summaryrefslogtreecommitdiffstats
path: root/Lib/statistics.py
blob: bd3813ce1a4f190016887142bed5c47241cdcf25 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
"""
Basic statistics module.

This module provides functions for calculating statistics of data, including
averages, variance, and standard deviation.

Calculating averages
--------------------

==================  ==================================================
Function            Description
==================  ==================================================
mean                Arithmetic mean (average) of data.
fmean               Fast, floating point arithmetic mean.
geometric_mean      Geometric mean of data.
harmonic_mean       Harmonic mean of data.
median              Median (middle value) of data.
median_low          Low median of data.
median_high         High median of data.
median_grouped      Median, or 50th percentile, of grouped data.
mode                Mode (most common value) of data.
multimode           List of modes (most common values of data).
quantiles           Divide data into intervals with equal probability.
==================  ==================================================

Calculate the arithmetic mean ("the average") of data:

>>> mean([-1.0, 2.5, 3.25, 5.75])
2.625


Calculate the standard median of discrete data:

>>> median([2, 3, 4, 5])
3.5


Calculate the median, or 50th percentile, of data grouped into class intervals
centred on the data values provided. E.g. if your data points are rounded to
the nearest whole number:

>>> median_grouped([2, 2, 3, 3, 3, 4])  #doctest: +ELLIPSIS
2.8333333333...

This should be interpreted in this way: you have two data points in the class
interval 1.5-2.5, three data points in the class interval 2.5-3.5, and one in
the class interval 3.5-4.5. The median of these data points is 2.8333...


Calculating variability or spread
---------------------------------

==================  =============================================
Function            Description
==================  =============================================
pvariance           Population variance of data.
variance            Sample variance of data.
pstdev              Population standard deviation of data.
stdev               Sample standard deviation of data.
==================  =============================================

Calculate the standard deviation of sample data:

>>> stdev([2.5, 3.25, 5.5, 11.25, 11.75])  #doctest: +ELLIPSIS
4.38961843444...

If you have previously calculated the mean, you can pass it as the optional
second argument to the four "spread" functions to avoid recalculating it:

>>> data = [1, 2, 2, 4, 4, 4, 5, 6]
>>> mu = mean(data)
>>> pvariance(data, mu)
2.5


Statistics for relations between two inputs
-------------------------------------------

==================  ====================================================
Function            Description
==================  ====================================================
covariance          Sample covariance for two variables.
correlation         Pearson's correlation coefficient for two variables.
linear_regression   Intercept and slope for simple linear regression.
==================  ====================================================

Calculate covariance, Pearson's correlation, and simple linear regression
for two inputs:

>>> x = [1, 2, 3, 4, 5, 6, 7, 8, 9]
>>> y = [1, 2, 3, 1, 2, 3, 1, 2, 3]
>>> covariance(x, y)
0.75
>>> correlation(x, y)  #doctest: +ELLIPSIS
0.31622776601...
>>> linear_regression(x, y)  #doctest:
LinearRegression(intercept=1.5, slope=0.1)


Exceptions
----------

A single exception is defined: StatisticsError is a subclass of ValueError.

"""

__all__ = [
    'NormalDist',
    'StatisticsError',
    'correlation',
    'covariance',
    'fmean',
    'geometric_mean',
    'harmonic_mean',
    'linear_regression',
    'mean',
    'median',
    'median_grouped',
    'median_high',
    'median_low',
    'mode',
    'multimode',
    'pstdev',
    'pvariance',
    'quantiles',
    'stdev',
    'variance',
]

import math
import numbers
import random

from fractions import Fraction
from decimal import Decimal
from itertools import groupby, repeat
from bisect import bisect_left, bisect_right
from math import hypot, sqrt, fabs, exp, erf, tau, log, fsum
from operator import itemgetter, mul
from collections import Counter, namedtuple

# === Exceptions ===

class StatisticsError(ValueError):
    pass


# === Private utilities ===

def _sum(data, start=0):
    """_sum(data [, start]) -> (type, sum, count)

    Return a high-precision sum of the given numeric data as a fraction,
    together with the type to be converted to and the count of items.

    If optional argument ``start`` is given, it is added to the total.
    If ``data`` is empty, ``start`` (defaulting to 0) is returned.


    Examples
    --------

    >>> _sum([3, 2.25, 4.5, -0.5, 1.0], 0.75)
    (<class 'float'>, Fraction(11, 1), 5)

    Some sources of round-off error will be avoided:

    # Built-in sum returns zero.
    >>> _sum([1e50, 1, -1e50] * 1000)
    (<class 'float'>, Fraction(1000, 1), 3000)

    Fractions and Decimals are also supported:

    >>> from fractions import Fraction as F
    >>> _sum([F(2, 3), F(7, 5), F(1, 4), F(5, 6)])
    (<class 'fractions.Fraction'>, Fraction(63, 20), 4)

    >>> from decimal import Decimal as D
    >>> data = [D("0.1375"), D("0.2108"), D("0.3061"), D("0.0419")]
    >>> _sum(data)
    (<class 'decimal.Decimal'>, Fraction(6963, 10000), 4)

