forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathperiod.pyx
1248 lines (1047 loc) · 42.1 KB
/
period.pyx
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 datetime import datetime, date, timedelta
import operator
from cpython cimport (
PyUnicode_Check,
PyObject_RichCompareBool,
Py_EQ, Py_NE)
from numpy cimport (int8_t, int32_t, int64_t, import_array, ndarray,
NPY_INT64, NPY_DATETIME, NPY_TIMEDELTA)
import numpy as np
cdef extern from "datetime_helper.h":
double total_seconds(object)
from libc.stdlib cimport free
from pandas import compat
from pandas.compat import PY2
cimport cython
from datetime cimport (
is_leapyear,
PyDateTime_IMPORT,
pandas_datetimestruct,
pandas_datetimestruct_to_datetime,
pandas_datetime_to_datetimestruct,
PANDAS_FR_ns,
INT32_MIN)
cimport util, lib
from lib cimport is_null_datetimelike, is_period
from pandas._libs import tslib, lib
from pandas._libs.tslib import (Timedelta, Timestamp, iNaT,
NaT, _get_utcoffset)
from tslib cimport (
maybe_get_tz,
_is_utc,
_is_tzlocal,
_get_dst_info,
_nat_scalar_rules)
from pandas.tseries import offsets
from pandas.core.tools.datetimes import parse_time_string
from pandas.tseries import frequencies
cdef int64_t NPY_NAT = util.get_nat()
cdef int RESO_US = frequencies.RESO_US
cdef int RESO_MS = frequencies.RESO_MS
cdef int RESO_SEC = frequencies.RESO_SEC
cdef int RESO_MIN = frequencies.RESO_MIN
cdef int RESO_HR = frequencies.RESO_HR
cdef int RESO_DAY = frequencies.RESO_DAY
cdef extern from "period_helper.h":
ctypedef struct date_info:
int64_t absdate
double abstime
double second
int minute
int hour
int day
int month
int quarter
int year
int day_of_week
int day_of_year
int calendar
ctypedef struct asfreq_info:
int from_week_end
int to_week_end
int from_a_year_end
int to_a_year_end
int from_q_year_end
int to_q_year_end
ctypedef int64_t (*freq_conv_func)(int64_t, char, asfreq_info*)
void initialize_daytime_conversion_factor_matrix()
int64_t asfreq(int64_t dtordinal, int freq1, int freq2,
char relation) except INT32_MIN
freq_conv_func get_asfreq_func(int fromFreq, int toFreq)
void get_asfreq_info(int fromFreq, int toFreq, asfreq_info *af_info)
int64_t get_period_ordinal(int year, int month, int day,
int hour, int minute, int second,
int microseconds, int picoseconds,
int freq) nogil except INT32_MIN
int64_t get_python_ordinal(int64_t period_ordinal,
int freq) except INT32_MIN
int get_date_info(int64_t ordinal, int freq,
date_info *dinfo) nogil except INT32_MIN
double getAbsTime(int, int64_t, int64_t)
int pyear(int64_t ordinal, int freq) except INT32_MIN
int pqyear(int64_t ordinal, int freq) except INT32_MIN
int pquarter(int64_t ordinal, int freq) except INT32_MIN
int pmonth(int64_t ordinal, int freq) except INT32_MIN
int pday(int64_t ordinal, int freq) except INT32_MIN
int pweekday(int64_t ordinal, int freq) except INT32_MIN
int pday_of_week(int64_t ordinal, int freq) except INT32_MIN
int pday_of_year(int64_t ordinal, int freq) except INT32_MIN
int pweek(int64_t ordinal, int freq) except INT32_MIN
int phour(int64_t ordinal, int freq) except INT32_MIN
int pminute(int64_t ordinal, int freq) except INT32_MIN
int psecond(int64_t ordinal, int freq) except INT32_MIN
int pdays_in_month(int64_t ordinal, int freq) except INT32_MIN
char *c_strftime(date_info *dinfo, char *fmt)
int get_yq(int64_t ordinal, int freq, int *quarter, int *year)
initialize_daytime_conversion_factor_matrix()
# Period logic
#----------------------------------------------------------------------
@cython.wraparound(False)
@cython.boundscheck(False)
def dt64arr_to_periodarr(ndarray[int64_t] dtarr, int freq, tz=None):
"""
Convert array of datetime64 values (passed in as 'i8' dtype) to a set of
periods corresponding to desired frequency, per period convention.
