File size: 87,157 Bytes
7885a28 |
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 |
"""
Module contains tools for processing files into DataFrames or other objects
GH#48849 provides a convenient way of deprecating keyword arguments
"""
from __future__ import annotations
from collections import (
abc,
defaultdict,
)
import csv
import sys
from textwrap import fill
from typing import (
IO,
TYPE_CHECKING,
Any,
Callable,
Literal,
NamedTuple,
TypedDict,
overload,
)
import warnings
import numpy as np
from pandas._config import using_copy_on_write
from pandas._libs import lib
from pandas._libs.parsers import STR_NA_VALUES
from pandas.errors import (
AbstractMethodError,
ParserWarning,
)
from pandas.util._decorators import Appender
from pandas.util._exceptions import find_stack_level
from pandas.util._validators import check_dtype_backend
from pandas.core.dtypes.common import (
is_file_like,
is_float,
is_hashable,
is_integer,
is_list_like,
pandas_dtype,
)
from pandas import Series
from pandas.core.frame import DataFrame
from pandas.core.indexes.api import RangeIndex
from pandas.core.shared_docs import _shared_docs
from pandas.io.common import (
IOHandles,
get_handle,
stringify_path,
validate_header_arg,
)
from pandas.io.parsers.arrow_parser_wrapper import ArrowParserWrapper
from pandas.io.parsers.base_parser import (
ParserBase,
is_index_col,
parser_defaults,
)
from pandas.io.parsers.c_parser_wrapper import CParserWrapper
from pandas.io.parsers.python_parser import (
FixedWidthFieldParser,
PythonParser,
)
if TYPE_CHECKING:
from collections.abc import (
Hashable,
Iterable,
Mapping,
Sequence,
)
from types import TracebackType
from pandas._typing import (
CompressionOptions,
CSVEngine,
DtypeArg,
DtypeBackend,
FilePath,
IndexLabel,
ReadCsvBuffer,
Self,
StorageOptions,
UsecolsArgType,
)
_doc_read_csv_and_table = (
r"""
{summary}
Also supports optionally iterating or breaking of the file
into chunks.
Additional help can be found in the online docs for
`IO Tools <https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html>`_.
Parameters
----------
filepath_or_buffer : str, path object or file-like object
Any valid string path is acceptable. The string could be a URL. Valid
URL schemes include http, ftp, s3, gs, and file. For file URLs, a host is
expected. A local file could be: file://localhost/path/to/table.csv.
If you want to pass in a path object, pandas accepts any ``os.PathLike``.
By file-like object, we refer to objects with a ``read()`` method, such as
a file handle (e.g. via builtin ``open`` function) or ``StringIO``.
sep : str, default {_default_sep}
Character or regex pattern to treat as the delimiter. If ``sep=None``, the
C engine cannot automatically detect
the separator, but the Python parsing engine can, meaning the latter will
be used and automatically detect the separator from only the first valid
row of the file by Python's builtin sniffer tool, ``csv.Sniffer``.
In addition, separators longer than 1 character and different from
``'\s+'`` will be interpreted as regular expressions and will also force
the use of the Python parsing engine. Note that regex delimiters are prone
to ignoring quoted data. Regex example: ``'\r\t'``.
delimiter : str, optional
Alias for ``sep``.
header : int, Sequence of int, 'infer' or None, default 'infer'
Row number(s) containing column labels and marking the start of the
data (zero-indexed). Default behavior is to infer the column names: if no ``names``
are passed the behavior is identical to ``header=0`` and column
names are inferred from the first line of the file, if column
names are passed explicitly to ``names`` then the behavior is identical to
``header=None``. Explicitly pass ``header=0`` to be able to
replace existing names. The header can be a list of integers that
specify row locations for a :class:`~pandas.MultiIndex` on the columns
e.g. ``[0, 1, 3]``. Intervening rows that are not specified will be
skipped (e.g. 2 in this example is skipped). Note that this
parameter ignores commented lines and empty lines if
``skip_blank_lines=True``, so ``header=0`` denotes the first line of
data rather than the first line of the file.
names : Sequence of Hashable, optional
Sequence of column labels to apply. If the file contains a header row,
then you should explicitly pass ``header=0`` to override the column names.
Duplicates in this list are not allowed.
index_col : Hashable, Sequence of Hashable or False, optional
Column(s) to use as row label(s), denoted either by column labels or column
indices. If a sequence of labels or indices is given, :class:`~pandas.MultiIndex`
will be formed for the row labels.
Note: ``index_col=False`` can be used to force pandas to *not* use the first
column as the index, e.g., when you have a malformed file with delimiters at
the end of each line.
usecols : Sequence of Hashable or Callable, optional
Subset of columns to select, denoted either by column labels or column indices.
If list-like, all elements must either
be positional (i.e. integer indices into the document columns) or strings
that correspond to column names provided either by the user in ``names`` or
inferred from the document header row(s). If ``names`` are given, the document
header row(s) are not taken into account. For example, a valid list-like
``usecols`` parameter would be ``[0, 1, 2]`` or ``['foo', 'bar', 'baz']``.
Element order is ignored, so ``usecols=[0, 1]`` is the same as ``[1, 0]``.
To instantiate a :class:`~pandas.DataFrame` from ``data`` with element order
preserved use ``pd.read_csv(data, usecols=['foo', 'bar'])[['foo', 'bar']]``
for columns in ``['foo', 'bar']`` order or
``pd.read_csv(data, usecols=['foo', 'bar'])[['bar', 'foo']]``
for ``['bar', 'foo']`` order.
If callable, the callable function will be evaluated against the column
names, returning names where the callable function evaluates to ``True``. An
example of a valid callable argument would be ``lambda x: x.upper() in
['AAA', 'BBB', 'DDD']``. Using this parameter results in much faster
parsing time and lower memory usage.
dtype : dtype or dict of {{Hashable : dtype}}, optional
Data type(s) to apply to either the whole dataset or individual columns.
E.g., ``{{'a': np.float64, 'b': np.int32, 'c': 'Int64'}}``
Use ``str`` or ``object`` together with suitable ``na_values`` settings
to preserve and not interpret ``dtype``.
If ``converters`` are specified, they will be applied INSTEAD
of ``dtype`` conversion.
.. versionadded:: 1.5.0
Support for ``defaultdict`` was added. Specify a ``defaultdict`` as input where
the default determines the ``dtype`` of the columns which are not explicitly
listed.
engine : {{'c', 'python', 'pyarrow'}}, optional
Parser engine to use. The C and pyarrow engines are faster, while the python engine
is currently more feature-complete. Multithreading is currently only supported by
the pyarrow engine.
.. versionadded:: 1.4.0
The 'pyarrow' engine was added as an *experimental* engine, and some features
are unsupported, or may not work correctly, with this engine.
converters : dict of {{Hashable : Callable}}, optional
Functions for converting values in specified columns. Keys can either
be column labels or column indices.
true_values : list, optional
Values to consider as ``True`` in addition to case-insensitive variants of 'True'.
false_values : list, optional
Values to consider as ``False`` in addition to case-insensitive variants of 'False'.
skipinitialspace : bool, default False
Skip spaces after delimiter.
skiprows : int, list of int or Callable, optional
Line numbers to skip (0-indexed) or number of lines to skip (``int``)
at the start of the file.
If callable, the callable function will be evaluated against the row
indices, returning ``True`` if the row should be skipped and ``False`` otherwise.
An example of a valid callable argument would be ``lambda x: x in [0, 2]``.
skipfooter : int, default 0
Number of lines at bottom of file to skip (Unsupported with ``engine='c'``).
nrows : int, optional
Number of rows of file to read. Useful for reading pieces of large files.
na_values : Hashable, Iterable of Hashable or dict of {{Hashable : Iterable}}, optional
Additional strings to recognize as ``NA``/``NaN``. If ``dict`` passed, specific
per-column ``NA`` values. By default the following values are interpreted as
``NaN``: " """
+ fill('", "'.join(sorted(STR_NA_VALUES)), 70, subsequent_indent=" ")
+ """ ".
keep_default_na : bool, default True
Whether or not to include the default ``NaN`` values when parsing the data.
Depending on whether ``na_values`` is passed in, the behavior is as follows:
* If ``keep_default_na`` is ``True``, and ``na_values`` are specified, ``na_values``
is appended to the default ``NaN`` values used for parsing.
* If ``keep_default_na`` is ``True``, and ``na_values`` are not specified, only
the default ``NaN`` values are used for parsing.
* If ``keep_default_na`` is ``False``, and ``na_values`` are specified, only
the ``NaN`` values specified ``na_values`` are used for parsing.
* If ``keep_default_na`` is ``False``, and ``na_values`` are not specified, no
strings will be parsed as ``NaN``.
Note that if ``na_filter`` is passed in as ``False``, the ``keep_default_na`` and
``na_values`` parameters will be ignored.
na_filter : bool, default True
Detect missing value markers (empty strings and the value of ``na_values``). In
data without any ``NA`` values, passing ``na_filter=False`` can improve the
performance of reading a large file.
verbose : bool, default False
Indicate number of ``NA`` values placed in non-numeric columns.