    Mixed types are currently treated as an error, except that int is
    allowed.
    """
    count = 0
    n, d = _exact_ratio(start)
    partials = {d: n}
    partials_get = partials.get
    T = _coerce(int, type(start))
    for typ, values in groupby(data, type):
        T = _coerce(T, typ)  # or raise TypeError
        for n, d in map(_exact_ratio, values):
            count += 1
            partials[d] = partials_get(d, 0) + n
    if None in partials:
        # The sum will be a NAN or INF. We can ignore all the finite
        # partials, and just look at this special one.
        total = partials[None]
        assert not _isfinite(total)
    else:
        # Sum all the partial sums using builtin sum.
        # FIXME is this faster if we sum them in order of the denominator?
        total = sum(Fraction(n, d) for d, n in sorted(partials.items()))
    return (T, total, count)


def _isfinite(x):
    try:
        return x.is_finite()  # Likely a Decimal.
    except AttributeError:
        return math.isfinite(x)  # Coerces to float first.


def _coerce(T, S):
    """Coerce types T and S to a common type, or raise TypeError.

    Coercion rules are currently an implementation detail. See the CoerceTest
    test class in test_statistics for details.
    """
    # See http://bugs.python.org/issue24068.
    assert T is not bool, "initial type T is bool"
    # If the types are the same, no need to coerce anything. Put this
    # first, so that the usual case (no coercion needed) happens as soon
    # as possible.
    if T is S:  return T
    # Mixed int & other coerce to the other type.
    if S is int or S is bool:  return T
    if T is int:  return S
    # If one is a (strict) subclass of the other, coerce to the subclass.
    if issubclass(S, T):  return S
    if issubclass(T, S):  return T
    # Ints coerce to the other type.
    if issubclass(T, int):  return S
    if issubclass(S, int):  return T
    # Mixed fraction & float coerces to float (or float subclass).
    if issubclass(T, Fraction) and issubclass(S, float):
        return S
    if issubclass(T, float) and issubclass(S, Fraction):
        return T
    # Any other combination is disallowed.
    msg = "don't know how to coerce %s and %s"
    raise TypeError(msg % (T.__name__, S.__name__))


def _exact_ratio(x):
    """Return Real number x to exact (numerator, denominator) pair.

    >>> _exact_ratio(0.25)
    (1, 4)

    x is expected to be an int, Fraction, Decimal or float.
    """
    try:
        # Optimise the common case of floats. We expect that the most often
        # used numeric type will be builtin floats, so try to make this as
        # fast as possible.
        if type(x) is float or type(x) is Decimal:
            return x.as_integer_ratio()
        try:
            # x may be an int, Fraction, or Integral ABC.
            return (x.numerator, x.denominator)
        except AttributeError:
            try:
                # x may be a float or Decimal subclass.
                return x.as_integer_ratio()
            except AttributeError:
                # Just give up?
                pass
    except (OverflowError, ValueError):
        # float NAN or INF.
        assert not _isfinite(x)
        return (x, None)
    msg = "can't convert type '{}' to numerator/denominator"
    raise TypeError(msg.format(type(x).__name__))


def _convert(value, T):
    """Convert value to given numeric type T."""
    if type(value) is T:
        # This covers the cases where T is Fraction, or where value is
        # a NAN or INF (Decimal or float).
        return value
    if issubclass(T, int) and value.denominator != 1:
        T = float
    try:
        # FIXME: what do we do if this overflows?
        return T(value)
    except TypeError:
        if issubclass(T, Decimal):
            return T(value.numerator) / T(value.denominator)
        else:
            raise


def _find_lteq(a, x):
    'Locate the leftmost value exactly equal to x'
    i = bisect_left(a, x)
    if i != len(a) and a[i] == x:
        return i
    raise ValueError


def _find_rteq(a, l, x):
    'Locate the rightmost value exactly equal to x'
    i = bisect_right(a, x, lo=l)
    if i != (len(a) + 1) and a[i - 1] == x:
        return i - 1
    raise ValueError


def _fail_neg(values, errmsg='negative value'):
    """Iterate over values, failing if any are less than zero."""
    for x in values:
        if x < 0:
            raise StatisticsError(errmsg)
        yield x


# === Measures of central tendency (averages) ===

def mean(data):
    """Return the sample arithmetic mean of data.

    >>> mean([1, 2, 3, 4, 4])
    2.8

    >>> from fractions import Fraction as F
    >>> mean([F(3, 7), F(1, 21), F(5, 3), F(1, 3)])
    Fraction(13, 21)

    >>> from decimal import Decimal as D
    >>> mean([D("0.5"), D("0.75"), D("0.625"), D("0.375")])
    Decimal('0.5625')

    If ``data`` is empty, StatisticsError will be raised.
    """
    if iter(data) is data:
        data = list(data)
    n = len(data)
    if n < 1:
        raise StatisticsError('mean requires at least one data point')
    T, total, count = _sum(data)
    assert count == n
    return _convert(total / n, T)


def fmean(data, weights=None):
    """Convert data to floats and compute the arithmetic mean.

    This runs faster than the mean() function and it always returns a float.
    If the input dataset is empty, it raises a StatisticsError.

