-
-
Notifications
You must be signed in to change notification settings - Fork 5
Expand file tree
/
Copy pathfunction_base.py
More file actions
executable file
·4358 lines (3677 loc) · 140 KB
/
Copy pathfunction_base.py
File metadata and controls
executable file
·4358 lines (3677 loc) · 140 KB
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 division, absolute_import, print_function
import warnings
import sys
import collections
import operator
import numpy as np
import numpy.core.numeric as _nx
from numpy.core import linspace, atleast_1d, atleast_2d
from numpy.core.numeric import (
ones, zeros, arange, concatenate, array, asarray, asanyarray, empty,
empty_like, ndarray, around, floor, ceil, take, dot, where, intp,
integer, isscalar
)
from numpy.core.umath import (
pi, multiply, add, arctan2, frompyfunc, cos, less_equal, sqrt, sin,
mod, exp, log10
)
from numpy.core.fromnumeric import (
ravel, nonzero, sort, partition, mean, any, sum
)
from numpy.core.numerictypes import typecodes, number
from numpy.lib.twodim_base import diag
from .utils import deprecate
from numpy.core.multiarray import _insert, add_docstring
from numpy.core.multiarray import digitize, bincount, interp as compiled_interp
from numpy.core.umath import _add_newdoc_ufunc as add_newdoc_ufunc
from numpy.compat import long
from numpy.compat.py3k import basestring
# Force range to be a generator, for np.delete's usage.
if sys.version_info[0] < 3:
range = xrange
__all__ = [
'select', 'piecewise', 'trim_zeros', 'copy', 'iterable', 'percentile',
'diff', 'gradient', 'angle', 'unwrap', 'sort_complex', 'disp',
'extract', 'place', 'vectorize', 'asarray_chkfinite', 'average',
'histogram', 'histogramdd', 'bincount', 'digitize', 'cov', 'corrcoef',
'msort', 'median', 'sinc', 'hamming', 'hanning', 'bartlett',
'blackman', 'kaiser', 'trapz', 'i0', 'add_newdoc', 'add_docstring',
'meshgrid', 'delete', 'insert', 'append', 'interp', 'add_newdoc_ufunc'
]
def iterable(y):
"""
Check whether or not an object can be iterated over.
Parameters
----------
y : object
Input object.
Returns
-------
b : {0, 1}
Return 1 if the object has an iterator method or is a sequence,
and 0 otherwise.
Examples
--------
>>> np.iterable([1, 2, 3])
1
>>> np.iterable(2)
0
"""
try:
iter(y)
except:
return 0
return 1
def _hist_optim_numbins_estimator(a, estimator):
"""
A helper function to be called from histogram to deal with estimating optimal number of bins
estimator: str
If estimator is one of ['auto', 'fd', 'scott', 'rice', 'sturges'] this function
will choose the appropriate estimator and return it's estimate for the optimal
number of bins.
"""
assert isinstance(estimator, basestring)
# private function should not be called otherwise
if a.size == 0:
return 1
def sturges(x):
"""
Sturges Estimator
A very simplistic estimator based on the assumption of normality of the data
Poor performance for non-normal data, especially obvious for large X.
Depends only on size of the data.
"""
return np.ceil(np.log2(x.size)) + 1
def rice(x):
"""
Rice Estimator
Another simple estimator, with no normality assumption.
It has better performance for large data, but tends to overestimate number of bins.
The number of bins is proportional to the cube root of data size (asymptotically optimal)
Depends only on size of the data
"""
return np.ceil(2 * x.size ** (1.0 / 3))
def scott(x):
"""
Scott Estimator
The binwidth is proportional to the standard deviation of the data and
inversely proportional to the cube root of data size (asymptotically optimal)
"""
h = 3.5 * x.std() * x.size ** (-1.0 / 3)
if h > 0:
return np.ceil(x.ptp() / h)
return 1
def fd(x):
"""
Freedman Diaconis rule using Inter Quartile Range (IQR) for binwidth
Considered a variation of the Scott rule with more robustness as the IQR
is less affected by outliers than the standard deviation. However the IQR depends on
fewer points than the sd so it is less accurate, especially for long tailed distributions.
