forked from pandas-dev/pandas
/
algos_common_helper.pxi.in
591 lines (480 loc) · 15.6 KB
/
algos_common_helper.pxi.in
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
"""
Template for each `dtype` helper function using 1-d template
# 1-d template
- map_indices
- pad
- pad_1d
- pad_2d
- backfill
- backfill_1d
- backfill_2d
- is_monotonic
- arrmap
WARNING: DO NOT edit .pxi FILE directly, .pxi is generated from .pxi.in
"""
#----------------------------------------------------------------------
# 1-d template
#----------------------------------------------------------------------
{{py:
# name, c_type, dtype, can_hold_na, nogil
dtypes = [('float64', 'float64_t', 'np.float64', True, True),
('float32', 'float32_t', 'np.float32', True, True),
('object', 'object', 'object', True, False),
('int32', 'int32_t', 'np.int32', False, True),
('int64', 'int64_t', 'np.int64', False, True),
('uint64', 'uint64_t', 'np.uint64', False, True),
('bool', 'uint8_t', 'np.bool', False, True)]
def get_dispatch(dtypes):
for name, c_type, dtype, can_hold_na, nogil in dtypes:
nogil_str = 'with nogil:' if nogil else ''
tab = ' ' if nogil else ''
yield name, c_type, dtype, can_hold_na, nogil_str, tab
}}
{{for name, c_type, dtype, can_hold_na, nogil_str, tab
in get_dispatch(dtypes)}}
@cython.wraparound(False)
@cython.boundscheck(False)
cpdef map_indices_{{name}}(ndarray[{{c_type}}] index):
"""
Produce a dict mapping the values of the input array to their respective
locations.
Example:
array(['hi', 'there']) --> {'hi' : 0 , 'there' : 1}
Better to do this with Cython because of the enormous speed boost.
"""
cdef Py_ssize_t i, length
cdef dict result = {}
length = len(index)
for i in range(length):
result[index[i]] = i
return result
@cython.boundscheck(False)
@cython.wraparound(False)
def pad_{{name}}(ndarray[{{c_type}}] old, ndarray[{{c_type}}] new,
limit=None):
cdef Py_ssize_t i, j, nleft, nright
cdef ndarray[int64_t, ndim=1] indexer
cdef {{c_type}} cur, next
cdef int lim, fill_count = 0
nleft = len(old)
nright = len(new)
indexer = np.empty(nright, dtype=np.int64)
indexer.fill(-1)
if limit is None:
lim = nright
else:
if not util.is_integer_object(limit):
raise ValueError('Limit must be an integer')
if limit < 1:
raise ValueError('Limit must be greater than 0')
lim = limit
if nleft == 0 or nright == 0 or new[nright - 1] < old[0]:
return indexer
i = j = 0
cur = old[0]
while j <= nright - 1 and new[j] < cur:
j += 1
while True:
if j == nright:
break
if i == nleft - 1:
while j < nright:
if new[j] == cur:
indexer[j] = i
elif new[j] > cur and fill_count < lim:
indexer[j] = i
fill_count += 1
j += 1
break
next = old[i + 1]
while j < nright and cur <= new[j] < next:
if new[j] == cur:
indexer[j] = i
elif fill_count < lim:
indexer[j] = i
fill_count += 1
j += 1
fill_count = 0
i += 1
cur = next
return indexer
@cython.boundscheck(False)
@cython.wraparound(False)
def pad_inplace_{{name}}(ndarray[{{c_type}}] values,
ndarray[uint8_t, cast=True] mask,
limit=None):
cdef Py_ssize_t i, N
cdef {{c_type}} val
cdef int lim, fill_count = 0
N = len(values)
# GH 2778
if N == 0:
return
if limit is None:
lim = N
else:
if not util.is_integer_object(limit):
raise ValueError('Limit must be an integer')
if limit < 1:
raise ValueError('Limit must be greater than 0')
lim = limit
val = values[0]
for i in range(N):
if mask[i]:
if fill_count >= lim:
continue
fill_count += 1
values[i] = val
else:
fill_count = 0
val = values[i]
@cython.boundscheck(False)
@cython.wraparound(False)
def pad_2d_inplace_{{name}}(ndarray[{{c_type}}, ndim=2] values,
ndarray[uint8_t, ndim=2] mask,
limit=None):
cdef Py_ssize_t i, j, N, K
cdef {{c_type}} val
cdef int lim, fill_count = 0
K, N = (<object> values).shape
# GH 2778
if N == 0:
return
if limit is None:
lim = N
else:
if not util.is_integer_object(limit):
raise ValueError('Limit must be an integer')
if limit < 1:
raise ValueError('Limit must be greater than 0')
lim = limit
for j in range(K):
fill_count = 0
val = values[j, 0]
for i in range(N):
if mask[j, i]:
if fill_count >= lim:
continue
fill_count += 1
values[j, i] = val
else:
fill_count = 0
val = values[j, i]
"""
Backfilling logic for generating fill vector
Diagram of what's going on
Old New Fill vector Mask
. 0 1
. 0 1
. 0 1
A A 0 1
. 1 1
. 1 1
. 1 1
. 1 1
. 1 1
B B 1 1
. 2 1
. 2 1
. 2 1
C C 2 1
. 0
. 0
D
"""
@cython.boundscheck(False)
@cython.wraparound(False)
def backfill_{{name}}(ndarray[{{c_type}}] old, ndarray[{{c_type}}] new,
limit=None):
cdef Py_ssize_t i, j, nleft, nright
cdef ndarray[int64_t, ndim=1] indexer
cdef {{c_type}} cur, prev
cdef int lim, fill_count = 0
nleft = len(old)
nright = len(new)
indexer = np.empty(nright, dtype=np.int64)
indexer.fill(-1)
if limit is None:
lim = nright
else:
if not util.is_integer_object(limit):
raise ValueError('Limit must be an integer')
if limit < 1:
raise ValueError('Limit must be greater than 0')
lim = limit
if nleft == 0 or nright == 0 or new[0] > old[nleft - 1]:
return indexer
i = nleft - 1
j = nright - 1
cur = old[nleft - 1]
while j >= 0 and new[j] > cur:
j -= 1
while True:
if j < 0:
break
if i == 0:
while j >= 0:
if new[j] == cur:
indexer[j] = i
elif new[j] < cur and fill_count < lim:
indexer[j] = i
fill_count += 1
j -= 1
break
prev = old[i - 1]
while j >= 0 and prev < new[j] <= cur:
if new[j] == cur:
indexer[j] = i
elif new[j] < cur and fill_count < lim:
indexer[j] = i
fill_count += 1
j -= 1
fill_count = 0
i -= 1
cur = prev
return indexer
@cython.boundscheck(False)
@cython.wraparound(False)
def backfill_inplace_{{name}}(ndarray[{{c_type}}] values,
ndarray[uint8_t, cast=True] mask,
limit=None):
cdef Py_ssize_t i, N
cdef {{c_type}} val
cdef int lim, fill_count = 0
N = len(values)
# GH 2778
if N == 0:
return
if limit is None:
lim = N
else:
if not util.is_integer_object(limit):
raise ValueError('Limit must be an integer')
if limit < 1:
raise ValueError('Limit must be greater than 0')
lim = limit
val = values[N - 1]
for i in range(N - 1, -1, -1):
if mask[i]:
if fill_count >= lim:
continue
fill_count += 1
values[i] = val
else:
fill_count = 0
val = values[i]
@cython.boundscheck(False)
@cython.wraparound(False)
def backfill_2d_inplace_{{name}}(ndarray[{{c_type}}, ndim=2] values,
ndarray[uint8_t, ndim=2] mask,
limit=None):
cdef Py_ssize_t i, j, N, K
cdef {{c_type}} val
cdef int lim, fill_count = 0
K, N = (<object> values).shape
# GH 2778
if N == 0:
return
if limit is None:
lim = N
else:
if not util.is_integer_object(limit):
raise ValueError('Limit must be an integer')
if limit < 1:
raise ValueError('Limit must be greater than 0')
lim = limit
for j in range(K):
fill_count = 0
val = values[j, N - 1]
for i in range(N - 1, -1, -1):
if mask[j, i]:
if fill_count >= lim:
continue
fill_count += 1
values[j, i] = val
else:
fill_count = 0
val = values[j, i]
@cython.boundscheck(False)
@cython.wraparound(False)
def is_monotonic_{{name}}(ndarray[{{c_type}}] arr, bint timelike):
"""
Returns
-------
is_monotonic_inc, is_monotonic_dec, is_unique
"""
cdef:
Py_ssize_t i, n
{{c_type}} prev, cur
bint is_monotonic_inc = 1
bint is_monotonic_dec = 1
bint is_unique = 1
n = len(arr)
if n == 1:
if arr[0] != arr[0] or (timelike and <int64_t>arr[0] == iNaT):
# single value is NaN
return False, False, True
else:
return True, True, True
elif n < 2:
return True, True, True
if timelike and <int64_t>arr[0] == iNaT:
return False, False, True
{{nogil_str}}
{{tab}}prev = arr[0]
{{tab}}for i in range(1, n):
{{tab}} cur = arr[i]
{{tab}} if timelike and <int64_t>cur == iNaT:
{{tab}} is_monotonic_inc = 0
{{tab}} is_monotonic_dec = 0
{{tab}} break
{{tab}} if cur < prev:
{{tab}} is_monotonic_inc = 0
{{tab}} elif cur > prev:
{{tab}} is_monotonic_dec = 0
{{tab}} elif cur == prev:
{{tab}} is_unique = 0
{{tab}} else:
{{tab}} # cur or prev is NaN
{{tab}} is_monotonic_inc = 0
{{tab}} is_monotonic_dec = 0
{{tab}} break
{{tab}} if not is_monotonic_inc and not is_monotonic_dec:
{{tab}} is_monotonic_inc = 0
{{tab}} is_monotonic_dec = 0
{{tab}} break
{{tab}} prev = cur
return is_monotonic_inc, is_monotonic_dec, \
