-
Notifications
You must be signed in to change notification settings - Fork 20
/
flarry.py
2118 lines (1828 loc) · 63.2 KB
/
flarry.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
"Functions that operate on larrys."
import numpy as np
from la.deflarry import larry
from la.flabel import flattenlabel, listmap, listmap_fill
from la.farray import covMissing
from la.missing import missing_marker, ismissing
__all__ = ['align', 'align_axis', 'align_raw', 'lrange', 'empty', 'ones',
'zeros', 'isaligned', 'union', 'intersection', 'binaryop', 'add',
'sortby', 'subtract', 'multiply', 'divide', 'unique', 'stack',
'panel', 'cov', 'rand', 'randn']
# Alignment -----------------------------------------------------------------
def align(lar1, lar2, join='inner', cast=True):
"""
Align two larrys using one of five join methods.
Parameters
----------
lar1 : larry
One of the input larrys. Must have the same number of dimensions as
`lar2`.
lar2 : larry
One of the input larrys. Must have the same number of dimensions as
`lar1`.
join : {'inner', 'outer', 'left', 'right', 'skip', list}, optional
The join method used to align the two larrys. The default join method
along each axis is 'inner', i.e., the intersection of the labels. If
`join` is a list of strings then the length of the list should be the
same as the number of dimensions of the two larrys. The first element
in the list is the join method for axis=0, the second element is the
join method for axis=1, and so on. The 'skip' join method means to
not align the specified axis.
cast : bool, optional
Only float, str, and object dtypes have missing value markers (la.nan,
'', and None, respectively). Other dtypes, such as int and bool, do
not have missing value markers. If `cast` is set to True (default)
then int and bool dtypes, for example, will be cast to float if any
new rows, columns, etc are created. If cast is set to False, then a
TypeError will be raised for int and bool dtype input if the join
introduces new rows, columns, etc. An inner join will never introduce
new rows, columns, etc.
Returns
-------
lar3 : larry
A copy of the aligned version of `lar1`.
lar4 : larry
A copy of the aligned version of `lar2`.
See Also
--------
la.isaligned: Return True if two larrys are aligned along specified axis.
la.align_raw: Low level version of la.align.
Examples
--------
Create two larrys:
>>> lar1 = larry([1, 2])
>>> lar2 = larry([1, 2, 3])
The default join method is an inner join:
>>> lar3, lar4 = la.align(lar1, lar2)
>>> lar3
label_0
0
1
x
array([1, 2])
>>> lar4
label_0
0
1
x
array([1, 2])
An outer join adds a missing value (NaN) to lar1, therefore the the dtype
of lar1 is changed from int to float:
>>> lar3, lar4 = la.align(lar1, lar2, join='outer')
>>> lar3
label_0
0
1
2
x
array([ 1., 2., NaN])
>>> lar4
label_0
0
1
2
x
array([1, 2, 3])
"""
# Align
x1, x2, label, x1isview, x2isview = align_raw(lar1, lar2, join=join,
cast=cast)
# Convert x1 array to larry
label1 = []
for j, lab in enumerate(label):
if lab is None:
label1.append(list(lar1.label[j]))
else:
label1.append(list(lab))
if x1isview:
x1 = x1.copy()
lar3 = larry(x1, label1, validate=False)
# Convert x2 array to larry
label2 = []
for j, lab in enumerate(label):
if lab is None:
label2.append(list(lar2.label[j]))
else:
label2.append(list(lab))
if x2isview:
x2 = x2.copy()
lar4 = larry(x2, label2, validate=False)
return lar3, lar4
def align_raw(lar1, lar2, join='inner', cast=True):
"""
Align two larrys but return Numpy arrays and label instead of larrys.
This function is the same as la.align() except that instead of returning
two larrys, the components of the two larrys are returned (two Numpy
arrays, a label, and flags for whether the two Numpy arrays are views of
the data arrays of the corresponding input larrys).
