/usr/lib/python3/dist-packages/numpy/ma/extras.py is in python3-numpy 1:1.12.1-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 | """
Masked arrays add-ons.
A collection of utilities for `numpy.ma`.
:author: Pierre Gerard-Marchant
:contact: pierregm_at_uga_dot_edu
:version: $Id: extras.py 3473 2007-10-29 15:18:13Z jarrod.millman $
"""
from __future__ import division, absolute_import, print_function
__all__ = [
'apply_along_axis', 'apply_over_axes', 'atleast_1d', 'atleast_2d',
'atleast_3d', 'average', 'clump_masked', 'clump_unmasked',
'column_stack', 'compress_cols', 'compress_nd', 'compress_rowcols',
'compress_rows', 'count_masked', 'corrcoef', 'cov', 'diagflat', 'dot',
'dstack', 'ediff1d', 'flatnotmasked_contiguous', 'flatnotmasked_edges',
'hsplit', 'hstack', 'in1d', 'intersect1d', 'mask_cols', 'mask_rowcols',
'mask_rows', 'masked_all', 'masked_all_like', 'median', 'mr_',
'notmasked_contiguous', 'notmasked_edges', 'polyfit', 'row_stack',
'setdiff1d', 'setxor1d', 'unique', 'union1d', 'vander', 'vstack',
]
import itertools
import warnings
from . import core as ma
from .core import (
MaskedArray, MAError, add, array, asarray, concatenate, filled, count,
getmask, getmaskarray, make_mask_descr, masked, masked_array, mask_or,
nomask, ones, sort, zeros, getdata, get_masked_subclass, dot,
mask_rowcols
)
import numpy as np
from numpy import ndarray, array as nxarray
import numpy.core.umath as umath
from numpy.lib.function_base import _ureduce
from numpy.lib.index_tricks import AxisConcatenator
def issequence(seq):
"""
Is seq a sequence (ndarray, list or tuple)?
"""
return isinstance(seq, (ndarray, tuple, list))
def count_masked(arr, axis=None):
"""
Count the number of masked elements along the given axis.
Parameters
----------
arr : array_like
An array with (possibly) masked elements.
axis : int, optional
Axis along which to count. If None (default), a flattened
version of the array is used.
Returns
-------
count : int, ndarray
The total number of masked elements (axis=None) or the number
of masked elements along each slice of the given axis.
See Also
--------
MaskedArray.count : Count non-masked elements.
Examples
--------
>>> import numpy.ma as ma
>>> a = np.arange(9).reshape((3,3))
>>> a = ma.array(a)
>>> a[1, 0] = ma.masked
>>> a[1, 2] = ma.masked
>>> a[2, 1] = ma.masked
>>> a
masked_array(data =
[[0 1 2]
[-- 4 --]
[6 -- 8]],
mask =
[[False False False]
[ True False True]
[False True False]],
fill_value=999999)
>>> ma.count_masked(a)
3
When the `axis` keyword is used an array is returned.
>>> ma.count_masked(a, axis=0)
array([1, 1, 1])
>>> ma.count_masked(a, axis=1)
array([0, 2, 1])
"""
m = getmaskarray(arr)
return m.sum(axis)
def masked_all(shape, dtype=float):
"""
Empty masked array with all elements masked.
Return an empty masked array of the given shape and dtype, where all the
data are masked.
Parameters
----------
shape : tuple
Shape of the required MaskedArray.
dtype : dtype, optional
Data type of the output.
Returns
-------
a : MaskedArray
A masked array with all data masked.
See Also
--------
masked_all_like : Empty masked array modelled on an existing array.
Examples
--------
>>> import numpy.ma as ma
>>> ma.masked_all((3, 3))
masked_array(data =
[[-- -- --]
[-- -- --]
[-- -- --]],
mask =
[[ True True True]
[ True True True]
[ True True True]],
fill_value=1e+20)
The `dtype` parameter defines the underlying data type.
>>> a = ma.masked_all((3, 3))
>>> a.dtype
dtype('float64')
>>> a = ma.masked_all((3, 3), dtype=np.int32)
>>> a.dtype
dtype('int32')
"""
a = masked_array(np.empty(shape, dtype),
mask=np.ones(shape, make_mask_descr(dtype)))
return a
def masked_all_like(arr):
"""
Empty masked array with the properties of an existing array.
Return an empty masked array of the same shape and dtype as
the array `arr`, where all the data are masked.
Parameters
----------
arr : ndarray
An array describing the shape and dtype of the required MaskedArray.
Returns
-------
a : MaskedArray
A masked array with all data masked.
Raises
------
AttributeError
If `arr` doesn't have a shape attribute (i.e. not an ndarray)
See Also
--------
masked_all : Empty masked array with all elements masked.
Examples
--------
>>> import numpy.ma as ma
>>> arr = np.zeros((2, 3), dtype=np.float32)
>>> arr
array([[ 0., 0., 0.],
[ 0., 0., 0.]], dtype=float32)
>>> ma.masked_all_like(arr)
masked_array(data =
[[-- -- --]
[-- -- --]],
mask =
[[ True True True]
[ True True True]],
fill_value=1e+20)
The dtype of the masked array matches the dtype of `arr`.
>>> arr.dtype
dtype('float32')
>>> ma.masked_all_like(arr).dtype
dtype('float32')
"""
a = np.empty_like(arr).view(MaskedArray)
a._mask = np.ones(a.shape, dtype=make_mask_descr(a.dtype))
return a
#####--------------------------------------------------------------------------
#---- --- Standard functions ---
#####--------------------------------------------------------------------------
class _fromnxfunction:
"""
Defines a wrapper to adapt NumPy functions to masked arrays.
An instance of `_fromnxfunction` can be called with the same parameters
as the wrapped NumPy function. The docstring of `newfunc` is adapted from
the wrapped function as well, see `getdoc`.
This class should not be used directly. Instead, one of its extensions that
provides support for a specific type of input should be used.
Parameters
----------
funcname : str
The name of the function to be adapted. The function should be
in the NumPy namespace (i.e. ``np.funcname``).
"""
def __init__(self, funcname):
self.__name__ = funcname
self.__doc__ = self.getdoc()
def getdoc(self):
"""
Retrieve the docstring and signature from the function.
The ``__doc__`` attribute of the function is used as the docstring for
the new masked array version of the function. A note on application
of the function to the mask is appended.
.. warning::
If the function docstring already contained a Notes section, the
new docstring will have two Notes sections instead of appending a note
to the existing section.