If the IQR is 0, we return 1 for the number of bins.
Binwidth is inversely proportional to the cube root of data size (asymptotically optimal)
"""
iqr = np.subtract(*np.percentile(x, [75, 25]))
if iqr > 0:
h = (2 * iqr * x.size ** (-1.0 / 3))
return np.ceil(x.ptp() / h)
# If iqr is 0, default number of bins is 1
return 1
def auto(x):
"""
The FD estimator is usually the most robust method, but it tends to be too small
for small X. The Sturges estimator is quite good for small (<1000) datasets and is
the default in R.
This method gives good off the shelf behaviour.
"""
return max(fd(x), sturges(x))
optimal_numbins_methods = {'sturges': sturges, 'rice': rice, 'scott': scott,
'fd': fd, 'auto': auto}
try:
estimator_func = optimal_numbins_methods[estimator.lower()]
except KeyError:
raise ValueError("{0} not a valid method for `bins`".format(estimator))
else:
# these methods return floats, np.histogram requires an int
return int(estimator_func(a))
def histogram(a, bins=10, range=None, normed=False, weights=None,
density=None):
"""
Compute the histogram of a set of data.
Parameters
----------
a : array_like
Input data. The histogram is computed over the flattened array.
bins : int or sequence of scalars or str, optional
If `bins` is an int, it defines the number of equal-width
bins in the given range (10, by default). If `bins` is a sequence,
it defines the bin edges, including the rightmost edge, allowing
for non-uniform bin widths.
.. versionadded:: 1.11.0
If `bins` is a string from the list below, `histogram` will use the method
chosen to calculate the optimal number of bins (see Notes for more detail
on the estimators). For visualisation, we suggest using the 'auto' option.
'auto'
Maximum of the 'sturges' and 'fd' estimators. Provides good all round performance
'fd' (Freedman Diaconis Estimator)
Robust (resilient to outliers) estimator that takes into account data
variability and data size .
'scott'
Less robust estimator that that takes into account data
variability and data size.
'rice'
Estimator does not take variability into account, only data size.
Commonly overestimates number of bins required.
'sturges'
R's default method, only accounts for data size. Only optimal for
gaussian data and underestimates number of bins for large non-gaussian datasets.
range : (float, float), optional
The lower and upper range of the bins. If not provided, range
is simply ``(a.min(), a.max())``. Values outside the range are
ignored.
normed : bool, optional
This keyword is deprecated in Numpy 1.6 due to confusing/buggy
behavior. It will be removed in Numpy 2.0. Use the density keyword
instead.
If False, the result will contain the number of samples
in each bin. If True, the result is the value of the
probability *density* function at the bin, normalized such that
the *integral* over the range is 1. Note that this latter behavior is
known to be buggy with unequal bin widths; use `density` instead.
weights : array_like, optional
An array of weights, of the same shape as `a`. Each value in `a`
only contributes its associated weight towards the bin count
(instead of 1). If `normed` is True, the weights are normalized,
so that the integral of the density over the range remains 1
density : bool, optional
If False, the result will contain the number of samples
in each bin. If True, the result is the value of the
probability *density* function at the bin, normalized such that
the *integral* over the range is 1. Note that the sum of the
histogram values will not be equal to 1 unless bins of unity
width are chosen; it is not a probability *mass* function.
Overrides the `normed` keyword if given.
Returns
-------
hist : array
The values of the histogram. See `normed` and `weights` for a
description of the possible semantics.
bin_edges : array of dtype float
Return the bin edges ``(length(hist)+1)``.
See Also
--------
histogramdd, bincount, searchsorted, digitize
Notes
-----
All but the last (righthand-most) bin is half-open. In other words, if
`bins` is::
[1, 2, 3, 4]
then the first bin is ``[1, 2)`` (including 1, but excluding 2) and the
second ``[2, 3)``. The last bin, however, is ``[3, 4]``, which *includes*
4.