Parameters
----------
lar1 : larry
One of the input larrys. Must have the same number of dimensions as
`lar2`.
lar2 : larry
One of the input larrys. Must have the same number of dimensions as
`lar1`.
join : {'inner', 'outer', 'left', 'right', 'skip', list}, optional
The join method used to align the two larrys. The default join method
along each axis is 'inner', i.e., the intersection of the labels. If
`join` is a list of strings then the length of the list should be the
same as the number of dimensions of the two larrys. The first element
in the list is the join method for axis=0, the second element is the
join method for axis=1, and so on. The 'skip' join method means to
not align the specified axis.
cast : bool, optional
Only float, str, and object dtypes have missing value markers (la.nan,
'', and None, respectively). Other dtypes, such as int and bool, do
not have missing value markers. If `cast` is set to True (default)
then int and bool dtypes, for example, will be cast to float if any
new rows, columns, etc are created. If cast is set to False, then a
TypeError will be raised for int and bool dtype input if the join
introduces new rows, columns, etc. An inner join will never introduce
new rows, columns, etc.
Returns
-------
x1 : ndarray
The aligned version of `lar1`.
x2 : ndarray
The aligned version of `lar2`.
label : list of lists
The label of the joined larrys. If join method along any axis is
'skip', then the corresponding entry of label is `None`.
x1isview : bool
True if x1 is a view of lar1.x; False otherwise. A view of lar1.x is
retuned if the labels of `lar1` and `lar2` are the same along all
axes; otherwise a copy is returned.
x2isview : bool
True if x2 is a view of lar2.x; False otherwise. A view of lar2.x is
retuned if the labels of `lar1` and `lar2` are the same along all
axes; otherwise a copy is returned.
See Also
--------
la.align: Align two larrys using one of five join methods.
la.isaligned: Return True if two larrys are aligned along specified axis.
Notes
-----
The returned Numpy arrays are views of the corresponding input larrys if
the labels of the two input larrys are the same along all axes. If the
labels are not the same along any axis then a copy is returned.
Examples
--------
Create two larrys:
>>> y1 = larry([1, 2])
>>> y2 = larry([1, 2, 3])
The default join method is an inner join:
>>> x1, x2, label, x1isview, x2isview = la.flarry._align_raw(lar1, lar2)
>>> x1
array([1, 2])
>>> x2
array([1, 2])
>>> label
[[0, 1]]
>>> x1isview
False
>>> x2isview
False
An outer join adds a missing value (NaN) to lar1, therefore the the dtype
of lar1 is changed from int to float:
>>> x1, x2, label, x1isview, x2isview = la.flarry._align_raw(lar1, lar2, join='outer')
>>> x1
array([ 1., 2., NaN])
>>> x2
array([1, 2, 3])
>>> label
[[0, 1, 2]]
>>> x1isview
False
>>> x2isview
False
If the labels are already aligned, then a view of the data array is
returned:
>>> lar1 = larry([1, 2])
>>> lar2 = larry([3, 4])
>>> x1, x2, label, x1isview, x2isview = la.flarry._align_raw(lar1, lar2)
>>> x1isview
True
>>> x2isview
True
"""
# Check number of dimensions
ndim = lar2.ndim
if lar1.ndim != ndim:
msg = "'lar1' and 'lar2' must have the same number of dimensions."
raise ValueError, msg
# Check join type
typejoin = type(join)
if typejoin is str:
join = [join] * ndim
elif typejoin is list:
if len(join) != ndim:
msg = "Length of `join` list equal number of dimension of `lar1`."
raise ValueError, msg
else:
raise TypeError, "`join` must be a string or a list."