    >>> fmean([3.5, 4.0, 5.25])
    4.25
    """
    try:
        n = len(data)
    except TypeError:
        # Handle iterators that do not define __len__().
        n = 0
        def count(iterable):
            nonlocal n
            for n, x in enumerate(iterable, start=1):
                yield x
        data = count(data)
    if weights is None:
        total = fsum(data)
        if not n:
            raise StatisticsError('fmean requires at least one data point')
        return total / n
    try:
        num_weights = len(weights)
    except TypeError:
        weights = list(weights)
        num_weights = len(weights)
    num = fsum(map(mul, data, weights))
    if n != num_weights:
        raise StatisticsError('data and weights must be the same length')
    den = fsum(weights)
    if not den:
        raise StatisticsError('sum of weights must be non-zero')
    return num / den


def geometric_mean(data):
    """Convert data to floats and compute the geometric mean.

    Raises a StatisticsError if the input dataset is empty,
    if it contains a zero, or if it contains a negative value.

    No special efforts are made to achieve exact results.
    (However, this may change in the future.)

    >>> round(geometric_mean([54, 24, 36]), 9)
    36.0
    """
    try:
        return exp(fmean(map(log, data)))
    except ValueError:
        raise StatisticsError('geometric mean requires a non-empty dataset '
                              ' containing positive numbers') from None


def harmonic_mean(data, weights=None):
    """Return the harmonic mean of data.

    The harmonic mean is the reciprocal of the arithmetic mean of the
    reciprocals of the data.  It can be used for averaging ratios or
    rates, for example speeds.

    Suppose a car travels 40 km/hr for 5 km and then speeds-up to
    60 km/hr for another 5 km. What is the average speed?

        >>> harmonic_mean([40, 60])
        48.0

    Suppose a car travels 40 km/hr for 5 km, and when traffic clears,
    speeds-up to 60 km/hr for the remaining 30 km of the journey. What
    is the average speed?

        >>> harmonic_mean([40, 60], weights=[5, 30])
        56.0

    If ``data`` is empty, or any element is less than zero,
    ``harmonic_mean`` will raise ``StatisticsError``.
    """
    if iter(data) is data:
        data = list(data)
    errmsg = 'harmonic mean does not support negative values'
    n = len(data)
    if n < 1:
        raise StatisticsError('harmonic_mean requires at least one data point')
    elif n == 1 and weights is None:
        x = data[0]
        if isinstance(x, (numbers.Real, Decimal)):
            if x < 0:
                raise StatisticsError(errmsg)
            return x
        else:
            raise TypeError('unsupported type')
    if weights is None:
        weights = repeat(1, n)
        sum_weights = n
    else:
        if iter(weights) is weights:
            weights = list(weights)
        if len(weights) != n:
            raise StatisticsError('Number of weights does not match data size')
        _, sum_weights, _ = _sum(w for w in _fail_neg(weights, errmsg))
    try:
        data = _fail_neg(data, errmsg)
        T, total, count = _sum(w / x if w else 0 for w, x in zip(weights, data))
    except ZeroDivisionError:
        return 0
    if total <= 0:
        raise StatisticsError('Weighted sum must be positive')
    return _convert(sum_weights / total, T)

# FIXME: investigate ways to calculate medians without sorting? Quickselect?
def median(data):
    """Return the median (middle value) of numeric data.

    When the number of data points is odd, return the middle data point.
    When the number of data points is even, the median is interpolated by
    taking the average of the two middle values:

    >>> median([1, 3, 5])
    3
    >>> median([1, 3, 5, 7])
    4.0

    """
    data = sorted(data)
    n = len(data)
    if n == 0:
        raise StatisticsError("no median for empty data")
    if n % 2 == 1:
        return data[n // 2]
    else:
        i = n // 2
        return (data[i - 1] + data[i]) / 2


def median_low(data):
    """Return the low median of numeric data.

    When the number of data points is odd, the middle value is returned.
    When it is even, the smaller of the two middle values is returned.

    >>> median_low([1, 3, 5])
    3
    >>> median_low([1, 3, 5, 7])
    3

    """
    data = sorted(data)
    n = len(data)
    if n == 0:
        raise StatisticsError("no median for empty data")
    if n % 2 == 1:
        return data[n // 2]
    else:
        return data[n // 2 - 1]


def median_high(data):
    """Return the high median of data.

    When the number of data points is odd, the middle value is returned.
    When it is even, the larger of the two middle values is returned.

    >>> median_high([1, 3, 5])
    3
    >>> median_high([1, 3, 5, 7])
    5

    """
    data = sorted(data)
    n = len(data)
    if n == 0:
        raise StatisticsError("no median for empty data")
    return data[n // 2]


def median_grouped(data, interval=1):
    """Return the 50th percentile (median) of grouped continuous data.

    >>> median_grouped([1, 2, 2, 3, 4, 4, 4, 4, 4, 5])
    3.7
    >>> median_grouped([52, 52, 53, 54])
    52.5

    This calculates the median as the 50th percentile, and should be
    used when your data is continuous and grouped. In the above example,
    the values 1, 2, 3, etc. actually represent the midpoint of classes
    0.5-1.5, 1.5-2.5, 2.5-3.5, etc. The middle value falls somewhere in
    class 3.5-4.5, and interpolation is used to estimate it.