.. deprecated:: 2.2.0
skip_blank_lines : bool, default True
If ``True``, skip over blank lines rather than interpreting as ``NaN`` values.
parse_dates : bool, list of Hashable, list of lists or dict of {{Hashable : list}}, \
default False
The behavior is as follows:
* ``bool``. If ``True`` -> try parsing the index. Note: Automatically set to
``True`` if ``date_format`` or ``date_parser`` arguments have been passed.
* ``list`` of ``int`` or names. e.g. If ``[1, 2, 3]`` -> try parsing columns 1, 2, 3
each as a separate date column.
* ``list`` of ``list``. e.g. If ``[[1, 3]]`` -> combine columns 1 and 3 and parse
as a single date column. Values are joined with a space before parsing.
* ``dict``, e.g. ``{{'foo' : [1, 3]}}`` -> parse columns 1, 3 as date and call
result 'foo'. Values are joined with a space before parsing.
If a column or index cannot be represented as an array of ``datetime``,
say because of an unparsable value or a mixture of timezones, the column
or index will be returned unaltered as an ``object`` data type. For
non-standard ``datetime`` parsing, use :func:`~pandas.to_datetime` after
:func:`~pandas.read_csv`.
Note: A fast-path exists for iso8601-formatted dates.
infer_datetime_format : bool, default False
If ``True`` and ``parse_dates`` is enabled, pandas will attempt to infer the
format of the ``datetime`` strings in the columns, and if it can be inferred,
switch to a faster method of parsing them. In some cases this can increase
the parsing speed by 5-10x.
.. deprecated:: 2.0.0
A strict version of this argument is now the default, passing it has no effect.
keep_date_col : bool, default False
If ``True`` and ``parse_dates`` specifies combining multiple columns then
keep the original columns.
date_parser : Callable, optional
Function to use for converting a sequence of string columns to an array of
``datetime`` instances. The default uses ``dateutil.parser.parser`` to do the
conversion. pandas will try to call ``date_parser`` in three different ways,
advancing to the next if an exception occurs: 1) Pass one or more arrays
(as defined by ``parse_dates``) as arguments; 2) concatenate (row-wise) the
string values from the columns defined by ``parse_dates`` into a single array
and pass that; and 3) call ``date_parser`` once for each row using one or
more strings (corresponding to the columns defined by ``parse_dates``) as
arguments.
.. deprecated:: 2.0.0
Use ``date_format`` instead, or read in as ``object`` and then apply
:func:`~pandas.to_datetime` as-needed.
date_format : str or dict of column -> format, optional
Format to use for parsing dates when used in conjunction with ``parse_dates``.
The strftime to parse time, e.g. :const:`"%d/%m/%Y"`. See
`strftime documentation
<https://docs.python.org/3/library/datetime.html
#strftime-and-strptime-behavior>`_ for more information on choices, though
note that :const:`"%f"` will parse all the way up to nanoseconds.
You can also pass:
- "ISO8601", to parse any `ISO8601 <https://en.wikipedia.org/wiki/ISO_8601>`_
time string (not necessarily in exactly the same format);
- "mixed", to infer the format for each element individually. This is risky,
and you should probably use it along with `dayfirst`.
.. versionadded:: 2.0.0
dayfirst : bool, default False
DD/MM format dates, international and European format.
cache_dates : bool, default True
If ``True``, use a cache of unique, converted dates to apply the ``datetime``
conversion. May produce significant speed-up when parsing duplicate
date strings, especially ones with timezone offsets.
iterator : bool, default False
Return ``TextFileReader`` object for iteration or getting chunks with
``get_chunk()``.
chunksize : int, optional
Number of lines to read from the file per chunk. Passing a value will cause the
function to return a ``TextFileReader`` object for iteration.
See the `IO Tools docs
<https://pandas.pydata.org/pandas-docs/stable/io.html#io-chunking>`_
for more information on ``iterator`` and ``chunksize``.
{decompression_options}
.. versionchanged:: 1.4.0 Zstandard support.
thousands : str (length 1), optional
Character acting as the thousands separator in numerical values.
decimal : str (length 1), default '.'
Character to recognize as decimal point (e.g., use ',' for European data).
lineterminator : str (length 1), optional
Character used to denote a line break. Only valid with C parser.
quotechar : str (length 1), optional
Character used to denote the start and end of a quoted item. Quoted
items can include the ``delimiter`` and it will be ignored.
quoting : {{0 or csv.QUOTE_MINIMAL, 1 or csv.QUOTE_ALL, 2 or csv.QUOTE_NONNUMERIC, \
3 or csv.QUOTE_NONE}}, default csv.QUOTE_MINIMAL
Control field quoting behavior per ``csv.QUOTE_*`` constants. Default is
``csv.QUOTE_MINIMAL`` (i.e., 0) which implies that only fields containing special
characters are quoted (e.g., characters defined in ``quotechar``, ``delimiter``,
or ``lineterminator``.
doublequote : bool, default True
When ``quotechar`` is specified and ``quoting`` is not ``QUOTE_NONE``, indicate
whether or not to interpret two consecutive ``quotechar`` elements INSIDE a
field as a single ``quotechar`` element.
escapechar : str (length 1), optional
Character used to escape other characters.
comment : str (length 1), optional
Character indicating that the remainder of line should not be parsed.
If found at the beginning
of a line, the line will be ignored altogether. This parameter must be a
single character. Like empty lines (as long as ``skip_blank_lines=True``),
fully commented lines are ignored by the parameter ``header`` but not by
``skiprows``. For example, if ``comment='#'``, parsing
``#empty\\na,b,c\\n1,2,3`` with ``header=0`` will result in ``'a,b,c'`` being
treated as the header.
encoding : str, optional, default 'utf-8'
Encoding to use for UTF when reading/writing (ex. ``'utf-8'``). `List of Python
standard encodings
<https://docs.python.org/3/library/codecs.html#standard-encodings>`_ .
encoding_errors : str, optional, default 'strict'
How encoding errors are treated. `List of possible values
<https://docs.python.org/3/library/codecs.html#error-handlers>`_ .
.. versionadded:: 1.3.0
dialect : str or csv.Dialect, optional
If provided, this parameter will override values (default or not) for the
following parameters: ``delimiter``, ``doublequote``, ``escapechar``,
``skipinitialspace``, ``quotechar``, and ``quoting``. If it is necessary to
override values, a ``ParserWarning`` will be issued. See ``csv.Dialect``
documentation for more details.
on_bad_lines : {{'error', 'warn', 'skip'}} or Callable, default 'error'
Specifies what to do upon encountering a bad line (a line with too many fields).
Allowed values are :
- ``'error'``, raise an Exception when a bad line is encountered.
- ``'warn'``, raise a warning when a bad line is encountered and skip that line.
- ``'skip'``, skip bad lines without raising or warning when they are encountered.
.. versionadded:: 1.3.0
.. versionadded:: 1.4.0
- Callable, function with signature
``(bad_line: list[str]) -> list[str] | None`` that will process a single
bad line. ``bad_line`` is a list of strings split by the ``sep``.
If the function returns ``None``, the bad line will be ignored.
If the function returns a new ``list`` of strings with more elements than
expected, a ``ParserWarning`` will be emitted while dropping extra elements.
Only supported when ``engine='python'``
.. versionchanged:: 2.2.0
- Callable, function with signature
as described in `pyarrow documentation
<https://arrow.apache.org/docs/python/generated/pyarrow.csv.ParseOptions.html
#pyarrow.csv.ParseOptions.invalid_row_handler>`_ when ``engine='pyarrow'``
delim_whitespace : bool, default False
Specifies whether or not whitespace (e.g. ``' '`` or ``'\\t'``) will be
used as the ``sep`` delimiter. Equivalent to setting ``sep='\\s+'``. If this option
is set to ``True``, nothing should be passed in for the ``delimiter``
parameter.
.. deprecated:: 2.2.0
Use ``sep="\\s+"`` instead.
low_memory : bool, default True
Internally process the file in chunks, resulting in lower memory use
while parsing, but possibly mixed type inference. To ensure no mixed
types either set ``False``, or specify the type with the ``dtype`` parameter.
Note that the entire file is read into a single :class:`~pandas.DataFrame`
regardless, use the ``chunksize`` or ``iterator`` parameter to return the data in
chunks. (Only valid with C parser).
memory_map : bool, default False
If a filepath is provided for ``filepath_or_buffer``, map the file object
directly onto memory and access the data directly from there. Using this
option can improve performance because there is no longer any I/O overhead.
float_precision : {{'high', 'legacy', 'round_trip'}}, optional
Specifies which converter the C engine should use for floating-point
values. The options are ``None`` or ``'high'`` for the ordinary converter,
``'legacy'`` for the original lower precision pandas converter, and
``'round_trip'`` for the round-trip converter.
{storage_options}
dtype_backend : {{'numpy_nullable', 'pyarrow'}}, default 'numpy_nullable'
Back-end data type applied to the resultant :class:`DataFrame`
(still experimental). Behaviour is as follows:
* ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame`
(default).