"""
cdef:
ndarray[int64_t] out
Py_ssize_t i, l
pandas_datetimestruct dts
l = len(dtarr)
out = np.empty(l, dtype='i8')
if tz is None:
with nogil:
for i in range(l):
if dtarr[i] == NPY_NAT:
out[i] = NPY_NAT
continue
pandas_datetime_to_datetimestruct(dtarr[i], PANDAS_FR_ns, &dts)
out[i] = get_period_ordinal(dts.year, dts.month, dts.day,
dts.hour, dts.min, dts.sec,
dts.us, dts.ps, freq)
else:
out = localize_dt64arr_to_period(dtarr, freq, tz)
return out
@cython.wraparound(False)
@cython.boundscheck(False)
def periodarr_to_dt64arr(ndarray[int64_t] periodarr, int freq):
"""
Convert array to datetime64 values from a set of ordinals corresponding to
periods per period convention.
"""
cdef:
ndarray[int64_t] out
Py_ssize_t i, l
l = len(periodarr)
out = np.empty(l, dtype='i8')
with nogil:
for i in range(l):
if periodarr[i] == NPY_NAT:
out[i] = NPY_NAT
continue
out[i] = period_ordinal_to_dt64(periodarr[i], freq)
return out
cdef char START = 'S'
cdef char END = 'E'
cpdef int64_t period_asfreq(int64_t period_ordinal, int freq1, int freq2,
bint end):
"""
Convert period ordinal from one frequency to another, and if upsampling,
choose to use start ('S') or end ('E') of period.
"""
cdef:
int64_t retval
if period_ordinal == iNaT:
return iNaT
if end:
retval = asfreq(period_ordinal, freq1, freq2, END)
else:
retval = asfreq(period_ordinal, freq1, freq2, START)
if retval == INT32_MIN:
raise ValueError('Frequency conversion failed')
return retval
def period_asfreq_arr(ndarray[int64_t] arr, int freq1, int freq2, bint end):
"""
Convert int64-array of period ordinals from one frequency to another, and
if upsampling, choose to use start ('S') or end ('E') of period.
"""
cdef:
ndarray[int64_t] result
Py_ssize_t i, n
freq_conv_func func
asfreq_info finfo
int64_t val, ordinal
char relation
n = len(arr)
result = np.empty(n, dtype=np.int64)
func = get_asfreq_func(freq1, freq2)
get_asfreq_info(freq1, freq2, &finfo)
if end:
relation = END
else:
relation = START
mask = arr == iNaT
if mask.any(): # NaT process
for i in range(n):
val = arr[i]
if val != iNaT:
val = func(val, relation, &finfo)
if val == INT32_MIN:
raise ValueError("Unable to convert to desired frequency.")
result[i] = val
else:
for i in range(n):
val = func(arr[i], relation, &finfo)
if val == INT32_MIN:
raise ValueError("Unable to convert to desired frequency.")