Parameters
----------
None
"""
npfunc = getattr(np, self.__name__, None)
doc = getattr(npfunc, '__doc__', None)
if doc:
sig = self.__name__ + ma.get_object_signature(npfunc)
locdoc = "Notes\n-----\nThe function is applied to both the _data"\
" and the _mask, if any."
return '\n'.join((sig, doc, locdoc))
return
def __call__(self, *args, **params):
pass
class _fromnxfunction_single(_fromnxfunction):
"""
A version of `_fromnxfunction` that is called with a single array
argument followed by auxiliary args that are passed verbatim for
both the data and mask calls.
"""
def __call__(self, x, *args, **params):
func = getattr(np, self.__name__)
if isinstance(x, ndarray):
_d = func(x.__array__(), *args, **params)
_m = func(getmaskarray(x), *args, **params)
return masked_array(_d, mask=_m)
else:
_d = func(np.asarray(x), *args, **params)
_m = func(getmaskarray(x), *args, **params)
return masked_array(_d, mask=_m)
class _fromnxfunction_seq(_fromnxfunction):
"""
A version of `_fromnxfunction` that is called with a single sequence
of arrays followed by auxiliary args that are passed verbatim for
both the data and mask calls.
"""
def __call__(self, x, *args, **params):
func = getattr(np, self.__name__)
_d = func(tuple([np.asarray(a) for a in x]), *args, **params)
_m = func(tuple([getmaskarray(a) for a in x]), *args, **params)
return masked_array(_d, mask=_m)
class _fromnxfunction_args(_fromnxfunction):
"""
A version of `_fromnxfunction` that is called with multiple array
arguments. The first non-array-like input marks the beginning of the
arguments that are passed verbatim for both the data and mask calls.
Array arguments are processed independently and the results are
returned in a list. If only one array is found, the return value is
just the processed array instead of a list.
"""
def __call__(self, *args, **params):
func = getattr(np, self.__name__)
arrays = []
args = list(args)
while len(args) > 0 and issequence(args[0]):
arrays.append(args.pop(0))
res = []
for x in arrays:
_d = func(np.asarray(x), *args, **params)
_m = func(getmaskarray(x), *args, **params)
res.append(masked_array(_d, mask=_m))
if len(arrays) == 1:
return res[0]
return res
class _fromnxfunction_allargs(_fromnxfunction):
"""
A version of `_fromnxfunction` that is called with multiple array
arguments. Similar to `_fromnxfunction_args` except that all args
are converted to arrays even if they are not so already. This makes
it possible to process scalars as 1-D arrays. Only keyword arguments
are passed through verbatim for the data and mask calls. Arrays
arguments are processed independently and the results are returned
in a list. If only one arg is present, the return value is just the
processed array instead of a list.
"""
def __call__(self, *args, **params):
func = getattr(np, self.__name__)
res = []
for x in args:
_d = func(np.asarray(x), **params)
_m = func(getmaskarray(x), **params)
res.append(masked_array(_d, mask=_m))
if len(args) == 1:
return res[0]
return res
atleast_1d = _fromnxfunction_allargs('atleast_1d')
atleast_2d = _fromnxfunction_allargs('atleast_2d')
atleast_3d = _fromnxfunction_allargs('atleast_3d')
vstack = row_stack = _fromnxfunction_seq('vstack')
hstack = _fromnxfunction_seq('hstack')
column_stack = _fromnxfunction_seq('column_stack')
dstack = _fromnxfunction_seq('dstack')
hsplit = _fromnxfunction_single('hsplit')
diagflat = _fromnxfunction_single('diagflat')
#####--------------------------------------------------------------------------
#----
#####--------------------------------------------------------------------------
def flatten_inplace(seq):
"""Flatten a sequence in place."""
k = 0
while (k != len(seq)):
while hasattr(seq[k], '__iter__'):
seq[k:(k + 1)] = seq[k]
k += 1
return seq
def apply_along_axis(func1d, axis, arr, *args, **kwargs):
"""
(This docstring should be overwritten)
"""
arr = array(arr, copy=False, subok=True)
nd = arr.ndim
if axis < 0:
axis += nd
if (axis >= nd):
raise ValueError("axis must be less than arr.ndim; axis=%d, rank=%d."
% (axis, nd))
ind = [0] * (nd - 1)
i = np.zeros(nd, 'O')
indlist = list(range(nd))
indlist.remove(axis)
i[axis] = slice(None, None)
outshape = np.asarray(arr.shape).take(indlist)
i.put(indlist, ind)
j = i.copy()
res = func1d(arr[tuple(i.tolist())], *args, **kwargs)
# if res is a number, then we have a smaller output array
asscalar = np.isscalar(res)
if not asscalar:
try:
len(res)
except TypeError:
asscalar = True
# Note: we shouldn't set the dtype of the output from the first result
# so we force the type to object, and build a list of dtypes. We'll
# just take the largest, to avoid some downcasting
dtypes = []
if asscalar:
dtypes.append(np.asarray(res).dtype)
outarr = zeros(outshape, object)
outarr[tuple(ind)] = res
Ntot = np.product(outshape)
k = 1
while k < Ntot:
# increment the index
ind[-1] += 1
n = -1
while (ind[n] >= outshape[n]) and (n > (1 - nd)):
ind[n - 1] += 1
ind[n] = 0
n -= 1
i.put(indlist, ind)
res = func1d(arr[tuple(i.tolist())], *args, **kwargs)
outarr[tuple(ind)] = res
dtypes.append(asarray(res).dtype)
k += 1
else:
res = array(res, copy=False, subok=True)
j = i.copy()
j[axis] = ([slice(None, None)] * res.ndim)
j.put(indlist, ind)
Ntot = np.product(outshape)
holdshape = outshape
outshape = list(arr.shape)
outshape[axis] = res.shape
dtypes.append(asarray(res).dtype)
outshape = flatten_inplace(outshape)
outarr = zeros(outshape, object)
outarr[tuple(flatten_inplace(j.tolist()))] = res
k = 1
while k < Ntot:
# increment the index
ind[-1] += 1
n = -1
while (ind[n] >= holdshape[n]) and (n > (1 - nd)):
ind[n - 1] += 1
ind[n] = 0
n -= 1
i.put(indlist, ind)
j.put(indlist, ind)
res = func1d(arr[tuple(i.tolist())], *args, **kwargs)
outarr[tuple(flatten_inplace(j.tolist()))] = res
dtypes.append(asarray(res).dtype)
k += 1
max_dtypes = np.dtype(np.asarray(dtypes).max())
if not hasattr(arr, '_mask'):
result = np.asarray(outarr, dtype=max_dtypes)
else:
result = asarray(outarr, dtype=max_dtypes)
result.fill_value = ma.default_fill_value(result)
return result
apply_along_axis.__doc__ = np.apply_along_axis.__doc__
def apply_over_axes(func, a, axes):
"""
(This docstring will be overwritten)
"""
val = asarray(a)
N = a.ndim
if array(axes).ndim == 0:
axes = (axes,)
for axis in axes:
if axis < 0:
axis = N + axis
args = (val, axis)
res = func(*args)
if res.ndim == val.ndim:
val = res
else:
res = ma.expand_dims(res, axis)
if res.ndim == val.ndim:
val = res
else:
raise ValueError("function is not returning "
"an array of the correct shape")
return val
if apply_over_axes.__doc__ is not None:
apply_over_axes.__doc__ = np.apply_over_axes.__doc__[
:np.apply_over_axes.__doc__.find('Notes')].rstrip() + \
"""
Examples
--------
>>> a = ma.arange(24).reshape(2,3,4)
>>> a[:,0,1] = ma.masked
>>> a[:,1,:] = ma.masked
>>> print(a)
[[[0 -- 2 3]
[-- -- -- --]
[8 9 10 11]]
[[12 -- 14 15]
[-- -- -- --]
[20 21 22 23]]]
>>> print(ma.apply_over_axes(ma.sum, a, [0,2]))
[[[46]
[--]
[124]]]
Tuple axis arguments to ufuncs are equivalent:
>>> print(ma.sum(a, axis=(0,2)).reshape((1,-1,1)))
[[[46]
[--]
[124]]]
"""
def average(a, axis=None, weights=None, returned=False):
"""
Return the weighted average of array over the given axis.