is_unique and (is_monotonic_inc or is_monotonic_dec)
@cython.wraparound(False)
@cython.boundscheck(False)
def arrmap_{{name}}(ndarray[{{c_type}}] index, object func):
cdef Py_ssize_t length = index.shape[0]
cdef Py_ssize_t i = 0
cdef ndarray[object] result = np.empty(length, dtype=np.object_)
from pandas._libs.lib import maybe_convert_objects
for i in range(length):
result[i] = func(index[i])
return maybe_convert_objects(result)
{{endfor}}
#----------------------------------------------------------------------
# put template
#----------------------------------------------------------------------
{{py:
# name, c_type, dest_type, dest_dtype
dtypes = [('float64', 'float64_t', 'float64_t', 'np.float64'),
('float32', 'float32_t', 'float32_t', 'np.float32'),
('int8', 'int8_t', 'float32_t', 'np.float32'),
('int16', 'int16_t', 'float32_t', 'np.float32'),
('int32', 'int32_t', 'float64_t', 'np.float64'),
('int64', 'int64_t', 'float64_t', 'np.float64')]
def get_dispatch(dtypes):
for name, c_type, dest_type, dest_dtype, in dtypes:
dest_type2 = dest_type
dest_type = dest_type.replace('_t', '')
yield name, c_type, dest_type, dest_type2, dest_dtype
}}
{{for name, c_type, dest_type, dest_type2, dest_dtype
in get_dispatch(dtypes)}}
@cython.boundscheck(False)
@cython.wraparound(False)
def diff_2d_{{name}}(ndarray[{{c_type}}, ndim=2] arr,
ndarray[{{dest_type2}}, ndim=2] out,
Py_ssize_t periods, int axis):
cdef:
Py_ssize_t i, j, sx, sy
sx, sy = (<object> arr).shape
if arr.flags.f_contiguous:
if axis == 0:
if periods >= 0:
start, stop = periods, sx
else:
start, stop = 0, sx + periods
for j in range(sy):
for i in range(start, stop):
out[i, j] = arr[i, j] - arr[i - periods, j]
else:
if periods >= 0:
start, stop = periods, sy
else:
start, stop = 0, sy + periods
for j in range(start, stop):
for i in range(sx):
out[i, j] = arr[i, j] - arr[i, j - periods]
else:
if axis == 0:
if periods >= 0:
start, stop = periods, sx
else:
start, stop = 0, sx + periods
for i in range(start, stop):
for j in range(sy):
out[i, j] = arr[i, j] - arr[i - periods, j]
else:
if periods >= 0:
start, stop = periods, sy
else:
start, stop = 0, sy + periods
for i in range(sx):
for j in range(start, stop):
out[i, j] = arr[i, j] - arr[i, j - periods]
def put2d_{{name}}_{{dest_type}}(ndarray[{{c_type}}, ndim=2, cast=True] values,
ndarray[int64_t] indexer, Py_ssize_t loc,
ndarray[{{dest_type2}}] out):
cdef:
Py_ssize_t i, j, k
k = len(values)
for j from 0 <= j < k:
i = indexer[j]
out[i] = values[j, loc]
{{endfor}}
#----------------------------------------------------------------------
# ensure_dtype
#----------------------------------------------------------------------
cdef int PLATFORM_INT = (<ndarray> np.arange(0, dtype=np.intp)).descr.type_num
cpdef ensure_platform_int(object arr):
# GH3033, GH1392
# platform int is the size of the int pointer, e.g. np.intp
if util.is_array(arr):
if (<ndarray> arr).descr.type_num == PLATFORM_INT:
return arr
else:
return arr.astype(np.intp)
else:
return np.array(arr, dtype=np.intp)
cpdef ensure_object(object arr):
if util.is_array(arr):
if (<ndarray> arr).descr.type_num == NPY_OBJECT:
return arr
else:
return arr.astype(np.object_)
elif hasattr(arr, '_box_values_as_index'):
return arr._box_values_as_index()
else:
return np.array(arr, dtype=np.object_)
{{py:
# name, c_type, dtype
dtypes = [('float64', 'FLOAT64', 'float64'),
('float32', 'FLOAT32', 'float32'),
('int8', 'INT8', 'int8'),
('int16', 'INT16', 'int16'),
('int32', 'INT32', 'int32'),
('int64', 'INT64', 'int64'),
('uint64', 'UINT64', 'uint64'),
# ('platform_int', 'INT', 'int_'),
# ('object', 'OBJECT', 'object_'),
]
def get_dispatch(dtypes):
for name, c_type, dtype in dtypes:
yield name, c_type, dtype
}}
{{for name, c_type, dtype in get_dispatch(dtypes)}}
cpdef ensure_{{name}}(object arr, copy=True):
if util.is_array(arr):
if (<ndarray> arr).descr.type_num == NPY_{{c_type}}:
return arr
else:
return arr.astype(np.{{dtype}}, copy=copy)
else:
return np.array(arr, dtype=np.{{dtype}})
{{endfor}}