.. versionadded:: 1.11.0
The methods to estimate the optimal number of bins are well found in literature,
and are inspired by the choices R provides for histogram visualisation.
Note that having the number of bins proportional to :math:`n^{1/3}` is asymptotically optimal,
which is why it appears in most estimators.
These are simply plug-in methods that give good starting points for number of bins.
In the equations below, :math:`h` is the binwidth and :math:`n_h` is the number of bins
'Auto' (maximum of the 'Sturges' and 'FD' estimators)
A compromise to get a good value. For small datasets the sturges
value will usually be chosen, while larger datasets will usually default to FD.
Avoids the overly conservative behaviour of FD and Sturges for small and
large datasets respectively. Switchover point is usually x.size~1000.
'FD' (Freedman Diaconis Estimator)
.. math:: h = 2 \\frac{IQR}{n^{-1/3}}
The binwidth is proportional to the interquartile range (IQR)
and inversely proportional to cube root of a.size. Can be too
conservative for small datasets, but is quite good
for large datasets. The IQR is very robust to outliers.
'Scott'
.. math:: h = \\frac{3.5\\sigma}{n^{-1/3}}
The binwidth is proportional to the standard deviation (sd) of the data
and inversely proportional to cube root of a.size. Can be too
conservative for small datasets, but is quite good
for large datasets. The sd is not very robust to outliers. Values
are very similar to the Freedman Diaconis Estimator in the absence of outliers.
'Rice'
.. math:: n_h = \\left\\lceil 2n^{1/3} \\right\\rceil
The number of bins is only proportional to cube root of a.size.
It tends to overestimate the number of bins
and it does not take into account data variability.
'Sturges'
.. math:: n_h = \\left\\lceil \\log _{2}n+1 \\right\\rceil
The number of bins is the base2 log of a.size.
This estimator assumes normality of data and is too conservative for larger,
non-normal datasets. This is the default method in R's `hist` method.
Examples
--------
>>> np.histogram([1, 2, 1], bins=[0, 1, 2, 3])
(array([0, 2, 1]), array([0, 1, 2, 3]))
>>> np.histogram(np.arange(4), bins=np.arange(5), density=True)
(array([ 0.25, 0.25, 0.25, 0.25]), array([0, 1, 2, 3, 4]))
>>> np.histogram([[1, 2, 1], [1, 0, 1]], bins=[0,1,2,3])
(array([1, 4, 1]), array([0, 1, 2, 3]))
>>> a = np.arange(5)
>>> hist, bin_edges = np.histogram(a, density=True)
>>> hist
array([ 0.5, 0. , 0.5, 0. , 0. , 0.5, 0. , 0.5, 0. , 0.5])
>>> hist.sum()
2.4999999999999996
>>> np.sum(hist*np.diff(bin_edges))
1.0
.. versionadded:: 1.11.0
Automated Bin Selection Methods example, using 2 peak random data with 2000 points
>>> import matplotlib.pyplot as plt
>>> rng = np.random.RandomState(10) # deterministic random data
>>> a = np.hstack((rng.normal(size = 1000), rng.normal(loc = 5, scale = 2, size = 1000)))
>>> plt.hist(a, bins = 'auto') # plt.hist passes it's arguments to np.histogram
>>> plt.title("Histogram with 'auto' bins")
>>> plt.show()
"""
a = asarray(a)
if weights is not None:
weights = asarray(weights)
if np.any(weights.shape != a.shape):
raise ValueError(
'weights should have the same shape as a.')
weights = weights.ravel()
a = a.ravel()
if (range is not None):
mn, mx = range
if (mn > mx):
raise AttributeError(
'max must be larger than min in range parameter.')