Parameters
----------
a : array_like
Data to be averaged.
Masked entries are not taken into account in the computation.
axis : int, optional
Axis along which to average `a`. If `None`, averaging is done over
the flattened array.
weights : array_like, optional
The importance that each element has in the computation of the average.
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. If `weights` is complex, the imaginary parts
are ignored.
returned : bool, optional
Flag indicating whether a tuple ``(result, sum of weights)``
should be returned as output (True), or just the result (False).
Default is False.
Returns
-------
average, [sum_of_weights] : (tuple of) scalar or MaskedArray
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 `np.float64`
if `a` is of integer type and floats smaller than `float64`, or the
input data-type, otherwise. If returned, `sum_of_weights` is always
`float64`.
Examples
--------
>>> a = np.ma.array([1., 2., 3., 4.], mask=[False, False, True, True])
>>> np.ma.average(a, weights=[3, 1, 0, 0])
1.25
>>> x = np.ma.arange(6.).reshape(3, 2)
>>> print(x)
[[ 0. 1.]
[ 2. 3.]
[ 4. 5.]]
>>> avg, sumweights = np.ma.average(x, axis=0, weights=[1, 2, 3],
... returned=True)
>>> print(avg)
[2.66666666667 3.66666666667]
"""
a = asarray(a)
m = getmask(a)
# inspired by 'average' in numpy/lib/function_base.py
if weights is None:
avg = a.mean(axis)
scl = avg.dtype.type(a.count(axis))
else:
wgt = np.asanyarray(weights)
if issubclass(a.dtype.type, (np.integer, np.bool_)):
result_dtype = np.result_type(a.dtype, wgt.dtype, 'f8')
else:
result_dtype = np.result_type(a.dtype, wgt.dtype)
# 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.broadcast_to(wgt, (a.ndim-1)*(1,) + wgt.shape)
wgt = wgt.swapaxes(-1, axis)
if m is not nomask:
wgt = wgt*(~a.mask)
scl = wgt.sum(axis=axis, dtype=result_dtype)
avg = np.multiply(a, wgt, dtype=result_dtype).sum(axis)/scl
if returned:
if scl.shape != avg.shape:
scl = np.broadcast_to(scl, avg.shape).copy()
return avg, scl
else:
return avg
def median(a, axis=None, out=None, overwrite_input=False, keepdims=False):
"""
Compute the median along the specified axis.
Returns the median of the array elements.
Parameters
----------
a : array_like
Input array or object that can be converted to an array.
axis : int, optional
Axis along which the medians are computed. The default (None) is
to compute the median along a flattened version of the array.
out : ndarray, optional
Alternative output array in which to place the result. It must
have the same shape and buffer length as the expected output
but the type will be cast if necessary.
overwrite_input : bool, optional
If True, then allow use of memory of input array (a) for
calculations. The input array will be modified by the call to
median. This will save memory when you do not need to preserve
the contents of the input array. Treat the input as undefined,
but it will probably be fully or partially sorted. Default is
False. Note that, if `overwrite_input` is True, and the input
is not already an `ndarray`, an error will be raised.
keepdims : bool, optional
If this is set to True, the axes which are reduced are left
in the result as dimensions with size one. With this option,
the result will broadcast correctly against the input array.
.. versionadded:: 1.10.0
Returns
-------
median : ndarray
A new array holding the result is returned unless out is
specified, in which case a reference to out is returned.
Return data-type is `float64` for integers and floats smaller than
`float64`, or the input data-type, otherwise.
See Also
--------
mean
Notes
-----
Given a vector ``V`` with ``N`` non masked values, the median of ``V``
is the middle value of a sorted copy of ``V`` (``Vs``) - i.e.
``Vs[(N-1)/2]``, when ``N`` is odd, or ``{Vs[N/2 - 1] + Vs[N/2]}/2``
when ``N`` is even.
