File size: 59,073 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 |
from __future__ import annotations
from collections.abc import (
Hashable,
Iterable,
Mapping,
Sequence,
)
import datetime
from functools import partial
from io import BytesIO
import os
from textwrap import fill
from typing import (
IO,
TYPE_CHECKING,
Any,
Callable,
Generic,
Literal,
TypeVar,
Union,
cast,
overload,
)
import warnings
import zipfile
from pandas._config import config
from pandas._libs import lib
from pandas._libs.parsers import STR_NA_VALUES
from pandas.compat._optional import (
get_version,
import_optional_dependency,
)
from pandas.errors import EmptyDataError
from pandas.util._decorators import (
Appender,
doc,
)
from pandas.util._exceptions import find_stack_level
from pandas.util._validators import check_dtype_backend
from pandas.core.dtypes.common import (
is_bool,
is_float,
is_integer,
is_list_like,
)
from pandas.core.frame import DataFrame
from pandas.core.shared_docs import _shared_docs
from pandas.util.version import Version
from pandas.io.common import (
IOHandles,
get_handle,
stringify_path,
validate_header_arg,
)
from pandas.io.excel._util import (
fill_mi_header,
get_default_engine,
get_writer,
maybe_convert_usecols,
pop_header_name,
)
from pandas.io.parsers import TextParser
from pandas.io.parsers.readers import validate_integer
if TYPE_CHECKING:
from types import TracebackType
from pandas._typing import (
DtypeArg,
DtypeBackend,
ExcelWriterIfSheetExists,
FilePath,
IntStrT,
ReadBuffer,
Self,
SequenceNotStr,
StorageOptions,
WriteExcelBuffer,
)
_read_excel_doc = (
"""
Read an Excel file into a ``pandas`` ``DataFrame``.
Supports `xls`, `xlsx`, `xlsm`, `xlsb`, `odf`, `ods` and `odt` file extensions
read from a local filesystem or URL. Supports an option to read
a single sheet or a list of sheets.
Parameters
----------
io : str, bytes, ExcelFile, xlrd.Book, 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, and file. For file URLs, a host is
expected. A local file could be: ``file://localhost/path/to/table.xlsx``.
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``.
.. deprecated:: 2.1.0
Passing byte strings is deprecated. To read from a
byte string, wrap it in a ``BytesIO`` object.
sheet_name : str, int, list, or None, default 0
Strings are used for sheet names. Integers are used in zero-indexed
sheet positions (chart sheets do not count as a sheet position).
Lists of strings/integers are used to request multiple sheets.
Specify ``None`` to get all worksheets.
Available cases:
* Defaults to ``0``: 1st sheet as a `DataFrame`
* ``1``: 2nd sheet as a `DataFrame`
* ``"Sheet1"``: Load sheet with name "Sheet1"
* ``[0, 1, "Sheet5"]``: Load first, second and sheet named "Sheet5"
as a dict of `DataFrame`
* ``None``: All worksheets.
header : int, list of int, default 0
Row (0-indexed) to use for the column labels of the parsed
DataFrame. If a list of integers is passed those row positions will
be combined into a ``MultiIndex``. Use None if there is no header.
names : array-like, default None
List of column names to use. If file contains no header row,
then you should explicitly pass header=None.
index_col : int, str, list of int, default None
Column (0-indexed) to use as the row labels of the DataFrame.
Pass None if there is no such column. If a list is passed,
those columns will be combined into a ``MultiIndex``. If a
subset of data is selected with ``usecols``, index_col
is based on the subset.
Missing values will be forward filled to allow roundtripping with
``to_excel`` for ``merged_cells=True``. To avoid forward filling the
missing values use ``set_index`` after reading the data instead of
``index_col``.
usecols : str, list-like, or callable, default None
* If None, then parse all columns.
* If str, then indicates comma separated list of Excel column letters
and column ranges (e.g. "A:E" or "A,C,E:F"). Ranges are inclusive of
both sides.
* If list of int, then indicates list of column numbers to be parsed
(0-indexed).
* If list of string, then indicates list of column names to be parsed.
* If callable, then evaluate each column name against it and parse the
column if the callable returns ``True``.
Returns a subset of the columns according to behavior above.
dtype : Type name or dict of column -> type, default None
Data type for data or columns. E.g. {{'a': np.float64, 'b': np.int32}}
Use ``object`` to preserve data as stored in Excel and not interpret dtype,
which will necessarily result in ``object`` dtype.
If converters are specified, they will be applied INSTEAD
of dtype conversion.
If you use ``None``, it will infer the dtype of each column based on the data.
engine : {{'openpyxl', 'calamine', 'odf', 'pyxlsb', 'xlrd'}}, default None
If io is not a buffer or path, this must be set to identify io.
Engine compatibility :
- ``openpyxl`` supports newer Excel file formats.
- ``calamine`` supports Excel (.xls, .xlsx, .xlsm, .xlsb)
and OpenDocument (.ods) file formats.