    Optional argument ``interval`` represents the class interval, and
    defaults to 1. Changing the class interval naturally will change the
    interpolated 50th percentile value:

    >>> median_grouped([1, 3, 3, 5, 7], interval=1)
    3.25
    >>> median_grouped([1, 3, 3, 5, 7], interval=2)
    3.5

    This function does not check whether the data points are at least
    ``interval`` apart.
    """
    data = sorted(data)
    n = len(data)
    if n == 0:
        raise StatisticsError("no median for empty data")
    elif n == 1:
        return data[0]
    # Find the value at the midpoint. Remember this corresponds to the
    # centre of the class interval.
    x = data[n // 2]
    for obj in (x, interval):
        if isinstance(obj, (str, bytes)):
            raise TypeError('expected number but got %r' % obj)
    try:
        L = x - interval / 2  # The lower limit of the median interval.
    except TypeError:
        # Mixed type. For now we just coerce to float.
        L = float(x) - float(interval) / 2

    # Uses bisection search to search for x in data with log(n) time complexity
    # Find the position of leftmost occurrence of x in data
    l1 = _find_lteq(data, x)
    # Find the position of rightmost occurrence of x in data[l1...len(data)]
    # Assuming always l1 <= l2
    l2 = _find_rteq(data, l1, x)
    cf = l1
    f = l2 - l1 + 1
    return L + interval * (n / 2 - cf) / f


def mode(data):
    """Return the most common data point from discrete or nominal data.

    ``mode`` assumes discrete data, and returns a single value. This is the
    standard treatment of the mode as commonly taught in schools:

        >>> mode([1, 1, 2, 3, 3, 3, 3, 4])
        3

    This also works with nominal (non-numeric) data:

        >>> mode(["red", "blue", "blue", "red", "green", "red", "red"])
        'red'

    If there are multiple modes with same frequency, return the first one
    encountered:

        >>> mode(['red', 'red', 'green', 'blue', 'blue'])
        'red'

    If *data* is empty, ``mode``, raises StatisticsError.

    """
    pairs = Counter(iter(data)).most_common(1)
    try:
        return pairs[0][0]
    except IndexError:
        raise StatisticsError('no mode for empty data') from None


def multimode(data):
    """Return a list of the most frequently occurring values.

    Will return more than one result if there are multiple modes
    or an empty list if *data* is empty.

    >>> multimode('aabbbbbbbbcc')
    ['b']
    >>> multimode('aabbbbccddddeeffffgg')
    ['b', 'd', 'f']
    >>> multimode('')
    []
    """
    counts = Counter(iter(data)).most_common()
    maxcount, mode_items = next(groupby(counts, key=itemgetter(1)), (0, []))
    return list(map(itemgetter(0), mode_items))


# Notes on methods for computing quantiles
# ----------------------------------------
#
# There is no one perfect way to compute quantiles.  Here we offer
# two methods that serve common needs.  Most other packages
# surveyed offered at least one or both of these two, making them
# "standard" in the sense of "widely-adopted and reproducible".
# They are also easy to explain, easy to compute manually, and have
# straight-forward interpretations that aren't surprising.

# The default method is known as "R6", "PERCENTILE.EXC", or "expected
# value of rank order statistics". The alternative method is known as
# "R7", "PERCENTILE.INC", or "mode of rank order statistics".

# For sample data where there is a positive probability for values
# beyond the range of the data, the R6 exclusive method is a
# reasonable choice.  Consider a random sample of nine values from a
# population with a uniform distribution from 0.0 to 1.0.  The
# distribution of the third ranked sample point is described by
# betavariate(alpha=3, beta=7) which has mode=0.250, median=0.286, and
# mean=0.300.  Only the latter (which corresponds with R6) gives the
# desired cut point with 30% of the population falling below that
# value, making it comparable to a result from an inv_cdf() function.
# The R6 exclusive method is also idempotent.

# For describing population data where the end points are known to
# be included in the data, the R7 inclusive method is a reasonable
# choice.  Instead of the mean, it uses the mode of the beta
# distribution for the interior points.  Per Hyndman & Fan, "One nice
# property is that the vertices of Q7(p) divide the range into n - 1
# intervals, and exactly 100p% of the intervals lie to the left of
# Q7(p) and 100(1 - p)% of the intervals lie to the right of Q7(p)."

# If needed, other methods could be added.  However, for now, the
# position is that fewer options make for easier choices and that
# external packages can be used for anything more advanced.

def quantiles(data, *, n=4, method='exclusive'):
    """Divide *data* into *n* continuous intervals with equal probability.

    Returns a list of (n - 1) cut points separating the intervals.

    Set *n* to 4 for quartiles (the default).  Set *n* to 10 for deciles.
    Set *n* to 100 for percentiles which gives the 99 cuts points that
    separate *data* in to 100 equal sized groups.

    The *data* can be any iterable containing sample.
    The cut points are linearly interpolated between data points.