# Initialize missing markers, set value later (in loop) only if needed.
# The weird initialization value ensures a user would never pick the same
undefined = 'aB!@12#E~=-'
miss1 = undefined
miss2 = undefined
# For loop initialization
label = []
x1 = lar1.x
x2 = lar2.x
label1 = lar1.label
label2 = lar2.label
x1isview = True
x2isview = True
# Loop: align one axis at a time
msg = "`fill` type not compatible with larry dtype"
for ax in range(ndim):
list1 = label1[ax]
list2 = label2[ax]
joinax = join[ax]
if joinax == 'inner':
if list1 == list2:
list3 = list(list1)
else:
list3 = list(set(list1) & (set(list2)))
list3.sort()
idx1 = listmap(list1, list3)
idx2 = listmap(list2, list3)
x1 = x1.take(idx1, ax)
x2 = x2.take(idx2, ax)
x1isview = False
x2isview = False
elif joinax == 'outer':
if list1 == list2:
list3 = list(list1)
else:
list3 = list(set(list1) | (set(list2)))
list3.sort()
idx1, idx1_miss = listmap_fill(list1, list3, fill=0)
idx2, idx2_miss = listmap_fill(list2, list3, fill=0)
x1 = x1.take(idx1, ax)
x2 = x2.take(idx2, ax)
if len(idx1_miss) > 0:
if miss1 == undefined:
miss1 = missing_marker(lar1)
if miss1 == NotImplemented:
if cast:
x1 = x1.astype(float)
miss1 = missing_marker(x1)
else:
raise TypeError, msg
index1 = [slice(None)] * ndim
index1[ax] = idx1_miss
x1[index1] = miss1
if len(idx2_miss) > 0:
if miss2 == undefined:
miss2 = missing_marker(lar2)
if miss2 == NotImplemented:
if cast:
x2 = x2.astype(float)
miss2 = missing_marker(x2)
else:
raise TypeError, msg
index2 = [slice(None)] * ndim
index2[ax] = idx2_miss
x2[index2] = miss2
x1isview = False
x2isview = False
elif joinax == 'left':
list3 = list(list1)
if list1 != list2:
idx2, idx2_miss = listmap_fill(list2, list3, fill=0)
x2 = x2.take(idx2, ax)
if len(idx2_miss) > 0:
if miss2 == undefined:
miss2 = missing_marker(lar2)
if miss2 == NotImplemented:
if miss2 is None:
miss2 = missing_marker(lar2)
if miss2 is None:
miss2 = missing_marker(lar2)
if cast:
x2 = x2.astype(float)
miss2 = missing_marker(x2)
else:
raise TypeError, msg
index2 = [slice(None)] * ndim
index2[ax] = idx2_miss
x2[index2] = miss2
x2isview = False
elif joinax == 'right':
list3 = list(list2)
if list1 != list2:
idx1, idx1_miss = listmap_fill(list1, list3, fill=0)
x1 = x1.take(idx1, ax)
if len(idx1_miss) > 0:
if miss1 == undefined:
miss1 = missing_marker(lar1)
if miss1 == NotImplemented:
if cast:
x1 = x1.astype(float)
miss1 = missing_marker(x1)
else:
raise TypeError, msg
index1 = [slice(None)] * ndim
index1[ax] = idx1_miss
x1[index1] = miss1
x1isview = False
elif joinax == 'skip':
list3 = None
else:
raise ValueError, 'join type not recognized'
label.append(list3)
return x1, x2, label, x1isview, x2isview
def align_axis(lars, axis=0, join='inner', flag=False):
"""
Align many larrys along potentially different axes.
Parameters
----------
lars : array_like
A collection (list, tuple, set, array, etc.) of larrys to align.
axis : {int, array_like}, optional
An integer indicating which axis along which to align the larrys in
`lars`, or a sequence of integers of the same length as `lars`
indicating which axis to use for each entry in `lars`.
join : {'inner', 'outer', 'left', 'right'}, optional
If 'inner', then labels present in every larry will be kept. If
'outer', all labels appearing in any array are kept, and additional
entries are added to larrys containing fewer labels. See la.morph() for
rules on how this is done. If 'right' or 'left' then the labels of the
output will match those of either the first or last entry of `lars`,
respectively
Returns
-------
(lar1, lar2, ...) : tuple
Tuple of larrys, one corresponding to each entry of lars. None of the
output refer to input, and the labels of the output do not refer to one
another.