- ``odf`` supports OpenDocument file formats (.odf, .ods, .odt).
- ``pyxlsb`` supports Binary Excel files.
- ``xlrd`` supports old-style Excel files (.xls).
When ``engine=None``, the following logic will be used to determine the engine:
- If ``path_or_buffer`` is an OpenDocument format (.odf, .ods, .odt),
then `odf <https://pypi.org/project/odfpy/>`_ will be used.
- Otherwise if ``path_or_buffer`` is an xls format, ``xlrd`` will be used.
- Otherwise if ``path_or_buffer`` is in xlsb format, ``pyxlsb`` will be used.
- Otherwise ``openpyxl`` will be used.
converters : dict, default None
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 Excel cell content, and return the transformed
content.
true_values : list, default None
Values to consider as True.
false_values : list, default None
Values to consider as False.
skiprows : list-like, 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]``.
nrows : int, default None
Number of rows to parse.
na_values : scalar, str, list-like, or dict, default None
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 NAs, 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.
parse_dates : bool, list-like, or dict, default False
The behavior is as follows:
* ``bool``. If True -> try parsing the index.
* ``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 lists. e.g. If [[1, 3]] -> combine columns 1 and 3 and parse as
a single date column.
* ``dict``, e.g. {{'foo' : [1, 3]}} -> parse columns 1, 3 as date and call
result 'foo'
If a column or index contains an unparsable date, the entire column or
index will be returned unaltered as an object data type. If you don`t want to
parse some cells as date just change their type in Excel to "Text".
For non-standard datetime parsing, use ``pd.to_datetime`` after ``pd.read_excel``.
Note: A fast-path exists for iso8601-formatted dates.
date_parser : function, 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:`to_datetime` as-needed.
date_format : str or dict of column -> format, default ``None``
If used in conjunction with ``parse_dates``, will parse dates according to this
format. For anything more complex,
please read in as ``object`` and then apply :func:`to_datetime` as-needed.
.. versionadded:: 2.0.0
thousands : str, default None
Thousands separator for parsing string columns to numeric. Note that
this parameter is only necessary for columns stored as TEXT in Excel,
any numeric columns will automatically be parsed, regardless of display
format.
decimal : str, default '.'
Character to recognize as decimal point for parsing string columns to numeric.
Note that this parameter is only necessary for columns stored as TEXT in Excel,
any numeric columns will automatically be parsed, regardless of display
format.(e.g. use ',' for European data).
.. versionadded:: 1.4.0
comment : str, default None
Comments out remainder of line. Pass a character or characters to this
argument to indicate comments in the input file. Any data between the
comment string and the end of the current line is ignored.
skipfooter : int, default 0
Rows at the end to skip (0-indexed).
{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
engine_kwargs : dict, optional
Arbitrary keyword arguments passed to excel engine.
Returns
-------
DataFrame or dict of DataFrames
DataFrame from the passed in Excel file. See notes in sheet_name
argument for more information on when a dict of DataFrames is returned.
See Also
--------
DataFrame.to_excel : Write DataFrame to an Excel file.
DataFrame.to_csv : Write DataFrame to a comma-separated values (csv) file.
read_csv : Read a comma-separated values (csv) file into DataFrame.
read_fwf : Read a table of fixed-width formatted lines into DataFrame.
Notes
-----
For specific information on the methods used for each Excel engine, refer to the pandas
:ref:`user guide <io.excel_reader>`
Examples
--------
The file can be read using the file name as string or an open file object:
>>> pd.read_excel('tmp.xlsx', index_col=0) # doctest: +SKIP
Name Value
0 string1 1
1 string2 2
2 #Comment 3
>>> pd.read_excel(open('tmp.xlsx', 'rb'),
... sheet_name='Sheet3') # doctest: +SKIP
Unnamed: 0 Name Value
0 0 string1 1
1 1 string2 2
2 2 #Comment 3
Index and header can be specified via the `index_col` and `header` arguments
>>> pd.read_excel('tmp.xlsx', index_col=None, header=None) # doctest: +SKIP
0 1 2
0 NaN Name Value
1 0.0 string1 1
2 1.0 string2 2
3 2.0 #Comment 3
Column types are inferred but can be explicitly specified
>>> pd.read_excel('tmp.xlsx', index_col=0,
... dtype={{'Name': str, 'Value': float}}) # doctest: +SKIP
Name Value
0 string1 1.0
1 string2 2.0
2 #Comment 3.0
True, False, and NA values, and thousands separators have defaults,
but can be explicitly specified, too. Supply the values you would like
as strings or lists of strings!
>>> pd.read_excel('tmp.xlsx', index_col=0,
... na_values=['string1', 'string2']) # doctest: +SKIP
Name Value
0 NaN 1
1 NaN 2
2 #Comment 3
Comment lines in the excel input file can be skipped using the
``comment`` kwarg.