* ``"pyarrow"``: returns pyarrow-backed nullable :class:`ArrowDtype`
DataFrame.
.. versionadded:: 2.0
Returns
-------
DataFrame or TextFileReader
A comma-separated values (csv) file is returned as two-dimensional
data structure with labeled axes.
See Also
--------
DataFrame.to_csv : Write DataFrame to a comma-separated values (csv) file.
{see_also_func_name} : {see_also_func_summary}
read_fwf : Read a table of fixed-width formatted lines into DataFrame.
Examples
--------
>>> pd.{func_name}('data.csv') # doctest: +SKIP
"""
)
class _C_Parser_Defaults(TypedDict):
delim_whitespace: Literal[False]
na_filter: Literal[True]
low_memory: Literal[True]
memory_map: Literal[False]
float_precision: None
_c_parser_defaults: _C_Parser_Defaults = {
"delim_whitespace": False,
"na_filter": True,
"low_memory": True,
"memory_map": False,
"float_precision": None,
}
class _Fwf_Defaults(TypedDict):
colspecs: Literal["infer"]
infer_nrows: Literal[100]
widths: None
_fwf_defaults: _Fwf_Defaults = {"colspecs": "infer", "infer_nrows": 100, "widths": None}
_c_unsupported = {"skipfooter"}
_python_unsupported = {"low_memory", "float_precision"}
_pyarrow_unsupported = {
"skipfooter",
"float_precision",
"chunksize",
"comment",
"nrows",
"thousands",
"memory_map",
"dialect",
"delim_whitespace",
"quoting",
"lineterminator",
"converters",
"iterator",
"dayfirst",
"verbose",
"skipinitialspace",
"low_memory",
}
class _DeprecationConfig(NamedTuple):
default_value: Any
msg: str | None
@overload
def validate_integer(name: str, val: None, min_val: int = ...) -> None:
...
@overload
def validate_integer(name: str, val: float, min_val: int = ...) -> int:
...
@overload
def validate_integer(name: str, val: int | None, min_val: int = ...) -> int | None:
...
def validate_integer(
name: str, val: int | float | None, min_val: int = 0
) -> int | None:
"""
Checks whether the 'name' parameter for parsing is either
an integer OR float that can SAFELY be cast to an integer
without losing accuracy. Raises a ValueError if that is
not the case.
Parameters
----------
name : str
Parameter name (used for error reporting)
val : int or float
The value to check
min_val : int
Minimum allowed value (val < min_val will result in a ValueError)
"""
if val is None:
return val
msg = f"'{name:s}' must be an integer >={min_val:d}"
if is_float(val):
if int(val) != val:
raise ValueError(msg)
val = int(val)
elif not (is_integer(val) and val >= min_val):
raise ValueError(msg)
return int(val)
def _validate_names(names: Sequence[Hashable] | None) -> None:
"""
Raise ValueError if the `names` parameter contains duplicates or has an
invalid data type.
Parameters
----------
names : array-like or None
An array containing a list of the names used for the output DataFrame.
Raises
------
ValueError
If names are not unique or are not ordered (e.g. set).
"""
if names is not None:
if len(names) != len(set(names)):
raise ValueError("Duplicate names are not allowed.")
if not (
is_list_like(names, allow_sets=False) or isinstance(names, abc.KeysView)
):
raise ValueError("Names should be an ordered collection.")
def _read(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str], kwds
) -> DataFrame | TextFileReader:
"""Generic reader of line files."""
# if we pass a date_parser and parse_dates=False, we should not parse the
# dates GH#44366
if kwds.get("parse_dates", None) is None:
if (
kwds.get("date_parser", lib.no_default) is lib.no_default
and kwds.get("date_format", None) is None
):
kwds["parse_dates"] = False
else:
kwds["parse_dates"] = True
# Extract some of the arguments (pass chunksize on).
iterator = kwds.get("iterator", False)
chunksize = kwds.get("chunksize", None)
if kwds.get("engine") == "pyarrow":
if iterator:
raise ValueError(
"The 'iterator' option is not supported with the 'pyarrow' engine"
)
if chunksize is not None:
raise ValueError(
"The 'chunksize' option is not supported with the 'pyarrow' engine"
)
else:
chunksize = validate_integer("chunksize", chunksize, 1)
nrows = kwds.get("nrows", None)
# Check for duplicates in names.
_validate_names(kwds.get("names", None))
# Create the parser.
parser = TextFileReader(filepath_or_buffer, **kwds)
if chunksize or iterator:
return parser
with parser:
return parser.read(nrows)
# iterator=True -> TextFileReader
@overload
def read_csv(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = ...,
delimiter: str | None | lib.NoDefault = ...,
header: int | Sequence[int] | None | Literal["infer"] = ...,
names: Sequence[Hashable] | None | lib.NoDefault = ...,
index_col: IndexLabel | Literal[False] | None = ...,
usecols: UsecolsArgType = ...,
dtype: DtypeArg | None = ...,
engine: CSVEngine | None = ...,
converters: Mapping[Hashable, Callable] | None = ...,
true_values: list | None = ...,
false_values: list | None = ...,
skipinitialspace: bool = ...,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = ...,
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Hashable
| Iterable[Hashable]
| Mapping[Hashable, Iterable[Hashable]]
| None = ...,
na_filter: bool = ...,
verbose: bool | lib.NoDefault = ...,
skip_blank_lines: bool = ...,
parse_dates: bool | Sequence[Hashable] | None = ...,
infer_datetime_format: bool | lib.NoDefault = ...,
keep_date_col: bool | lib.NoDefault = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: str | dict[Hashable, str] | None = ...,
dayfirst: bool = ...,
cache_dates: bool = ...,
iterator: Literal[True],
chunksize: int | None = ...,
compression: CompressionOptions = ...,
thousands: str | None = ...,
decimal: str = ...,
lineterminator: str | None = ...,
quotechar: str = ...,
quoting: int = ...,
doublequote: bool = ...,
escapechar: str | None = ...,
comment: str | None = ...,
encoding: str | None = ...,
encoding_errors: str | None = ...,
dialect: str | csv.Dialect | None = ...,
on_bad_lines=...,
delim_whitespace: bool | lib.NoDefault = ...,
low_memory: bool = ...,
memory_map: bool = ...,
float_precision: Literal["high", "legacy"] | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> TextFileReader:
...
# chunksize=int -> TextFileReader
@overload
def read_csv(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = ...,
delimiter: str | None | lib.NoDefault = ...,
header: int | Sequence[int] | None | Literal["infer"] = ...,
names: Sequence[Hashable] | None | lib.NoDefault = ...,
index_col: IndexLabel | Literal[False] | None = ...,
usecols: UsecolsArgType = ...,
dtype: DtypeArg | None = ...,
engine: CSVEngine | None = ...,
converters: Mapping[Hashable, Callable] | None = ...,
true_values: list | None = ...,
false_values: list | None = ...,
skipinitialspace: bool = ...,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = ...,
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Hashable
| Iterable[Hashable]
| Mapping[Hashable, Iterable[Hashable]]
| None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool | lib.NoDefault = ...,
skip_blank_lines: bool = ...,
parse_dates: bool | Sequence[Hashable] | None = ...,
infer_datetime_format: bool | lib.NoDefault = ...,
keep_date_col: bool | lib.NoDefault = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: str | dict[Hashable, str] | None = ...,
dayfirst: bool = ...,
cache_dates: bool = ...,
iterator: bool = ...,
chunksize: int,
compression: CompressionOptions = ...,
thousands: str | None = ...,
decimal: str = ...,
lineterminator: str | None = ...,
quotechar: str = ...,
quoting: int = ...,
doublequote: bool = ...,
escapechar: str | None = ...,
comment: str | None = ...,
encoding: str | None = ...,
encoding_errors: str | None = ...,
dialect: str | csv.Dialect | None = ...,
on_bad_lines=...,
delim_whitespace: bool | lib.NoDefault = ...,
low_memory: bool = ...,
memory_map: bool = ...,
float_precision: Literal["high", "legacy"] | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> TextFileReader:
...
# default case -> DataFrame
@overload
def read_csv(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = ...,
delimiter: str | None | lib.NoDefault = ...,
header: int | Sequence[int] | None | Literal["infer"] = ...,
names: Sequence[Hashable] | None | lib.NoDefault = ...,
index_col: IndexLabel | Literal[False] | None = ...,
usecols: UsecolsArgType = ...,
dtype: DtypeArg | None = ...,
engine: CSVEngine | None = ...,
converters: Mapping[Hashable, Callable] | None = ...,
true_values: list | None = ...,
false_values: list | None = ...,
skipinitialspace: bool = ...,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = ...,
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Hashable
| Iterable[Hashable]
| Mapping[Hashable, Iterable[Hashable]]
| None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool | lib.NoDefault = ...,
skip_blank_lines: bool = ...,
parse_dates: bool | Sequence[Hashable] | None = ...,
infer_datetime_format: bool | lib.NoDefault = ...,
keep_date_col: bool | lib.NoDefault = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: str | dict[Hashable, str] | None = ...,
dayfirst: bool = ...,
cache_dates: bool = ...,
iterator: Literal[False] = ...,
chunksize: None = ...,
compression: CompressionOptions = ...,
thousands: str | None = ...,
decimal: str = ...,
lineterminator: str | None = ...,
quotechar: str = ...,
quoting: int = ...,
doublequote: bool = ...,
escapechar: str | None = ...,
comment: str | None = ...,
encoding: str | None = ...,
encoding_errors: str | None = ...,
dialect: str | csv.Dialect | None = ...,
on_bad_lines=...,
delim_whitespace: bool | lib.NoDefault = ...,
low_memory: bool = ...,
memory_map: bool = ...,
float_precision: Literal["high", "legacy"] | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> DataFrame:
...