Examples
--------
>>> x = np.ma.array(np.arange(8), mask=[0]*4 + [1]*4)
>>> np.ma.median(x)
1.5
>>> x = np.ma.array(np.arange(10).reshape(2, 5), mask=[0]*6 + [1]*4)
>>> np.ma.median(x)
2.5
>>> np.ma.median(x, axis=-1, overwrite_input=True)
masked_array(data = [ 2. 5.],
mask = False,
fill_value = 1e+20)
"""
if not hasattr(a, 'mask'):
m = np.median(getdata(a, subok=True), axis=axis,
out=out, overwrite_input=overwrite_input,
keepdims=keepdims)
if isinstance(m, np.ndarray) and 1 <= m.ndim:
return masked_array(m, copy=False)
else:
return m
r, k = _ureduce(a, func=_median, axis=axis, out=out,
overwrite_input=overwrite_input)
if keepdims:
return r.reshape(k)
else:
return r
def _median(a, axis=None, out=None, overwrite_input=False):
# when an unmasked NaN is present return it, so we need to sort the NaN
# values behind the mask
if np.issubdtype(a.dtype, np.inexact):
fill_value = np.inf
else:
fill_value = None
if overwrite_input:
if axis is None:
asorted = a.ravel()
asorted.sort(fill_value=fill_value)
else:
a.sort(axis=axis, fill_value=fill_value)
asorted = a
else:
asorted = sort(a, axis=axis, fill_value=fill_value)
if axis is None:
axis = 0
elif axis < 0:
axis += asorted.ndim
if asorted.shape[axis] == 0:
# for empty axis integer indices fail so use slicing to get same result
# as median (which is mean of empty slice = nan)
indexer = [slice(None)] * asorted.ndim
indexer[axis] = slice(0, 0)
return np.ma.mean(asorted[indexer], axis=axis, out=out)
if asorted.ndim == 1:
counts = count(asorted)
idx, odd = divmod(count(asorted), 2)
mid = asorted[idx + odd - 1:idx + 1]
if np.issubdtype(asorted.dtype, np.inexact) and asorted.size > 0:
# avoid inf / x = masked
s = mid.sum(out=out)
if not odd:
s = np.true_divide(s, 2., casting='safe', out=out)
# masked ufuncs do not fullfill `returned is out` (gh-8416)
# fix this to return the same in the nd path
if out is not None:
s = out
s = np.lib.utils._median_nancheck(asorted, s, axis, out)
else:
s = mid.mean(out=out)
# if result is masked either the input contained enough
# minimum_fill_value so that it would be the median or all values
# masked
if np.ma.is_masked(s) and not np.all(asorted.mask):
return np.ma.minimum_fill_value(asorted)
return s
counts = count(asorted, axis=axis)
h = counts // 2
# create indexing mesh grid for all but reduced axis
axes_grid = [np.arange(x) for i, x in enumerate(asorted.shape)
if i != axis]
ind = np.meshgrid(*axes_grid, sparse=True, indexing='ij')
# insert indices of low and high median
ind.insert(axis, h - 1)
low = asorted[tuple(ind)]
ind[axis] = np.minimum(h, asorted.shape[axis] - 1)
high = asorted[tuple(ind)]
def replace_masked(s):
# Replace masked entries with minimum_full_value unless it all values
# are masked. This is required as the sort order of values equal or
# larger than the fill value is undefined and a valid value placed
# elsewhere, e.g. [4, --, inf].
if np.ma.is_masked(s):
rep = (~np.all(asorted.mask, axis=axis)) & s.mask
s.data[rep] = np.ma.minimum_fill_value(asorted)
s.mask[rep] = False
replace_masked(low)
replace_masked(high)
# duplicate high if odd number of elements so mean does nothing
odd = counts % 2 == 1
np.copyto(low, high, where=odd)
# not necessary for scalar True/False masks
try:
np.copyto(low.mask, high.mask, where=odd)
except:
pass
if np.issubdtype(asorted.dtype, np.inexact):
# avoid inf / x = masked
s = np.ma.sum([low, high], axis=0, out=out)
np.true_divide(s.data, 2., casting='unsafe', out=s.data)
s = np.lib.utils._median_nancheck(asorted, s, axis, out)
else:
s = np.ma.mean([low, high], axis=0, out=out)
return s
def compress_nd(x, axis=None):
"""Supress slices from multiple dimensions which contain masked values.
Parameters
----------
x : array_like, MaskedArray
The array to operate on. If not a MaskedArray instance (or if no array
elements are masked, `x` is interpreted as a MaskedArray with `mask`
set to `nomask`.
axis : tuple of ints or int, optional
Which dimensions to supress slices from can be configured with this
parameter.
- If axis is a tuple of ints, those are the axes to supress slices from.
- If axis is an int, then that is the only axis to supress slices from.
- If axis is None, all axis are selected.
Returns
-------
compress_array : ndarray
The compressed array.
"""
x = asarray(x)
m = getmask(x)
# Set axis to tuple of ints
if isinstance(axis, int):
axis = (axis,)
elif axis is None:
axis = tuple(range(x.ndim))
elif not isinstance(axis, tuple):
raise ValueError('Invalid type for axis argument')
# Check axis input
axis = [ax + x.ndim if ax < 0 else ax for ax in axis]
if not all(0 <= ax < x.ndim for ax in axis):
raise ValueError("'axis' entry is out of bounds")
if len(axis) != len(set(axis)):
raise ValueError("duplicate value in 'axis'")
# Nothing is masked: return x
if m is nomask or not m.any():
return x._data
# All is masked: return empty
if m.all():
return nxarray([])
# Filter elements through boolean indexing
data = x._data
for ax in axis:
axes = tuple(list(range(ax)) + list(range(ax + 1, x.ndim)))
data = data[(slice(None),)*ax + (~m.any(axis=axes),)]
return data
def compress_rowcols(x, axis=None):
"""
Suppress the rows and/or columns of a 2-D array that contain
masked values.
The suppression behavior is selected with the `axis` parameter.
- If axis is None, both rows and columns are suppressed.
- If axis is 0, only rows are suppressed.
- If axis is 1 or -1, only columns are suppressed.
Parameters
----------
x : array_like, MaskedArray
The array to operate on. If not a MaskedArray instance (or if no array
elements are masked), `x` is interpreted as a MaskedArray with
`mask` set to `nomask`. Must be a 2D array.
axis : int, optional
Axis along which to perform the operation. Default is None.
Returns
-------
compressed_array : ndarray
The compressed array.
Examples
--------
>>> x = np.ma.array(np.arange(9).reshape(3, 3), mask=[[1, 0, 0],
... [1, 0, 0],
... [0, 0, 0]])
>>> x
masked_array(data =
[[-- 1 2]
[-- 4 5]
[6 7 8]],
mask =
[[ True False False]
[ True False False]
[False False False]],
fill_value = 999999)
>>> np.ma.compress_rowcols(x)
array([[7, 8]])
>>> np.ma.compress_rowcols(x, 0)
array([[6, 7, 8]])
>>> np.ma.compress_rowcols(x, 1)
array([[1, 2],
[4, 5],
[7, 8]])
"""
if asarray(x).ndim != 2:
raise NotImplementedError("compress_rowcols works for 2D arrays only.")
return compress_nd(x, axis=axis)
def compress_rows(a):
"""
Suppress whole rows of a 2-D array that contain masked values.
This is equivalent to ``np.ma.compress_rowcols(a, 0)``, see
`extras.compress_rowcols` for details.
See Also
--------
extras.compress_rowcols
"""
a = asarray(a)
if a.ndim != 2:
raise NotImplementedError("compress_rows works for 2D arrays only.")
return compress_rowcols(a, 0)
def compress_cols(a):
"""
Suppress whole columns of a 2-D array that contain masked values.
