Spaces:
Running
Running
File size: 91,905 Bytes
dc2106c |
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 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 |
import sys
import os
import re
import functools
import itertools
import warnings
import weakref
import contextlib
from operator import itemgetter, index as opindex
from collections.abc import Mapping
import numpy as np
from . import format
from ._datasource import DataSource
from numpy.core import overrides
from numpy.core.multiarray import packbits, unpackbits
from numpy.core.overrides import set_array_function_like_doc, set_module
from numpy.core._internal import recursive
from ._iotools import (
LineSplitter, NameValidator, StringConverter, ConverterError,
ConverterLockError, ConversionWarning, _is_string_like,
has_nested_fields, flatten_dtype, easy_dtype, _decode_line
)
from numpy.compat import (
asbytes, asstr, asunicode, os_fspath, os_PathLike,
pickle
)
@set_module('numpy')
def loads(*args, **kwargs):
# NumPy 1.15.0, 2017-12-10
warnings.warn(
"np.loads is deprecated, use pickle.loads instead",
DeprecationWarning, stacklevel=2)
return pickle.loads(*args, **kwargs)
__all__ = [
'savetxt', 'loadtxt', 'genfromtxt', 'ndfromtxt', 'mafromtxt',
'recfromtxt', 'recfromcsv', 'load', 'loads', 'save', 'savez',
'savez_compressed', 'packbits', 'unpackbits', 'fromregex', 'DataSource'
]
array_function_dispatch = functools.partial(
overrides.array_function_dispatch, module='numpy')
class BagObj:
"""
BagObj(obj)
Convert attribute look-ups to getitems on the object passed in.
Parameters
----------
obj : class instance
Object on which attribute look-up is performed.
Examples
--------
>>> from numpy.lib.npyio import BagObj as BO
>>> class BagDemo:
... def __getitem__(self, key): # An instance of BagObj(BagDemo)
... # will call this method when any
... # attribute look-up is required
... result = "Doesn't matter what you want, "
... return result + "you're gonna get this"
...
>>> demo_obj = BagDemo()
>>> bagobj = BO(demo_obj)
>>> bagobj.hello_there
"Doesn't matter what you want, you're gonna get this"
>>> bagobj.I_can_be_anything
"Doesn't matter what you want, you're gonna get this"
"""
def __init__(self, obj):
# Use weakref to make NpzFile objects collectable by refcount
self._obj = weakref.proxy(obj)
def __getattribute__(self, key):
try:
return object.__getattribute__(self, '_obj')[key]
except KeyError:
raise AttributeError(key) from None
def __dir__(self):
"""
Enables dir(bagobj) to list the files in an NpzFile.
This also enables tab-completion in an interpreter or IPython.
"""
return list(object.__getattribute__(self, '_obj').keys())
def zipfile_factory(file, *args, **kwargs):
"""
Create a ZipFile.
Allows for Zip64, and the `file` argument can accept file, str, or
pathlib.Path objects. `args` and `kwargs` are passed to the zipfile.ZipFile
constructor.
"""
if not hasattr(file, 'read'):
file = os_fspath(file)
import zipfile
kwargs['allowZip64'] = True
return zipfile.ZipFile(file, *args, **kwargs)
class NpzFile(Mapping):
"""
NpzFile(fid)
A dictionary-like object with lazy-loading of files in the zipped
archive provided on construction.
`NpzFile` is used to load files in the NumPy ``.npz`` data archive
format. It assumes that files in the archive have a ``.npy`` extension,
other files are ignored.
The arrays and file strings are lazily loaded on either
getitem access using ``obj['key']`` or attribute lookup using
``obj.f.key``. A list of all files (without ``.npy`` extensions) can
be obtained with ``obj.files`` and the ZipFile object itself using
``obj.zip``.
Attributes
----------
files : list of str
List of all files in the archive with a ``.npy`` extension.
zip : ZipFile instance
The ZipFile object initialized with the zipped archive.
f : BagObj instance
An object on which attribute can be performed as an alternative
to getitem access on the `NpzFile` instance itself.
allow_pickle : bool, optional
Allow loading pickled data. Default: False
.. versionchanged:: 1.16.3
Made default False in response to CVE-2019-6446.
pickle_kwargs : dict, optional
Additional keyword arguments to pass on to pickle.load.
These are only useful when loading object arrays saved on
Python 2 when using Python 3.
Parameters
----------
fid : file or str
The zipped archive to open. This is either a file-like object
or a string containing the path to the archive.
own_fid : bool, optional
Whether NpzFile should close the file handle.
Requires that `fid` is a file-like object.
Examples
--------
>>> from tempfile import TemporaryFile
>>> outfile = TemporaryFile()
>>> x = np.arange(10)
>>> y = np.sin(x)
>>> np.savez(outfile, x=x, y=y)
>>> _ = outfile.seek(0)
>>> npz = np.load(outfile)
>>> isinstance(npz, np.lib.io.NpzFile)
True
>>> sorted(npz.files)
['x', 'y']
>>> npz['x'] # getitem access
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
>>> npz.f.x # attribute lookup
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
"""
# Make __exit__ safe if zipfile_factory raises an exception
zip = None
fid = None
def __init__(self, fid, own_fid=False, allow_pickle=False,
pickle_kwargs=None):
# Import is postponed to here since zipfile depends on gzip, an
# optional component of the so-called standard library.
_zip = zipfile_factory(fid)
self._files = _zip.namelist()
self.files = []
self.allow_pickle = allow_pickle
self.pickle_kwargs = pickle_kwargs
for x in self._files:
if x.endswith('.npy'):
self.files.append(x[:-4])
else:
self.files.append(x)
self.zip = _zip
self.f = BagObj(self)
if own_fid:
self.fid = fid
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self.close()
def close(self):
"""
Close the file.
"""
if self.zip is not None:
self.zip.close()
self.zip = None
if self.fid is not None:
self.fid.close()
self.fid = None
self.f = None # break reference cycle
def __del__(self):
self.close()
# Implement the Mapping ABC
def __iter__(self):
return iter(self.files)
def __len__(self):
return len(self.files)
def __getitem__(self, key):
# FIXME: This seems like it will copy strings around
# more than is strictly necessary. The zipfile
# will read the string and then
# the format.read_array will copy the string
# to another place in memory.
# It would be better if the zipfile could read
# (or at least uncompress) the data
# directly into the array memory.
member = False
if key in self._files:
member = True
elif key in self.files:
member = True
key += '.npy'
if member:
bytes = self.zip.open(key)
magic = bytes.read(len(format.MAGIC_PREFIX))
bytes.close()
if magic == format.MAGIC_PREFIX:
bytes = self.zip.open(key)
return format.read_array(bytes,
allow_pickle=self.allow_pickle,
pickle_kwargs=self.pickle_kwargs)
else:
return self.zip.read(key)
else:
raise KeyError("%s is not a file in the archive" % key)
# deprecate the python 2 dict apis that we supported by accident in
# python 3. We forgot to implement itervalues() at all in earlier
# versions of numpy, so no need to deprecated it here.
def iteritems(self):
# Numpy 1.15, 2018-02-20
warnings.warn(
"NpzFile.iteritems is deprecated in python 3, to match the "
"removal of dict.itertems. Use .items() instead.",
DeprecationWarning, stacklevel=2)
return self.items()
def iterkeys(self):
# Numpy 1.15, 2018-02-20
warnings.warn(
"NpzFile.iterkeys is deprecated in python 3, to match the "
"removal of dict.iterkeys. Use .keys() instead.",
DeprecationWarning, stacklevel=2)
return self.keys()
@set_module('numpy')
def load(file, mmap_mode=None, allow_pickle=False, fix_imports=True,
encoding='ASCII'):
"""
Load arrays or pickled objects from ``.npy``, ``.npz`` or pickled files.
.. warning:: Loading files that contain object arrays uses the ``pickle``
module, which is not secure against erroneous or maliciously
constructed data. Consider passing ``allow_pickle=False`` to
load data that is known not to contain object arrays for the
safer handling of untrusted sources.
Parameters
----------
file : file-like object, string, or pathlib.Path
The file to read. File-like objects must support the
``seek()`` and ``read()`` methods. Pickled files require that the
file-like object support the ``readline()`` method as well.
mmap_mode : {None, 'r+', 'r', 'w+', 'c'}, optional
If not None, then memory-map the file, using the given mode (see
`numpy.memmap` for a detailed description of the modes). A
memory-mapped array is kept on disk. However, it can be accessed
and sliced like any ndarray. Memory mapping is especially useful
for accessing small fragments of large files without reading the
entire file into memory.
allow_pickle : bool, optional
Allow loading pickled object arrays stored in npy files. Reasons for
disallowing pickles include security, as loading pickled data can
execute arbitrary code. If pickles are disallowed, loading object
arrays will fail. Default: False
.. versionchanged:: 1.16.3
Made default False in response to CVE-2019-6446.
fix_imports : bool, optional
Only useful when loading Python 2 generated pickled files on Python 3,
which includes npy/npz files containing object arrays. If `fix_imports`
is True, pickle will try to map the old Python 2 names to the new names
used in Python 3.
encoding : str, optional
What encoding to use when reading Python 2 strings. Only useful when
loading Python 2 generated pickled files in Python 3, which includes
npy/npz files containing object arrays. Values other than 'latin1',
'ASCII', and 'bytes' are not allowed, as they can corrupt numerical
data. Default: 'ASCII'
Returns
-------
result : array, tuple, dict, etc.