result[i] = val
return result
def period_ordinal(int y, int m, int d, int h, int min,
int s, int us, int ps, int freq):
cdef:
int64_t ordinal
return get_period_ordinal(y, m, d, h, min, s, us, ps, freq)
cpdef int64_t period_ordinal_to_dt64(int64_t ordinal, int freq) nogil:
cdef:
pandas_datetimestruct dts
date_info dinfo
float subsecond_fraction
if ordinal == NPY_NAT:
return NPY_NAT
get_date_info(ordinal, freq, &dinfo)
dts.year = dinfo.year
dts.month = dinfo.month
dts.day = dinfo.day
dts.hour = dinfo.hour
dts.min = dinfo.minute
dts.sec = int(dinfo.second)
subsecond_fraction = dinfo.second - dts.sec
dts.us = int((subsecond_fraction) * 1e6)
dts.ps = int(((subsecond_fraction) * 1e6 - dts.us) * 1e6)
return pandas_datetimestruct_to_datetime(PANDAS_FR_ns, &dts)
def period_format(int64_t value, int freq, object fmt=None):
cdef:
int freq_group
if value == iNaT:
return repr(NaT)
if fmt is None:
freq_group = (freq // 1000) * 1000
if freq_group == 1000: # FR_ANN
fmt = b'%Y'
elif freq_group == 2000: # FR_QTR
fmt = b'%FQ%q'
elif freq_group == 3000: # FR_MTH
fmt = b'%Y-%m'
elif freq_group == 4000: # WK
left = period_asfreq(value, freq, 6000, 0)
right = period_asfreq(value, freq, 6000, 1)
return '%s/%s' % (period_format(left, 6000),
period_format(right, 6000))
elif (freq_group == 5000 # BUS
or freq_group == 6000): # DAY
fmt = b'%Y-%m-%d'
elif freq_group == 7000: # HR
fmt = b'%Y-%m-%d %H:00'
elif freq_group == 8000: # MIN
fmt = b'%Y-%m-%d %H:%M'
elif freq_group == 9000: # SEC
fmt = b'%Y-%m-%d %H:%M:%S'
elif freq_group == 10000: # MILLISEC
fmt = b'%Y-%m-%d %H:%M:%S.%l'
elif freq_group == 11000: # MICROSEC
fmt = b'%Y-%m-%d %H:%M:%S.%u'
elif freq_group == 12000: # NANOSEC
fmt = b'%Y-%m-%d %H:%M:%S.%n'
else:
raise ValueError('Unknown freq: %d' % freq)
return _period_strftime(value, freq, fmt)
cdef list extra_fmts = [(b"%q", b"^`AB`^"),
(b"%f", b"^`CD`^"),
(b"%F", b"^`EF`^"),
(b"%l", b"^`GH`^"),
(b"%u", b"^`IJ`^"),
(b"%n", b"^`KL`^")]
cdef list str_extra_fmts = ["^`AB`^", "^`CD`^", "^`EF`^",
"^`GH`^", "^`IJ`^", "^`KL`^"]
cdef object _period_strftime(int64_t value, int freq, object fmt):
import sys
cdef:
Py_ssize_t i
date_info dinfo
char *formatted
object pat, repl, result
list found_pat = [False] * len(extra_fmts)
int year, quarter
if PyUnicode_Check(fmt):
fmt = fmt.encode('utf-8')
get_date_info(value, freq, &dinfo)
for i in range(len(extra_fmts)):
pat = extra_fmts[i][0]
repl = extra_fmts[i][1]
if pat in fmt:
fmt = fmt.replace(pat, repl)
found_pat[i] = True
formatted = c_strftime(&dinfo, <char*> fmt)
result = util.char_to_string(formatted)
free(formatted)
for i in range(len(extra_fmts)):
if found_pat[i]:
if get_yq(value, freq, &quarter, &year) < 0:
raise ValueError('Unable to get quarter and year')
if i == 0:
repl = '%d' % quarter
elif i == 1: # %f, 2-digit year
repl = '%.2d' % (year % 100)
elif i == 2:
repl = '%d' % year
elif i == 3:
repl = '%03d' % (value % 1000)
elif i == 4:
repl = '%06d' % (value % 1000000)
elif i == 5:
repl = '%09d' % (value % 1000000000)
result = result.replace(str_extra_fmts[i], repl)
if PY2:
result = result.decode('utf-8', 'ignore')
return result
# period accessors
ctypedef int (*accessor)(int64_t ordinal, int freq) except INT32_MIN
def get_period_field(int code, int64_t value, int freq):
cdef accessor f = _get_accessor_func(code)
if f is NULL:
raise ValueError('Unrecognized period code: %d' % code)
if value == iNaT:
return np.nan
return f(value, freq)
def get_period_field_arr(int code, ndarray[int64_t] arr, int freq):
cdef:
Py_ssize_t i, sz
ndarray[int64_t] out
accessor f
f = _get_accessor_func(code)
if f is NULL:
raise ValueError('Unrecognized period code: %d' % code)
sz = len(arr)
out = np.empty(sz, dtype=np.int64)
for i in range(sz):
if arr[i] == iNaT:
out[i] = -1
continue
out[i] = f(arr[i], freq)
return out
cdef accessor _get_accessor_func(int code):
if code == 0:
return &pyear
elif code == 1:
return &pqyear
elif code == 2:
return &pquarter
elif code == 3:
return &pmonth
elif code == 4:
return &pday
elif code == 5:
return &phour
elif code == 6:
return &pminute
elif code == 7:
return &psecond
elif code == 8:
return &pweek
elif code == 9:
return &pday_of_year
elif code == 10:
return &pweekday
elif code == 11:
return &pdays_in_month
return NULL
def extract_ordinals(ndarray[object] values, freq):
cdef:
Py_ssize_t i, n = len(values)
ndarray[int64_t] ordinals = np.empty(n, dtype=np.int64)
object p
freqstr = Period._maybe_convert_freq(freq).freqstr
for i in range(n):
p = values[i]
if is_null_datetimelike(p):
ordinals[i] = iNaT
else:
try:
ordinals[i] = p.ordinal
if p.freqstr != freqstr:
msg = _DIFFERENT_FREQ_INDEX.format(freqstr, p.freqstr)
raise IncompatibleFrequency(msg)
except AttributeError:
p = Period(p, freq=freq)
if p is NaT:
# input may contain NaT-like string
ordinals[i] = iNaT
else:
ordinals[i] = p.ordinal
return ordinals
def extract_freq(ndarray[object] values):
cdef:
Py_ssize_t i, n = len(values)
object p
for i in range(n):
p = values[i]
try:
# now Timestamp / NaT has freq attr
if is_period(p):
return p.freq
except AttributeError:
pass
raise ValueError('freq not specified and cannot be inferred')
cpdef resolution(ndarray[int64_t] stamps, tz=None):
cdef:
Py_ssize_t i, n = len(stamps)
pandas_datetimestruct dts
int reso = RESO_DAY, curr_reso
if tz is not None:
tz = maybe_get_tz(tz)
return _reso_local(stamps, tz)
else:
for i in range(n):
if stamps[i] == NPY_NAT:
continue
pandas_datetime_to_datetimestruct(stamps[i], PANDAS_FR_ns, &dts)
curr_reso = _reso_stamp(&dts)
if curr_reso < reso:
reso = curr_reso
return reso
cdef inline int _reso_stamp(pandas_datetimestruct *dts):
if dts.us != 0:
if dts.us % 1000 == 0:
return RESO_MS
return RESO_US
elif dts.sec != 0:
return RESO_SEC
elif dts.min != 0:
return RESO_MIN
elif dts.hour != 0:
return RESO_HR
return RESO_DAY
cdef _reso_local(ndarray[int64_t] stamps, object tz):
cdef:
Py_ssize_t n = len(stamps)
int reso = RESO_DAY, curr_reso
ndarray[int64_t] trans, deltas, pos
pandas_datetimestruct dts
if _is_utc(tz):
for i in range(n):
if stamps[i] == NPY_NAT:
continue
pandas_datetime_to_datetimestruct(stamps[i], PANDAS_FR_ns, &dts)
curr_reso = _reso_stamp(&dts)
if curr_reso < reso:
reso = curr_reso
elif _is_tzlocal(tz):
for i in range(n):
if stamps[i] == NPY_NAT:
continue
pandas_datetime_to_datetimestruct(stamps[i], PANDAS_FR_ns,
&dts)
dt = datetime(dts.year, dts.month, dts.day, dts.hour,
dts.min, dts.sec, dts.us, tz)
delta = int(total_seconds(_get_utcoffset(tz, dt))) * 1000000000
pandas_datetime_to_datetimestruct(stamps[i] + delta,
PANDAS_FR_ns, &dts)
curr_reso = _reso_stamp(&dts)
if curr_reso < reso:
reso = curr_reso
else:
# Adjust datetime64 timestamp, recompute datetimestruct
trans, deltas, typ = _get_dst_info(tz)