>>> pd.read_excel('tmp.xlsx', index_col=0, comment='#') # doctest: +SKIP
Name Value
0 string1 1.0
1 string2 2.0
2 None NaN
"""
)
@overload
def read_excel(
io,
# sheet name is str or int -> DataFrame
sheet_name: str | int = ...,
*,
header: int | Sequence[int] | None = ...,
names: SequenceNotStr[Hashable] | range | None = ...,
index_col: int | str | Sequence[int] | None = ...,
usecols: int
| str
| Sequence[int]
| Sequence[str]
| Callable[[str], bool]
| None = ...,
dtype: DtypeArg | None = ...,
engine: Literal["xlrd", "openpyxl", "odf", "pyxlsb", "calamine"] | None = ...,
converters: dict[str, Callable] | dict[int, Callable] | None = ...,
true_values: Iterable[Hashable] | None = ...,
false_values: Iterable[Hashable] | None = ...,
skiprows: Sequence[int] | int | Callable[[int], object] | None = ...,
nrows: int | None = ...,
na_values=...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool = ...,
parse_dates: list | dict | bool = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: dict[Hashable, str] | str | None = ...,
thousands: str | None = ...,
decimal: str = ...,
comment: str | None = ...,
skipfooter: int = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> DataFrame:
...
@overload
def read_excel(
io,
# sheet name is list or None -> dict[IntStrT, DataFrame]
sheet_name: list[IntStrT] | None,
*,
header: int | Sequence[int] | None = ...,
names: SequenceNotStr[Hashable] | range | None = ...,
index_col: int | str | Sequence[int] | None = ...,
usecols: int
| str
| Sequence[int]
| Sequence[str]
| Callable[[str], bool]
| None = ...,
dtype: DtypeArg | None = ...,
engine: Literal["xlrd", "openpyxl", "odf", "pyxlsb", "calamine"] | None = ...,
converters: dict[str, Callable] | dict[int, Callable] | None = ...,
true_values: Iterable[Hashable] | None = ...,
false_values: Iterable[Hashable] | None = ...,
skiprows: Sequence[int] | int | Callable[[int], object] | None = ...,
nrows: int | None = ...,
na_values=...,
keep_default_na: bool = ...,
na_filter: bool = ...,
verbose: bool = ...,
parse_dates: list | dict | bool = ...,
date_parser: Callable | lib.NoDefault = ...,
date_format: dict[Hashable, str] | str | None = ...,
thousands: str | None = ...,
decimal: str = ...,
comment: str | None = ...,
skipfooter: int = ...,
storage_options: StorageOptions = ...,
dtype_backend: DtypeBackend | lib.NoDefault = ...,
) -> dict[IntStrT, DataFrame]:
...
@doc(storage_options=_shared_docs["storage_options"])
@Appender(_read_excel_doc)
def read_excel(
io,
sheet_name: str | int | list[IntStrT] | None = 0,
*,
header: int | Sequence[int] | None = 0,
names: SequenceNotStr[Hashable] | range | None = None,
index_col: int | str | Sequence[int] | None = None,
usecols: int
| str
| Sequence[int]
| Sequence[str]
| Callable[[str], bool]
| None = None,
dtype: DtypeArg | None = None,
engine: Literal["xlrd", "openpyxl", "odf", "pyxlsb", "calamine"] | None = None,
converters: dict[str, Callable] | dict[int, Callable] | None = None,
true_values: Iterable[Hashable] | None = None,
false_values: Iterable[Hashable] | None = None,
skiprows: Sequence[int] | int | Callable[[int], object] | None = None,
nrows: int | None = None,
na_values=None,
keep_default_na: bool = True,
na_filter: bool = True,
verbose: bool = False,
parse_dates: list | dict | bool = False,
date_parser: Callable | lib.NoDefault = lib.no_default,
date_format: dict[Hashable, str] | str | None = None,
thousands: str | None = None,
decimal: str = ".",
comment: str | None = None,
skipfooter: int = 0,
storage_options: StorageOptions | None = None,
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
engine_kwargs: dict | None = None,
) -> DataFrame | dict[IntStrT, DataFrame]:
check_dtype_backend(dtype_backend)
should_close = False
if engine_kwargs is None:
engine_kwargs = {}
if not isinstance(io, ExcelFile):
should_close = True
io = ExcelFile(
io,
storage_options=storage_options,
engine=engine,
engine_kwargs=engine_kwargs,
)
elif engine and engine != io.engine:
raise ValueError(
"Engine should not be specified when passing "
"an ExcelFile - ExcelFile already has the engine set"
)
try:
data = io.parse(
sheet_name=sheet_name,
header=header,
names=names,
index_col=index_col,
usecols=usecols,
dtype=dtype,
converters=converters,
true_values=true_values,
false_values=false_values,
skiprows=skiprows,
nrows=nrows,
na_values=na_values,
keep_default_na=keep_default_na,
na_filter=na_filter,
verbose=verbose,
parse_dates=parse_dates,
date_parser=date_parser,
date_format=date_format,
thousands=thousands,
decimal=decimal,
comment=comment,
skipfooter=skipfooter,
dtype_backend=dtype_backend,
)
finally:
# make sure to close opened file handles
if should_close:
io.close()
return data
_WorkbookT = TypeVar("_WorkbookT")
class BaseExcelReader(Generic[_WorkbookT]):
book: _WorkbookT
def __init__(
self,
filepath_or_buffer,
storage_options: StorageOptions | None = None,
engine_kwargs: dict | None = None,
) -> None:
if engine_kwargs is None:
engine_kwargs = {}
# First argument can also be bytes, so create a buffer
if isinstance(filepath_or_buffer, bytes):
filepath_or_buffer = BytesIO(filepath_or_buffer)
self.handles = IOHandles(
handle=filepath_or_buffer, compression={"method": None}
)
if not isinstance(filepath_or_buffer, (ExcelFile, self._workbook_class)):
self.handles = get_handle(
filepath_or_buffer, "rb", storage_options=storage_options, is_text=False
)
if isinstance(self.handles.handle, self._workbook_class):
self.book = self.handles.handle
elif hasattr(self.handles.handle, "read"):
# N.B. xlrd.Book has a read attribute too
self.handles.handle.seek(0)
try:
self.book = self.load_workbook(self.handles.handle, engine_kwargs)
except Exception:
self.close()
raise
else:
raise ValueError(
"Must explicitly set engine if not passing in buffer or path for io."