    If *method* is set to *inclusive*, *data* is treated as population
    data.  The minimum value is treated as the 0th percentile and the
    maximum value is treated as the 100th percentile.
    """
    if n < 1:
        raise StatisticsError('n must be at least 1')
    data = sorted(data)
    ld = len(data)
    if ld < 2:
        raise StatisticsError('must have at least two data points')
    if method == 'inclusive':
        m = ld - 1
        result = []
        for i in range(1, n):
            j, delta = divmod(i * m, n)
            interpolated = (data[j] * (n - delta) + data[j + 1] * delta) / n
            result.append(interpolated)
        return result
    if method == 'exclusive':
        m = ld + 1
        result = []
        for i in range(1, n):
            j = i * m // n                               # rescale i to m/n
            j = 1 if j < 1 else ld-1 if j > ld-1 else j  # clamp to 1 .. ld-1
            delta = i*m - j*n                            # exact integer math
            interpolated = (data[j - 1] * (n - delta) + data[j] * delta) / n
            result.append(interpolated)
        return result
    raise ValueError(f'Unknown method: {method!r}')


# === Measures of spread ===

# See http://mathworld.wolfram.com/Variance.html
#     http://mathworld.wolfram.com/SampleVariance.html
#     http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
#
# Under no circumstances use the so-called "computational formula for
# variance", as that is only suitable for hand calculations with a small
# amount of low-precision data. It has terrible numeric properties.
#
# See a comparison of three computational methods here:
# http://www.johndcook.com/blog/2008/09/26/comparing-three-methods-of-computing-standard-deviation/

def _ss(data, c=None):
    """Return sum of square deviations of sequence data.

    If ``c`` is None, the mean is calculated in one pass, and the deviations
    from the mean are calculated in a second pass. Otherwise, deviations are
    calculated from ``c`` as given. Use the second case with care, as it can
    lead to garbage results.
    """
    if c is not None:
        T, total, count = _sum((x-c)**2 for x in data)
        return (T, total)
    c = mean(data)
    T, total, count = _sum((x-c)**2 for x in data)
    # The following sum should mathematically equal zero, but due to rounding
    # error may not.
    U, total2, count2 = _sum((x - c) for x in data)
    assert T == U and count == count2
    total -= total2 ** 2 / len(data)
    assert not total < 0, 'negative sum of square deviations: %f' % total
    return (T, total)


def variance(data, xbar=None):
    """Return the sample variance of data.

    data should be an iterable of Real-valued numbers, with at least two
    values. The optional argument xbar, if given, should be the mean of
    the data. If it is missing or None, the mean is automatically calculated.

    Use this function when your data is a sample from a population. To
    calculate the variance from the entire population, see ``pvariance``.

    Examples:

    >>> data = [2.75, 1.75, 1.25, 0.25, 0.5, 1.25, 3.5]
    >>> variance(data)
    1.3720238095238095

    If you have already calculated the mean of your data, you can pass it as
    the optional second argument ``xbar`` to avoid recalculating it:

    >>> m = mean(data)
    >>> variance(data, m)
    1.3720238095238095

    This function does not check that ``xbar`` is actually the mean of
    ``data``. Giving arbitrary values for ``xbar`` may lead to invalid or
    impossible results.

    Decimals and Fractions are supported:

    >>> from decimal import Decimal as D
    >>> variance([D("27.5"), D("30.25"), D("30.25"), D("34.5"), D("41.75")])
    Decimal('31.01875')

    >>> from fractions import Fraction as F
    >>> variance([F(1, 6), F(1, 2), F(5, 3)])
    Fraction(67, 108)

    """
    if iter(data) is data:
        data = list(data)
    n = len(data)
    if n < 2:
        raise StatisticsError('variance requires at least two data points')
    T, ss = _ss(data, xbar)
    return _convert(ss / (n - 1), T)


def pvariance(data, mu=None):
    """Return the population variance of ``data``.

    data should be a sequence or iterable of Real-valued numbers, with at least one
    value. The optional argument mu, if given, should be the mean of
    the data. If it is missing or None, the mean is automatically calculated.

    Use this function to calculate the variance from the entire population.
    To estimate the variance from a sample, the ``variance`` function is
    usually a better choice.

    Examples:

    >>> data = [0.0, 0.25, 0.25, 1.25, 1.5, 1.75, 2.75, 3.25]
    >>> pvariance(data)
    1.25

    If you have already calculated the mean of the data, you can pass it as
    the optional second argument to avoid recalculating it:

    >>> mu = mean(data)
    >>> pvariance(data, mu)
    1.25

    Decimals and Fractions are supported:

    >>> from decimal import Decimal as D
    >>> pvariance([D("27.5"), D("30.25"), D("30.25"), D("34.5"), D("41.75")])
    Decimal('24.815')

    >>> from fractions import Fraction as F
    >>> pvariance([F(1, 4), F(5, 4), F(1, 2)])
    Fraction(13, 72)

    """
    if iter(data) is data:
        data = list(data)
    n = len(data)
    if n < 1:
        raise StatisticsError('pvariance requires at least one data point')
    T, ss = _ss(data, mu)
    return _convert(ss / n, T)


def stdev(data, xbar=None):
    """Return the square root of the sample variance.

    See ``variance`` for arguments and other details.

    >>> stdev([1.5, 2.5, 2.5, 2.75, 3.25, 4.75])
    1.0810874155219827

    """
    var = variance(data, xbar)
    try:
        return var.sqrt()
    except AttributeError:
        return math.sqrt(var)


def pstdev(data, mu=None):
    """Return the square root of the population variance.

    See ``pvariance`` for arguments and other details.

    >>> pstdev([1.5, 2.5, 2.5, 2.75, 3.25, 4.75])
    0.986893273527251

    """
    var = pvariance(data, mu)
    try:
        return var.sqrt()
    except AttributeError:
        return math.sqrt(var)


# === Statistics for relations between two inputs ===

# See https://en.wikipedia.org/wiki/Covariance
#     https://en.wikipedia.org/wiki/Pearson_correlation_coefficient
#     https://en.wikipedia.org/wiki/Simple_linear_regression


def covariance(x, y, /):
    """Covariance

    Return the sample covariance of two inputs *x* and *y*. Covariance
    is a measure of the joint variability of two inputs.