# Unions -> DataFrame | TextFileReader
@overload
def read_csv(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = ...,
delimiter: str | None | lib.NoDefault = ...,
header: int | Sequence[int] | None | Literal["infer"] = ...,
names: Sequence[Hashable] | None | lib.NoDefault = ...,
index_col: IndexLabel | Literal[False] | None = ...,
usecols: UsecolsArgType = ...,
dtype: DtypeArg | None = ...,
engine: CSVEngine | None = ...,
converters: Mapping[Hashable, Callable] | None = ...,
true_values: list | None = ...,
false_values: list | None = ...,
skipinitialspace: bool = ...,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = ...,
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Hashable
| Iterable[Hashable]
| Mapping[Hashable, Iterable[Hashable]]
| None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool | lib.NoDefault = ...,
skip_blank_lines: bool = ...,
parse_dates: bool | Sequence[Hashable] | None = ...,
infer_datetime_format: bool | lib.NoDefault = ...,
keep_date_col: bool | lib.NoDefault = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: str | dict[Hashable, str] | None = ...,
dayfirst: bool = ...,
cache_dates: bool = ...,
iterator: bool = ...,
chunksize: int | None = ...,
compression: CompressionOptions = ...,
thousands: str | None = ...,
decimal: str = ...,
lineterminator: str | None = ...,
quotechar: str = ...,
quoting: int = ...,
doublequote: bool = ...,
escapechar: str | None = ...,
comment: str | None = ...,
encoding: str | None = ...,
encoding_errors: str | None = ...,
dialect: str | csv.Dialect | None = ...,
on_bad_lines=...,
delim_whitespace: bool | lib.NoDefault = ...,
low_memory: bool = ...,
memory_map: bool = ...,
float_precision: Literal["high", "legacy"] | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> DataFrame | TextFileReader:
...
@Appender(
_doc_read_csv_and_table.format(
func_name="read_csv",
summary="Read a comma-separated values (csv) file into DataFrame.",
see_also_func_name="read_table",
see_also_func_summary="Read general delimited file into DataFrame.",
_default_sep="','",
storage_options=_shared_docs["storage_options"],
decompression_options=_shared_docs["decompression_options"]
% "filepath_or_buffer",
)
)
def read_csv(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = lib.no_default,
delimiter: str | None | lib.NoDefault = None,
# Column and Index Locations and Names
header: int | Sequence[int] | None | Literal["infer"] = "infer",
names: Sequence[Hashable] | None | lib.NoDefault = lib.no_default,
index_col: IndexLabel | Literal[False] | None = None,
usecols: UsecolsArgType = None,
# General Parsing Configuration
dtype: DtypeArg | None = None,
engine: CSVEngine | None = None,
converters: Mapping[Hashable, Callable] | None = None,
true_values: list | None = None,
false_values: list | None = None,
skipinitialspace: bool = False,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = None,
skipfooter: int = 0,
nrows: int | None = None,
# NA and Missing Data Handling
na_values: Hashable
| Iterable[Hashable]
| Mapping[Hashable, Iterable[Hashable]]
| None = None,
keep_default_na: bool = True,
na_filter: bool = True,
verbose: bool | lib.NoDefault = lib.no_default,
skip_blank_lines: bool = True,
# Datetime Handling
parse_dates: bool | Sequence[Hashable] | None = None,
infer_datetime_format: bool | lib.NoDefault = lib.no_default,
keep_date_col: bool | lib.NoDefault = lib.no_default,
date_parser: Callable | lib.NoDefault = lib.no_default,
date_format: str | dict[Hashable, str] | None = None,
dayfirst: bool = False,
cache_dates: bool = True,
# Iteration
iterator: bool = False,
chunksize: int | None = None,
# Quoting, Compression, and File Format
compression: CompressionOptions = "infer",
thousands: str | None = None,
decimal: str = ".",
lineterminator: str | None = None,
quotechar: str = '"',
quoting: int = csv.QUOTE_MINIMAL,
doublequote: bool = True,
escapechar: str | None = None,
comment: str | None = None,
encoding: str | None = None,
encoding_errors: str | None = "strict",
dialect: str | csv.Dialect | None = None,
# Error Handling
on_bad_lines: str = "error",
# Internal
delim_whitespace: bool | lib.NoDefault = lib.no_default,
low_memory: bool = _c_parser_defaults["low_memory"],
memory_map: bool = False,
float_precision: Literal["high", "legacy"] | None = None,
storage_options: StorageOptions | None = None,
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
) -> DataFrame | TextFileReader:
if keep_date_col is not lib.no_default:
# GH#55569
warnings.warn(
"The 'keep_date_col' keyword in pd.read_csv is deprecated and "
"will be removed in a future version. Explicitly remove unwanted "
"columns after parsing instead.",
FutureWarning,
stacklevel=find_stack_level(),
)
else:
keep_date_col = False
if lib.is_list_like(parse_dates):
# GH#55569
depr = False
# error: Item "bool" of "bool | Sequence[Hashable] | None" has no
# attribute "__iter__" (not iterable)
if not all(is_hashable(x) for x in parse_dates): # type: ignore[union-attr]
depr = True
elif isinstance(parse_dates, dict) and any(
lib.is_list_like(x) for x in parse_dates.values()
):
depr = True
if depr:
warnings.warn(
"Support for nested sequences for 'parse_dates' in pd.read_csv "
"is deprecated. Combine the desired columns with pd.to_datetime "
"after parsing instead.",
FutureWarning,
stacklevel=find_stack_level(),
)
if infer_datetime_format is not lib.no_default:
warnings.warn(
"The argument 'infer_datetime_format' is deprecated and will "
"be removed in a future version. "
"A strict version of it is now the default, see "
"https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. "
"You can safely remove this argument.",
FutureWarning,
stacklevel=find_stack_level(),
)
if delim_whitespace is not lib.no_default:
# GH#55569
warnings.warn(
"The 'delim_whitespace' keyword in pd.read_csv is deprecated and "
"will be removed in a future version. Use ``sep='\\s+'`` instead",
FutureWarning,
stacklevel=find_stack_level(),
)
else:
delim_whitespace = False
if verbose is not lib.no_default:
# GH#55569
warnings.warn(
"The 'verbose' keyword in pd.read_csv is deprecated and "
"will be removed in a future version.",
FutureWarning,
stacklevel=find_stack_level(),
)
else:
verbose = False
# locals() should never be modified
kwds = locals().copy()
del kwds["filepath_or_buffer"]
del kwds["sep"]
kwds_defaults = _refine_defaults_read(
dialect,
delimiter,
delim_whitespace,
engine,
sep,
on_bad_lines,
names,
defaults={"delimiter": ","},
dtype_backend=dtype_backend,
)
kwds.update(kwds_defaults)
return _read(filepath_or_buffer, kwds)
# iterator=True -> TextFileReader
@overload
def read_table(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = ...,
delimiter: str | None | lib.NoDefault = ...,
header: int | Sequence[int] | None | Literal["infer"] = ...,
names: Sequence[Hashable] | None | lib.NoDefault = ...,
index_col: IndexLabel | Literal[False] | None = ...,
usecols: UsecolsArgType = ...,
dtype: DtypeArg | None = ...,
engine: CSVEngine | None = ...,
converters: Mapping[Hashable, Callable] | None = ...,
true_values: list | None = ...,
false_values: list | None = ...,
skipinitialspace: bool = ...,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = ...,
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool | lib.NoDefault = ...,
skip_blank_lines: bool = ...,
parse_dates: bool | Sequence[Hashable] = ...,
infer_datetime_format: bool | lib.NoDefault = ...,
keep_date_col: bool | lib.NoDefault = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: str | dict[Hashable, str] | None = ...,
dayfirst: bool = ...,
cache_dates: bool = ...,
iterator: Literal[True],
chunksize: int | None = ...,
compression: CompressionOptions = ...,
thousands: str | None = ...,
decimal: str = ...,
lineterminator: str | None = ...,
quotechar: str = ...,
quoting: int = ...,
doublequote: bool = ...,
escapechar: str | None = ...,
comment: str | None = ...,
encoding: str | None = ...,
encoding_errors: str | None = ...,
dialect: str | csv.Dialect | None = ...,
on_bad_lines=...,
delim_whitespace: bool = ...,
low_memory: bool = ...,
memory_map: bool = ...,
float_precision: str | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> TextFileReader:
...