Examples
--------
Create three larrys:
>>> l1 = la.larry([1, 2, 3, 4], [['a', 'b', 'c', 'd']])
>>> l2 = la.larry([[4, 5], [6, 7]], [['x', 'y'], ['c', 'd']])
>>> l3 = la.larry([8, 9, 10], [['c', 'd', 'e']])
Align the first axis of the first larry with the second axis of the
second larry using an inner join:
>>> a1, a2 = la.align_axis([l1, l2], axis=[0, 1])
>>> a1
label_0
c
d
x
array([3, 4])
>>> a2
label_0
x
y
label_1
c
d
x
array([[4, 5],
[6, 7]])
Align the first axis of two larrys with an outer join:
>>> a1, a2 = la.align_axis([l1, l3], join='outer')
>>> a1
label_0
a
b
c
d
e
x
array([ 1., 2., 3., 4., nan])
>>> a2
label_0
a
b
c
d
e
x
array([ nan, nan, 8., 9., 10.])
Align multiple larrys with an inner join:
>>> a1, a2, a3 = la.align_axis([l1, l2, l3], axis=[0, 1, 0])
>>> a1
label_0
c
d
x
array([3, 4])
>>> a2
label_0
x
y
label_1
c
d
x
array([[4, 5],
[6, 7]])
>>> a3
label_0
c
d
x
array([8, 9])
"""
# Input checks and preprocessing
nlar = len(lars)
if isinstance(axis, int):
axis = [axis for j in range(nlar)]
for j, lar in enumerate(lars):
if not isinstance(lar, larry):
raise ValueError("Inputs must be larry.")
if (axis[j] >= lar.ndim) or (axis[j] < -lar.ndim):
raise ValueError("Axis out of range for input larry %d" % j)
if join not in ['inner', 'outer', 'left', 'right']:
raise ValueError("Value of `join` not recognized.")
# Alignment
if join == 'left':
label = lars[0].label[axis[0]]
elif join == 'right':
label = lars[-1].label[axis[-1]]
else:
labels = [set(lar.label[axis[j]]) for j, lar in enumerate(lars)]
label = labels[0]
if join == 'inner':
for new_label in labels[1:]:
label &= new_label
elif join == 'outer':
for new_label in labels[1:]:
label |= new_label
label = list(label)
label.sort()
lars_out = []
# Create output
for j, lar in enumerate(lars):
lab = list(label)
lars_out.append(lar.morph(lab, axis[j]))
return tuple(lars_out)
def isaligned(lar1, lar2, axis=None):
"""
Return True if labels of two given larrys are aligned along specified axis.
Parameters
----------
lar1 : larry
Input.
lar2 : larry
Input
axis : {int, None}, optional
The axis along which to check for aligment of labels. By default
(axis=None) all axes are checked.
Returns
-------
y : bool
Returns True if labels are aligned; False if labels are not aligned.
See Also
--------
la.align: Align two larrys using one of five join methods.
Examples
--------
Make two 2d larrys that are aligned along columns but not rows:
>>> lar1 = larry([[1, 2], [3, 4]], [['row1', 'row2'], ['col1', 'col2']])
>>> lar2 = larry([[1, 2], [3, 4]], [['row2', 'row1'], ['col1', 'col2']])
The two larrys are not aligned:
>>> la.isaligned(lar1, lar2)
False
>>> la.isaligned(lar1, lar2, axis=0)
False
But the columns of the two larrys are aligned:
>>> la.isaligned(lar1, lar2, axis=1)
True
"""
if axis is None:
return lar1.label == lar2.label
else:
return lar1.label[axis] == lar2.label[axis]
def union(axis, *args):
"""
Union of labels along specified axis.
Parameters
----------
axis : int
The axis along which to take the union of the labels.
args : larrys
The larrys (separated by commas) over which the union is taken.
Returns
-------
out : list
A list containing the union of the labels.
See Also
--------
la.intersection : Intersection of labels along specified axis.