_pos = trans.searchsorted(stamps, side='right') - 1
if _pos.dtype != np.int64:
_pos = _pos.astype(np.int64)
pos = _pos
# statictzinfo
if typ not in ['pytz', 'dateutil']:
for i in range(n):
if stamps[i] == NPY_NAT:
continue
pandas_datetime_to_datetimestruct(stamps[i] + deltas[0],
PANDAS_FR_ns, &dts)
curr_reso = _reso_stamp(&dts)
if curr_reso < reso:
reso = curr_reso
else:
for i in range(n):
if stamps[i] == NPY_NAT:
continue
pandas_datetime_to_datetimestruct(stamps[i] + deltas[pos[i]],
PANDAS_FR_ns, &dts)
curr_reso = _reso_stamp(&dts)
if curr_reso < reso:
reso = curr_reso
return reso
# period helpers
cdef ndarray[int64_t] localize_dt64arr_to_period(ndarray[int64_t] stamps,
int freq, object tz):
cdef:
Py_ssize_t n = len(stamps)
ndarray[int64_t] result = np.empty(n, dtype=np.int64)
ndarray[int64_t] trans, deltas, pos
pandas_datetimestruct dts
if _is_utc(tz):
for i in range(n):
if stamps[i] == NPY_NAT:
result[i] = NPY_NAT
continue
pandas_datetime_to_datetimestruct(stamps[i], PANDAS_FR_ns, &dts)
result[i] = get_period_ordinal(dts.year, dts.month, dts.day,
dts.hour, dts.min, dts.sec,
dts.us, dts.ps, freq)
elif _is_tzlocal(tz):
for i in range(n):
if stamps[i] == NPY_NAT:
result[i] = NPY_NAT
continue
pandas_datetime_to_datetimestruct(stamps[i], PANDAS_FR_ns,
&dts)
dt = datetime(dts.year, dts.month, dts.day, dts.hour,
dts.min, dts.sec, dts.us, tz)
delta = int(total_seconds(_get_utcoffset(tz, dt))) * 1000000000
pandas_datetime_to_datetimestruct(stamps[i] + delta,
PANDAS_FR_ns, &dts)
result[i] = get_period_ordinal(dts.year, dts.month, dts.day,
dts.hour, dts.min, dts.sec,
dts.us, dts.ps, freq)
else:
# Adjust datetime64 timestamp, recompute datetimestruct
trans, deltas, typ = _get_dst_info(tz)
_pos = trans.searchsorted(stamps, side='right') - 1
if _pos.dtype != np.int64:
_pos = _pos.astype(np.int64)
pos = _pos
# statictzinfo
if typ not in ['pytz', 'dateutil']:
for i in range(n):
if stamps[i] == NPY_NAT:
result[i] = NPY_NAT
continue
pandas_datetime_to_datetimestruct(stamps[i] + deltas[0],
PANDAS_FR_ns, &dts)
result[i] = get_period_ordinal(dts.year, dts.month, dts.day,
dts.hour, dts.min, dts.sec,
dts.us, dts.ps, freq)
else:
for i in range(n):
if stamps[i] == NPY_NAT:
result[i] = NPY_NAT
continue
pandas_datetime_to_datetimestruct(stamps[i] + deltas[pos[i]],
PANDAS_FR_ns, &dts)
result[i] = get_period_ordinal(dts.year, dts.month, dts.day,
dts.hour, dts.min, dts.sec,
dts.us, dts.ps, freq)
return result
_DIFFERENT_FREQ = "Input has different freq={1} from Period(freq={0})"
_DIFFERENT_FREQ_INDEX = ("Input has different freq={1} "
"from PeriodIndex(freq={0})")
class IncompatibleFrequency(ValueError):
pass
cdef class _Period(object):
cdef readonly:
int64_t ordinal
object freq
_comparables = ['name', 'freqstr']
_typ = 'period'
def __cinit__(self, ordinal, freq):
self.ordinal = ordinal
self.freq = freq
@classmethod
def _maybe_convert_freq(cls, object freq):
if isinstance(freq, (int, tuple)):
code, stride = frequencies.get_freq_code(freq)
freq = frequencies._get_freq_str(code, stride)
freq = frequencies.to_offset(freq)
if freq.n <= 0:
raise ValueError('Frequency must be positive, because it'
' represents span: {0}'.format(freq.freqstr))
return freq
@classmethod
def _from_ordinal(cls, ordinal, freq):
"""
Fast creation from an ordinal and freq that are already validated!