)
@property
def _workbook_class(self) -> type[_WorkbookT]:
raise NotImplementedError
def load_workbook(self, filepath_or_buffer, engine_kwargs) -> _WorkbookT:
raise NotImplementedError
def close(self) -> None:
if hasattr(self, "book"):
if hasattr(self.book, "close"):
# pyxlsb: opens a TemporaryFile
# openpyxl: https://stackoverflow.com/questions/31416842/
# openpyxl-does-not-close-excel-workbook-in-read-only-mode
self.book.close()
elif hasattr(self.book, "release_resources"):
# xlrd
# https://github.com/python-excel/xlrd/blob/2.0.1/xlrd/book.py#L548
self.book.release_resources()
self.handles.close()
@property
def sheet_names(self) -> list[str]:
raise NotImplementedError
def get_sheet_by_name(self, name: str):
raise NotImplementedError
def get_sheet_by_index(self, index: int):
raise NotImplementedError
def get_sheet_data(self, sheet, rows: int | None = None):
raise NotImplementedError
def raise_if_bad_sheet_by_index(self, index: int) -> None:
n_sheets = len(self.sheet_names)
if index >= n_sheets:
raise ValueError(
f"Worksheet index {index} is invalid, {n_sheets} worksheets found"
)
def raise_if_bad_sheet_by_name(self, name: str) -> None:
if name not in self.sheet_names:
raise ValueError(f"Worksheet named '{name}' not found")
def _check_skiprows_func(
self,
skiprows: Callable,
rows_to_use: int,
) -> int:
"""
Determine how many file rows are required to obtain `nrows` data
rows when `skiprows` is a function.
Parameters
----------
skiprows : function
The function passed to read_excel by the user.
rows_to_use : int
The number of rows that will be needed for the header and
the data.
Returns
-------
int
"""
i = 0
rows_used_so_far = 0
while rows_used_so_far < rows_to_use:
if not skiprows(i):
rows_used_so_far += 1
i += 1
return i
def _calc_rows(
self,
header: int | Sequence[int] | None,
index_col: int | Sequence[int] | None,
skiprows: Sequence[int] | int | Callable[[int], object] | None,
nrows: int | None,
) -> int | None:
"""
If nrows specified, find the number of rows needed from the
file, otherwise return None.
Parameters
----------
header : int, list of int, or None
See read_excel docstring.
index_col : int, str, list of int, or None
See read_excel docstring.
skiprows : list-like, int, callable, or None
See read_excel docstring.
nrows : int or None
See read_excel docstring.
Returns
-------
int or None
"""
if nrows is None:
return None
if header is None:
header_rows = 1
elif is_integer(header):
header = cast(int, header)
header_rows = 1 + header
else:
header = cast(Sequence, header)
header_rows = 1 + header[-1]
# If there is a MultiIndex header and an index then there is also
# a row containing just the index name(s)
if is_list_like(header) and index_col is not None:
header = cast(Sequence, header)
if len(header) > 1:
header_rows += 1
if skiprows is None:
return header_rows + nrows
if is_integer(skiprows):
skiprows = cast(int, skiprows)
return header_rows + nrows + skiprows
if is_list_like(skiprows):
def f(skiprows: Sequence, x: int) -> bool:
return x in skiprows
skiprows = cast(Sequence, skiprows)
return self._check_skiprows_func(partial(f, skiprows), header_rows + nrows)
if callable(skiprows):
return self._check_skiprows_func(
skiprows,
header_rows + nrows,
)
# else unexpected skiprows type: read_excel will not optimize
# the number of rows read from file
return None
def parse(
self,
sheet_name: str | int | list[int] | list[str] | None = 0,
header: int | Sequence[int] | None = 0,
names: SequenceNotStr[Hashable] | range | None = None,
index_col: int | Sequence[int] | None = None,
usecols=None,
dtype: DtypeArg | None = None,
true_values: Iterable[Hashable] | None = None,
false_values: Iterable[Hashable] | None = None,
skiprows: Sequence[int] | int | Callable[[int], object] | None = None,
nrows: int | None = None,
na_values=None,
verbose: bool = False,
parse_dates: list | dict | bool = False,
date_parser: Callable | lib.NoDefault = lib.no_default,
date_format: dict[Hashable, str] | str | None = None,
thousands: str | None = None,
decimal: str = ".",
comment: str | None = None,
skipfooter: int = 0,
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
**kwds,
):
validate_header_arg(header)
validate_integer("nrows", nrows)