Examples
--------
>>> import la
>>> y1 = larry([[1, 2], [3, 4]], [['a', 'b'], ['c', 'd']])
>>> y2 = larry([[1, 2], [3, 4]], [['e', 'b'], ['f', 'd']])
>>> la.union(0, y1, y2)
['a', 'b', 'e']
>>> la.union(1, y1, y2)
['c', 'd', 'f']
"""
rc = frozenset([])
for arg in args:
if isinstance(arg, larry):
rc = frozenset(arg.label[axis]) | rc
else:
raise TypeError, 'One or more input is not a larry'
rc = list(rc)
rc.sort()
return rc
def intersection(axis, *args):
"""
Sorted list containing the intersection of labels along specified axis.
Parameters
----------
axis : int
The axis along which to take the intersection of the labels.
args : larrys
The larrys (separated by commas) over which the intersection is taken.
Returns
-------
out : list
A sorted list containing the intersection of the labels.
See Also
--------
la.union : Union of labels along specified axis.
Examples
--------
>>> import la
>>> y1 = larry([[1, 2], [3, 4]], [['a', 'b'], ['c', 'd']])
>>> y2 = larry([[1, 2], [3, 4]], [['e', 'b'], ['f', 'd']])
>>> la.intersection(0, y1, y2)
['b']
>>> la.intersection(1, y1, y2)
['d']
"""
rc = frozenset(args[0].label[axis])
for i in xrange(1, len(args)):
arg = args[i]
if isinstance(arg, larry):
rc = frozenset(arg.label[axis]) & rc
else:
raise TypeError, 'One or more input is not a larry'
rc = list(rc)
rc.sort()
return rc
# Binary-- -----------------------------------------------------------------
def binaryop(func, lar1, lar2, join='inner', cast=True, missone='ignore',
misstwo='ignore', **kwargs):
"""
Binary operation on two larrys using given function and join method.
Parameters
----------
func : function
A function that takes two Numpy arrays as input and returns a Numpy
array as output. For example: np.add. You can also pass keyword
arguments to the function; see `**kwargs`.
lar1 : larry
The larry on the left-hand side of the binary operation. Must have
the same number of dimensions as `lar2`.
lar2 : larry
The larry on the right-hand side of the binary operation. Must have
the same number of dimensions as `lar1`.
join : {'inner', 'outer', 'left', 'right', list}, optional
The method used to join the two larrys. The default join method along
all axes is 'inner', i.e., the intersection of the labels. If `join`
is a list of strings then the length of the list should be the number
of dimensions of the two larrys. The first element in the list is the
join method for axis=0, the second element is the join method for
axis=1, and so on.
cast : bool, optional
Only float, str, and object dtypes have missing value markers (la.nan,
'', and None, respectively). Other dtypes, such as int and bool, do
not have missing value markers. If `cast` is set to True (default)
then int and bool dtypes, for example, will be cast to float if any
new rows, columns, etc are created. If cast is set to False, then a
TypeError will be raised for int and bool dtype input if the join
introduces new rows, columns, etc. An inner join will never introduce
new rows, columns, etc.
missone : {scalar, 'ignore'}, optional
By default ('ignore') no special treatment of missing values is made.
If, however, `missone` is set to something other than 'ignore', such
as 0, then all elements that are missing in one larry but not missing
in the other larry are replaced by `missone`. For example, if an
element is in one larry but missing in the other larry then you may
want to set the missing value to zero when summing two larrys.
misstwo : {scalar, 'ignore'}, optional
By default ('ignore') no special treatment of missing values is made.
If, however, `misstwo` is set to something other than 'ignore', such
as 0, then all elements that are missing in both larrys are replaced
by `misstwo`.
**kwargs : Keyword arguments, optional
Keyword arguments to pass to `func`. The keyword arguments passed to
`func` cannot have the following keys: join, cast, missone, misstwo.
Returns
-------
lar3 : larry
The result of the binary operation.
See Also
--------
la.align: Align two larrys using one of five join methods.