"""
if ordinal == iNaT:
return NaT
else:
freq = cls._maybe_convert_freq(freq)
self = _Period.__new__(cls, ordinal, freq)
return self
def __richcmp__(self, other, op):
if isinstance(other, Period):
if other.freq != self.freq:
msg = _DIFFERENT_FREQ.format(self.freqstr, other.freqstr)
raise IncompatibleFrequency(msg)
return PyObject_RichCompareBool(self.ordinal, other.ordinal, op)
elif other is NaT:
return _nat_scalar_rules[op]
# index/series like
elif hasattr(other, '_typ'):
return NotImplemented
else:
if op == Py_EQ:
return NotImplemented
elif op == Py_NE:
return NotImplemented
raise TypeError('Cannot compare type %r with type %r' %
(type(self).__name__, type(other).__name__))
def __hash__(self):
return hash((self.ordinal, self.freqstr))
def _add_delta(self, other):
if isinstance(other, (timedelta, np.timedelta64,
offsets.Tick, Timedelta)):
offset = frequencies.to_offset(self.freq.rule_code)
if isinstance(offset, offsets.Tick):
nanos = tslib._delta_to_nanoseconds(other)
offset_nanos = tslib._delta_to_nanoseconds(offset)
if nanos % offset_nanos == 0:
ordinal = self.ordinal + (nanos // offset_nanos)
return Period(ordinal=ordinal, freq=self.freq)
msg = 'Input cannot be converted to Period(freq={0})'
raise IncompatibleFrequency(msg.format(self.freqstr))
elif isinstance(other, offsets.DateOffset):
freqstr = other.rule_code
base = frequencies.get_base_alias(freqstr)
if base == self.freq.rule_code:
ordinal = self.ordinal + other.n
return Period(ordinal=ordinal, freq=self.freq)
msg = _DIFFERENT_FREQ.format(self.freqstr, other.freqstr)
raise IncompatibleFrequency(msg)
else: # pragma no cover
return NotImplemented
def __add__(self, other):
if isinstance(self, Period):
if isinstance(other, (timedelta, np.timedelta64,
offsets.DateOffset,
Timedelta)):
return self._add_delta(other)
elif other is NaT:
return NaT
elif lib.is_integer(other):
ordinal = self.ordinal + other * self.freq.n
return Period(ordinal=ordinal, freq=self.freq)
else: # pragma: no cover
return NotImplemented
elif isinstance(other, Period):
return other + self
else:
return NotImplemented
def __sub__(self, other):
if isinstance(self, Period):
if isinstance(other, (timedelta, np.timedelta64,
offsets.DateOffset,
Timedelta)):
neg_other = -other
return self + neg_other
elif lib.is_integer(other):
ordinal = self.ordinal - other * self.freq.n
return Period(ordinal=ordinal, freq=self.freq)
elif isinstance(other, Period):
if other.freq != self.freq:
msg = _DIFFERENT_FREQ.format(self.freqstr, other.freqstr)
raise IncompatibleFrequency(msg)
return self.ordinal - other.ordinal
elif getattr(other, '_typ', None) == 'periodindex':
return -other.__sub__(self)
else: # pragma: no cover
return NotImplemented
elif isinstance(other, Period):
if self is NaT:
return NaT
return NotImplemented
else:
return NotImplemented
def asfreq(self, freq, how='E'):
"""
Convert Period to desired frequency, either at the start or end of the
interval
Parameters
----------
freq : string
how : {'E', 'S', 'end', 'start'}, default 'end'
Start or end of the timespan
Returns
-------
resampled : Period
"""
freq = self._maybe_convert_freq(freq)
how = _validate_end_alias(how)
base1, mult1 = frequencies.get_freq_code(self.freq)
base2, mult2 = frequencies.get_freq_code(freq)
# mult1 can't be negative or 0
end = how == 'E'
if end:
ordinal = self.ordinal + mult1 - 1
else:
ordinal = self.ordinal
ordinal = period_asfreq(ordinal, base1, base2, end)
return Period(ordinal=ordinal, freq=freq)
@property
def start_time(self):
return self.to_timestamp(how='S')
@property
def end_time(self):
# freq.n can't be negative or 0
# ordinal = (self + self.freq.n).start_time.value - 1
ordinal = (self + 1).start_time.value - 1
return Timestamp(ordinal)
def to_timestamp(self, freq=None, how='start', tz=None):
"""
Return the Timestamp representation of the Period at the target
frequency at the specified end (how) of the Period
Parameters
----------
freq : string or DateOffset, default is 'D' if self.freq is week or
longer and 'S' otherwise
Target frequency
how: str, default 'S' (start)