This is equivalent to ``np.ma.compress_rowcols(a, 1)``, see
`extras.compress_rowcols` for details.
See Also
--------
extras.compress_rowcols
"""
a = asarray(a)
if a.ndim != 2:
raise NotImplementedError("compress_cols works for 2D arrays only.")
return compress_rowcols(a, 1)
def mask_rows(a, axis=None):
"""
Mask rows of a 2D array that contain masked values.
This function is a shortcut to ``mask_rowcols`` with `axis` equal to 0.
See Also
--------
mask_rowcols : Mask rows and/or columns of a 2D array.
masked_where : Mask where a condition is met.
Examples
--------
>>> import numpy.ma as ma
>>> a = np.zeros((3, 3), dtype=np.int)
>>> a[1, 1] = 1
>>> a
array([[0, 0, 0],
[0, 1, 0],
[0, 0, 0]])
>>> a = ma.masked_equal(a, 1)
>>> a
masked_array(data =
[[0 0 0]
[0 -- 0]
[0 0 0]],
mask =
[[False False False]
[False True False]
[False False False]],
fill_value=999999)
>>> ma.mask_rows(a)
masked_array(data =
[[0 0 0]
[-- -- --]
[0 0 0]],
mask =
[[False False False]
[ True True True]
[False False False]],
fill_value=999999)
"""
return mask_rowcols(a, 0)
def mask_cols(a, axis=None):
"""
Mask columns of a 2D array that contain masked values.
This function is a shortcut to ``mask_rowcols`` with `axis` equal to 1.
See Also
--------
mask_rowcols : Mask rows and/or columns of a 2D array.
masked_where : Mask where a condition is met.
Examples
--------
>>> import numpy.ma as ma
>>> a = np.zeros((3, 3), dtype=np.int)
>>> a[1, 1] = 1
>>> a
array([[0, 0, 0],
[0, 1, 0],
[0, 0, 0]])
>>> a = ma.masked_equal(a, 1)
>>> a
masked_array(data =
[[0 0 0]
[0 -- 0]
[0 0 0]],
mask =
[[False False False]
[False True False]
[False False False]],
fill_value=999999)
>>> ma.mask_cols(a)
masked_array(data =
[[0 -- 0]
[0 -- 0]
[0 -- 0]],
mask =
[[False True False]
[False True False]
[False True False]],
fill_value=999999)
"""
return mask_rowcols(a, 1)
#####--------------------------------------------------------------------------
#---- --- arraysetops ---
#####--------------------------------------------------------------------------
def ediff1d(arr, to_end=None, to_begin=None):
"""
Compute the differences between consecutive elements of an array.
This function is the equivalent of `numpy.ediff1d` that takes masked
values into account, see `numpy.ediff1d` for details.
See Also
--------
numpy.ediff1d : Equivalent function for ndarrays.
"""
arr = ma.asanyarray(arr).flat
ed = arr[1:] - arr[:-1]
arrays = [ed]
#
if to_begin is not None:
arrays.insert(0, to_begin)
if to_end is not None:
arrays.append(to_end)
#
if len(arrays) != 1:
# We'll save ourselves a copy of a potentially large array in the common
# case where neither to_begin or to_end was given.
ed = hstack(arrays)
#
return ed
def unique(ar1, return_index=False, return_inverse=False):
"""
Finds the unique elements of an array.
Masked values are considered the same element (masked). The output array
is always a masked array. See `numpy.unique` for more details.
See Also
--------
numpy.unique : Equivalent function for ndarrays.
"""
output = np.unique(ar1,
return_index=return_index,
return_inverse=return_inverse)
if isinstance(output, tuple):
output = list(output)
output[0] = output[0].view(MaskedArray)
output = tuple(output)
else:
output = output.view(MaskedArray)
return output
def intersect1d(ar1, ar2, assume_unique=False):
"""
Returns the unique elements common to both arrays.
Masked values are considered equal one to the other.
The output is always a masked array.
See `numpy.intersect1d` for more details.
See Also
--------
numpy.intersect1d : Equivalent function for ndarrays.
Examples
--------
>>> x = array([1, 3, 3, 3], mask=[0, 0, 0, 1])
>>> y = array([3, 1, 1, 1], mask=[0, 0, 0, 1])
>>> intersect1d(x, y)
masked_array(data = [1 3 --],
mask = [False False True],
fill_value = 999999)
"""
if assume_unique:
aux = ma.concatenate((ar1, ar2))
else:
# Might be faster than unique( intersect1d( ar1, ar2 ) )?
aux = ma.concatenate((unique(ar1), unique(ar2)))
aux.sort()
return aux[:-1][aux[1:] == aux[:-1]]
def setxor1d(ar1, ar2, assume_unique=False):
"""
Set exclusive-or of 1-D arrays with unique elements.
The output is always a masked array. See `numpy.setxor1d` for more details.
See Also
--------
numpy.setxor1d : Equivalent function for ndarrays.
"""
if not assume_unique:
ar1 = unique(ar1)
ar2 = unique(ar2)
aux = ma.concatenate((ar1, ar2))
if aux.size == 0:
return aux
aux.sort()
auxf = aux.filled()
# flag = ediff1d( aux, to_end = 1, to_begin = 1 ) == 0
flag = ma.concatenate(([True], (auxf[1:] != auxf[:-1]), [True]))
# flag2 = ediff1d( flag ) == 0
flag2 = (flag[1:] == flag[:-1])
return aux[flag2]
def in1d(ar1, ar2, assume_unique=False, invert=False):
"""
Test whether each element of an array is also present in a second
array.
The output is always a masked array. See `numpy.in1d` for more details.
See Also
--------
numpy.in1d : Equivalent function for ndarrays.
Notes
-----
.. versionadded:: 1.4.0
"""
if not assume_unique:
ar1, rev_idx = unique(ar1, return_inverse=True)
ar2 = unique(ar2)
ar = ma.concatenate((ar1, ar2))
# We need this to be a stable sort, so always use 'mergesort'
# here. The values from the first array should always come before
# the values from the second array.
order = ar.argsort(kind='mergesort')
sar = ar[order]
if invert:
bool_ar = (sar[1:] != sar[:-1])
else:
bool_ar = (sar[1:] == sar[:-1])
flag = ma.concatenate((bool_ar, [invert]))
indx = order.argsort(kind='mergesort')[:len(ar1)]
if assume_unique:
return flag[indx]
else:
return flag[indx][rev_idx]
def union1d(ar1, ar2):
"""
Union of two arrays.