Examples
--------
Create two larrys:
>>> from la import nan
>>> lar1 = larry([1, 2, nan], [['a', 'b', 'c']])
>>> lar2 = larry([1, nan, nan], [['a', 'b', 'dd']])
The default is an inner join (note that lar1 and lar2 have two labels in
common):
>>> la.binaryop(np.add, lar1, lar2)
label_0
a
b
x
array([ 2., NaN])
If one data element is missing in one larry but not in the other, then you
can replace the missing value with `missone` (here 0):
>>> la.binaryop(np.add, lar1, lar2, missone=0)
label_0
a
b
x
array([ 2., 2.])
An outer join:
>>> la.binaryop(np.add, lar1, lar2, join='outer')
label_0
a
b
c
dd
x
array([ 2., NaN, NaN, NaN])
An outer join with single and double missing values replaced by zero:
>>> la.binaryop(np.add, lar1, lar2, join='outer', missone=0, misstwo=0)
label_0
a
b
c
dd
x
array([ 2., 2., 0., 0.])
"""
# Align
x1, x2, label, ign1, ign2 = align_raw(lar1, lar2, join=join, cast=cast)
# Replacing missing values is slow, so only do if requested
if missone != 'ignore' or misstwo != 'ignore':
miss1 = ismissing(x1)
miss2 = ismissing(x2)
if missone != 'ignore':
missone1 = miss1 & ~miss2
if missone1.any():
x1[missone1] = missone
missone2 = miss2 & ~miss1
if missone2.any():
x2[missone2] = missone
if misstwo != 'ignore':
misstwo12 = miss1 & miss2
if misstwo12.any():
x1[misstwo12] = misstwo
x2[misstwo12] = misstwo
# Binary function
x = func(x1, x2, **kwargs)
return larry(x, label, validate=False)
def add(lar1, lar2, join='inner', cast=True, missone='ignore',
misstwo='ignore'):
"""
Sum of two larrys using given join and fill methods.
Parameters
----------
lar1 : larry
The larry on the left-hand side of the sum. Must have the same number
of dimensions as `lar2`.
lar2 : larry
The larry on the right-hand side of the sum. Must have the same number
of dimensions as `lar1`.
join : {'inner', 'outer', 'left', 'right', list}, optional
The method used to join the two larrys. The default join method along
all axes is 'inner', i.e., the intersection of the labels. If `join`
is a list of strings then the length of the list should be the number
of dimensions of the two larrys. The first element in the list is the
join method for axis=0, the second element is the join method for
axis=1, and so on.
cast : bool, optional
Only float, str, and object dtypes have missing value markers (la.nan,
'', and None, respectively). Other dtypes, such as int and bool, do
not have missing value markers. If `cast` is set to True (default)
then int and bool dtypes, for example, will be cast to float if any
new rows, columns, etc are created. If cast is set to False, then a
TypeError will be raised for int and bool dtype input if the join
introduces new rows, columns, etc. An inner join will never introduce
new rows, columns, etc.
missone : {scalar, 'ignore'}, optional
By default ('ignore') no special treatment of missing values is made.
If, however, `missone` is set to something other than 'ignore', such
as 0, then all elements that are missing in one larry but not missing
in the other larry are replaced by `missone`. For example, if an
element is in one larry but missing in the other larry then you may
want to set the missing value to zero when summing two larrys.
misstwo : {scalar, 'ignore'}, optional
By default ('ignore') no special treatment of missing values is made.
If, however, `misstwo` is set to something other than 'ignore', such
as 0, then all elements that are missing in both larrys are replaced
by `misstwo`.
Returns
-------
y : larry
The sum of the two larrys, `lar1` and `lar2`.
See Also
--------
la.larry.__add__: Sum a larry with another larry, Numpy array, or scalar.
la.binaryop: Binary operation on two larrys using given function.
Notes
-----
This is a convenience function that calls la.binaryop() with `func` set
to numpy.add.