    >>> x = [1, 2, 3, 4, 5, 6, 7, 8, 9]
    >>> y = [1, 2, 3, 1, 2, 3, 1, 2, 3]
    >>> covariance(x, y)
    0.75
    >>> z = [9, 8, 7, 6, 5, 4, 3, 2, 1]
    >>> covariance(x, z)
    -7.5
    >>> covariance(z, x)
    -7.5

    """
    n = len(x)
    if len(y) != n:
        raise StatisticsError('covariance requires that both inputs have same number of data points')
    if n < 2:
        raise StatisticsError('covariance requires at least two data points')
    xbar = fsum(x) / n
    ybar = fsum(y) / n
    sxy = fsum((xi - xbar) * (yi - ybar) for xi, yi in zip(x, y))
    return sxy / (n - 1)


def correlation(x, y, /):
    """Pearson's correlation coefficient

    Return the Pearson's correlation coefficient for two inputs. Pearson's
    correlation coefficient *r* takes values between -1 and +1. It measures the
    strength and direction of the linear relationship, where +1 means very
    strong, positive linear relationship, -1 very strong, negative linear
    relationship, and 0 no linear relationship.

    >>> x = [1, 2, 3, 4, 5, 6, 7, 8, 9]
    >>> y = [9, 8, 7, 6, 5, 4, 3, 2, 1]
    >>> correlation(x, x)
    1.0
    >>> correlation(x, y)
    -1.0

    """
    n = len(x)
    if len(y) != n:
        raise StatisticsError('correlation requires that both inputs have same number of data points')
    if n < 2:
        raise StatisticsError('correlation requires at least two data points')
    xbar = fsum(x) / n
    ybar = fsum(y) / n
    sxy = fsum((xi - xbar) * (yi - ybar) for xi, yi in zip(x, y))
    s2x = fsum((xi - xbar) ** 2.0 for xi in x)
    s2y = fsum((yi - ybar) ** 2.0 for yi in y)
    try:
        return sxy / sqrt(s2x * s2y)
    except ZeroDivisionError:
        raise StatisticsError('at least one of the inputs is constant')


LinearRegression = namedtuple('LinearRegression', ['intercept', 'slope'])


def linear_regression(regressor, dependent_variable, /):
    """Intercept and slope for simple linear regression

    Return the intercept and slope of simple linear regression
    parameters estimated using ordinary least squares. Simple linear
    regression describes relationship between *regressor* and
    *dependent variable* in terms of linear function:

        dependent_variable = intercept + slope * regressor + noise

    where *intercept* and *slope* are the regression parameters that are
    estimated, and noise represents the variability of the data that was
    not explained by the linear regression (it is equal to the
    difference between predicted and actual values of dependent
    variable).

    The parameters are returned as a named tuple.

    >>> regressor = [1, 2, 3, 4, 5]
    >>> noise = NormalDist().samples(5, seed=42)
    >>> dependent_variable = [2 + 3 * regressor[i] + noise[i] for i in range(5)]
    >>> linear_regression(regressor, dependent_variable)  #doctest: +ELLIPSIS
    LinearRegression(intercept=1.75684970486..., slope=3.09078914170...)

    """
    n = len(regressor)
    if len(dependent_variable) != n:
        raise StatisticsError('linear regression requires that both inputs have same number of data points')
    if n < 2:
        raise StatisticsError('linear regression requires at least two data points')
    x, y = regressor, dependent_variable
    xbar = fsum(x) / n
    ybar = fsum(y) / n
    sxy = fsum((xi - xbar) * (yi - ybar) for xi, yi in zip(x, y))
    s2x = fsum((xi - xbar) ** 2.0 for xi in x)
    try:
        slope = sxy / s2x   # equivalent to:  covariance(x, y) / variance(x)
    except ZeroDivisionError:
        raise StatisticsError('regressor is constant')
    intercept = ybar - slope * xbar
    return LinearRegression(intercept=intercept, slope=slope)