if isinstance(bins, basestring):
bins = _hist_optim_numbins_estimator(a, bins)
# if `bins` is a string for an automatic method,
# this will replace it with the number of bins calculated
# Histogram is an integer or a float array depending on the weights.
if weights is None:
ntype = np.dtype(np.intp)
else:
ntype = weights.dtype
# We set a block size, as this allows us to iterate over chunks when
# computing histograms, to minimize memory usage.
BLOCK = 65536
if not iterable(bins):
if np.isscalar(bins) and bins < 1:
raise ValueError(
'`bins` should be a positive integer.')
if range is None:
if a.size == 0:
# handle empty arrays. Can't determine range, so use 0-1.
range = (0, 1)
else:
range = (a.min(), a.max())
mn, mx = [mi + 0.0 for mi in range]
if mn == mx:
mn -= 0.5
mx += 0.5
# At this point, if the weights are not integer, floating point, or
# complex, we have to use the slow algorithm.
if weights is not None and not (np.can_cast(weights.dtype, np.double) or
np.can_cast(weights.dtype, np.complex)):
bins = linspace(mn, mx, bins + 1, endpoint=True)
if not iterable(bins):
# We now convert values of a to bin indices, under the assumption of
# equal bin widths (which is valid here).
# Initialize empty histogram
n = np.zeros(bins, ntype)
# Pre-compute histogram scaling factor
norm = bins / (mx - mn)
# We iterate over blocks here for two reasons: the first is that for
# large arrays, it is actually faster (for example for a 10^8 array it
# is 2x as fast) and it results in a memory footprint 3x lower in the
# limit of large arrays.
for i in arange(0, len(a), BLOCK):
tmp_a = a[i:i+BLOCK]
if weights is None:
tmp_w = None
else:
tmp_w = weights[i:i + BLOCK]
# Only include values in the right range
keep = (tmp_a >= mn)
keep &= (tmp_a <= mx)
if not np.logical_and.reduce(keep):
tmp_a = tmp_a[keep]
if tmp_w is not None:
tmp_w = tmp_w[keep]
tmp_a = tmp_a.astype(float)
tmp_a -= mn
tmp_a *= norm
# Compute the bin indices, and for values that lie exactly on mx we
# need to subtract one
indices = tmp_a.astype(np.intp)
indices[indices == bins] -= 1
# We now compute the histogram using bincount
if ntype.kind == 'c':
n.real += np.bincount(indices, weights=tmp_w.real, minlength=bins)
n.imag += np.bincount(indices, weights=tmp_w.imag, minlength=bins)
else:
n += np.bincount(indices, weights=tmp_w, minlength=bins).astype(ntype)
# We now compute the bin edges since these are returned
bins = linspace(mn, mx, bins + 1, endpoint=True)
else:
bins = asarray(bins)
if (np.diff(bins) < 0).any():
raise AttributeError(
'bins must increase monotonically.')
# Initialize empty histogram
n = np.zeros(bins.shape, ntype)
if weights is None:
for i in arange(0, len(a), BLOCK):
sa = sort(a[i:i+BLOCK])
n += np.r_[sa.searchsorted(bins[:-1], 'left'),
sa.searchsorted(bins[-1], 'right')]
else:
zero = array(0, dtype=ntype)
for i in arange(0, len(a), BLOCK):
tmp_a = a[i:i+BLOCK]
tmp_w = weights[i:i+BLOCK]
sorting_index = np.argsort(tmp_a)
sa = tmp_a[sorting_index]
sw = tmp_w[sorting_index]
cw = np.concatenate(([zero, ], sw.cumsum()))
bin_index = np.r_[sa.searchsorted(bins[:-1], 'left'),
sa.searchsorted(bins[-1], 'right')]
n += cw[bin_index]
n = np.diff(n)
if density is not None:
if density:
db = array(np.diff(bins), float)
return n/db/n.sum(), bins
else:
return n, bins
else:
# deprecated, buggy behavior. Remove for Numpy 2.0
if normed:
db = array(np.diff(bins), float)
return n/(n*db).sum(), bins
else:
return n, bins
def histogramdd(sample, bins=10, range=None, normed=False, weights=None):
"""
Compute the multidimensional histogram of some data.