Data stored in the file. For ``.npz`` files, the returned instance
of NpzFile class must be closed to avoid leaking file descriptors.
Raises
------
IOError
If the input file does not exist or cannot be read.
ValueError
The file contains an object array, but allow_pickle=False given.
See Also
--------
save, savez, savez_compressed, loadtxt
memmap : Create a memory-map to an array stored in a file on disk.
lib.format.open_memmap : Create or load a memory-mapped ``.npy`` file.
Notes
-----
- If the file contains pickle data, then whatever object is stored
in the pickle is returned.
- If the file is a ``.npy`` file, then a single array is returned.
- If the file is a ``.npz`` file, then a dictionary-like object is
returned, containing ``{filename: array}`` key-value pairs, one for
each file in the archive.
- If the file is a ``.npz`` file, the returned value supports the
context manager protocol in a similar fashion to the open function::
with load('foo.npz') as data:
a = data['a']
The underlying file descriptor is closed when exiting the 'with'
block.
Examples
--------
Store data to disk, and load it again:
>>> np.save('/tmp/123', np.array([[1, 2, 3], [4, 5, 6]]))
>>> np.load('/tmp/123.npy')
array([[1, 2, 3],
[4, 5, 6]])
Store compressed data to disk, and load it again:
>>> a=np.array([[1, 2, 3], [4, 5, 6]])
>>> b=np.array([1, 2])
>>> np.savez('/tmp/123.npz', a=a, b=b)
>>> data = np.load('/tmp/123.npz')
>>> data['a']
array([[1, 2, 3],
[4, 5, 6]])
>>> data['b']
array([1, 2])
>>> data.close()
Mem-map the stored array, and then access the second row
directly from disk:
>>> X = np.load('/tmp/123.npy', mmap_mode='r')
>>> X[1, :]
memmap([4, 5, 6])
"""
if encoding not in ('ASCII', 'latin1', 'bytes'):
# The 'encoding' value for pickle also affects what encoding
# the serialized binary data of NumPy arrays is loaded
# in. Pickle does not pass on the encoding information to
# NumPy. The unpickling code in numpy.core.multiarray is
# written to assume that unicode data appearing where binary
# should be is in 'latin1'. 'bytes' is also safe, as is 'ASCII'.
#
# Other encoding values can corrupt binary data, and we
# purposefully disallow them. For the same reason, the errors=
# argument is not exposed, as values other than 'strict'
# result can similarly silently corrupt numerical data.
raise ValueError("encoding must be 'ASCII', 'latin1', or 'bytes'")
pickle_kwargs = dict(encoding=encoding, fix_imports=fix_imports)
with contextlib.ExitStack() as stack:
if hasattr(file, 'read'):
fid = file
own_fid = False
else:
fid = stack.enter_context(open(os_fspath(file), "rb"))
own_fid = True
# Code to distinguish from NumPy binary files and pickles.
_ZIP_PREFIX = b'PK\x03\x04'
_ZIP_SUFFIX = b'PK\x05\x06' # empty zip files start with this
N = len(format.MAGIC_PREFIX)
magic = fid.read(N)
# If the file size is less than N, we need to make sure not
# to seek past the beginning of the file
fid.seek(-min(N, len(magic)), 1) # back-up
if magic.startswith(_ZIP_PREFIX) or magic.startswith(_ZIP_SUFFIX):
# zip-file (assume .npz)
# Potentially transfer file ownership to NpzFile
stack.pop_all()
ret = NpzFile(fid, own_fid=own_fid, allow_pickle=allow_pickle,
pickle_kwargs=pickle_kwargs)
return ret
elif magic == format.MAGIC_PREFIX:
# .npy file
if mmap_mode:
return format.open_memmap(file, mode=mmap_mode)
else:
return format.read_array(fid, allow_pickle=allow_pickle,
pickle_kwargs=pickle_kwargs)
else:
# Try a pickle
if not allow_pickle:
raise ValueError("Cannot load file containing pickled data "
"when allow_pickle=False")
try:
return pickle.load(fid, **pickle_kwargs)
except Exception as e:
raise IOError(
"Failed to interpret file %s as a pickle" % repr(file)) from e
def _save_dispatcher(file, arr, allow_pickle=None, fix_imports=None):
return (arr,)
@array_function_dispatch(_save_dispatcher)
def save(file, arr, allow_pickle=True, fix_imports=True):
"""
Save an array to a binary file in NumPy ``.npy`` format.
Parameters
----------
file : file, str, or pathlib.Path
File or filename to which the data is saved. If file is a file-object,
then the filename is unchanged. If file is a string or Path, a ``.npy``
extension will be appended to the filename if it does not already
have one.
arr : array_like
Array data to be saved.
allow_pickle : bool, optional
Allow saving object arrays using Python pickles. Reasons for disallowing
pickles include security (loading pickled data can execute arbitrary
code) and portability (pickled objects may not be loadable on different
Python installations, for example if the stored objects require libraries
that are not available, and not all pickled data is compatible between
Python 2 and Python 3).
Default: True
fix_imports : bool, optional
Only useful in forcing objects in object arrays on Python 3 to be
pickled in a Python 2 compatible way. If `fix_imports` is True, pickle
will try to map the new Python 3 names to the old module names used in
Python 2, so that the pickle data stream is readable with Python 2.
See Also
--------
savez : Save several arrays into a ``.npz`` archive
savetxt, load
Notes
-----
For a description of the ``.npy`` format, see :py:mod:`numpy.lib.format`.
Any data saved to the file is appended to the end of the file.
Examples
--------
>>> from tempfile import TemporaryFile
>>> outfile = TemporaryFile()
>>> x = np.arange(10)
>>> np.save(outfile, x)
>>> _ = outfile.seek(0) # Only needed here to simulate closing & reopening file
>>> np.load(outfile)
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
>>> with open('test.npy', 'wb') as f:
... np.save(f, np.array([1, 2]))
... np.save(f, np.array([1, 3]))
>>> with open('test.npy', 'rb') as f:
... a = np.load(f)
... b = np.load(f)
>>> print(a, b)
# [1 2] [1 3]
"""
if hasattr(file, 'write'):
file_ctx = contextlib.nullcontext(file)
else:
file = os_fspath(file)
if not file.endswith('.npy'):
file = file + '.npy'
file_ctx = open(file, "wb")
with file_ctx as fid:
arr = np.asanyarray(arr)
format.write_array(fid, arr, allow_pickle=allow_pickle,
pickle_kwargs=dict(fix_imports=fix_imports))
def _savez_dispatcher(file, *args, **kwds):
yield from args
yield from kwds.values()
@array_function_dispatch(_savez_dispatcher)
def savez(file, *args, **kwds):
"""Save several arrays into a single file in uncompressed ``.npz`` format.
Provide arrays as keyword arguments to store them under the
corresponding name in the output file: ``savez(fn, x=x, y=y)``.
If arrays are specified as positional arguments, i.e., ``savez(fn,
x, y)``, their names will be `arr_0`, `arr_1`, etc.
Parameters
----------
file : str or file
Either the filename (string) or an open file (file-like object)
where the data will be saved. If file is a string or a Path, the
``.npz`` extension will be appended to the filename if it is not
already there.
args : Arguments, optional
Arrays to save to the file. Please use keyword arguments (see
`kwds` below) to assign names to arrays. Arrays specified as
args will be named "arr_0", "arr_1", and so on.
kwds : Keyword arguments, optional
Arrays to save to the file. Each array will be saved to the
output file with its corresponding keyword name.
Returns
-------
None
See Also
--------
save : Save a single array to a binary file in NumPy format.
savetxt : Save an array to a file as plain text.
savez_compressed : Save several arrays into a compressed ``.npz`` archive
Notes
-----
The ``.npz`` file format is a zipped archive of files named after the
variables they contain. The archive is not compressed and each file
in the archive contains one variable in ``.npy`` format. For a
description of the ``.npy`` format, see :py:mod:`numpy.lib.format`.
When opening the saved ``.npz`` file with `load` a `NpzFile` object is
returned. This is a dictionary-like object which can be queried for
its list of arrays (with the ``.files`` attribute), and for the arrays
themselves.
When saving dictionaries, the dictionary keys become filenames
inside the ZIP archive. Therefore, keys should be valid filenames.
E.g., avoid keys that begin with ``/`` or contain ``.``.
Examples
--------
>>> from tempfile import TemporaryFile
>>> outfile = TemporaryFile()
>>> x = np.arange(10)
>>> y = np.sin(x)
Using `savez` with \\*args, the arrays are saved with default names.