ret_dict = False
# Keep sheetname to maintain backwards compatibility.
sheets: list[int] | list[str]
if isinstance(sheet_name, list):
sheets = sheet_name
ret_dict = True
elif sheet_name is None:
sheets = self.sheet_names
ret_dict = True
elif isinstance(sheet_name, str):
sheets = [sheet_name]
else:
sheets = [sheet_name]
# handle same-type duplicates.
sheets = cast(Union[list[int], list[str]], list(dict.fromkeys(sheets).keys()))
output = {}
last_sheetname = None
for asheetname in sheets:
last_sheetname = asheetname
if verbose:
print(f"Reading sheet {asheetname}")
if isinstance(asheetname, str):
sheet = self.get_sheet_by_name(asheetname)
else: # assume an integer if not a string
sheet = self.get_sheet_by_index(asheetname)
file_rows_needed = self._calc_rows(header, index_col, skiprows, nrows)
data = self.get_sheet_data(sheet, file_rows_needed)
if hasattr(sheet, "close"):
# pyxlsb opens two TemporaryFiles
sheet.close()
usecols = maybe_convert_usecols(usecols)
if not data:
output[asheetname] = DataFrame()
continue
is_list_header = False
is_len_one_list_header = False
if is_list_like(header):
assert isinstance(header, Sequence)
is_list_header = True
if len(header) == 1:
is_len_one_list_header = True
if is_len_one_list_header:
header = cast(Sequence[int], header)[0]
# forward fill and pull out names for MultiIndex column
header_names = None
if header is not None and is_list_like(header):
assert isinstance(header, Sequence)
header_names = []
control_row = [True] * len(data[0])
for row in header:
if is_integer(skiprows):
assert isinstance(skiprows, int)
row += skiprows
if row > len(data) - 1:
raise ValueError(
f"header index {row} exceeds maximum index "
f"{len(data) - 1} of data.",
)
data[row], control_row = fill_mi_header(data[row], control_row)
if index_col is not None:
header_name, _ = pop_header_name(data[row], index_col)
header_names.append(header_name)
# If there is a MultiIndex header and an index then there is also
# a row containing just the index name(s)
has_index_names = False
if is_list_header and not is_len_one_list_header and index_col is not None:
index_col_list: Sequence[int]
if isinstance(index_col, int):
index_col_list = [index_col]
else:
assert isinstance(index_col, Sequence)
index_col_list = index_col
# We have to handle mi without names. If any of the entries in the data
# columns are not empty, this is a regular row
assert isinstance(header, Sequence)
if len(header) < len(data):
potential_index_names = data[len(header)]
potential_data = [
x
for i, x in enumerate(potential_index_names)
if not control_row[i] and i not in index_col_list
]
has_index_names = all(x == "" or x is None for x in potential_data)
if is_list_like(index_col):
# Forward fill values for MultiIndex index.
if header is None:
offset = 0
elif isinstance(header, int):
offset = 1 + header
else:
offset = 1 + max(header)
# GH34673: if MultiIndex names present and not defined in the header,
# offset needs to be incremented so that forward filling starts
# from the first MI value instead of the name
if has_index_names:
offset += 1
# Check if we have an empty dataset
# before trying to collect data.
if offset < len(data):
assert isinstance(index_col, Sequence)
for col in index_col:
last = data[offset][col]
for row in range(offset + 1, len(data)):
if data[row][col] == "" or data[row][col] is None:
data[row][col] = last
else:
last = data[row][col]
# GH 12292 : error when read one empty column from excel file
try:
parser = TextParser(
data,
names=names,
header=header,
index_col=index_col,
has_index_names=has_index_names,
dtype=dtype,
true_values=true_values,
false_values=false_values,
skiprows=skiprows,
nrows=nrows,
na_values=na_values,
skip_blank_lines=False, # GH 39808
parse_dates=parse_dates,
date_parser=date_parser,
date_format=date_format,
thousands=thousands,
decimal=decimal,
comment=comment,
skipfooter=skipfooter,
usecols=usecols,
dtype_backend=dtype_backend,
**kwds,
)
output[asheetname] = parser.read(nrows=nrows)
if header_names:
output[asheetname].columns = output[asheetname].columns.set_names(
header_names
)
except EmptyDataError:
# No Data, return an empty DataFrame
output[asheetname] = DataFrame()
except Exception as err:
err.args = (f"{err.args[0]} (sheet: {asheetname})", *err.args[1:])
raise err
if last_sheetname is None:
raise ValueError("Sheet name is an empty list")
if ret_dict:
return output
else:
return output[last_sheetname]
@doc(storage_options=_shared_docs["storage_options"])
class ExcelWriter(Generic[_WorkbookT]):
"""
Class for writing DataFrame objects into excel sheets.