# chunksize=int -> TextFileReader
@overload
def read_table(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = ...,
delimiter: str | None | lib.NoDefault = ...,
header: int | Sequence[int] | None | Literal["infer"] = ...,
names: Sequence[Hashable] | None | lib.NoDefault = ...,
index_col: IndexLabel | Literal[False] | None = ...,
usecols: UsecolsArgType = ...,
dtype: DtypeArg | None = ...,
engine: CSVEngine | None = ...,
converters: Mapping[Hashable, Callable] | None = ...,
true_values: list | None = ...,
false_values: list | None = ...,
skipinitialspace: bool = ...,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = ...,
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool | lib.NoDefault = ...,
skip_blank_lines: bool = ...,
parse_dates: bool | Sequence[Hashable] = ...,
infer_datetime_format: bool | lib.NoDefault = ...,
keep_date_col: bool | lib.NoDefault = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: str | dict[Hashable, str] | None = ...,
dayfirst: bool = ...,
cache_dates: bool = ...,
iterator: bool = ...,
chunksize: int,
compression: CompressionOptions = ...,
thousands: str | None = ...,
decimal: str = ...,
lineterminator: str | None = ...,
quotechar: str = ...,
quoting: int = ...,
doublequote: bool = ...,
escapechar: str | None = ...,
comment: str | None = ...,
encoding: str | None = ...,
encoding_errors: str | None = ...,
dialect: str | csv.Dialect | None = ...,
on_bad_lines=...,
delim_whitespace: bool = ...,
low_memory: bool = ...,
memory_map: bool = ...,
float_precision: str | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> TextFileReader:
...
# default -> DataFrame
@overload
def read_table(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = ...,
delimiter: str | None | lib.NoDefault = ...,
header: int | Sequence[int] | None | Literal["infer"] = ...,
names: Sequence[Hashable] | None | lib.NoDefault = ...,
index_col: IndexLabel | Literal[False] | None = ...,
usecols: UsecolsArgType = ...,
dtype: DtypeArg | None = ...,
engine: CSVEngine | None = ...,
converters: Mapping[Hashable, Callable] | None = ...,
true_values: list | None = ...,
false_values: list | None = ...,
skipinitialspace: bool = ...,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = ...,
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool | lib.NoDefault = ...,
skip_blank_lines: bool = ...,
parse_dates: bool | Sequence[Hashable] = ...,
infer_datetime_format: bool | lib.NoDefault = ...,
keep_date_col: bool | lib.NoDefault = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: str | dict[Hashable, str] | None = ...,
dayfirst: bool = ...,
cache_dates: bool = ...,
iterator: Literal[False] = ...,
chunksize: None = ...,
compression: CompressionOptions = ...,
thousands: str | None = ...,
decimal: str = ...,
lineterminator: str | None = ...,
quotechar: str = ...,
quoting: int = ...,
doublequote: bool = ...,
escapechar: str | None = ...,
comment: str | None = ...,
encoding: str | None = ...,
encoding_errors: str | None = ...,
dialect: str | csv.Dialect | None = ...,
on_bad_lines=...,
delim_whitespace: bool = ...,
low_memory: bool = ...,
memory_map: bool = ...,
float_precision: str | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> DataFrame:
...
# Unions -> DataFrame | TextFileReader
@overload
def read_table(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = ...,
delimiter: str | None | lib.NoDefault = ...,
header: int | Sequence[int] | None | Literal["infer"] = ...,
names: Sequence[Hashable] | None | lib.NoDefault = ...,
index_col: IndexLabel | Literal[False] | None = ...,
usecols: UsecolsArgType = ...,
dtype: DtypeArg | None = ...,
engine: CSVEngine | None = ...,
converters: Mapping[Hashable, Callable] | None = ...,
true_values: list | None = ...,
false_values: list | None = ...,
skipinitialspace: bool = ...,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = ...,
skipfooter: int = ...,
nrows: int | None = ...,
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = ...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool | lib.NoDefault = ...,
skip_blank_lines: bool = ...,
parse_dates: bool | Sequence[Hashable] = ...,
infer_datetime_format: bool | lib.NoDefault = ...,
keep_date_col: bool | lib.NoDefault = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: str | dict[Hashable, str] | None = ...,
dayfirst: bool = ...,
cache_dates: bool = ...,
iterator: bool = ...,
chunksize: int | None = ...,
compression: CompressionOptions = ...,
thousands: str | None = ...,
decimal: str = ...,
lineterminator: str | None = ...,
quotechar: str = ...,
quoting: int = ...,
doublequote: bool = ...,
escapechar: str | None = ...,
comment: str | None = ...,
encoding: str | None = ...,
encoding_errors: str | None = ...,
dialect: str | csv.Dialect | None = ...,
on_bad_lines=...,
delim_whitespace: bool = ...,
low_memory: bool = ...,
memory_map: bool = ...,
float_precision: str | None = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> DataFrame | TextFileReader:
...
@Appender(
_doc_read_csv_and_table.format(
func_name="read_table",
summary="Read general delimited file into DataFrame.",
see_also_func_name="read_csv",
see_also_func_summary=(
"Read a comma-separated values (csv) file into DataFrame."
),
_default_sep=r"'\\t' (tab-stop)",
storage_options=_shared_docs["storage_options"],
decompression_options=_shared_docs["decompression_options"]
% "filepath_or_buffer",
)
)
def read_table(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
sep: str | None | lib.NoDefault = lib.no_default,
delimiter: str | None | lib.NoDefault = None,
# Column and Index Locations and Names
header: int | Sequence[int] | None | Literal["infer"] = "infer",
names: Sequence[Hashable] | None | lib.NoDefault = lib.no_default,
index_col: IndexLabel | Literal[False] | None = None,
usecols: UsecolsArgType = None,
# General Parsing Configuration
dtype: DtypeArg | None = None,
engine: CSVEngine | None = None,
converters: Mapping[Hashable, Callable] | None = None,
true_values: list | None = None,
false_values: list | None = None,
skipinitialspace: bool = False,
skiprows: list[int] | int | Callable[[Hashable], bool] | None = None,
skipfooter: int = 0,
nrows: int | None = None,
# NA and Missing Data Handling
na_values: Sequence[str] | Mapping[str, Sequence[str]] | None = None,
keep_default_na: bool = True,
na_filter: bool = True,
verbose: bool | lib.NoDefault = lib.no_default,
skip_blank_lines: bool = True,
# Datetime Handling
parse_dates: bool | Sequence[Hashable] = False,
infer_datetime_format: bool | lib.NoDefault = lib.no_default,
keep_date_col: bool | lib.NoDefault = lib.no_default,
date_parser: Callable | lib.NoDefault = lib.no_default,
date_format: str | dict[Hashable, str] | None = None,
dayfirst: bool = False,
cache_dates: bool = True,
# Iteration
iterator: bool = False,
chunksize: int | None = None,
# Quoting, Compression, and File Format
compression: CompressionOptions = "infer",
thousands: str | None = None,
decimal: str = ".",
lineterminator: str | None = None,
quotechar: str = '"',
quoting: int = csv.QUOTE_MINIMAL,
doublequote: bool = True,
escapechar: str | None = None,
comment: str | None = None,
encoding: str | None = None,
encoding_errors: str | None = "strict",
dialect: str | csv.Dialect | None = None,
# Error Handling
on_bad_lines: str = "error",
# Internal
delim_whitespace: bool | lib.NoDefault = lib.no_default,
low_memory: bool = _c_parser_defaults["low_memory"],
memory_map: bool = False,
float_precision: str | None = None,
storage_options: StorageOptions | None = None,
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
) -> DataFrame | TextFileReader:
if keep_date_col is not lib.no_default:
# GH#55569
warnings.warn(
"The 'keep_date_col' keyword in pd.read_table is deprecated and "
"will be removed in a future version. Explicitly remove unwanted "
"columns after parsing instead.",
FutureWarning,
stacklevel=find_stack_level(),
)
else:
keep_date_col = False
# error: Item "bool" of "bool | Sequence[Hashable]" has no attribute "__iter__"
if lib.is_list_like(parse_dates) and not all(is_hashable(x) for x in parse_dates): # type: ignore[union-attr]
# GH#55569
warnings.warn(
"Support for nested sequences for 'parse_dates' in pd.read_table "
"is deprecated. Combine the desired columns with pd.to_datetime "
"after parsing instead.",
FutureWarning,
stacklevel=find_stack_level(),
)
if infer_datetime_format is not lib.no_default:
warnings.warn(
"The argument 'infer_datetime_format' is deprecated and will "
"be removed in a future version. "
"A strict version of it is now the default, see "
"https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. "
"You can safely remove this argument.",
FutureWarning,
stacklevel=find_stack_level(),
)
if delim_whitespace is not lib.no_default:
# GH#55569
warnings.warn(
"The 'delim_whitespace' keyword in pd.read_table is deprecated and "
"will be removed in a future version. Use ``sep='\\s+'`` instead",
FutureWarning,
stacklevel=find_stack_level(),
)
else:
delim_whitespace = False
if verbose is not lib.no_default:
# GH#55569
warnings.warn(
"The 'verbose' keyword in pd.read_table is deprecated and "
"will be removed in a future version.",
FutureWarning,
stacklevel=find_stack_level(),
)
else:
verbose = False
# locals() should never be modified
kwds = locals().copy()
del kwds["filepath_or_buffer"]
del kwds["sep"]
kwds_defaults = _refine_defaults_read(
dialect,
delimiter,
delim_whitespace,
engine,
sep,
on_bad_lines,
names,
defaults={"delimiter": "\t"},
dtype_backend=dtype_backend,
)
kwds.update(kwds_defaults)
return _read(filepath_or_buffer, kwds)
@overload
def read_fwf(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
colspecs: Sequence[tuple[int, int]] | str | None = ...,
widths: Sequence[int] | None = ...,
infer_nrows: int = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
iterator: Literal[True],
chunksize: int | None = ...,
**kwds,
) -> TextFileReader:
...