>>> np.savez(outfile, x, y)
>>> _ = outfile.seek(0) # Only needed here to simulate closing & reopening file
>>> npzfile = np.load(outfile)
>>> npzfile.files
['arr_0', 'arr_1']
>>> npzfile['arr_0']
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
Using `savez` with \\**kwds, the arrays are saved with the keyword names.
>>> outfile = TemporaryFile()
>>> np.savez(outfile, x=x, y=y)
>>> _ = outfile.seek(0)
>>> npzfile = np.load(outfile)
>>> sorted(npzfile.files)
['x', 'y']
>>> npzfile['x']
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
"""
_savez(file, args, kwds, False)
def _savez_compressed_dispatcher(file, *args, **kwds):
yield from args
yield from kwds.values()
@array_function_dispatch(_savez_compressed_dispatcher)
def savez_compressed(file, *args, **kwds):
"""
Save several arrays into a single file in compressed ``.npz`` format.
Provide arrays as keyword arguments to store them under the
corresponding name in the output file: ``savez(fn, x=x, y=y)``.
If arrays are specified as positional arguments, i.e., ``savez(fn,
x, y)``, their names will be `arr_0`, `arr_1`, etc.
Parameters
----------
file : str or file
Either the filename (string) or an open file (file-like object)
where the data will be saved. If file is a string or a Path, the
``.npz`` extension will be appended to the filename if it is not
already there.
args : Arguments, optional
Arrays to save to the file. Please use keyword arguments (see
`kwds` below) to assign names to arrays. Arrays specified as
args will be named "arr_0", "arr_1", and so on.
kwds : Keyword arguments, optional
Arrays to save to the file. Each array will be saved to the
output file with its corresponding keyword name.
Returns
-------
None
See Also
--------
numpy.save : Save a single array to a binary file in NumPy format.
numpy.savetxt : Save an array to a file as plain text.
numpy.savez : Save several arrays into an uncompressed ``.npz`` file format
numpy.load : Load the files created by savez_compressed.
Notes
-----
The ``.npz`` file format is a zipped archive of files named after the
variables they contain. The archive is compressed with
``zipfile.ZIP_DEFLATED`` and each file in the archive contains one variable
in ``.npy`` format. For a description of the ``.npy`` format, see
:py:mod:`numpy.lib.format`.
When opening the saved ``.npz`` file with `load` a `NpzFile` object is
returned. This is a dictionary-like object which can be queried for
its list of arrays (with the ``.files`` attribute), and for the arrays
themselves.
Examples
--------
>>> test_array = np.random.rand(3, 2)
>>> test_vector = np.random.rand(4)
>>> np.savez_compressed('/tmp/123', a=test_array, b=test_vector)
>>> loaded = np.load('/tmp/123.npz')
>>> print(np.array_equal(test_array, loaded['a']))
True
>>> print(np.array_equal(test_vector, loaded['b']))
True
"""
_savez(file, args, kwds, True)
def _savez(file, args, kwds, compress, allow_pickle=True, pickle_kwargs=None):
# Import is postponed to here since zipfile depends on gzip, an optional
# component of the so-called standard library.
import zipfile
if not hasattr(file, 'write'):
file = os_fspath(file)
if not file.endswith('.npz'):
file = file + '.npz'
namedict = kwds
for i, val in enumerate(args):
key = 'arr_%d' % i
if key in namedict.keys():
raise ValueError(
"Cannot use un-named variables and keyword %s" % key)
namedict[key] = val
if compress:
compression = zipfile.ZIP_DEFLATED
else:
compression = zipfile.ZIP_STORED
zipf = zipfile_factory(file, mode="w", compression=compression)
for key, val in namedict.items():
fname = key + '.npy'
val = np.asanyarray(val)
# always force zip64, gh-10776
with zipf.open(fname, 'w', force_zip64=True) as fid:
format.write_array(fid, val,
allow_pickle=allow_pickle,
pickle_kwargs=pickle_kwargs)
zipf.close()
def _getconv(dtype):
""" Find the correct dtype converter. Adapted from matplotlib """
def floatconv(x):
x.lower()
if '0x' in x:
return float.fromhex(x)
return float(x)
typ = dtype.type
if issubclass(typ, np.bool_):
return lambda x: bool(int(x))
if issubclass(typ, np.uint64):
return np.uint64
if issubclass(typ, np.int64):
return np.int64
if issubclass(typ, np.integer):
return lambda x: int(float(x))
elif issubclass(typ, np.longdouble):
return np.longdouble
elif issubclass(typ, np.floating):
return floatconv
elif issubclass(typ, complex):
return lambda x: complex(asstr(x).replace('+-', '-'))
elif issubclass(typ, np.bytes_):
return asbytes
elif issubclass(typ, np.unicode_):
return asunicode
else:
return asstr
# amount of lines loadtxt reads in one chunk, can be overridden for testing
_loadtxt_chunksize = 50000
def _loadtxt_dispatcher(fname, dtype=None, comments=None, delimiter=None,
converters=None, skiprows=None, usecols=None, unpack=None,
ndmin=None, encoding=None, max_rows=None, *, like=None):
return (like,)
@set_array_function_like_doc
@set_module('numpy')
def loadtxt(fname, dtype=float, comments='#', delimiter=None,
converters=None, skiprows=0, usecols=None, unpack=False,
ndmin=0, encoding='bytes', max_rows=None, *, like=None):
r"""
Load data from a text file.
Each row in the text file must have the same number of values.
Parameters
----------
fname : file, str, or pathlib.Path
File, filename, or generator to read. If the filename extension is
``.gz`` or ``.bz2``, the file is first decompressed. Note that
generators should return byte strings.
dtype : data-type, optional
Data-type of the resulting array; default: float. If this is a
structured data-type, the resulting array will be 1-dimensional, and
each row will be interpreted as an element of the array. In this
case, the number of columns used must match the number of fields in
the data-type.
comments : str or sequence of str, optional
The characters or list of characters used to indicate the start of a
comment. None implies no comments. For backwards compatibility, byte
strings will be decoded as 'latin1'. The default is '#'.
delimiter : str, optional
The string used to separate values. For backwards compatibility, byte
strings will be decoded as 'latin1'. The default is whitespace.
converters : dict, optional
A dictionary mapping column number to a function that will parse the
column string into the desired value. E.g., if column 0 is a date
string: ``converters = {0: datestr2num}``. Converters can also be
used to provide a default value for missing data (but see also
`genfromtxt`): ``converters = {3: lambda s: float(s.strip() or 0)}``.
Default: None.
skiprows : int, optional
Skip the first `skiprows` lines, including comments; default: 0.
usecols : int or sequence, optional
Which columns to read, with 0 being the first. For example,
``usecols = (1,4,5)`` will extract the 2nd, 5th and 6th columns.
The default, None, results in all columns being read.
.. versionchanged:: 1.11.0
When a single column has to be read it is possible to use
an integer instead of a tuple. E.g ``usecols = 3`` reads the
fourth column the same way as ``usecols = (3,)`` would.
unpack : bool, optional
If True, the returned array is transposed, so that arguments may be
unpacked using ``x, y, z = loadtxt(...)``. When used with a
structured data-type, arrays are returned for each field.
Default is False.
ndmin : int, optional
The returned array will have at least `ndmin` dimensions.
Otherwise mono-dimensional axes will be squeezed.
Legal values: 0 (default), 1 or 2.
.. versionadded:: 1.6.0
encoding : str, optional
Encoding used to decode the inputfile. Does not apply to input streams.
The special value 'bytes' enables backward compatibility workarounds
that ensures you receive byte arrays as results if possible and passes
'latin1' encoded strings to converters. Override this value to receive
unicode arrays and pass strings as input to converters. If set to None
the system default is used. The default value is 'bytes'.
.. versionadded:: 1.14.0
max_rows : int, optional
Read `max_rows` lines of content after `skiprows` lines. The default
is to read all the lines.
.. versionadded:: 1.16.0
${ARRAY_FUNCTION_LIKE}
.. versionadded:: 1.20.0
Returns
-------
out : ndarray
Data read from the text file.
See Also
--------
load, fromstring, fromregex
genfromtxt : Load data with missing values handled as specified.
scipy.io.loadmat : reads MATLAB data files
Notes
-----
This function aims to be a fast reader for simply formatted files. The
`genfromtxt` function provides more sophisticated handling of, e.g.,
lines with missing values.
.. versionadded:: 1.10.0
The strings produced by the Python float.hex method can be used as
input for floats.
Examples
--------
>>> from io import StringIO # StringIO behaves like a file object
>>> c = StringIO("0 1\n2 3")
>>> np.loadtxt(c)
array([[0., 1.],
[2., 3.]])
>>> d = StringIO("M 21 72\nF 35 58")
>>> np.loadtxt(d, dtype={'names': ('gender', 'age', 'weight'),
... 'formats': ('S1', 'i4', 'f4')})
array([(b'M', 21, 72.), (b'F', 35, 58.)],
dtype=[('gender', 'S1'), ('age', '<i4'), ('weight', '<f4')])
>>> c = StringIO("1,0,2\n3,0,4")
>>> x, y = np.loadtxt(c, delimiter=',', usecols=(0, 2), unpack=True)
>>> x
array([1., 3.])