The output is always a masked array. See `numpy.union1d` for more details.
See also
--------
numpy.union1d : Equivalent function for ndarrays.
"""
return unique(ma.concatenate((ar1, ar2)))
def setdiff1d(ar1, ar2, assume_unique=False):
"""
Set difference of 1D arrays with unique elements.
The output is always a masked array. See `numpy.setdiff1d` for more
details.
See Also
--------
numpy.setdiff1d : Equivalent function for ndarrays.
Examples
--------
>>> x = np.ma.array([1, 2, 3, 4], mask=[0, 1, 0, 1])
>>> np.ma.setdiff1d(x, [1, 2])
masked_array(data = [3 --],
mask = [False True],
fill_value = 999999)
"""
if assume_unique:
ar1 = ma.asarray(ar1).ravel()
else:
ar1 = unique(ar1)
ar2 = unique(ar2)
return ar1[in1d(ar1, ar2, assume_unique=True, invert=True)]
###############################################################################
# Covariance #
###############################################################################
def _covhelper(x, y=None, rowvar=True, allow_masked=True):
"""
Private function for the computation of covariance and correlation
coefficients.
"""
x = ma.array(x, ndmin=2, copy=True, dtype=float)
xmask = ma.getmaskarray(x)
# Quick exit if we can't process masked data
if not allow_masked and xmask.any():
raise ValueError("Cannot process masked data.")
#
if x.shape[0] == 1:
rowvar = True
# Make sure that rowvar is either 0 or 1
rowvar = int(bool(rowvar))
axis = 1 - rowvar
if rowvar:
tup = (slice(None), None)
else:
tup = (None, slice(None))
#
if y is None:
xnotmask = np.logical_not(xmask).astype(int)
else:
y = array(y, copy=False, ndmin=2, dtype=float)
ymask = ma.getmaskarray(y)
if not allow_masked and ymask.any():
raise ValueError("Cannot process masked data.")
if xmask.any() or ymask.any():
if y.shape == x.shape:
# Define some common mask
common_mask = np.logical_or(xmask, ymask)
if common_mask is not nomask:
xmask = x._mask = y._mask = ymask = common_mask
x._sharedmask = False
y._sharedmask = False
x = ma.concatenate((x, y), axis)
xnotmask = np.logical_not(np.concatenate((xmask, ymask), axis)).astype(int)
x -= x.mean(axis=rowvar)[tup]
return (x, xnotmask, rowvar)
def cov(x, y=None, rowvar=True, bias=False, allow_masked=True, ddof=None):
"""
Estimate the covariance matrix.
Except for the handling of missing data this function does the same as
`numpy.cov`. For more details and examples, see `numpy.cov`.
By default, masked values are recognized as such. If `x` and `y` have the
same shape, a common mask is allocated: if ``x[i,j]`` is masked, then
``y[i,j]`` will also be masked.
Setting `allow_masked` to False will raise an exception if values are
missing in either of the input arrays.
Parameters
----------
x : array_like
A 1-D or 2-D array containing multiple variables and observations.
Each row of `x` represents a variable, and each column a single
observation of all those variables. Also see `rowvar` below.
y : array_like, optional
An additional set of variables and observations. `y` has the same
form as `x`.
rowvar : bool, optional
If `rowvar` is True (default), then each row represents a
variable, with observations in the columns. Otherwise, the relationship
is transposed: each column represents a variable, while the rows
contain observations.
bias : bool, optional
Default normalization (False) is by ``(N-1)``, where ``N`` is the
number of observations given (unbiased estimate). If `bias` is True,
then normalization is by ``N``. This keyword can be overridden by
the keyword ``ddof`` in numpy versions >= 1.5.
allow_masked : bool, optional
If True, masked values are propagated pair-wise: if a value is masked
in `x`, the corresponding value is masked in `y`.
If False, raises a `ValueError` exception when some values are missing.
ddof : {None, int}, optional
If not ``None`` normalization is by ``(N - ddof)``, where ``N`` is
the number of observations; this overrides the value implied by
``bias``. The default value is ``None``.
.. versionadded:: 1.5
Raises
------
ValueError
Raised if some values are missing and `allow_masked` is False.
See Also
--------
numpy.cov
"""
# Check inputs
if ddof is not None and ddof != int(ddof):
raise ValueError("ddof must be an integer")
# Set up ddof
if ddof is None:
if bias:
ddof = 0
else:
ddof = 1
(x, xnotmask, rowvar) = _covhelper(x, y, rowvar, allow_masked)
if not rowvar:
fact = np.dot(xnotmask.T, xnotmask) * 1. - ddof
result = (dot(x.T, x.conj(), strict=False) / fact).squeeze()
else:
fact = np.dot(xnotmask, xnotmask.T) * 1. - ddof
result = (dot(x, x.T.conj(), strict=False) / fact).squeeze()
return result
def corrcoef(x, y=None, rowvar=True, bias=np._NoValue, allow_masked=True,
ddof=np._NoValue):
"""
Return Pearson product-moment correlation coefficients.
Except for the handling of missing data this function does the same as
`numpy.corrcoef`. For more details and examples, see `numpy.corrcoef`.
Parameters
----------
x : array_like
A 1-D or 2-D array containing multiple variables and observations.
Each row of `x` represents a variable, and each column a single
observation of all those variables. Also see `rowvar` below.
y : array_like, optional
An additional set of variables and observations. `y` has the same
shape as `x`.
rowvar : bool, optional
If `rowvar` is True (default), then each row represents a
variable, with observations in the columns. Otherwise, the relationship
is transposed: each column represents a variable, while the rows
contain observations.
bias : _NoValue, optional
Has no effect, do not use.
.. deprecated:: 1.10.0
allow_masked : bool, optional
If True, masked values are propagated pair-wise: if a value is masked
in `x`, the corresponding value is masked in `y`.
If False, raises an exception. Because `bias` is deprecated, this
argument needs to be treated as keyword only to avoid a warning.
ddof : _NoValue, optional
Has no effect, do not use.
.. deprecated:: 1.10.0
See Also
--------
numpy.corrcoef : Equivalent function in top-level NumPy module.
cov : Estimate the covariance matrix.
Notes
-----
This function accepts but discards arguments `bias` and `ddof`. This is
for backwards compatibility with previous versions of this function. These
arguments had no effect on the return values of the function and can be
safely ignored in this and previous versions of numpy.