Parameters
----------
sample : array_like
The data to be histogrammed. It must be an (N,D) array or data
that can be converted to such. The rows of the resulting array
are the coordinates of points in a D dimensional polytope.
bins : sequence or int, optional
The bin specification:
* A sequence of arrays describing the bin edges along each dimension.
* The number of bins for each dimension (nx, ny, ... =bins)
* The number of bins for all dimensions (nx=ny=...=bins).
range : sequence, optional
A sequence of lower and upper bin edges to be used if the edges are
not given explicitly in `bins`. Defaults to the minimum and maximum
values along each dimension.
normed : bool, optional
If False, returns the number of samples in each bin. If True,
returns the bin density ``bin_count / sample_count / bin_volume``.
weights : (N,) array_like, optional
An array of values `w_i` weighing each sample `(x_i, y_i, z_i, ...)`.
Weights are normalized to 1 if normed is True. If normed is False,
the values of the returned histogram are equal to the sum of the
weights belonging to the samples falling into each bin.
Returns
-------
H : ndarray
The multidimensional histogram of sample x. See normed and weights
for the different possible semantics.
edges : list
A list of D arrays describing the bin edges for each dimension.
See Also
--------
histogram: 1-D histogram
histogram2d: 2-D histogram
Examples
--------
>>> r = np.random.randn(100,3)
>>> H, edges = np.histogramdd(r, bins = (5, 8, 4))
>>> H.shape, edges[0].size, edges[1].size, edges[2].size
((5, 8, 4), 6, 9, 5)
"""
try:
# Sample is an ND-array.
N, D = sample.shape
except (AttributeError, ValueError):
# Sample is a sequence of 1D arrays.
sample = atleast_2d(sample).T
N, D = sample.shape
nbin = empty(D, int)
edges = D*[None]
dedges = D*[None]
if weights is not None:
weights = asarray(weights)
try:
M = len(bins)
if M != D:
raise AttributeError(
'The dimension of bins must be equal to the dimension of the '
' sample x.')
except TypeError:
# bins is an integer
bins = D*[bins]
# Select range for each dimension
# Used only if number of bins is given.
if range is None:
# Handle empty input. Range can't be determined in that case, use 0-1.
if N == 0:
smin = zeros(D)
smax = ones(D)
else:
smin = atleast_1d(array(sample.min(0), float))
smax = atleast_1d(array(sample.max(0), float))
else:
smin = zeros(D)
smax = zeros(D)
for i in arange(D):
smin[i], smax[i] = range[i]
# Make sure the bins have a finite width.
for i in arange(len(smin)):
if smin[i] == smax[i]:
smin[i] = smin[i] - .5
smax[i] = smax[i] + .5
# avoid rounding issues for comparisons when dealing with inexact types
if np.issubdtype(sample.dtype, np.inexact):
edge_dt = sample.dtype
else:
edge_dt = float
# Create edge arrays
for i in arange(D):
if isscalar(bins[i]):
if bins[i] < 1:
raise ValueError(
"Element at index %s in `bins` should be a positive "
"integer." % i)
nbin[i] = bins[i] + 2 # +2 for outlier bins
edges[i] = linspace(smin[i], smax[i], nbin[i]-1, dtype=edge_dt)
else:
edges[i] = asarray(bins[i], edge_dt)
nbin[i] = len(edges[i]) + 1 # +1 for outlier bins
dedges[i] = diff(edges[i])
if np.any(np.asarray(dedges[i]) <= 0):
raise ValueError(
"Found bin edge of size <= 0. Did you specify `bins` with"
"non-monotonic sequence?")