>>> y
array([2., 4.])
This example shows how `converters` can be used to convert a field
with a trailing minus sign into a negative number.
>>> s = StringIO('10.01 31.25-\n19.22 64.31\n17.57- 63.94')
>>> def conv(fld):
... return -float(fld[:-1]) if fld.endswith(b'-') else float(fld)
...
>>> np.loadtxt(s, converters={0: conv, 1: conv})
array([[ 10.01, -31.25],
[ 19.22, 64.31],
[-17.57, 63.94]])
"""
if like is not None:
return _loadtxt_with_like(
fname, dtype=dtype, comments=comments, delimiter=delimiter,
converters=converters, skiprows=skiprows, usecols=usecols,
unpack=unpack, ndmin=ndmin, encoding=encoding,
max_rows=max_rows, like=like
)
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Nested functions used by loadtxt.
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# not to be confused with the flatten_dtype we import...
@recursive
def flatten_dtype_internal(self, dt):
"""Unpack a structured data-type, and produce re-packing info."""
if dt.names is None:
# If the dtype is flattened, return.
# If the dtype has a shape, the dtype occurs
# in the list more than once.
shape = dt.shape
if len(shape) == 0:
return ([dt.base], None)
else:
packing = [(shape[-1], list)]
if len(shape) > 1:
for dim in dt.shape[-2::-1]:
packing = [(dim*packing[0][0], packing*dim)]
return ([dt.base] * int(np.prod(dt.shape)), packing)
else:
types = []
packing = []
for field in dt.names:
tp, bytes = dt.fields[field]
flat_dt, flat_packing = self(tp)
types.extend(flat_dt)
# Avoid extra nesting for subarrays
if tp.ndim > 0:
packing.extend(flat_packing)
else:
packing.append((len(flat_dt), flat_packing))
return (types, packing)
@recursive
def pack_items(self, items, packing):
"""Pack items into nested lists based on re-packing info."""
if packing is None:
return items[0]
elif packing is tuple:
return tuple(items)
elif packing is list:
return list(items)
else:
start = 0
ret = []
for length, subpacking in packing:
ret.append(self(items[start:start+length], subpacking))
start += length
return tuple(ret)
def split_line(line):
"""Chop off comments, strip, and split at delimiter. """
line = _decode_line(line, encoding=encoding)
if comments is not None:
line = regex_comments.split(line, maxsplit=1)[0]
line = line.strip('\r\n')
return line.split(delimiter) if line else []
def read_data(chunk_size):
"""Parse each line, including the first.
The file read, `fh`, is a global defined above.
Parameters
----------
chunk_size : int
At most `chunk_size` lines are read at a time, with iteration
until all lines are read.
"""
X = []
line_iter = itertools.chain([first_line], fh)
line_iter = itertools.islice(line_iter, max_rows)
for i, line in enumerate(line_iter):
vals = split_line(line)
if len(vals) == 0:
continue
if usecols:
vals = [vals[j] for j in usecols]
if len(vals) != N:
line_num = i + skiprows + 1
raise ValueError("Wrong number of columns at line %d"
% line_num)
# Convert each value according to its column and store
items = [conv(val) for (conv, val) in zip(converters, vals)]
# Then pack it according to the dtype's nesting
items = pack_items(items, packing)
X.append(items)
if len(X) > chunk_size:
yield X
X = []
if X:
yield X
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Main body of loadtxt.
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Check correctness of the values of `ndmin`
if ndmin not in [0, 1, 2]:
raise ValueError('Illegal value of ndmin keyword: %s' % ndmin)
# Type conversions for Py3 convenience
if comments is not None:
if isinstance(comments, (str, bytes)):
comments = [comments]
comments = [_decode_line(x) for x in comments]
# Compile regex for comments beforehand
comments = (re.escape(comment) for comment in comments)
regex_comments = re.compile('|'.join(comments))
if delimiter is not None:
delimiter = _decode_line(delimiter)
user_converters = converters
byte_converters = False
if encoding == 'bytes':
encoding = None
byte_converters = True
if usecols is not None:
# Allow usecols to be a single int or a sequence of ints
try:
usecols_as_list = list(usecols)
except TypeError:
usecols_as_list = [usecols]
for col_idx in usecols_as_list:
try:
opindex(col_idx)
except TypeError as e:
e.args = (
"usecols must be an int or a sequence of ints but "
"it contains at least one element of type %s" %
type(col_idx),
)
raise
# Fall back to existing code
usecols = usecols_as_list
# Make sure we're dealing with a proper dtype
dtype = np.dtype(dtype)
defconv = _getconv(dtype)
dtype_types, packing = flatten_dtype_internal(dtype)
fown = False
try:
if isinstance(fname, os_PathLike):
fname = os_fspath(fname)
if _is_string_like(fname):
fh = np.lib._datasource.open(fname, 'rt', encoding=encoding)
fencoding = getattr(fh, 'encoding', 'latin1')
fh = iter(fh)
fown = True
else:
fh = iter(fname)
fencoding = getattr(fname, 'encoding', 'latin1')
except TypeError as e:
raise ValueError(
'fname must be a string, file handle, or generator'
) from e
# input may be a python2 io stream
if encoding is not None:
fencoding = encoding
# we must assume local encoding
# TODO emit portability warning?
elif fencoding is None:
import locale
fencoding = locale.getpreferredencoding()
try:
# Skip the first `skiprows` lines
for i in range(skiprows):
next(fh)
# Read until we find a line with some values, and use
# it to estimate the number of columns, N.
first_vals = None
try:
while not first_vals:
first_line = next(fh)
first_vals = split_line(first_line)
except StopIteration:
# End of lines reached
first_line = ''
first_vals = []
warnings.warn('loadtxt: Empty input file: "%s"' % fname,
stacklevel=2)
N = len(usecols or first_vals)
# Now that we know N, create the default converters list, and
# set packing, if necessary.
if len(dtype_types) > 1:
# We're dealing with a structured array, each field of
# the dtype matches a column
converters = [_getconv(dt) for dt in dtype_types]
else:
# All fields have the same dtype
converters = [defconv for i in range(N)]
if N > 1:
packing = [(N, tuple)]
# By preference, use the converters specified by the user
for i, conv in (user_converters or {}).items():
if usecols:
try:
i = usecols.index(i)
except ValueError:
# Unused converter specified
continue
if byte_converters:
# converters may use decode to workaround numpy's old
# behaviour, so encode the string again before passing to
# the user converter
def tobytes_first(x, conv):
if type(x) is bytes:
return conv(x)
return conv(x.encode("latin1"))
converters[i] = functools.partial(tobytes_first, conv=conv)
else:
converters[i] = conv
converters = [conv if conv is not bytes else
lambda x: x.encode(fencoding) for conv in converters]
# read data in chunks and fill it into an array via resize
# over-allocating and shrinking the array later may be faster but is
# probably not relevant compared to the cost of actually reading and
# converting the data
X = None
for x in read_data(_loadtxt_chunksize):
if X is None:
X = np.array(x, dtype)
else:
nshape = list(X.shape)
pos = nshape[0]
nshape[0] += len(x)
X.resize(nshape, refcheck=False)
X[pos:, ...] = x
finally:
if fown:
fh.close()
if X is None:
X = np.array([], dtype)
# Multicolumn data are returned with shape (1, N, M), i.e.
# (1, 1, M) for a single row - remove the singleton dimension there
if X.ndim == 3 and X.shape[:2] == (1, 1):
X.shape = (1, -1)
# Verify that the array has at least dimensions `ndmin`.
# Tweak the size and shape of the arrays - remove extraneous dimensions
if X.ndim > ndmin:
X = np.squeeze(X)
# and ensure we have the minimum number of dimensions asked for
# - has to be in this order for the odd case ndmin=1, X.squeeze().ndim=0
if X.ndim < ndmin:
if ndmin == 1:
X = np.atleast_1d(X)
elif ndmin == 2:
X = np.atleast_2d(X).T
if unpack:
if len(dtype_types) > 1:
# For structured arrays, return an array for each field.
return [X[field] for field in dtype.names]
else:
return X.T
else:
return X
_loadtxt_with_like = array_function_dispatch(
_loadtxt_dispatcher
)(loadtxt)
def _savetxt_dispatcher(fname, X, fmt=None, delimiter=None, newline=None,
header=None, footer=None, comments=None,
encoding=None):
return (X,)
@array_function_dispatch(_savetxt_dispatcher)
def savetxt(fname, X, fmt='%.18e', delimiter=' ', newline='\n', header='',
footer='', comments='# ', encoding=None):
"""
Save an array to a text file.
Parameters
----------
fname : filename or file handle
If the filename ends in ``.gz``, the file is automatically saved in
compressed gzip format. `loadtxt` understands gzipped files
transparently.
X : 1D or 2D array_like
Data to be saved to a text file.
fmt : str or sequence of strs, optional
A single format (%10.5f), a sequence of formats, or a
multi-format string, e.g. 'Iteration %d -- %10.5f', in which
case `delimiter` is ignored. For complex `X`, the legal options
for `fmt` are:
* a single specifier, `fmt='%.4e'`, resulting in numbers formatted
like `' (%s+%sj)' % (fmt, fmt)`
* a full string specifying every real and imaginary part, e.g.