'S', 'E'. Can be aliased as case insensitive
'Start', 'Finish', 'Begin', 'End'
Returns
-------
Timestamp
"""
if freq is not None:
freq = self._maybe_convert_freq(freq)
how = _validate_end_alias(how)
if freq is None:
base, mult = frequencies.get_freq_code(self.freq)
freq = frequencies.get_to_timestamp_base(base)
base, mult = frequencies.get_freq_code(freq)
val = self.asfreq(freq, how)
dt64 = period_ordinal_to_dt64(val.ordinal, base)
return Timestamp(dt64, tz=tz)
cdef _field(self, alias):
base, mult = frequencies.get_freq_code(self.freq)
return get_period_field(alias, self.ordinal, base)
property year:
def __get__(self):
return self._field(0)
property month:
def __get__(self):
return self._field(3)
property day:
def __get__(self):
return self._field(4)
property hour:
def __get__(self):
return self._field(5)
property minute:
def __get__(self):
return self._field(6)
property second:
def __get__(self):
return self._field(7)
property weekofyear:
def __get__(self):
return self._field(8)
property week:
def __get__(self):
return self.weekofyear
property dayofweek:
def __get__(self):
return self._field(10)
property weekday:
def __get__(self):
return self.dayofweek
property dayofyear:
def __get__(self):
return self._field(9)
property quarter:
def __get__(self):
return self._field(2)
property qyear:
def __get__(self):
return self._field(1)
property days_in_month:
def __get__(self):
return self._field(11)
property daysinmonth:
def __get__(self):
return self.days_in_month
property is_leap_year:
def __get__(self):
return bool(is_leapyear(self._field(0)))
@classmethod
def now(cls, freq=None):
return Period(datetime.now(), freq=freq)
# HACK IT UP AND YOU BETTER FIX IT SOON
def __str__(self):
return self.__unicode__()
@property
def freqstr(self):
return self.freq.freqstr
def __repr__(self):
base, mult = frequencies.get_freq_code(self.freq)
formatted = period_format(self.ordinal, base)
return "Period('%s', '%s')" % (formatted, self.freqstr)
def __unicode__(self):
"""
Return a string representation for a particular DataFrame
Invoked by unicode(df) in py2 only. Yields a Unicode String in both
py2/py3.
"""
base, mult = frequencies.get_freq_code(self.freq)
formatted = period_format(self.ordinal, base)
value = ("%s" % formatted)
return value
def __setstate__(self, state):
self.freq=state[1]
self.ordinal=state[2]
def __reduce__(self):
object_state = None, self.freq, self.ordinal
return (Period, object_state)
def strftime(self, fmt):
"""
Returns the string representation of the :class:`Period`, depending
on the selected :keyword:`format`. :keyword:`format` must be a string
containing one or several directives. The method recognizes the same
directives as the :func:`time.strftime` function of the standard Python
distribution, as well as the specific additional directives ``%f``,
``%F``, ``%q``. (formatting & docs originally from scikits.timeries)
+-----------+--------------------------------+-------+
| Directive | Meaning | Notes |
+===========+================================+=======+
| ``%a`` | Locale's abbreviated weekday | |
| | name. | |
+-----------+--------------------------------+-------+
| ``%A`` | Locale's full weekday name. | |
+-----------+--------------------------------+-------+
| ``%b`` | Locale's abbreviated month | |
| | name. | |
+-----------+--------------------------------+-------+
| ``%B`` | Locale's full month name. | |
+-----------+--------------------------------+-------+
| ``%c`` | Locale's appropriate date and | |
| | time representation. | |
+-----------+--------------------------------+-------+
| ``%d`` | Day of the month as a decimal | |
| | number [01,31]. | |
+-----------+--------------------------------+-------+
| ``%f`` | 'Fiscal' year without a | \(1) |
| | century as a decimal number | |
| | [00,99] | |
+-----------+--------------------------------+-------+
| ``%F`` | 'Fiscal' year with a century | \(2) |
| | as a decimal number | |
+-----------+--------------------------------+-------+
| ``%H`` | Hour (24-hour clock) as a | |
| | decimal number [00,23]. | |