nbin = asarray(nbin)
# Handle empty input.
if N == 0:
return np.zeros(nbin-2), edges
# Compute the bin number each sample falls into.
Ncount = {}
for i in arange(D):
Ncount[i] = digitize(sample[:, i], edges[i])
# Using digitize, values that fall on an edge are put in the right bin.
# For the rightmost bin, we want values equal to the right edge to be
# counted in the last bin, and not as an outlier.
for i in arange(D):
# Rounding precision
mindiff = dedges[i].min()
if not np.isinf(mindiff):
decimal = int(-log10(mindiff)) + 6
# Find which points are on the rightmost edge.
not_smaller_than_edge = (sample[:, i] >= edges[i][-1])
on_edge = (around(sample[:, i], decimal) ==
around(edges[i][-1], decimal))
# Shift these points one bin to the left.
Ncount[i][where(on_edge & not_smaller_than_edge)[0]] -= 1
# Flattened histogram matrix (1D)
# Reshape is used so that overlarge arrays
# will raise an error.
hist = zeros(nbin, float).reshape(-1)
# Compute the sample indices in the flattened histogram matrix.
ni = nbin.argsort()
xy = zeros(N, int)
for i in arange(0, D-1):
xy += Ncount[ni[i]] * nbin[ni[i+1:]].prod()
xy += Ncount[ni[-1]]
# Compute the number of repetitions in xy and assign it to the
# flattened histmat.
if len(xy) == 0:
return zeros(nbin-2, int), edges
flatcount = bincount(xy, weights)
a = arange(len(flatcount))
hist[a] = flatcount
# Shape into a proper matrix
hist = hist.reshape(sort(nbin))
for i in arange(nbin.size):
j = ni.argsort()[i]
hist = hist.swapaxes(i, j)
ni[i], ni[j] = ni[j], ni[i]
# Remove outliers (indices 0 and -1 for each dimension).
core = D*[slice(1, -1)]
hist = hist[core]
# Normalize if normed is True
if normed:
s = hist.sum()
for i in arange(D):
shape = ones(D, int)
shape[i] = nbin[i] - 2
hist = hist / dedges[i].reshape(shape)
hist /= s
if (hist.shape != nbin - 2).any():
raise RuntimeError(
"Internal Shape Error")
return hist, edges
def average(a, axis=None, weights=None, returned=False):
"""
Compute the weighted average along the specified axis.
Parameters
----------
a : array_like
Array containing data to be averaged. If `a` is not an array, a
conversion is attempted.
axis : int, optional
Axis along which to average `a`. If `None`, averaging is done over
the flattened array.
weights : array_like, optional
An array of weights associated with the values in `a`. Each value in
`a` contributes to the average according to its associated weight.
The weights array can either be 1-D (in which case its length must be
the size of `a` along the given axis) or of the same shape as `a`.
If `weights=None`, then all data in `a` are assumed to have a
weight equal to one.
returned : bool, optional
Default is `False`. If `True`, the tuple (`average`, `sum_of_weights`)
is returned, otherwise only the average is returned.
If `weights=None`, `sum_of_weights` is equivalent to the number of
elements over which the average is taken.
Returns
-------
average, [sum_of_weights] : array_type or double
Return the average along the specified axis. When returned is `True`,
return a tuple with the average as the first element and the sum
of the weights as the second element. The return type is `Float`
if `a` is of integer type, otherwise it is of the same type as `a`.
`sum_of_weights` is of the same type as `average`.
Raises
------
ZeroDivisionError
When all weights along axis are zero. See `numpy.ma.average` for a
version robust to this type of error.
TypeError
When the length of 1D `weights` is not the same as the shape of `a`
along axis.
See Also
--------
mean
ma.average : average for masked arrays -- useful if your data contains
"missing" values
Examples
--------
>>> data = range(1,5)
>>> data
[1, 2, 3, 4]
>>> np.average(data)
2.5
>>> np.average(range(1,11), weights=range(10,0,-1))
4.0
>>> data = np.arange(6).reshape((3,2))
>>> data
array([[0, 1],
[2, 3],
[4, 5]])
>>> np.average(data, axis=1, weights=[1./4, 3./4])
array([ 0.75, 2.75, 4.75])
>>> np.average(data, weights=[1./4, 3./4])
Traceback (most recent call last):
...
TypeError: Axis must be specified when shapes of a and weights differ.