## Normal Distribution #####################################################


def _normal_dist_inv_cdf(p, mu, sigma):
    # There is no closed-form solution to the inverse CDF for the normal
    # distribution, so we use a rational approximation instead:
    # Wichura, M.J. (1988). "Algorithm AS241: The Percentage Points of the
    # Normal Distribution".  Applied Statistics. Blackwell Publishing. 37
    # (3): 477–484. doi:10.2307/2347330. JSTOR 2347330.
    q = p - 0.5
    if fabs(q) <= 0.425:
        r = 0.180625 - q * q
        # Hash sum: 55.88319_28806_14901_4439
        num = (((((((2.50908_09287_30122_6727e+3 * r +
                     3.34305_75583_58812_8105e+4) * r +
                     6.72657_70927_00870_0853e+4) * r +
                     4.59219_53931_54987_1457e+4) * r +
                     1.37316_93765_50946_1125e+4) * r +
                     1.97159_09503_06551_4427e+3) * r +
                     1.33141_66789_17843_7745e+2) * r +
                     3.38713_28727_96366_6080e+0) * q
        den = (((((((5.22649_52788_52854_5610e+3 * r +
                     2.87290_85735_72194_2674e+4) * r +
                     3.93078_95800_09271_0610e+4) * r +
                     2.12137_94301_58659_5867e+4) * r +
                     5.39419_60214_24751_1077e+3) * r +
                     6.87187_00749_20579_0830e+2) * r +
                     4.23133_30701_60091_1252e+1) * r +
                     1.0)
        x = num / den
        return mu + (x * sigma)
    r = p if q <= 0.0 else 1.0 - p
    r = sqrt(-log(r))
    if r <= 5.0:
        r = r - 1.6
        # Hash sum: 49.33206_50330_16102_89036
        num = (((((((7.74545_01427_83414_07640e-4 * r +
                     2.27238_44989_26918_45833e-2) * r +
                     2.41780_72517_74506_11770e-1) * r +
                     1.27045_82524_52368_38258e+0) * r +
                     3.64784_83247_63204_60504e+0) * r +
                     5.76949_72214_60691_40550e+0) * r +
                     4.63033_78461_56545_29590e+0) * r +
                     1.42343_71107_49683_57734e+0)
        den = (((((((1.05075_00716_44416_84324e-9 * r +
                     5.47593_80849_95344_94600e-4) * r +
                     1.51986_66563_61645_71966e-2) * r +
                     1.48103_97642_74800_74590e-1) * r +
                     6.89767_33498_51000_04550e-1) * r +
                     1.67638_48301_83803_84940e+0) * r +
                     2.05319_16266_37758_82187e+0) * r +
                     1.0)
    else:
        r = r - 5.0
        # Hash sum: 47.52583_31754_92896_71629
        num = (((((((2.01033_43992_92288_13265e-7 * r +
                     2.71155_55687_43487_57815e-5) * r +
                     1.24266_09473_88078_43860e-3) * r +
                     2.65321_89526_57612_30930e-2) * r +
                     2.96560_57182_85048_91230e-1) * r +
                     1.78482_65399_17291_33580e+0) * r +
                     5.46378_49111_64114_36990e+0) * r +
                     6.65790_46435_01103_77720e+0)
        den = (((((((2.04426_31033_89939_78564e-15 * r +
                     1.42151_17583_16445_88870e-7) * r +
                     1.84631_83175_10054_68180e-5) * r +
                     7.86869_13114_56132_59100e-4) * r +
                     1.48753_61290_85061_48525e-2) * r +
                     1.36929_88092_27358_05310e-1) * r +
                     5.99832_20655_58879_37690e-1) * r +
                     1.0)
    x = num / den
    if q < 0.0:
        x = -x
    return mu + (x * sigma)


# If available, use C implementation
try:
    from _statistics import _normal_dist_inv_cdf
except ImportError:
    pass


class NormalDist:
    "Normal distribution of a random variable"
    # https://en.wikipedia.org/wiki/Normal_distribution
    # https://en.wikipedia.org/wiki/Variance#Properties

    __slots__ = {
        '_mu': 'Arithmetic mean of a normal distribution',
        '_sigma': 'Standard deviation of a normal distribution',
    }

    def __init__(self, mu=0.0, sigma=1.0):
        "NormalDist where mu is the mean and sigma is the standard deviation."
        if sigma < 0.0:
            raise StatisticsError('sigma must be non-negative')
        self._mu = float(mu)
        self._sigma = float(sigma)

    @classmethod
    def from_samples(cls, data):
        "Make a normal distribution instance from sample data."
        if not isinstance(data, (list, tuple)):
            data = list(data)
        xbar = fmean(data)
        return cls(xbar, stdev(data, xbar))

    def samples(self, n, *, seed=None):
        "Generate *n* samples for a given mean and standard deviation."
        gauss = random.gauss if seed is None else random.Random(seed).gauss
        mu, sigma = self._mu, self._sigma
        return [gauss(mu, sigma) for i in range(n)]

    def pdf(self, x):
        "Probability density function.  P(x <= X < x+dx) / dx"
        variance = self._sigma ** 2.0
        if not variance:
            raise StatisticsError('pdf() not defined when sigma is zero')
        return exp((x - self._mu)**2.0 / (-2.0*variance)) / sqrt(tau*variance)

    def cdf(self, x):
        "Cumulative distribution function.  P(X <= x)"
        if not self._sigma:
            raise StatisticsError('cdf() not defined when sigma is zero')
        return 0.5 * (1.0 + erf((x - self._mu) / (self._sigma * sqrt(2.0))))

    def inv_cdf(self, p):
        """Inverse cumulative distribution function.  x : P(X <= x) = p

        Finds the value of the random variable such that the probability of
        the variable being less than or equal to that value equals the given
        probability.

        This function is also called the percent point function or quantile
        function.
        """
        if p <= 0.0 or p >= 1.0:
            raise StatisticsError('p must be in the range 0.0 < p < 1.0')
        if self._sigma <= 0.0:
            raise StatisticsError('cdf() not defined when sigma at or below zero')
        return _normal_dist_inv_cdf(p, self._mu, self._sigma)

    def quantiles(self, n=4):
        """Divide into *n* continuous intervals with equal probability.

        Returns a list of (n - 1) cut points separating the intervals.