Default is to use:
* `xlsxwriter <https://pypi.org/project/XlsxWriter/>`__ for xlsx files if xlsxwriter
is installed otherwise `openpyxl <https://pypi.org/project/openpyxl/>`__
* `odswriter <https://pypi.org/project/odswriter/>`__ for ods files
See ``DataFrame.to_excel`` for typical usage.
The writer should be used as a context manager. Otherwise, call `close()` to save
and close any opened file handles.
Parameters
----------
path : str or typing.BinaryIO
Path to xls or xlsx or ods file.
engine : str (optional)
Engine to use for writing. If None, defaults to
``io.excel.<extension>.writer``. NOTE: can only be passed as a keyword
argument.
date_format : str, default None
Format string for dates written into Excel files (e.g. 'YYYY-MM-DD').
datetime_format : str, default None
Format string for datetime objects written into Excel files.
(e.g. 'YYYY-MM-DD HH:MM:SS').
mode : {{'w', 'a'}}, default 'w'
File mode to use (write or append). Append does not work with fsspec URLs.
{storage_options}
if_sheet_exists : {{'error', 'new', 'replace', 'overlay'}}, default 'error'
How to behave when trying to write to a sheet that already
exists (append mode only).
* error: raise a ValueError.
* new: Create a new sheet, with a name determined by the engine.
* replace: Delete the contents of the sheet before writing to it.
* overlay: Write contents to the existing sheet without first removing,
but possibly over top of, the existing contents.
.. versionadded:: 1.3.0
.. versionchanged:: 1.4.0
Added ``overlay`` option
engine_kwargs : dict, optional
Keyword arguments to be passed into the engine. These will be passed to
the following functions of the respective engines:
* xlsxwriter: ``xlsxwriter.Workbook(file, **engine_kwargs)``
* openpyxl (write mode): ``openpyxl.Workbook(**engine_kwargs)``
* openpyxl (append mode): ``openpyxl.load_workbook(file, **engine_kwargs)``
* odswriter: ``odf.opendocument.OpenDocumentSpreadsheet(**engine_kwargs)``
.. versionadded:: 1.3.0
Notes
-----
For compatibility with CSV writers, ExcelWriter serializes lists
and dicts to strings before writing.
Examples
--------
Default usage:
>>> df = pd.DataFrame([["ABC", "XYZ"]], columns=["Foo", "Bar"]) # doctest: +SKIP
>>> with pd.ExcelWriter("path_to_file.xlsx") as writer:
... df.to_excel(writer) # doctest: +SKIP
To write to separate sheets in a single file:
>>> df1 = pd.DataFrame([["AAA", "BBB"]], columns=["Spam", "Egg"]) # doctest: +SKIP
>>> df2 = pd.DataFrame([["ABC", "XYZ"]], columns=["Foo", "Bar"]) # doctest: +SKIP
>>> with pd.ExcelWriter("path_to_file.xlsx") as writer:
... df1.to_excel(writer, sheet_name="Sheet1") # doctest: +SKIP
... df2.to_excel(writer, sheet_name="Sheet2") # doctest: +SKIP
You can set the date format or datetime format:
>>> from datetime import date, datetime # doctest: +SKIP
>>> df = pd.DataFrame(
... [
... [date(2014, 1, 31), date(1999, 9, 24)],
... [datetime(1998, 5, 26, 23, 33, 4), datetime(2014, 2, 28, 13, 5, 13)],
... ],
... index=["Date", "Datetime"],
... columns=["X", "Y"],
... ) # doctest: +SKIP
>>> with pd.ExcelWriter(
... "path_to_file.xlsx",
... date_format="YYYY-MM-DD",
... datetime_format="YYYY-MM-DD HH:MM:SS"
... ) as writer:
... df.to_excel(writer) # doctest: +SKIP
You can also append to an existing Excel file:
>>> with pd.ExcelWriter("path_to_file.xlsx", mode="a", engine="openpyxl") as writer:
... df.to_excel(writer, sheet_name="Sheet3") # doctest: +SKIP
Here, the `if_sheet_exists` parameter can be set to replace a sheet if it
already exists:
>>> with ExcelWriter(
... "path_to_file.xlsx",
... mode="a",
... engine="openpyxl",
... if_sheet_exists="replace",
... ) as writer:
... df.to_excel(writer, sheet_name="Sheet1") # doctest: +SKIP
You can also write multiple DataFrames to a single sheet. Note that the
``if_sheet_exists`` parameter needs to be set to ``overlay``:
>>> with ExcelWriter("path_to_file.xlsx",
... mode="a",
... engine="openpyxl",
... if_sheet_exists="overlay",
... ) as writer:
... df1.to_excel(writer, sheet_name="Sheet1")
... df2.to_excel(writer, sheet_name="Sheet1", startcol=3) # doctest: +SKIP
You can store Excel file in RAM:
>>> import io
>>> df = pd.DataFrame([["ABC", "XYZ"]], columns=["Foo", "Bar"])