"""
if not isinstance(a, np.matrix):
a = np.asarray(a)
if weights is None:
avg = a.mean(axis)
scl = avg.dtype.type(a.size/avg.size)
else:
a = a + 0.0
wgt = np.asarray(weights)
# Sanity checks
if a.shape != wgt.shape:
if axis is None:
raise TypeError(
"Axis must be specified when shapes of a and weights "
"differ.")
if wgt.ndim != 1:
raise TypeError(
"1D weights expected when shapes of a and weights differ.")
if wgt.shape[0] != a.shape[axis]:
raise ValueError(
"Length of weights not compatible with specified axis.")
# setup wgt to broadcast along axis
wgt = np.array(wgt, copy=0, ndmin=a.ndim).swapaxes(-1, axis)
scl = wgt.sum(axis=axis, dtype=np.result_type(a.dtype, wgt.dtype))
if (scl == 0.0).any():
raise ZeroDivisionError(
"Weights sum to zero, can't be normalized")
avg = np.multiply(a, wgt).sum(axis)/scl
if returned:
scl = np.multiply(avg, 0) + scl
return avg, scl
else:
return avg
def asarray_chkfinite(a, dtype=None, order=None):
"""Convert the input to an array, checking for NaNs or Infs.
Parameters
----------
a : array_like
Input data, in any form that can be converted to an array. This
includes lists, lists of tuples, tuples, tuples of tuples, tuples
of lists and ndarrays. Success requires no NaNs or Infs.
dtype : data-type, optional
By default, the data-type is inferred from the input data.
order : {'C', 'F'}, optional
Whether to use row-major (C-style) or
column-major (Fortran-style) memory representation.
Defaults to 'C'.
Returns
-------
out : ndarray
Array interpretation of `a`. No copy is performed if the input
is already an ndarray. If `a` is a subclass of ndarray, a base
class ndarray is returned.
Raises
------
ValueError
Raises ValueError if `a` contains NaN (Not a Number) or Inf (Infinity).
See Also
--------
asarray : Create and array.
asanyarray : Similar function which passes through subclasses.
ascontiguousarray : Convert input to a contiguous array.
asfarray : Convert input to a floating point ndarray.
asfortranarray : Convert input to an ndarray with column-major
memory order.
fromiter : Create an array from an iterator.
fromfunction : Construct an array by executing a function on grid
positions.
Examples
--------
Convert a list into an array. If all elements are finite
``asarray_chkfinite`` is identical to ``asarray``.
>>> a = [1, 2]
>>> np.asarray_chkfinite(a, dtype=float)
array([1., 2.])
Raises ValueError if array_like contains Nans or Infs.
>>> a = [1, 2, np.inf]
>>> try:
... np.asarray_chkfinite(a)
... except ValueError:
... print 'ValueError'
...
ValueError
"""
a = asarray(a, dtype=dtype, order=order)
if a.dtype.char in typecodes['AllFloat'] and not np.isfinite(a).all():
raise ValueError(
"array must not contain infs or NaNs")
return a
def piecewise(x, condlist, funclist, *args, **kw):
"""
Evaluate a piecewise-defined function.
Given a set of conditions and corresponding functions, evaluate each
function on the input data wherever its condition is true.
Parameters
----------
x : ndarray
The input domain.
condlist : list of bool arrays
Each boolean array corresponds to a function in `funclist`. Wherever
`condlist[i]` is True, `funclist[i](x)` is used as the output value.
Each boolean array in `condlist` selects a piece of `x`,
and should therefore be of the same shape as `x`.
The length of `condlist` must correspond to that of `funclist`.