`' %.4e %+.4ej %.4e %+.4ej %.4e %+.4ej'` for 3 columns
* a list of specifiers, one per column - in this case, the real
and imaginary part must have separate specifiers,
e.g. `['%.3e + %.3ej', '(%.15e%+.15ej)']` for 2 columns
delimiter : str, optional
String or character separating columns.
newline : str, optional
String or character separating lines.
.. versionadded:: 1.5.0
header : str, optional
String that will be written at the beginning of the file.
.. versionadded:: 1.7.0
footer : str, optional
String that will be written at the end of the file.
.. versionadded:: 1.7.0
comments : str, optional
String that will be prepended to the ``header`` and ``footer`` strings,
to mark them as comments. Default: '# ', as expected by e.g.
``numpy.loadtxt``.
.. versionadded:: 1.7.0
encoding : {None, str}, optional
Encoding used to encode the outputfile. Does not apply to output
streams. If the encoding is something other than 'bytes' or 'latin1'
you will not be able to load the file in NumPy versions < 1.14. Default
is 'latin1'.
.. versionadded:: 1.14.0
See Also
--------
save : Save an array to a binary file in NumPy ``.npy`` format
savez : Save several arrays into an uncompressed ``.npz`` archive
savez_compressed : Save several arrays into a compressed ``.npz`` archive
Notes
-----
Further explanation of the `fmt` parameter
(``%[flag]width[.precision]specifier``):
flags:
``-`` : left justify
``+`` : Forces to precede result with + or -.
``0`` : Left pad the number with zeros instead of space (see width).
width:
Minimum number of characters to be printed. The value is not truncated
if it has more characters.
precision:
- For integer specifiers (eg. ``d,i,o,x``), the minimum number of
digits.
- For ``e, E`` and ``f`` specifiers, the number of digits to print
after the decimal point.
- For ``g`` and ``G``, the maximum number of significant digits.
- For ``s``, the maximum number of characters.
specifiers:
``c`` : character
``d`` or ``i`` : signed decimal integer
``e`` or ``E`` : scientific notation with ``e`` or ``E``.
``f`` : decimal floating point
``g,G`` : use the shorter of ``e,E`` or ``f``
``o`` : signed octal
``s`` : string of characters
``u`` : unsigned decimal integer
``x,X`` : unsigned hexadecimal integer
This explanation of ``fmt`` is not complete, for an exhaustive
specification see [1]_.
References
----------
.. [1] `Format Specification Mini-Language
<https://docs.python.org/library/string.html#format-specification-mini-language>`_,
Python Documentation.
Examples
--------
>>> x = y = z = np.arange(0.0,5.0,1.0)
>>> np.savetxt('test.out', x, delimiter=',') # X is an array
>>> np.savetxt('test.out', (x,y,z)) # x,y,z equal sized 1D arrays
>>> np.savetxt('test.out', x, fmt='%1.4e') # use exponential notation
"""
# Py3 conversions first
if isinstance(fmt, bytes):
fmt = asstr(fmt)
delimiter = asstr(delimiter)
class WriteWrap:
"""Convert to bytes on bytestream inputs.
"""
def __init__(self, fh, encoding):
self.fh = fh
self.encoding = encoding
self.do_write = self.first_write
def close(self):
self.fh.close()
def write(self, v):
self.do_write(v)
def write_bytes(self, v):
if isinstance(v, bytes):
self.fh.write(v)
else:
self.fh.write(v.encode(self.encoding))
def write_normal(self, v):
self.fh.write(asunicode(v))
def first_write(self, v):
try:
self.write_normal(v)
self.write = self.write_normal
except TypeError:
# input is probably a bytestream
self.write_bytes(v)
self.write = self.write_bytes
own_fh = False
if isinstance(fname, os_PathLike):
fname = os_fspath(fname)
if _is_string_like(fname):
# datasource doesn't support creating a new file ...
open(fname, 'wt').close()
fh = np.lib._datasource.open(fname, 'wt', encoding=encoding)
own_fh = True
elif hasattr(fname, 'write'):
# wrap to handle byte output streams
fh = WriteWrap(fname, encoding or 'latin1')
else:
raise ValueError('fname must be a string or file handle')
try:
X = np.asarray(X)
# Handle 1-dimensional arrays
if X.ndim == 0 or X.ndim > 2:
raise ValueError(
"Expected 1D or 2D array, got %dD array instead" % X.ndim)
elif X.ndim == 1:
# Common case -- 1d array of numbers
if X.dtype.names is None:
X = np.atleast_2d(X).T
ncol = 1
# Complex dtype -- each field indicates a separate column
else:
ncol = len(X.dtype.names)
else:
ncol = X.shape[1]
iscomplex_X = np.iscomplexobj(X)
# `fmt` can be a string with multiple insertion points or a
# list of formats. E.g. '%10.5f\t%10d' or ('%10.5f', '$10d')
if type(fmt) in (list, tuple):
if len(fmt) != ncol:
raise AttributeError('fmt has wrong shape. %s' % str(fmt))
format = asstr(delimiter).join(map(asstr, fmt))
elif isinstance(fmt, str):
n_fmt_chars = fmt.count('%')
error = ValueError('fmt has wrong number of %% formats: %s' % fmt)
if n_fmt_chars == 1:
if iscomplex_X:
fmt = [' (%s+%sj)' % (fmt, fmt), ] * ncol
else:
fmt = [fmt, ] * ncol
format = delimiter.join(fmt)
elif iscomplex_X and n_fmt_chars != (2 * ncol):
raise error
elif ((not iscomplex_X) and n_fmt_chars != ncol):
raise error
else:
format = fmt
else:
raise ValueError('invalid fmt: %r' % (fmt,))
if len(header) > 0:
header = header.replace('\n', '\n' + comments)
fh.write(comments + header + newline)
if iscomplex_X:
for row in X:
row2 = []
for number in row:
row2.append(number.real)
row2.append(number.imag)
s = format % tuple(row2) + newline
fh.write(s.replace('+-', '-'))
else:
for row in X:
try:
v = format % tuple(row) + newline
except TypeError as e:
raise TypeError("Mismatch between array dtype ('%s') and "
"format specifier ('%s')"
% (str(X.dtype), format)) from e
fh.write(v)
if len(footer) > 0:
footer = footer.replace('\n', '\n' + comments)
fh.write(comments + footer + newline)
finally:
if own_fh:
fh.close()
@set_module('numpy')
def fromregex(file, regexp, dtype, encoding=None):
"""
Construct an array from a text file, using regular expression parsing.
The returned array is always a structured array, and is constructed from
all matches of the regular expression in the file. Groups in the regular
expression are converted to fields of the structured array.
Parameters
----------
file : str or file
Filename or file object to read.
regexp : str or regexp
Regular expression used to parse the file.
Groups in the regular expression correspond to fields in the dtype.
dtype : dtype or list of dtypes
Dtype for the structured array.
encoding : str, optional
Encoding used to decode the inputfile. Does not apply to input streams.
.. versionadded:: 1.14.0
Returns
-------
output : ndarray
The output array, containing the part of the content of `file` that
was matched by `regexp`. `output` is always a structured array.
Raises
------
TypeError
When `dtype` is not a valid dtype for a structured array.
See Also
--------
fromstring, loadtxt
Notes
-----
Dtypes for structured arrays can be specified in several forms, but all
forms specify at least the data type and field name. For details see
`basics.rec`.
Examples
--------
>>> f = open('test.dat', 'w')
>>> _ = f.write("1312 foo\\n1534 bar\\n444 qux")
>>> f.close()
>>> regexp = r"(\\d+)\\s+(...)" # match [digits, whitespace, anything]
>>> output = np.fromregex('test.dat', regexp,
... [('num', np.int64), ('key', 'S3')])
>>> output
array([(1312, b'foo'), (1534, b'bar'), ( 444, b'qux')],
dtype=[('num', '<i8'), ('key', 'S3')])
>>> output['num']
array([1312, 1534, 444])
"""
own_fh = False
if not hasattr(file, "read"):
file = np.lib._datasource.open(file, 'rt', encoding=encoding)
own_fh = True
try:
if not isinstance(dtype, np.dtype):
dtype = np.dtype(dtype)
content = file.read()
if isinstance(content, bytes) and isinstance(regexp, np.compat.unicode):
regexp = asbytes(regexp)
elif isinstance(content, np.compat.unicode) and isinstance(regexp, bytes):
regexp = asstr(regexp)
if not hasattr(regexp, 'match'):
regexp = re.compile(regexp)
seq = regexp.findall(content)
if seq and not isinstance(seq[0], tuple):
# Only one group is in the regexp.
# Create the new array as a single data-type and then
# re-interpret as a single-field structured array.
newdtype = np.dtype(dtype[dtype.names[0]])
output = np.array(seq, dtype=newdtype)
output.dtype = dtype
else:
output = np.array(seq, dtype=dtype)
return output
finally:
if own_fh:
file.close()
#####--------------------------------------------------------------------------
#---- --- ASCII functions ---
#####--------------------------------------------------------------------------
def _genfromtxt_dispatcher(fname, dtype=None, comments=None, delimiter=None,
skip_header=None, skip_footer=None, converters=None,
missing_values=None, filling_values=None, usecols=None,
names=None, excludelist=None, deletechars=None,
replace_space=None, autostrip=None, case_sensitive=None,
defaultfmt=None, unpack=None, usemask=None, loose=None,
invalid_raise=None, max_rows=None, encoding=None, *,
like=None):
return (like,)
@set_array_function_like_doc
@set_module('numpy')
def genfromtxt(fname, dtype=float, comments='#', delimiter=None,
skip_header=0, skip_footer=0, converters=None,
missing_values=None, filling_values=None, usecols=None,
names=None, excludelist=None,
deletechars=''.join(sorted(NameValidator.defaultdeletechars)),
replace_space='_', autostrip=False, case_sensitive=True,
defaultfmt="f%i", unpack=None, usemask=False, loose=True,
invalid_raise=True, max_rows=None, encoding='bytes', *,
like=None):
"""
Load data from a text file, with missing values handled as specified.