"""
msg = 'bias and ddof have no effect and are deprecated'
if bias is not np._NoValue or ddof is not np._NoValue:
# 2015-03-15, 1.10
warnings.warn(msg, DeprecationWarning, stacklevel=2)
# Get the data
(x, xnotmask, rowvar) = _covhelper(x, y, rowvar, allow_masked)
# Compute the covariance matrix
if not rowvar:
fact = np.dot(xnotmask.T, xnotmask) * 1.
c = (dot(x.T, x.conj(), strict=False) / fact).squeeze()
else:
fact = np.dot(xnotmask, xnotmask.T) * 1.
c = (dot(x, x.T.conj(), strict=False) / fact).squeeze()
# Check whether we have a scalar
try:
diag = ma.diagonal(c)
except ValueError:
return 1
#
if xnotmask.all():
_denom = ma.sqrt(ma.multiply.outer(diag, diag))
else:
_denom = diagflat(diag)
_denom._sharedmask = False # We know return is always a copy
n = x.shape[1 - rowvar]
if rowvar:
for i in range(n - 1):
for j in range(i + 1, n):
_x = mask_cols(vstack((x[i], x[j]))).var(axis=1)
_denom[i, j] = _denom[j, i] = ma.sqrt(ma.multiply.reduce(_x))
else:
for i in range(n - 1):
for j in range(i + 1, n):
_x = mask_cols(
vstack((x[:, i], x[:, j]))).var(axis=1)
_denom[i, j] = _denom[j, i] = ma.sqrt(ma.multiply.reduce(_x))
return c / _denom
#####--------------------------------------------------------------------------
#---- --- Concatenation helpers ---
#####--------------------------------------------------------------------------
class MAxisConcatenator(AxisConcatenator):
"""
Translate slice objects to concatenation along an axis.
For documentation on usage, see `mr_class`.
See Also
--------
mr_class
"""
def __init__(self, axis=0):
AxisConcatenator.__init__(self, axis, matrix=False)
def __getitem__(self, key):
if isinstance(key, str):
raise MAError("Unavailable for masked array.")
if not isinstance(key, tuple):
key = (key,)
objs = []
scalars = []
final_dtypedescr = None
for k in range(len(key)):
scalar = False
if isinstance(key[k], slice):
step = key[k].step
start = key[k].start
stop = key[k].stop
if start is None:
start = 0
if step is None:
step = 1
if isinstance(step, complex):
size = int(abs(step))
newobj = np.linspace(start, stop, num=size)
else:
newobj = np.arange(start, stop, step)
elif isinstance(key[k], str):
if (key[k] in 'rc'):
self.matrix = True
self.col = (key[k] == 'c')
continue
try:
self.axis = int(key[k])
continue
except (ValueError, TypeError):
raise ValueError("Unknown special directive")
elif type(key[k]) in np.ScalarType:
newobj = asarray([key[k]])
scalars.append(k)
scalar = True
else:
newobj = key[k]
objs.append(newobj)
if isinstance(newobj, ndarray) and not scalar:
if final_dtypedescr is None:
final_dtypedescr = newobj.dtype
elif newobj.dtype > final_dtypedescr:
final_dtypedescr = newobj.dtype
if final_dtypedescr is not None:
for k in scalars:
objs[k] = objs[k].astype(final_dtypedescr)
res = concatenate(tuple(objs), axis=self.axis)
return self._retval(res)
class mr_class(MAxisConcatenator):
"""
Translate slice objects to concatenation along the first axis.
This is the masked array version of `lib.index_tricks.RClass`.
See Also
--------
lib.index_tricks.RClass
Examples
--------
>>> np.ma.mr_[np.ma.array([1,2,3]), 0, 0, np.ma.array([4,5,6])]
array([1, 2, 3, 0, 0, 4, 5, 6])
"""
def __init__(self):
MAxisConcatenator.__init__(self, 0)
mr_ = mr_class()
#####--------------------------------------------------------------------------
#---- Find unmasked data ---
#####--------------------------------------------------------------------------
def flatnotmasked_edges(a):
"""
Find the indices of the first and last unmasked values.
Expects a 1-D `MaskedArray`, returns None if all values are masked.
Parameters
----------
a : array_like
Input 1-D `MaskedArray`
Returns
-------
edges : ndarray or None
The indices of first and last non-masked value in the array.
Returns None if all values are masked.
See Also
--------
flatnotmasked_contiguous, notmasked_contiguous, notmasked_edges,
clump_masked, clump_unmasked
Notes
-----
Only accepts 1-D arrays.
Examples
--------
>>> a = np.ma.arange(10)
>>> flatnotmasked_edges(a)
[0,-1]
>>> mask = (a < 3) | (a > 8) | (a == 5)
>>> a[mask] = np.ma.masked
>>> np.array(a[~a.mask])
array([3, 4, 6, 7, 8])
>>> flatnotmasked_edges(a)
array([3, 8])
>>> a[:] = np.ma.masked
>>> print(flatnotmasked_edges(ma))
None
"""
m = getmask(a)
if m is nomask or not np.any(m):
return np.array([0, a.size - 1])
unmasked = np.flatnonzero(~m)
if len(unmasked) > 0:
return unmasked[[0, -1]]
else:
return None
def notmasked_edges(a, axis=None):
"""
Find the indices of the first and last unmasked values along an axis.
If all values are masked, return None. Otherwise, return a list
of two tuples, corresponding to the indices of the first and last
unmasked values respectively.
Parameters
----------
a : array_like
The input array.
axis : int, optional
Axis along which to perform the operation.
If None (default), applies to a flattened version of the array.
Returns
-------
edges : ndarray or list
An array of start and end indexes if there are any masked data in
the array. If there are no masked data in the array, `edges` is a
list of the first and last index.
See Also
--------
flatnotmasked_contiguous, flatnotmasked_edges, notmasked_contiguous,
clump_masked, clump_unmasked
Examples
--------
>>> a = np.arange(9).reshape((3, 3))
>>> m = np.zeros_like(a)
>>> m[1:, 1:] = 1
>>> am = np.ma.array(a, mask=m)
>>> np.array(am[~am.mask])
array([0, 1, 2, 3, 6])
>>> np.ma.notmasked_edges(ma)
array([0, 6])
"""
a = asarray(a)
if axis is None or a.ndim == 1:
return flatnotmasked_edges(a)
m = getmaskarray(a)
idx = array(np.indices(a.shape), mask=np.asarray([m] * a.ndim))
return [tuple([idx[i].min(axis).compressed() for i in range(a.ndim)]),
tuple([idx[i].max(axis).compressed() for i in range(a.ndim)]), ]
def flatnotmasked_contiguous(a):
"""
Find contiguous unmasked data in a masked array along the given axis.