        Set *n* to 4 for quartiles (the default).  Set *n* to 10 for deciles.
        Set *n* to 100 for percentiles which gives the 99 cuts points that
        separate the normal distribution in to 100 equal sized groups.
        """
        return [self.inv_cdf(i / n) for i in range(1, n)]

    def overlap(self, other):
        """Compute the overlapping coefficient (OVL) between two normal distributions.

        Measures the agreement between two normal probability distributions.
        Returns a value between 0.0 and 1.0 giving the overlapping area in
        the two underlying probability density functions.

            >>> N1 = NormalDist(2.4, 1.6)
            >>> N2 = NormalDist(3.2, 2.0)
            >>> N1.overlap(N2)
            0.8035050657330205
        """
        # See: "The overlapping coefficient as a measure of agreement between
        # probability distributions and point estimation of the overlap of two
        # normal densities" -- Henry F. Inman and Edwin L. Bradley Jr
        # http://dx.doi.org/10.1080/03610928908830127
        if not isinstance(other, NormalDist):
            raise TypeError('Expected another NormalDist instance')
        X, Y = self, other
        if (Y._sigma, Y._mu) < (X._sigma, X._mu):  # sort to assure commutativity
            X, Y = Y, X
        X_var, Y_var = X.variance, Y.variance
        if not X_var or not Y_var:
            raise StatisticsError('overlap() not defined when sigma is zero')
        dv = Y_var - X_var
        dm = fabs(Y._mu - X._mu)
        if not dv:
            return 1.0 - erf(dm / (2.0 * X._sigma * sqrt(2.0)))
        a = X._mu * Y_var - Y._mu * X_var
        b = X._sigma * Y._sigma * sqrt(dm**2.0 + dv * log(Y_var / X_var))
        x1 = (a + b) / dv
        x2 = (a - b) / dv
        return 1.0 - (fabs(Y.cdf(x1) - X.cdf(x1)) + fabs(Y.cdf(x2) - X.cdf(x2)))

    def zscore(self, x):
        """Compute the Standard Score.  (x - mean) / stdev

        Describes *x* in terms of the number of standard deviations
        above or below the mean of the normal distribution.
        """
        # https://www.statisticshowto.com/probability-and-statistics/z-score/
        if not self._sigma:
            raise StatisticsError('zscore() not defined when sigma is zero')
        return (x - self._mu) / self._sigma

    @property
    def mean(self):
        "Arithmetic mean of the normal distribution."
        return self._mu

    @property
    def median(self):
        "Return the median of the normal distribution"
        return self._mu

    @property
    def mode(self):
        """Return the mode of the normal distribution

        The mode is the value x where which the probability density
        function (pdf) takes its maximum value.
        """
        return self._mu

    @property
    def stdev(self):
        "Standard deviation of the normal distribution."
        return self._sigma

    @property
    def variance(self):
        "Square of the standard deviation."
        return self._sigma ** 2.0

    def __add__(x1, x2):
        """Add a constant or another NormalDist instance.

        If *other* is a constant, translate mu by the constant,
        leaving sigma unchanged.

        If *other* is a NormalDist, add both the means and the variances.
        Mathematically, this works only if the two distributions are
        independent or if they are jointly normally distributed.
        """
        if isinstance(x2, NormalDist):
            return NormalDist(x1._mu + x2._mu, hypot(x1._sigma, x2._sigma))
        return NormalDist(x1._mu + x2, x1._sigma)

    def __sub__(x1, x2):
        """Subtract a constant or another NormalDist instance.

        If *other* is a constant, translate by the constant mu,
        leaving sigma unchanged.

        If *other* is a NormalDist, subtract the means and add the variances.
        Mathematically, this works only if the two distributions are
        independent or if they are jointly normally distributed.
        """
        if isinstance(x2, NormalDist):
            return NormalDist(x1._mu - x2._mu, hypot(x1._sigma, x2._sigma))
        return NormalDist(x1._mu - x2, x1._sigma)

    def __mul__(x1, x2):
        """Multiply both mu and sigma by a constant.

        Used for rescaling, perhaps to change measurement units.
        Sigma is scaled with the absolute value of the constant.
        """
        return NormalDist(x1._mu * x2, x1._sigma * fabs(x2))

    def __truediv__(x1, x2):
        """Divide both mu and sigma by a constant.

        Used for rescaling, perhaps to change measurement units.
        Sigma is scaled with the absolute value of the constant.
        """
        return NormalDist(x1._mu / x2, x1._sigma / fabs(x2))

    def __pos__(x1):
        "Return a copy of the instance."
        return NormalDist(x1._mu, x1._sigma)

    def __neg__(x1):
        "Negates mu while keeping sigma the same."
        return NormalDist(-x1._mu, x1._sigma)

    __radd__ = __add__

    def __rsub__(x1, x2):
        "Subtract a NormalDist from a constant or another NormalDist."
        return -(x1 - x2)

    __rmul__ = __mul__

    def __eq__(x1, x2):
        "Two NormalDist objects are equal if their mu and sigma are both equal."
        if not isinstance(x2, NormalDist):
            return NotImplemented
        return x1._mu == x2._mu and x1._sigma == x2._sigma

    def __hash__(self):
        "NormalDist objects hash equal if their mu and sigma are both equal."
        return hash((self._mu, self._sigma))

    def __repr__(self):
        return f'{type(self).__name__}(mu={self._mu!r}, sigma={self._sigma!r})'