If one extra function is given, i.e. if
``len(funclist) - len(condlist) == 1``, then that extra function
is the default value, used wherever all conditions are false.
funclist : list of callables, f(x,*args,**kw), or scalars
Each function is evaluated over `x` wherever its corresponding
condition is True. It should take an array as input and give an array
or a scalar value as output. If, instead of a callable,
a scalar is provided then a constant function (``lambda x: scalar``) is
assumed.
args : tuple, optional
Any further arguments given to `piecewise` are passed to the functions
upon execution, i.e., if called ``piecewise(..., ..., 1, 'a')``, then
each function is called as ``f(x, 1, 'a')``.
kw : dict, optional
Keyword arguments used in calling `piecewise` are passed to the
functions upon execution, i.e., if called
``piecewise(..., ..., lambda=1)``, then each function is called as
``f(x, lambda=1)``.
Returns
-------
out : ndarray
The output is the same shape and type as x and is found by
calling the functions in `funclist` on the appropriate portions of `x`,
as defined by the boolean arrays in `condlist`. Portions not covered
by any condition have a default value of 0.
See Also
--------
choose, select, where
Notes
-----
This is similar to choose or select, except that functions are
evaluated on elements of `x` that satisfy the corresponding condition from
`condlist`.
The result is::
|--
|funclist[0](x[condlist[0]])
out = |funclist[1](x[condlist[1]])
|...
|funclist[n2](x[condlist[n2]])
|--
Examples
--------
Define the sigma function, which is -1 for ``x < 0`` and +1 for ``x >= 0``.
>>> x = np.linspace(-2.5, 2.5, 6)
>>> np.piecewise(x, [x < 0, x >= 0], [-1, 1])
array([-1., -1., -1., 1., 1., 1.])
Define the absolute value, which is ``-x`` for ``x <0`` and ``x`` for
``x >= 0``.
>>> np.piecewise(x, [x < 0, x >= 0], [lambda x: -x, lambda x: x])
array([ 2.5, 1.5, 0.5, 0.5, 1.5, 2.5])
"""
x = asanyarray(x)
n2 = len(funclist)
if (isscalar(condlist) or not (isinstance(condlist[0], list) or
isinstance(condlist[0], ndarray))):
condlist = [condlist]
condlist = array(condlist, dtype=bool)
n = len(condlist)
# This is a hack to work around problems with NumPy's
# handling of 0-d arrays and boolean indexing with
# numpy.bool_ scalars
zerod = False
if x.ndim == 0:
x = x[None]
zerod = True
if condlist.shape[-1] != 1:
condlist = condlist.T
if n == n2 - 1: # compute the "otherwise" condition.
totlist = np.logical_or.reduce(condlist, axis=0)
condlist = np.vstack([condlist, ~totlist])
n += 1
if (n != n2):
raise ValueError(
"function list and condition list must be the same")
y = zeros(x.shape, x.dtype)
for k in range(n):
item = funclist[k]
if not isinstance(item, collections.Callable):
y[condlist[k]] = item
else:
vals = x[condlist[k]]
if vals.size > 0:
y[condlist[k]] = item(vals, *args, **kw)
if zerod:
y = y.squeeze()
return y
def select(condlist, choicelist, default=0):
"""
Return an array drawn from elements in choicelist, depending on conditions.
Parameters
----------
condlist : list of bool ndarrays
The list of conditions which determine from which array in `choicelist`
the output elements are taken. When multiple conditions are satisfied,
the first one encountered in `condlist` is used.
choicelist : list of ndarrays
The list of arrays from which the output elements are taken. It has
to be of the same length as `condlist`.
default : scalar, optional
The element inserted in `output` when all conditions evaluate to False.
Returns
-------
output : ndarray
The output at position m is the m-th element of the array in
`choicelist` where the m-th element of the corresponding array in
`condlist` is True.
See Also
--------
where : Return elements from one of two arrays depending on condition.
take, choose, compress, diag, diagonal
Examples
--------
>>> x = np.arange(10)
>>> condlist = [x<3, x>5]
>>> choicelist = [x, x**2]
>>> np.select(condlist, choicelist)
array([ 0, 1, 2, 0, 0, 0, 36, 49, 64, 81])
"""
# Check the size of condlist and choicelist are the same, or abort.
if len(condlist) != len(choicelist):
raise ValueError(
'list of cases must be same length as list of conditions')