Each line past the first `skip_header` lines is split at the `delimiter`
character, and characters following the `comments` character are discarded.
Parameters
----------
fname : file, str, pathlib.Path, list of str, generator
File, filename, list, or generator to read. If the filename
extension is `.gz` or `.bz2`, the file is first decompressed. Note
that generators must return byte strings. The strings
in a list or produced by a generator are treated as lines.
dtype : dtype, optional
Data type of the resulting array.
If None, the dtypes will be determined by the contents of each
column, individually.
comments : str, optional
The character used to indicate the start of a comment.
All the characters occurring on a line after a comment are discarded.
delimiter : str, int, or sequence, optional
The string used to separate values. By default, any consecutive
whitespaces act as delimiter. An integer or sequence of integers
can also be provided as width(s) of each field.
skiprows : int, optional
`skiprows` was removed in numpy 1.10. Please use `skip_header` instead.
skip_header : int, optional
The number of lines to skip at the beginning of the file.
skip_footer : int, optional
The number of lines to skip at the end of the file.
converters : variable, optional
The set of functions that convert the data of a column to a value.
The converters can also be used to provide a default value
for missing data: ``converters = {3: lambda s: float(s or 0)}``.
missing : variable, optional
`missing` was removed in numpy 1.10. Please use `missing_values`
instead.
missing_values : variable, optional
The set of strings corresponding to missing data.
filling_values : variable, optional
The set of values to be used as default when the data are missing.
usecols : sequence, optional
Which columns to read, with 0 being the first. For example,
``usecols = (1, 4, 5)`` will extract the 2nd, 5th and 6th columns.
names : {None, True, str, sequence}, optional
If `names` is True, the field names are read from the first line after
the first `skip_header` lines. This line can optionally be preceeded
by a comment delimiter. If `names` is a sequence or a single-string of
comma-separated names, the names will be used to define the field names
in a structured dtype. If `names` is None, the names of the dtype
fields will be used, if any.
excludelist : sequence, optional
A list of names to exclude. This list is appended to the default list
['return','file','print']. Excluded names are appended with an
underscore: for example, `file` would become `file_`.
deletechars : str, optional
A string combining invalid characters that must be deleted from the
names.
defaultfmt : str, optional
A format used to define default field names, such as "f%i" or "f_%02i".
autostrip : bool, optional
Whether to automatically strip white spaces from the variables.
replace_space : char, optional
Character(s) used in replacement of white spaces in the variable
names. By default, use a '_'.
case_sensitive : {True, False, 'upper', 'lower'}, optional
If True, field names are case sensitive.
If False or 'upper', field names are converted to upper case.
If 'lower', field names are converted to lower case.
unpack : bool, optional
If True, the returned array is transposed, so that arguments may be
unpacked using ``x, y, z = genfromtxt(...)``. When used with a
structured data-type, arrays are returned for each field.
Default is False.
usemask : bool, optional
If True, return a masked array.
If False, return a regular array.
loose : bool, optional
If True, do not raise errors for invalid values.
invalid_raise : bool, optional
If True, an exception is raised if an inconsistency is detected in the
number of columns.
If False, a warning is emitted and the offending lines are skipped.
max_rows : int, optional
The maximum number of rows to read. Must not be used with skip_footer
at the same time. If given, the value must be at least 1. Default is
to read the entire file.
.. versionadded:: 1.10.0
encoding : str, optional
Encoding used to decode the inputfile. Does not apply when `fname` is
a file object. The special value 'bytes' enables backward compatibility
workarounds that ensure that you receive byte arrays when possible
and passes latin1 encoded strings to converters. Override this value to
receive unicode arrays and pass strings as input to converters. If set
to None the system default is used. The default value is 'bytes'.
.. versionadded:: 1.14.0
${ARRAY_FUNCTION_LIKE}
.. versionadded:: 1.20.0
Returns
-------
out : ndarray
Data read from the text file. If `usemask` is True, this is a
masked array.
See Also
--------
numpy.loadtxt : equivalent function when no data is missing.
Notes
-----
* When spaces are used as delimiters, or when no delimiter has been given
as input, there should not be any missing data between two fields.
* When the variables are named (either by a flexible dtype or with `names`),
there must not be any header in the file (else a ValueError
exception is raised).
* Individual values are not stripped of spaces by default.
When using a custom converter, make sure the function does remove spaces.
References
----------
.. [1] NumPy User Guide, section `I/O with NumPy
<https://docs.scipy.org/doc/numpy/user/basics.io.genfromtxt.html>`_.
Examples
--------
>>> from io import StringIO
>>> import numpy as np
Comma delimited file with mixed dtype
>>> s = StringIO(u"1,1.3,abcde")
>>> data = np.genfromtxt(s, dtype=[('myint','i8'),('myfloat','f8'),
... ('mystring','S5')], delimiter=",")
>>> data
array((1, 1.3, b'abcde'),
dtype=[('myint', '<i8'), ('myfloat', '<f8'), ('mystring', 'S5')])
Using dtype = None
>>> _ = s.seek(0) # needed for StringIO example only
>>> data = np.genfromtxt(s, dtype=None,
... names = ['myint','myfloat','mystring'], delimiter=",")
>>> data
array((1, 1.3, b'abcde'),
dtype=[('myint', '<i8'), ('myfloat', '<f8'), ('mystring', 'S5')])
Specifying dtype and names
>>> _ = s.seek(0)
>>> data = np.genfromtxt(s, dtype="i8,f8,S5",
... names=['myint','myfloat','mystring'], delimiter=",")
>>> data
array((1, 1.3, b'abcde'),
dtype=[('myint', '<i8'), ('myfloat', '<f8'), ('mystring', 'S5')])
An example with fixed-width columns
>>> s = StringIO(u"11.3abcde")
>>> data = np.genfromtxt(s, dtype=None, names=['intvar','fltvar','strvar'],
... delimiter=[1,3,5])
>>> data
array((1, 1.3, b'abcde'),
dtype=[('intvar', '<i8'), ('fltvar', '<f8'), ('strvar', 'S5')])
An example to show comments
>>> f = StringIO('''
... text,# of chars
... hello world,11
... numpy,5''')
>>> np.genfromtxt(f, dtype='S12,S12', delimiter=',')
array([(b'text', b''), (b'hello world', b'11'), (b'numpy', b'5')],
dtype=[('f0', 'S12'), ('f1', 'S12')])
"""
if like is not None:
return _genfromtxt_with_like(
fname, dtype=dtype, comments=comments, delimiter=delimiter,
skip_header=skip_header, skip_footer=skip_footer,
converters=converters, missing_values=missing_values,
filling_values=filling_values, usecols=usecols, names=names,
excludelist=excludelist, deletechars=deletechars,
replace_space=replace_space, autostrip=autostrip,
case_sensitive=case_sensitive, defaultfmt=defaultfmt,
unpack=unpack, usemask=usemask, loose=loose,
invalid_raise=invalid_raise, max_rows=max_rows, encoding=encoding,
like=like
)
if max_rows is not None:
if skip_footer:
raise ValueError(
"The keywords 'skip_footer' and 'max_rows' can not be "
"specified at the same time.")
if max_rows < 1:
raise ValueError("'max_rows' must be at least 1.")
