raise",
) -> Self:
"""
Localize tz-naive Datetime Array/Index to tz-aware Datetime Array/Index.
This method takes a time zone (tz) naive Datetime Array/Index object
and makes this time zone aware. It does not move the time to another
time zone.
This method can also be used to do the inverse -- to create a time
zone unaware object from an aware object. To that end, pass `tz=None`.
Parameters
----------
tz : str, pytz.timezone, dateutil.tz.tzfile, datetime.tzinfo or None
Time zone to convert timestamps to. Passing ``None`` will
remove the time zone information preserving local time.
ambiguous : 'infer', 'NaT', bool array, default 'raise'
When clocks moved backward due to DST, ambiguous times may arise.
For example in Central European Time (UTC+01), when going from
03:00 DST to 02:00 non-DST, 02:30:00 local time occurs both at
00:30:00 UTC and at 01:30:00 UTC. In such a situation, the
`ambiguous` parameter dictates how ambiguous times should be
handled.
- 'infer' will attempt to infer fall dst-transition hours based on
order
- bool-ndarray where True signifies a DST time, False signifies a
non-DST time (note that this flag is only applicable for
ambiguous times)
- 'NaT' will return NaT where there are ambiguous times
- 'raise' will raise an AmbiguousTimeError if there are ambiguous
times.
nonexistent : 'shift_forward', 'shift_backward, 'NaT', timedelta, \
default 'raise'
A nonexistent time does not exist in a particular timezone
where clocks moved forward due to DST.
- 'shift_forward' will shift the nonexistent time forward to the
closest existing time
- 'shift_backward' will shift the nonexistent time backward to the
closest existing time
- 'NaT' will return NaT where there are nonexistent times
- timedelta objects will shift nonexistent times by the timedelta
- 'raise' will raise an NonExistentTimeError if there are
nonexistent times.
Returns
-------
Same type as self
Array/Index converted to the specified time zone.
Raises
------
TypeError
If the Datetime Array/Index is tz-aware and tz is not None.
See Also
--------
DatetimeIndex.tz_convert : Convert tz-aware DatetimeIndex from
one time zone to another.
Examples
--------
>>> tz_naive = pd.date_range('2018-03-01 09:00', periods=3)
>>> tz_naive
DatetimeIndex(['2018-03-01 09:00:00', '2018-03-02 09:00:00',
'2018-03-03 09:00:00'],