@overload
def read_fwf(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
colspecs: Sequence[tuple[int, int]] | str | None = ...,
widths: Sequence[int] | None = ...,
infer_nrows: int = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
iterator: bool = ...,
chunksize: int,
**kwds,
) -> TextFileReader:
...
@overload
def read_fwf(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
colspecs: Sequence[tuple[int, int]] | str | None = ...,
widths: Sequence[int] | None = ...,
infer_nrows: int = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
iterator: Literal[False] = ...,
chunksize: None = ...,
**kwds,
) -> DataFrame:
...
def read_fwf(
filepath_or_buffer: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str],
*,
colspecs: Sequence[tuple[int, int]] | str | None = "infer",
widths: Sequence[int] | None = None,
infer_nrows: int = 100,
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
iterator: bool = False,
chunksize: int | None = None,
**kwds,
) -> DataFrame | TextFileReader:
r"""
Read a table of fixed-width formatted lines into DataFrame.
Also supports optionally iterating or breaking of the file
into chunks.
Additional help can be found in the `online docs for IO Tools
<https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html>`_.
Parameters
----------
filepath_or_buffer : str, path object, or file-like object
String, path object (implementing ``os.PathLike[str]``), or file-like
object implementing a text ``read()`` function.The string could be a URL.
Valid URL schemes include http, ftp, s3, and file. For file URLs, a host is
expected. A local file could be:
``file://localhost/path/to/table.csv``.
colspecs : list of tuple (int, int) or 'infer'. optional
A list of tuples giving the extents of the fixed-width
fields of each line as half-open intervals (i.e., [from, to[ ).
String value 'infer' can be used to instruct the parser to try
detecting the column specifications from the first 100 rows of
the data which are not being skipped via skiprows (default='infer').
widths : list of int, optional
A list of field widths which can be used instead of 'colspecs' if
the intervals are contiguous.
infer_nrows : int, default 100
The number of rows to consider when letting the parser determine the
`colspecs`.
dtype_backend : {'numpy_nullable', 'pyarrow'}, default 'numpy_nullable'
Back-end data type applied to the resultant :class:`DataFrame`
(still experimental). Behaviour is as follows:
* ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame`
(default).
* ``"pyarrow"``: returns pyarrow-backed nullable :class:`ArrowDtype`
DataFrame.
.. versionadded:: 2.0
**kwds : optional
Optional keyword arguments can be passed to ``TextFileReader``.
Returns
-------
DataFrame or TextFileReader
A comma-separated values (csv) file is returned as two-dimensional
data structure with labeled axes.
See Also
--------
DataFrame.to_csv : Write DataFrame to a comma-separated values (csv) file.
read_csv : Read a comma-separated values (csv) file into DataFrame.
Examples
--------
>>> pd.read_fwf('data.csv') # doctest: +SKIP
"""
# Check input arguments.
if colspecs is None and widths is None:
raise ValueError("Must specify either colspecs or widths")
if colspecs not in (None, "infer") and widths is not None:
raise ValueError("You must specify only one of 'widths' and 'colspecs'")
# Compute 'colspecs' from 'widths', if specified.
if widths is not None:
colspecs, col = [], 0
for w in widths:
colspecs.append((col, col + w))
col += w
# for mypy
assert colspecs is not None
# GH#40830
# Ensure length of `colspecs` matches length of `names`
names = kwds.get("names")
if names is not None:
if len(names) != len(colspecs) and colspecs != "infer":
# need to check len(index_col) as it might contain
# unnamed indices, in which case it's name is not required
len_index = 0
if kwds.get("index_col") is not None:
index_col: Any = kwds.get("index_col")
if index_col is not False:
if not is_list_like(index_col):
len_index = 1
else:
len_index = len(index_col)
if kwds.get("usecols") is None and len(names) + len_index != len(colspecs):
# If usecols is used colspec may be longer than names
raise ValueError("Length of colspecs must match length of names")
kwds["colspecs"] = colspecs
kwds["infer_nrows"] = infer_nrows
kwds["engine"] = "python-fwf"
kwds["iterator"] = iterator
kwds["chunksize"] = chunksize
check_dtype_backend(dtype_backend)
kwds["dtype_backend"] = dtype_backend
return _read(filepath_or_buffer, kwds)
class TextFileReader(abc.Iterator):
"""
Passed dialect overrides any of the related parser options
"""
def __init__(
self,
f: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str] | list,
engine: CSVEngine | None = None,
**kwds,
) -> None:
if engine is not None:
engine_specified = True
else:
engine = "python"
engine_specified = False
self.engine = engine
self._engine_specified = kwds.get("engine_specified", engine_specified)
_validate_skipfooter(kwds)
dialect = _extract_dialect(kwds)
if dialect is not None:
if engine == "pyarrow":
raise ValueError(
"The 'dialect' option is not supported with the 'pyarrow' engine"
)
kwds = _merge_with_dialect_properties(dialect, kwds)
if kwds.get("header", "infer") == "infer":
kwds["header"] = 0 if kwds.get("names") is None else None
self.orig_options = kwds
# miscellanea
self._currow = 0
options = self._get_options_with_defaults(engine)
options["storage_options"] = kwds.get("storage_options", None)
self.chunksize = options.pop("chunksize", None)
self.nrows = options.pop("nrows", None)
self._check_file_or_buffer(f, engine)
self.options, self.engine = self._clean_options(options, engine)
if "has_index_names" in kwds:
self.options["has_index_names"] = kwds["has_index_names"]
self.handles: IOHandles | None = None
self._engine = self._make_engine(f, self.engine)
def close(self) -> None:
if self.handles is not None:
self.handles.close()
self._engine.close()
def _get_options_with_defaults(self, engine: CSVEngine) -> dict[str, Any]:
kwds = self.orig_options
options = {}
default: object | None
for argname, default in parser_defaults.items():
value = kwds.get(argname, default)
# see gh-12935
if (
engine == "pyarrow"
and argname in _pyarrow_unsupported
and value != default
and value != getattr(value, "value", default)
):
raise ValueError(
f"The {repr(argname)} option is not supported with the "
f"'pyarrow' engine"
)
options[argname] = value
for argname, default in _c_parser_defaults.items():
if argname in kwds:
value = kwds[argname]
if engine != "c" and value != default:
# TODO: Refactor this logic, its pretty convoluted
if "python" in engine and argname not in _python_unsupported:
pass
elif "pyarrow" in engine and argname not in _pyarrow_unsupported:
pass
else:
raise ValueError(
f"The {repr(argname)} option is not supported with the "
f"{repr(engine)} engine"
)
else:
value = default
options[argname] = value
if engine == "python-fwf":
for argname, default in _fwf_defaults.items():
options[argname] = kwds.get(argname, default)
return options
def _check_file_or_buffer(self, f, engine: CSVEngine) -> None:
# see gh-16530
if is_file_like(f) and engine != "c" and not hasattr(f, "__iter__"):
# The C engine doesn't need the file-like to have the "__iter__"
# attribute. However, the Python engine needs "__iter__(...)"
# when iterating through such an object, meaning it
# needs to have that attribute
raise ValueError(
"The 'python' engine cannot iterate through this file buffer."