if usemask:
from numpy.ma import MaskedArray, make_mask_descr
# Check the input dictionary of converters
user_converters = converters or {}
if not isinstance(user_converters, dict):
raise TypeError(
"The input argument 'converter' should be a valid dictionary "
"(got '%s' instead)" % type(user_converters))
if encoding == 'bytes':
encoding = None
byte_converters = True
else:
byte_converters = False
# Initialize the filehandle, the LineSplitter and the NameValidator
try:
if isinstance(fname, os_PathLike):
fname = os_fspath(fname)
if isinstance(fname, str):
fid = np.lib._datasource.open(fname, 'rt', encoding=encoding)
fid_ctx = contextlib.closing(fid)
else:
fid = fname
fid_ctx = contextlib.nullcontext(fid)
fhd = iter(fid)
except TypeError as e:
raise TypeError(
"fname must be a string, filehandle, list of strings, "
"or generator. Got %s instead." % type(fname)) from e
with fid_ctx:
split_line = LineSplitter(delimiter=delimiter, comments=comments,
autostrip=autostrip, encoding=encoding)
validate_names = NameValidator(excludelist=excludelist,
deletechars=deletechars,
case_sensitive=case_sensitive,
replace_space=replace_space)
# Skip the first `skip_header` rows
try:
for i in range(skip_header):
next(fhd)
# Keep on until we find the first valid values
first_values = None
while not first_values:
first_line = _decode_line(next(fhd), encoding)
if (names is True) and (comments is not None):
if comments in first_line:
first_line = (
''.join(first_line.split(comments)[1:]))
first_values = split_line(first_line)
except StopIteration:
# return an empty array if the datafile is empty
first_line = ''
first_values = []
warnings.warn('genfromtxt: Empty input file: "%s"' % fname, stacklevel=2)
# Should we take the first values as names ?
if names is True:
fval = first_values[0].strip()
if comments is not None:
if fval in comments:
del first_values[0]
# Check the columns to use: make sure `usecols` is a list
if usecols is not None:
try:
usecols = [_.strip() for _ in usecols.split(",")]
except AttributeError:
try:
usecols = list(usecols)
except TypeError:
usecols = [usecols, ]
nbcols = len(usecols or first_values)
# Check the names and overwrite the dtype.names if needed
if names is True:
names = validate_names([str(_.strip()) for _ in first_values])
first_line = ''
elif _is_string_like(names):
names = validate_names([_.strip() for _ in names.split(',')])
elif names:
names = validate_names(names)
# Get the dtype
if dtype is not None:
dtype = easy_dtype(dtype, defaultfmt=defaultfmt, names=names,
excludelist=excludelist,
deletechars=deletechars,
case_sensitive=case_sensitive,
replace_space=replace_space)
# Make sure the names is a list (for 2.5)
if names is not None:
names = list(names)
if usecols:
for (i, current) in enumerate(usecols):
# if usecols is a list of names, convert to a list of indices
if _is_string_like(current):
usecols[i] = names.index(current)
elif current < 0:
usecols[i] = current + len(first_values)
# If the dtype is not None, make sure we update it
if (dtype is not None) and (len(dtype) > nbcols):
descr = dtype.descr
dtype = np.dtype([descr[_] for _ in usecols])
names = list(dtype.names)
# If `names` is not None, update the names
elif (names is not None) and (len(names) > nbcols):
names = [names[_] for _ in usecols]
elif (names is not None) and (dtype is not None):
names = list(dtype.names)
# Process the missing values ...............................
# Rename missing_values for convenience
user_missing_values = missing_values or ()
if isinstance(user_missing_values, bytes):
user_missing_values = user_missing_values.decode('latin1')
# Define the list of missing_values (one column: one list)
missing_values = [list(['']) for _ in range(nbcols)]
# We have a dictionary: process it field by field
if isinstance(user_missing_values, dict):
# Loop on the items
for (key, val) in user_missing_values.items():
# Is the key a string ?
if _is_string_like(key):
try:
# Transform it into an integer
key = names.index(key)
except ValueError:
# We couldn't find it: the name must have been dropped
continue
# Redefine the key as needed if it's a column number
if usecols:
try:
key = usecols.index(key)
except ValueError:
pass
# Transform the value as a list of string
if isinstance(val, (list, tuple)):
val = [str(_) for _ in val]
else:
val = [str(val), ]
# Add the value(s) to the current list of missing
if key is None:
# None acts as default
for miss in missing_values:
miss.extend(val)
else:
missing_values[key].extend(val)
# We have a sequence : each item matches a column
elif isinstance(user_missing_values, (list, tuple)):
for (value, entry) in zip(user_missing_values, missing_values):
value = str(value)
if value not in entry:
entry.append(value)
# We have a string : apply it to all entries
elif isinstance(user_missing_values, str):
user_value = user_missing_values.split(",")
for entry in missing_values:
entry.extend(user_value)
# We have something else: apply it to all entries
else:
for entry in missing_values:
entry.extend([str(user_missing_values)])
# Process the filling_values ...............................
# Rename the input for convenience
user_filling_values = filling_values
if user_filling_values is None:
user_filling_values = []
# Define the default
filling_values = [None] * nbcols
# We have a dictionary : update each entry individually
if isinstance(user_filling_values, dict):
for (key, val) in user_filling_values.items():
if _is_string_like(key):
try:
# Transform it into an integer
key = names.index(key)
except ValueError:
# We couldn't find it: the name must have been dropped,
continue
# Redefine the key if it's a column number and usecols is defined
if usecols:
try:
key = usecols.index(key)
except ValueError:
pass
# Add the value to the list
filling_values[key] = val
# We have a sequence : update on a one-to-one basis
elif isinstance(user_filling_values, (list, tuple)):
n = len(user_filling_values)
if (n <= nbcols):
filling_values[:n] = user_filling_values
else:
filling_values = user_filling_values[:nbcols]
# We have something else : use it for all entries
else:
filling_values = [user_filling_values] * nbcols
# Initialize the converters ................................
if dtype is None:
# Note: we can't use a [...]*nbcols, as we would have 3 times the same
# ... converter, instead of 3 different converters.
converters = [StringConverter(None, missing_values=miss, default=fill)
for (miss, fill) in zip(missing_values, filling_values)]
else:
dtype_flat = flatten_dtype(dtype, flatten_base=True)
# Initialize the converters
if len(dtype_flat) > 1:
# Flexible type : get a converter from each dtype
zipit = zip(dtype_flat, missing_values, filling_values)
converters = [StringConverter(dt, locked=True,
missing_values=miss, default=fill)
for (dt, miss, fill) in zipit]
else:
# Set to a default converter (but w/ different missing values)
zipit = zip(missing_values, filling_values)
converters = [StringConverter(dtype, locked=True,
missing_values=miss, default=fill)
for (miss, fill) in zipit]
# Update the converters to use the user-defined ones
uc_update = []
for (j, conv) in user_converters.items():
# If the converter is specified by column names, use the index instead
if _is_string_like(j):
try:
j = names.index(j)
i = j
except ValueError:
continue
elif usecols:
try:
i = usecols.index(j)
except ValueError:
# Unused converter specified
continue
else:
i = j
# Find the value to test - first_line is not filtered by usecols:
if len(first_line):
testing_value = first_values[j]
else:
testing_value = None
if conv is bytes:
user_conv = asbytes
elif byte_converters:
# converters may use decode to workaround numpy's old behaviour,
# so encode the string again before passing to the user converter
def tobytes_first(x, conv):
if type(x) is bytes:
return conv(x)
return conv(x.encode("latin1"))
user_conv = functools.partial(tobytes_first, conv=conv)
else:
user_conv = conv
converters[i].update(user_conv, locked=True,
testing_value=testing_value,
default=filling_values[i],
missing_values=missing_values[i],)
uc_update.append((i, user_conv))
# Make sure we have the corrected keys in user_converters...
user_converters.update(uc_update)
# Fixme: possible error as following variable never used.
# miss_chars = [_.missing_values for _ in converters]
# Initialize the output lists ...
# ... rows
rows = []
append_to_rows = rows.append
# ... masks
if usemask:
masks = []
append_to_masks = masks.append
# ... invalid
invalid = []
append_to_invalid = invalid.append
# Parse each line
for (i, line) in enumerate(itertools.chain([first_line, ], fhd)):
values = split_line(line)
nbvalues = len(values)
# Skip an empty line
if nbvalues == 0:
continue
if usecols:
# Select only the columns we need
try:
values = [values[_] for _ in usecols]
except IndexError:
append_to_invalid((i + skip_header + 1, nbvalues))
continue
elif nbvalues != nbcols:
append_to_invalid((i + skip_header + 1, nbvalues))
continue
# Store the values
append_to_rows(tuple(values))
if usemask:
append_to_masks(tuple([v.strip() in m
for (v, m) in zip(values,
missing_values)]))
if len(rows) == max_rows:
break
# Upgrade the converters (if needed)
if dtype is None:
for (i, converter) in enumerate(converters):
current_column = [itemgetter(i)(_m) for _m in rows]
try:
converter.iterupgrade(current_column)
except ConverterLockError:
errmsg = "Converter #%i is locked and cannot be upgraded: " % i
current_column = map(itemgetter(i), rows)
for (j, value) in enumerate(current_column):
try:
converter.upgrade(value)
except (ConverterError, ValueError):
errmsg += "(occurred line #%i for value '%s')"
errmsg %= (j + 1 + skip_header, value)
raise ConverterError(errmsg)
# Check that we don't have invalid values
nbinvalid = len(invalid)
if nbinvalid > 0:
nbrows = len(rows) + nbinvalid - skip_footer
# Construct the error message
template = " Line #%%i (got %%i columns instead of %i)" % nbcols
if skip_footer > 0:
nbinvalid_skipped = len([_ for _ in invalid
if _[0] > nbrows + skip_header])
invalid = invalid[:nbinvalid - nbinvalid_skipped]
skip_footer -= nbinvalid_skipped
#
# nbrows -= skip_footer
# errmsg = [template % (i, nb)
# for (i, nb) in invalid if i < nbrows]
# else:
errmsg = [template % (i, nb)
for (i, nb) in invalid]
if len(errmsg):
errmsg.insert(0, "Some errors were detected !")