Examples
--------
Create two larrys:
>>> from la import nan
>>> lar1 = larry([1, 2, nan], [['a', 'b', 'c']])
>>> lar2 = larry([1, nan, nan], [['a', 'b', 'dd']])
The default is an inner join (note that lar1 and lar2 have two labels in
common):
>>> la.add(lar1, lar2)
label_0
a
b
x
array([ 2., NaN])
which is the same result you get with lar1 + lar2:
>>> lar1 + lar2
label_0
a
b
x
array([ 2., NaN])
If one data element is missing in one larry but not in the other, then you
can replace the missing value with `missone` (here 0):
>>> la.add(lar1, lar2, missone=0)
label_0
a
b
x
array([ 2., 2.])
An outer join:
>>> la.add(lar1, lar2, join='outer')
label_0
a
b
c
dd
x
array([ 2., NaN, NaN, NaN])
An outer join with single and double missing values replaced by zero:
>>> la.add(lar1, lar2, join='outer', missone=0, misstwo=0)
label_0
a
b
c
dd
x
array([ 2., 2., 0., 0.])
"""
return binaryop(np.add, lar1, lar2, join=join, cast=cast, missone=missone,
misstwo=misstwo)
def subtract(lar1, lar2, join='inner', cast=True, missone='ignore',
misstwo='ignore'):
"""
Difference of two larrys using given join and fill methods.
Parameters
----------
lar1 : larry
The larry on the left-hand side of the difference. Must have the same
number of dimensions as `lar2`.
lar2 : larry
The larry on the right-hand side of the difference. Must have the same
number of dimensions as `lar1`.
join : {'inner', 'outer', 'left', 'right', list}, optional
The method used to join the two larrys. The default join method along
all axes is 'inner', i.e., the intersection of the labels. If `join`
is a list of strings then the length of the list should be the number
of dimensions of the two larrys. The first element in the list is the
join method for axis=0, the second element is the join method for
axis=1, and so on.
cast : bool, optional
Only float, str, and object dtypes have missing value markers (la.nan,
'', and None, respectively). Other dtypes, such as int and bool, do
not have missing value markers. If `cast` is set to True (default)
then int and bool dtypes, for example, will be cast to float if any
new rows, columns, etc are created. If cast is set to False, then a
TypeError will be raised for int and bool dtype input if the join
introduces new rows, columns, etc. An inner join will never introduce
new rows, columns, etc.
missone : {scalar, 'ignore'}, optional
By default ('ignore') no special treatment of missing values is made.
If, however, `missone` is set to something other than 'ignore', such
as 0, then all elements that are missing in one larry but not missing
in the other larry are replaced by `missone`. For example, if an
element is in one larry but missing in the other larry then you may
want to set the missing value to zero when subtracting two larrys.
misstwo : {scalar, 'ignore'}, optional
By default ('ignore') no special treatment of missing values is made.
If, however, `misstwo` is set to something other than 'ignore', such
as 0, then all elements that are missing in both larrys are replaced
by `misstwo`.
Returns
-------
y : larry
The difference of the two larrys, `lar1` and `lar2`.
See Also
--------
la.larry.__sub__: Subtract a larry from another larry, array, or scalar.
la.binaryop: Binary operation on two larrys using given function.
Notes
-----
This is a convenience function that calls la.binaryop() with `func` set
to numpy.subtract.
Examples
--------
Create two larrys:
>>> from la import nan
>>> lar1 = larry([1, 2, nan], [['a', 'b', 'c']])
>>> lar2 = larry([1, nan, nan], [['a', 'b', 'dd']])
The default is an inner join (note that lar1 and lar2 have two labels in
common):
>>> la.subtract(lar1, lar2)
label_0
a
b
x
array([ 0., NaN])
which is the same result you get with lar1 - lar2:
>>> lar1 - lar2
label_0
a
b
x
array([ 0., NaN])
If one data element is missing in one larry but not in the other, then you
can replace the missing value with `missone` (here 0):
>>> la.subtract(lar1, lar2, missone=0)
label_0
a