)
def _clean_options(
self, options: dict[str, Any], engine: CSVEngine
) -> tuple[dict[str, Any], CSVEngine]:
result = options.copy()
fallback_reason = None
# C engine not supported yet
if engine == "c":
if options["skipfooter"] > 0:
fallback_reason = "the 'c' engine does not support skipfooter"
engine = "python"
sep = options["delimiter"]
delim_whitespace = options["delim_whitespace"]
if sep is None and not delim_whitespace:
if engine in ("c", "pyarrow"):
fallback_reason = (
f"the '{engine}' engine does not support "
"sep=None with delim_whitespace=False"
)
engine = "python"
elif sep is not None and len(sep) > 1:
if engine == "c" and sep == r"\s+":
result["delim_whitespace"] = True
del result["delimiter"]
elif engine not in ("python", "python-fwf"):
# wait until regex engine integrated
fallback_reason = (
f"the '{engine}' engine does not support "
"regex separators (separators > 1 char and "
r"different from '\s+' are interpreted as regex)"
)
engine = "python"
elif delim_whitespace:
if "python" in engine:
result["delimiter"] = r"\s+"
elif sep is not None:
encodeable = True
encoding = sys.getfilesystemencoding() or "utf-8"
try:
if len(sep.encode(encoding)) > 1:
encodeable = False
except UnicodeDecodeError:
encodeable = False
if not encodeable and engine not in ("python", "python-fwf"):
fallback_reason = (
f"the separator encoded in {encoding} "
f"is > 1 char long, and the '{engine}' engine "
"does not support such separators"
)
engine = "python"
quotechar = options["quotechar"]
if quotechar is not None and isinstance(quotechar, (str, bytes)):
if (
len(quotechar) == 1
and ord(quotechar) > 127
and engine not in ("python", "python-fwf")
):
fallback_reason = (
"ord(quotechar) > 127, meaning the "
"quotechar is larger than one byte, "
f"and the '{engine}' engine does not support such quotechars"
)
engine = "python"
if fallback_reason and self._engine_specified:
raise ValueError(fallback_reason)
if engine == "c":
for arg in _c_unsupported:
del result[arg]
if "python" in engine:
for arg in _python_unsupported:
if fallback_reason and result[arg] != _c_parser_defaults.get(arg):
raise ValueError(
"Falling back to the 'python' engine because "
f"{fallback_reason}, but this causes {repr(arg)} to be "
"ignored as it is not supported by the 'python' engine."
)
del result[arg]
if fallback_reason:
warnings.warn(
(
"Falling back to the 'python' engine because "
f"{fallback_reason}; you can avoid this warning by specifying "
"engine='python'."
),
ParserWarning,
stacklevel=find_stack_level(),
)
index_col = options["index_col"]
names = options["names"]
converters = options["converters"]
na_values = options["na_values"]
skiprows = options["skiprows"]
validate_header_arg(options["header"])
if index_col is True:
raise ValueError("The value of index_col couldn't be 'True'")
if is_index_col(index_col):
if not isinstance(index_col, (list, tuple, np.ndarray)):
index_col = [index_col]
result["index_col"] = index_col
names = list(names) if names is not None else names
# type conversion-related
if converters is not None:
if not isinstance(converters, dict):
raise TypeError(
"Type converters must be a dict or subclass, "
f"input was a {type(converters).__name__}"
)
else:
converters = {}
# Converting values to NA
keep_default_na = options["keep_default_na"]
floatify = engine != "pyarrow"
na_values, na_fvalues = _clean_na_values(
na_values, keep_default_na, floatify=floatify
)
# handle skiprows; this is internally handled by the
# c-engine, so only need for python and pyarrow parsers
if engine == "pyarrow":
if not is_integer(skiprows) and skiprows is not None:
# pyarrow expects skiprows to be passed as an integer
raise ValueError(
"skiprows argument must be an integer when using "
"engine='pyarrow'"
)
else:
if is_integer(skiprows):
skiprows = list(range(skiprows))
if skiprows is None:
skiprows = set()
elif not callable(skiprows):
skiprows = set(skiprows)
# put stuff back
result["names"] = names
result["converters"] = converters
result["na_values"] = na_values
result["na_fvalues"] = na_fvalues
result["skiprows"] = skiprows
return result, engine
def __next__(self) -> DataFrame:
try:
return self.get_chunk()
except StopIteration:
self.close()
raise
def _make_engine(
self,
f: FilePath | ReadCsvBuffer[bytes] | ReadCsvBuffer[str] | list | IO,
engine: CSVEngine = "c",
) -> ParserBase:
mapping: dict[str, type[ParserBase]] = {
"c": CParserWrapper,
"python": PythonParser,
"pyarrow": ArrowParserWrapper,
"python-fwf": FixedWidthFieldParser,
}
if engine not in mapping:
raise ValueError(
f"Unknown engine: {engine} (valid options are {mapping.keys()})"
)
if not isinstance(f, list):
# open file here
is_text = True
mode = "r"
if engine == "pyarrow":
is_text = False
mode = "rb"
elif (
engine == "c"
and self.options.get("encoding", "utf-8") == "utf-8"
and isinstance(stringify_path(f), str)
):
# c engine can decode utf-8 bytes, adding TextIOWrapper makes
# the c-engine especially for memory_map=True far slower
is_text = False
if "b" not in mode:
mode += "b"
self.handles = get_handle(
f,
mode,
encoding=self.options.get("encoding", None),
compression=self.options.get("compression", None),
memory_map=self.options.get("memory_map", False),
is_text=is_text,
errors=self.options.get("encoding_errors", "strict"),
storage_options=self.options.get("storage_options", None),
)
assert self.handles is not None
f = self.handles.handle
elif engine != "python":
msg = f"Invalid file path or buffer object type: {type(f)}"
raise ValueError(msg)
try:
return mapping[engine](f, **self.options)
except Exception:
if self.handles is not None:
self.handles.close()
raise
def _failover_to_python(self) -> None:
raise AbstractMethodError(self)
def read(self, nrows: int | None = None) -> DataFrame:
if self.engine == "pyarrow":
try:
# error: "ParserBase" has no attribute "read"
df = self._engine.read() # type: ignore[attr-defined]
except Exception:
self.close()
raise
else:
nrows = validate_integer("nrows", nrows)
try:
# error: "ParserBase" has no attribute "read"
(
index,
columns,
col_dict,
) = self._engine.read( # type: ignore[attr-defined]
nrows
)
except Exception:
self.close()
raise
if index is None:
if col_dict:
# Any column is actually fine:
new_rows = len(next(iter(col_dict.values())))
index = RangeIndex(self._currow, self._currow + new_rows)
else:
new_rows = 0
else:
new_rows = len(index)
if hasattr(self, "orig_options"):
dtype_arg = self.orig_options.get("dtype", None)
else:
dtype_arg = None
if isinstance(dtype_arg, dict):
dtype = defaultdict(lambda: None) # type: ignore[var-annotated]
dtype.update(dtype_arg)
elif dtype_arg is not None and pandas_dtype(dtype_arg) in (
np.str_,
np.object_,
):
dtype = defaultdict(lambda: dtype_arg)
else:
dtype = None
if dtype is not None:
new_col_dict = {}
for k, v in col_dict.items():
d = (
dtype[k]
if pandas_dtype(dtype[k]) in (np.str_, np.object_)
else None
)
new_col_dict[k] = Series(v, index=index, dtype=d, copy=False)
else:
new_col_dict = col_dict
df = DataFrame(
new_col_dict,
columns=columns,
index=index,
copy=not using_copy_on_write(),
)
self._currow += new_rows
return df
def get_chunk(self, size: int | None = None) -> DataFrame:
if size is None:
size = self.chunksize
if self.nrows is not None:
if self._currow >= self.nrows:
raise StopIteration
size = min(size, self.nrows - self._currow)
return self.read(nrows=size)
def __enter__(self) -> Self:
return self
def __exit__(
self,
exc_type: type[BaseException] | None,
exc_value: BaseException | None,
traceback: TracebackType | None,
) -> None:
self.close()
def TextParser(*args, **kwds) -> TextFileReader:
"""
Converts lists of lists/tuples into DataFrames with proper type inference
and optional (e.g. string to datetime) conversion. Also enables iterating
lazily over chunks of large files
Parameters
----------
data : file-like object or list
delimiter : separator character to use
dialect : str or csv.Dialect instance, optional
Ignored if delimiter is longer than 1 character
names : sequence, default
header : int, default 0
Row to use to parse column labels. Defaults to the first row. Prior
rows will be discarded
index_col : int or list, optional
Column or columns to use as the (possibly hierarchical) index
has_index_names: bool, default False
True if the cols defined in index_col have an index name and are
not in the header.
na_values : scalar, str, list-like, or dict, optional
Additional strings to recognize as NA/NaN.
keep_default_na : bool, default True
thousands : str, optional
Thousands separator
comment : str, optional
Comment out remainder of line
parse_dates : bool, default False
keep_date_col : bool, default False
date_parser : function, optional
.. deprecated:: 2.0.0
date_format : str or dict of column -> format, default ``None``
.. versionadded:: 2.0.0
skiprows : list of integers
Row numbers to skip
skipfooter : int
Number of line at bottom of file to skip
converters : dict, optional
Dict of functions for converting values in certain columns. Keys can
either be integers or column labels, values are functions that take one
input argument, the cell (not column) content, and return the
transformed content.
encoding : str, optional
Encoding to use for UTF when reading/writing (ex. 'utf-8')
float_precision : str, optional
Specifies which converter the C engine should use for floating-point
values. The options are `None` or `high` for the ordinary converter,
`legacy` for the original lower precision pandas converter, and
`round_trip` for the round-trip converter.