errmsg = "\n".join(errmsg)
# Raise an exception ?
if invalid_raise:
raise ValueError(errmsg)
# Issue a warning ?
else:
warnings.warn(errmsg, ConversionWarning, stacklevel=2)
# Strip the last skip_footer data
if skip_footer > 0:
rows = rows[:-skip_footer]
if usemask:
masks = masks[:-skip_footer]
# Convert each value according to the converter:
# We want to modify the list in place to avoid creating a new one...
if loose:
rows = list(
zip(*[[conv._loose_call(_r) for _r in map(itemgetter(i), rows)]
for (i, conv) in enumerate(converters)]))
else:
rows = list(
zip(*[[conv._strict_call(_r) for _r in map(itemgetter(i), rows)]
for (i, conv) in enumerate(converters)]))
# Reset the dtype
data = rows
if dtype is None:
# Get the dtypes from the types of the converters
column_types = [conv.type for conv in converters]
# Find the columns with strings...
strcolidx = [i for (i, v) in enumerate(column_types)
if v == np.unicode_]
if byte_converters and strcolidx:
# convert strings back to bytes for backward compatibility
warnings.warn(
"Reading unicode strings without specifying the encoding "
"argument is deprecated. Set the encoding, use None for the "
"system default.",
np.VisibleDeprecationWarning, stacklevel=2)
def encode_unicode_cols(row_tup):
row = list(row_tup)
for i in strcolidx:
row[i] = row[i].encode('latin1')
return tuple(row)
try:
data = [encode_unicode_cols(r) for r in data]
except UnicodeEncodeError:
pass
else:
for i in strcolidx:
column_types[i] = np.bytes_
# Update string types to be the right length
sized_column_types = column_types[:]
for i, col_type in enumerate(column_types):
if np.issubdtype(col_type, np.character):
n_chars = max(len(row[i]) for row in data)
sized_column_types[i] = (col_type, n_chars)
if names is None:
# If the dtype is uniform (before sizing strings)
base = {
c_type
for c, c_type in zip(converters, column_types)
if c._checked}
if len(base) == 1:
uniform_type, = base
(ddtype, mdtype) = (uniform_type, bool)
else:
ddtype = [(defaultfmt % i, dt)
for (i, dt) in enumerate(sized_column_types)]
if usemask:
mdtype = [(defaultfmt % i, bool)
for (i, dt) in enumerate(sized_column_types)]
else:
ddtype = list(zip(names, sized_column_types))
mdtype = list(zip(names, [bool] * len(sized_column_types)))
output = np.array(data, dtype=ddtype)
if usemask:
outputmask = np.array(masks, dtype=mdtype)
else:
# Overwrite the initial dtype names if needed
if names and dtype.names is not None:
dtype.names = names
# Case 1. We have a structured type
if len(dtype_flat) > 1:
# Nested dtype, eg [('a', int), ('b', [('b0', int), ('b1', 'f4')])]
# First, create the array using a flattened dtype:
# [('a', int), ('b1', int), ('b2', float)]
# Then, view the array using the specified dtype.
if 'O' in (_.char for _ in dtype_flat):
if has_nested_fields(dtype):
raise NotImplementedError(
"Nested fields involving objects are not supported...")
else:
output = np.array(data, dtype=dtype)
else:
rows = np.array(data, dtype=[('', _) for _ in dtype_flat])
output = rows.view(dtype)
# Now, process the rowmasks the same way
if usemask:
rowmasks = np.array(
masks, dtype=np.dtype([('', bool) for t in dtype_flat]))
# Construct the new dtype
mdtype = make_mask_descr(dtype)
outputmask = rowmasks.view(mdtype)
# Case #2. We have a basic dtype
else:
# We used some user-defined converters
if user_converters:
ishomogeneous = True
descr = []
for i, ttype in enumerate([conv.type for conv in converters]):
# Keep the dtype of the current converter
if i in user_converters:
ishomogeneous &= (ttype == dtype.type)
if np.issubdtype(ttype, np.character):
ttype = (ttype, max(len(row[i]) for row in data))
descr.append(('', ttype))
else:
descr.append(('', dtype))
# So we changed the dtype ?
if not ishomogeneous:
# We have more than one field
if len(descr) > 1:
dtype = np.dtype(descr)
# We have only one field: drop the name if not needed.
else:
dtype = np.dtype(ttype)
#
output = np.array(data, dtype)
if usemask:
if dtype.names is not None:
mdtype = [(_, bool) for _ in dtype.names]
else:
mdtype = bool
outputmask = np.array(masks, dtype=mdtype)
# Try to take care of the missing data we missed
names = output.dtype.names
if usemask and names:
for (name, conv) in zip(names, converters):
missing_values = [conv(_) for _ in conv.missing_values
if _ != '']
for mval in missing_values:
outputmask[name] |= (output[name] == mval)
# Construct the final array
if usemask:
output = output.view(MaskedArray)
output._mask = outputmask
output = np.squeeze(output)
if unpack:
if names is None:
return output.T
elif len(names) == 1:
# squeeze single-name dtypes too
return output[names[0]]
else:
# For structured arrays with multiple fields,
# return an array for each field.
return [output[field] for field in names]
return output
_genfromtxt_with_like = array_function_dispatch(
_genfromtxt_dispatcher
)(genfromtxt)
def ndfromtxt(fname, **kwargs):
"""
Load ASCII data stored in a file and return it as a single array.
.. deprecated:: 1.17
ndfromtxt` is a deprecated alias of `genfromtxt` which
overwrites the ``usemask`` argument with `False` even when
explicitly called as ``ndfromtxt(..., usemask=True)``.
Use `genfromtxt` instead.
Parameters
----------
fname, kwargs : For a description of input parameters, see `genfromtxt`.
See Also
--------
numpy.genfromtxt : generic function.
"""
kwargs['usemask'] = False
# Numpy 1.17
warnings.warn(
"np.ndfromtxt is a deprecated alias of np.genfromtxt, "
"prefer the latter.",
DeprecationWarning, stacklevel=2)
return genfromtxt(fname, **kwargs)
def mafromtxt(fname, **kwargs):
"""
Load ASCII data stored in a text file and return a masked array.
.. deprecated:: 1.17
np.mafromtxt is a deprecated alias of `genfromtxt` which
overwrites the ``usemask`` argument with `True` even when
explicitly called as ``mafromtxt(..., usemask=False)``.
Use `genfromtxt` instead.
Parameters
----------
fname, kwargs : For a description of input parameters, see `genfromtxt`.
See Also
--------
numpy.genfromtxt : generic function to load ASCII data.
"""
kwargs['usemask'] = True
# Numpy 1.17
warnings.warn(
"np.mafromtxt is a deprecated alias of np.genfromtxt, "
"prefer the latter.",
DeprecationWarning, stacklevel=2)
return genfromtxt(fname, **kwargs)
def recfromtxt(fname, **kwargs):
"""
Load ASCII data from a file and return it in a record array.
If ``usemask=False`` a standard `recarray` is returned,
if ``usemask=True`` a MaskedRecords array is returned.
Parameters
----------
fname, kwargs : For a description of input parameters, see `genfromtxt`.
See Also
--------
numpy.genfromtxt : generic function
Notes
-----
By default, `dtype` is None, which means that the data-type of the output
array will be determined from the data.
"""
kwargs.setdefault("dtype", None)
usemask = kwargs.get('usemask', False)
output = genfromtxt(fname, **kwargs)
if usemask:
from numpy.ma.mrecords import MaskedRecords
output = output.view(MaskedRecords)
else:
output = output.view(np.recarray)
return output
def recfromcsv(fname, **kwargs):
"""
Load ASCII data stored in a comma-separated file.
The returned array is a record array (if ``usemask=False``, see
`recarray`) or a masked record array (if ``usemask=True``,
see `ma.mrecords.MaskedRecords`).
Parameters
----------
fname, kwargs : For a description of input parameters, see `genfromtxt`.
See Also
--------
numpy.genfromtxt : generic function to load ASCII data.
Notes
-----
By default, `dtype` is None, which means that the data-type of the output
array will be determined from the data.
"""
# Set default kwargs for genfromtxt as relevant to csv import.
kwargs.setdefault("case_sensitive", "lower")
kwargs.setdefault("names", True)
kwargs.setdefault("delimiter", ",")
kwargs.setdefault("dtype", None)
output = genfromtxt(fname, **kwargs)
usemask = kwargs.get("usemask", False)
if usemask:
from numpy.ma.mrecords import MaskedRecords
output = output.view(MaskedRecords)
else:
output = output.view(np.recarray)
return output
|