>>> buffer = io.BytesIO()
>>> with pd.ExcelWriter(buffer) as writer:
... df.to_excel(writer)
You can pack Excel file into zip archive:
>>> import zipfile # doctest: +SKIP
>>> df = pd.DataFrame([["ABC", "XYZ"]], columns=["Foo", "Bar"]) # doctest: +SKIP
>>> with zipfile.ZipFile("path_to_file.zip", "w") as zf:
... with zf.open("filename.xlsx", "w") as buffer:
... with pd.ExcelWriter(buffer) as writer:
... df.to_excel(writer) # doctest: +SKIP
You can specify additional arguments to the underlying engine:
>>> with pd.ExcelWriter(
... "path_to_file.xlsx",
... engine="xlsxwriter",
... engine_kwargs={{"options": {{"nan_inf_to_errors": True}}}}
... ) as writer:
... df.to_excel(writer) # doctest: +SKIP
In append mode, ``engine_kwargs`` are passed through to
openpyxl's ``load_workbook``:
>>> with pd.ExcelWriter(
... "path_to_file.xlsx",
... engine="openpyxl",
... mode="a",
... engine_kwargs={{"keep_vba": True}}
... ) as writer:
... df.to_excel(writer, sheet_name="Sheet2") # doctest: +SKIP
"""
# Defining an ExcelWriter implementation (see abstract methods for more...)
# - Mandatory
# - ``write_cells(self, cells, sheet_name=None, startrow=0, startcol=0)``
# --> called to write additional DataFrames to disk
# - ``_supported_extensions`` (tuple of supported extensions), used to
# check that engine supports the given extension.
# - ``_engine`` - string that gives the engine name. Necessary to
# instantiate class directly and bypass ``ExcelWriterMeta`` engine
# lookup.
# - ``save(self)`` --> called to save file to disk
# - Mostly mandatory (i.e. should at least exist)
# - book, cur_sheet, path
# - Optional:
# - ``__init__(self, path, engine=None, **kwargs)`` --> always called
# with path as first argument.
# You also need to register the class with ``register_writer()``.
# Technically, ExcelWriter implementations don't need to subclass
# ExcelWriter.
_engine: str
_supported_extensions: tuple[str, ...]
def __new__(
cls,
path: FilePath | WriteExcelBuffer | ExcelWriter,
engine: str | None = None,
date_format: str | None = None,
datetime_format: str | None = None,
mode: str = "w",
storage_options: StorageOptions | None = None,
if_sheet_exists: ExcelWriterIfSheetExists | None = None,
engine_kwargs: dict | None = None,
) -> Self:
# only switch class if generic(ExcelWriter)
if cls is ExcelWriter:
if engine is None or (isinstance(engine, str) and engine == "auto"):
if isinstance(path, str):
ext = os.path.splitext(path)[-1][1:]
else:
ext = "xlsx"
try:
engine = config.get_option(f"io.excel.{ext}.writer", silent=True)
if engine == "auto":
engine = get_default_engine(ext, mode="writer")
except KeyError as err:
raise ValueError(f"No engine for filetype: '{ext}'") from err
# for mypy
assert engine is not None
# error: Incompatible types in assignment (expression has type
# "type[ExcelWriter[Any]]", variable has type "type[Self]")
cls = get_writer(engine) # type: ignore[assignment]
return object.__new__(cls)
# declare external properties you can count on
_path = None
@property
def supported_extensions(self) -> tuple[str, ...]:
"""Extensions that writer engine supports."""
return self._supported_extensions
@property
def engine(self) -> str:
"""Name of engine."""
return self._engine
@property
def sheets(self) -> dict[str, Any]:
"""Mapping of sheet names to sheet objects."""
raise NotImplementedError
@property
def book(self) -> _WorkbookT:
"""
Book instance. Class type will depend on the engine used.
This attribute can be used to access engine-specific features.
"""
raise NotImplementedError
def _write_cells(
self,
cells,
sheet_name: str | None = None,
startrow: int = 0,
startcol: int = 0,
freeze_panes: tuple[int, int] | None = None,
) -> None:
"""
Write given formatted cells into Excel an excel sheet
Parameters
----------
cells : generator
cell of formatted data to save to Excel sheet
sheet_name : str, default None
Name of Excel sheet, if None, then use self.cur_sheet
startrow : upper left cell row to dump data frame
startcol : upper left cell column to dump data frame
freeze_panes: int tuple of length 2
contains the bottom-most row and right-most column to freeze
"""
raise NotImplementedError
def _save(self) -> None:
"""
Save workbook to disk.