"""
kwds["engine"] = "python"
return TextFileReader(*args, **kwds)
def _clean_na_values(na_values, keep_default_na: bool = True, floatify: bool = True):
na_fvalues: set | dict
if na_values is None:
if keep_default_na:
na_values = STR_NA_VALUES
else:
na_values = set()
na_fvalues = set()
elif isinstance(na_values, dict):
old_na_values = na_values.copy()
na_values = {} # Prevent aliasing.
# Convert the values in the na_values dictionary
# into array-likes for further use. This is also
# where we append the default NaN values, provided
# that `keep_default_na=True`.
for k, v in old_na_values.items():
if not is_list_like(v):
v = [v]
if keep_default_na:
v = set(v) | STR_NA_VALUES
na_values[k] = v
na_fvalues = {k: _floatify_na_values(v) for k, v in na_values.items()}
else:
if not is_list_like(na_values):
na_values = [na_values]
na_values = _stringify_na_values(na_values, floatify)
if keep_default_na:
na_values = na_values | STR_NA_VALUES
na_fvalues = _floatify_na_values(na_values)
return na_values, na_fvalues
def _floatify_na_values(na_values):
# create float versions of the na_values
result = set()
for v in na_values:
try:
v = float(v)
if not np.isnan(v):
result.add(v)
except (TypeError, ValueError, OverflowError):
pass
return result
def _stringify_na_values(na_values, floatify: bool):
"""return a stringified and numeric for these values"""
result: list[str | float] = []
for x in na_values:
result.append(str(x))
result.append(x)
try:
v = float(x)
# we are like 999 here
if v == int(v):
v = int(v)
result.append(f"{v}.0")
result.append(str(v))
if floatify:
result.append(v)
except (TypeError, ValueError, OverflowError):
pass
if floatify:
try:
result.append(int(x))
except (TypeError, ValueError, OverflowError):
pass
return set(result)
def _refine_defaults_read(
dialect: str | csv.Dialect | None,
delimiter: str | None | lib.NoDefault,
delim_whitespace: bool,
engine: CSVEngine | None,
sep: str | None | lib.NoDefault,
on_bad_lines: str | Callable,
names: Sequence[Hashable] | None | lib.NoDefault,
defaults: dict[str, Any],
dtype_backend: DtypeBackend | lib.NoDefault,
):
"""Validate/refine default values of input parameters of read_csv, read_table.
Parameters
----------
dialect : str or csv.Dialect
If provided, this parameter will override values (default or not) for the
following parameters: `delimiter`, `doublequote`, `escapechar`,
`skipinitialspace`, `quotechar`, and `quoting`. If it is necessary to
override values, a ParserWarning will be issued. See csv.Dialect
documentation for more details.
delimiter : str or object
Alias for sep.
delim_whitespace : bool
Specifies whether or not whitespace (e.g. ``' '`` or ``'\t'``) will be
used as the sep. Equivalent to setting ``sep='\\s+'``. If this option
is set to True, nothing should be passed in for the ``delimiter``
parameter.
.. deprecated:: 2.2.0
Use ``sep="\\s+"`` instead.
engine : {{'c', 'python'}}
Parser engine to use. The C engine is faster while the python engine is
currently more feature-complete.
sep : str or object
A delimiter provided by the user (str) or a sentinel value, i.e.
pandas._libs.lib.no_default.
on_bad_lines : str, callable
An option for handling bad lines or a sentinel value(None).
names : array-like, optional
List of column names to use. If the file contains a header row,
then you should explicitly pass ``header=0`` to override the column names.
Duplicates in this list are not allowed.
defaults: dict
Default values of input parameters.
Returns
-------
kwds : dict
Input parameters with correct values.
Raises
------
ValueError :
If a delimiter was specified with ``sep`` (or ``delimiter``) and
``delim_whitespace=True``.
"""
# fix types for sep, delimiter to Union(str, Any)
delim_default = defaults["delimiter"]
kwds: dict[str, Any] = {}
# gh-23761
#
# When a dialect is passed, it overrides any of the overlapping
# parameters passed in directly. We don't want to warn if the
# default parameters were passed in (since it probably means
# that the user didn't pass them in explicitly in the first place).
#
# "delimiter" is the annoying corner case because we alias it to
# "sep" before doing comparison to the dialect values later on.
# Thus, we need a flag to indicate that we need to "override"
# the comparison to dialect values by checking if default values
# for BOTH "delimiter" and "sep" were provided.
if dialect is not None:
kwds["sep_override"] = delimiter is None and (
sep is lib.no_default or sep == delim_default
)
if delimiter and (sep is not lib.no_default):
raise ValueError("Specified a sep and a delimiter; you can only specify one.")
kwds["names"] = None if names is lib.no_default else names
# Alias sep -> delimiter.
if delimiter is None:
delimiter = sep
if delim_whitespace and (delimiter is not lib.no_default):
raise ValueError(
"Specified a delimiter with both sep and "
"delim_whitespace=True; you can only specify one."
)
if delimiter == "\n":
raise ValueError(
r"Specified \n as separator or delimiter. This forces the python engine "
"which does not accept a line terminator. Hence it is not allowed to use "
"the line terminator as separator.",
)
if delimiter is lib.no_default:
# assign default separator value
kwds["delimiter"] = delim_default
else:
kwds["delimiter"] = delimiter
if engine is not None:
kwds["engine_specified"] = True
else:
kwds["engine"] = "c"
kwds["engine_specified"] = False
if on_bad_lines == "error":
kwds["on_bad_lines"] = ParserBase.BadLineHandleMethod.ERROR
elif on_bad_lines == "warn":
kwds["on_bad_lines"] = ParserBase.BadLineHandleMethod.WARN
elif on_bad_lines == "skip":
kwds["on_bad_lines"] = ParserBase.BadLineHandleMethod.SKIP
elif callable(on_bad_lines):
if engine not in ["python", "pyarrow"]:
raise ValueError(
"on_bad_line can only be a callable function "
"if engine='python' or 'pyarrow'"
)
kwds["on_bad_lines"] = on_bad_lines
else:
raise ValueError(f"Argument {on_bad_lines} is invalid for on_bad_lines")
check_dtype_backend(dtype_backend)
kwds["dtype_backend"] = dtype_backend
return kwds
def _extract_dialect(kwds: dict[str, Any]) -> csv.Dialect | None:
"""
Extract concrete csv dialect instance.
Returns
-------
csv.Dialect or None
"""
if kwds.get("dialect") is None:
return None
dialect = kwds["dialect"]
if dialect in csv.list_dialects():
dialect = csv.get_dialect(dialect)
_validate_dialect(dialect)
return dialect
MANDATORY_DIALECT_ATTRS = (
"delimiter",
"doublequote",
"escapechar",
"skipinitialspace",
"quotechar",
"quoting",
)
def _validate_dialect(dialect: csv.Dialect) -> None:
"""
Validate csv dialect instance.
Raises
------
ValueError
If incorrect dialect is provided.
"""
for param in MANDATORY_DIALECT_ATTRS:
if not hasattr(dialect, param):
raise ValueError(f"Invalid dialect {dialect} provided")
def _merge_with_dialect_properties(
dialect: csv.Dialect,
defaults: dict[str, Any],
) -> dict[str, Any]:
"""
Merge default kwargs in TextFileReader with dialect parameters.
Parameters
----------
dialect : csv.Dialect
Concrete csv dialect. See csv.Dialect documentation for more details.
defaults : dict
Keyword arguments passed to TextFileReader.
Returns
-------
kwds : dict
Updated keyword arguments, merged with dialect parameters.
"""
kwds = defaults.copy()
for param in MANDATORY_DIALECT_ATTRS:
dialect_val = getattr(dialect, param)
parser_default = parser_defaults[param]
provided = kwds.get(param, parser_default)
# Messages for conflicting values between the dialect
# instance and the actual parameters provided.
conflict_msgs = []
# Don't warn if the default parameter was passed in,
# even if it conflicts with the dialect (gh-23761).
if provided not in (parser_default, dialect_val):
msg = (
f"Conflicting values for '{param}': '{provided}' was "
f"provided, but the dialect specifies '{dialect_val}'. "
"Using the dialect-specified value."
)
# Annoying corner case for not warning about
# conflicts between dialect and delimiter parameter.
# Refer to the outer "_read_" function for more info.
if not (param == "delimiter" and kwds.pop("sep_override", False)):
conflict_msgs.append(msg)
if conflict_msgs:
warnings.warn(
"\n\n".join(conflict_msgs), ParserWarning, stacklevel=find_stack_level()
)
kwds[param] = dialect_val
return kwds
def _validate_skipfooter(kwds: dict[str, Any]) -> None:
"""
Check whether skipfooter is compatible with other kwargs in TextFileReader.
Parameters
----------
kwds : dict
Keyword arguments passed to TextFileReader.
Raises
------
ValueError
If skipfooter is not compatible with other parameters.
"""
if kwds.get("skipfooter"):
if kwds.get("iterator") or kwds.get("chunksize"):
raise ValueError("'skipfooter' not supported for iteration")
if kwds.get("nrows"):
raise ValueError("'skipfooter' not supported with 'nrows'")
|