Parameters
----------
a : narray
The input array.
Returns
-------
slice_list : list
A sorted sequence of slices (start index, end index).
See Also
--------
flatnotmasked_edges, notmasked_contiguous, notmasked_edges,
clump_masked, clump_unmasked
Notes
-----
Only accepts 2-D arrays at most.
Examples
--------
>>> a = np.ma.arange(10)
>>> np.ma.flatnotmasked_contiguous(a)
slice(0, 10, None)
>>> mask = (a < 3) | (a > 8) | (a == 5)
>>> a[mask] = np.ma.masked
>>> np.array(a[~a.mask])
array([3, 4, 6, 7, 8])
>>> np.ma.flatnotmasked_contiguous(a)
[slice(3, 5, None), slice(6, 9, None)]
>>> a[:] = np.ma.masked
>>> print(np.ma.flatnotmasked_edges(a))
None
"""
m = getmask(a)
if m is nomask:
return slice(0, a.size, None)
i = 0
result = []
for (k, g) in itertools.groupby(m.ravel()):
n = len(list(g))
if not k:
result.append(slice(i, i + n))
i += n
return result or None
def notmasked_contiguous(a, axis=None):
"""
Find contiguous unmasked data in a masked array along the given axis.
Parameters
----------
a : array_like
The input array.
axis : int, optional
Axis along which to perform the operation.
If None (default), applies to a flattened version of the array.
Returns
-------
endpoints : list
A list of slices (start and end indexes) of unmasked indexes
in the array.
See Also
--------
flatnotmasked_edges, flatnotmasked_contiguous, notmasked_edges,
clump_masked, clump_unmasked
Notes
-----
Only accepts 2-D arrays at most.
Examples
--------
>>> a = np.arange(9).reshape((3, 3))
>>> mask = np.zeros_like(a)
>>> mask[1:, 1:] = 1
>>> ma = np.ma.array(a, mask=mask)
>>> np.array(ma[~ma.mask])
array([0, 1, 2, 3, 6])
>>> np.ma.notmasked_contiguous(ma)
[slice(0, 4, None), slice(6, 7, None)]
"""
a = asarray(a)
nd = a.ndim
if nd > 2:
raise NotImplementedError("Currently limited to atmost 2D array.")
if axis is None or nd == 1:
return flatnotmasked_contiguous(a)
#
result = []
#
other = (axis + 1) % 2
idx = [0, 0]
idx[axis] = slice(None, None)
#
for i in range(a.shape[other]):
idx[other] = i
result.append(flatnotmasked_contiguous(a[idx]) or None)
return result
def _ezclump(mask):
"""
Finds the clumps (groups of data with the same values) for a 1D bool array.
Returns a series of slices.
"""
if mask.ndim > 1:
mask = mask.ravel()
idx = (mask[1:] ^ mask[:-1]).nonzero()
idx = idx[0] + 1
if mask[0]:
if len(idx) == 0:
return [slice(0, mask.size)]
r = [slice(0, idx[0])]
r.extend((slice(left, right)
for left, right in zip(idx[1:-1:2], idx[2::2])))
else:
if len(idx) == 0:
return []
r = [slice(left, right) for left, right in zip(idx[:-1:2], idx[1::2])]
if mask[-1]:
r.append(slice(idx[-1], mask.size))
return r
def clump_unmasked(a):
"""
Return list of slices corresponding to the unmasked clumps of a 1-D array.
(A "clump" is defined as a contiguous region of the array).
Parameters
----------
a : ndarray
A one-dimensional masked array.
Returns
-------
slices : list of slice
The list of slices, one for each continuous region of unmasked
elements in `a`.
Notes
-----
.. versionadded:: 1.4.0
See Also
--------
flatnotmasked_edges, flatnotmasked_contiguous, notmasked_edges,
notmasked_contiguous, clump_masked
Examples
--------
>>> a = np.ma.masked_array(np.arange(10))
>>> a[[0, 1, 2, 6, 8, 9]] = np.ma.masked
>>> np.ma.clump_unmasked(a)
[slice(3, 6, None), slice(7, 8, None)]
"""
mask = getattr(a, '_mask', nomask)
if mask is nomask:
return [slice(0, a.size)]
return _ezclump(~mask)
def clump_masked(a):
"""
Returns a list of slices corresponding to the masked clumps of a 1-D array.
(A "clump" is defined as a contiguous region of the array).
Parameters
----------
a : ndarray
A one-dimensional masked array.
Returns
-------
slices : list of slice
The list of slices, one for each continuous region of masked elements
in `a`.
Notes
-----
.. versionadded:: 1.4.0
See Also
--------
flatnotmasked_edges, flatnotmasked_contiguous, notmasked_edges,
notmasked_contiguous, clump_unmasked
Examples
--------
>>> a = np.ma.masked_array(np.arange(10))
>>> a[[0, 1, 2, 6, 8, 9]] = np.ma.masked
>>> np.ma.clump_masked(a)
[slice(0, 3, None), slice(6, 7, None), slice(8, 10, None)]
"""
mask = ma.getmask(a)
if mask is nomask:
return []
return _ezclump(mask)
###############################################################################
# Polynomial fit #
###############################################################################
def vander(x, n=None):
"""
Masked values in the input array result in rows of zeros.
"""
_vander = np.vander(x, n)
m = getmask(x)
if m is not nomask:
_vander[m] = 0
return _vander
vander.__doc__ = ma.doc_note(np.vander.__doc__, vander.__doc__)
def polyfit(x, y, deg, rcond=None, full=False, w=None, cov=False):
"""
Any masked values in x is propagated in y, and vice-versa.
"""
x = asarray(x)
y = asarray(y)
m = getmask(x)
if y.ndim == 1:
m = mask_or(m, getmask(y))
elif y.ndim == 2:
my = getmask(mask_rows(y))
if my is not nomask:
m = mask_or(m, my[:, 0])
else:
raise TypeError("Expected a 1D or 2D array for y!")
if w is not None:
w = asarray(w)
if w.ndim != 1:
raise TypeError("expected a 1-d array for weights")
if w.shape[0] != y.shape[0]:
raise TypeError("expected w and y to have the same length")
m = mask_or(m, getmask(w))
if m is not nomask:
not_m = ~m
if w is not None:
w = w[not_m]
return np.polyfit(x[not_m], y[not_m], deg, rcond, full, w, cov)
else:
return np.polyfit(x, y, deg, rcond, full, w, cov)
polyfit.__doc__ = ma.doc_note(np.polyfit.__doc__, polyfit.__doc__)
|