"""
raise NotImplementedError
def __init__(
self,
path: FilePath | WriteExcelBuffer | ExcelWriter,
engine: str | None = None,
date_format: str | None = None,
datetime_format: str | None = None,
mode: str = "w",
storage_options: StorageOptions | None = None,
if_sheet_exists: ExcelWriterIfSheetExists | None = None,
engine_kwargs: dict[str, Any] | None = None,
) -> None:
# validate that this engine can handle the extension
if isinstance(path, str):
ext = os.path.splitext(path)[-1]
self.check_extension(ext)
# use mode to open the file
if "b" not in mode:
mode += "b"
# use "a" for the user to append data to excel but internally use "r+" to let
# the excel backend first read the existing file and then write any data to it
mode = mode.replace("a", "r+")
if if_sheet_exists not in (None, "error", "new", "replace", "overlay"):
raise ValueError(
f"'{if_sheet_exists}' is not valid for if_sheet_exists. "
"Valid options are 'error', 'new', 'replace' and 'overlay'."
)
if if_sheet_exists and "r+" not in mode:
raise ValueError("if_sheet_exists is only valid in append mode (mode='a')")
if if_sheet_exists is None:
if_sheet_exists = "error"
self._if_sheet_exists = if_sheet_exists
# cast ExcelWriter to avoid adding 'if self._handles is not None'
self._handles = IOHandles(
cast(IO[bytes], path), compression={"compression": None}
)
if not isinstance(path, ExcelWriter):
self._handles = get_handle(
path, mode, storage_options=storage_options, is_text=False
)
self._cur_sheet = None
if date_format is None:
self._date_format = "YYYY-MM-DD"
else:
self._date_format = date_format
if datetime_format is None:
self._datetime_format = "YYYY-MM-DD HH:MM:SS"
else:
self._datetime_format = datetime_format
self._mode = mode
@property
def date_format(self) -> str:
"""
Format string for dates written into Excel files (e.g. 'YYYY-MM-DD').
"""
return self._date_format
@property
def datetime_format(self) -> str:
"""
Format string for dates written into Excel files (e.g. 'YYYY-MM-DD').
"""
return self._datetime_format
@property
def if_sheet_exists(self) -> str:
"""
How to behave when writing to a sheet that already exists in append mode.
"""
return self._if_sheet_exists
def __fspath__(self) -> str:
return getattr(self._handles.handle, "name", "")
def _get_sheet_name(self, sheet_name: str | None) -> str:
if sheet_name is None:
sheet_name = self._cur_sheet
if sheet_name is None: # pragma: no cover
raise ValueError("Must pass explicit sheet_name or set _cur_sheet property")
return sheet_name
def _value_with_fmt(
self, val
) -> tuple[
int | float | bool | str | datetime.datetime | datetime.date, str | None
]:
"""
Convert numpy types to Python types for the Excel writers.
Parameters
----------
val : object
Value to be written into cells
Returns
-------
Tuple with the first element being the converted value and the second
being an optional format
"""
fmt = None
if is_integer(val):
val = int(val)
elif is_float(val):
val = float(val)
elif is_bool(val):
val = bool(val)
elif isinstance(val, datetime.datetime):
fmt = self._datetime_format
elif isinstance(val, datetime.date):
fmt = self._date_format
elif isinstance(val, datetime.timedelta):
val = val.total_seconds() / 86400
fmt = "0"
else:
val = str(val)
return val, fmt
@classmethod
def check_extension(cls, ext: str) -> Literal[True]:
"""
checks that path's extension against the Writer's supported
extensions. If it isn't supported, raises UnsupportedFiletypeError.
"""
if ext.startswith("."):
ext = ext[1:]
if not any(ext in extension for extension in cls._supported_extensions):
raise ValueError(f"Invalid extension for engine '{cls.engine}': '{ext}'")
return True
# Allow use as a contextmanager
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 close(self) -> None:
"""synonym for save, to make it more file-like"""
self._save()
self._handles.close()
XLS_SIGNATURES = (
b"\x09\x00\x04\x00\x07\x00\x10\x00", # BIFF2
b"\x09\x02\x06\x00\x00\x00\x10\x00", # BIFF3
b"\x09\x04\x06\x00\x00\x00\x10\x00", # BIFF4
b"\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1", # Compound File Binary
)
ZIP_SIGNATURE = b"PK\x03\x04"
PEEK_SIZE = max(map(len, XLS_SIGNATURES + (ZIP_SIGNATURE,)))
@doc(storage_options=_shared_docs["storage_options"])
def inspect_excel_format(
content_or_path: FilePath | ReadBuffer[bytes],
storage_options: StorageOptions | None = None,
) -> str | None:
"""
Inspect the path or content of an excel file and get its format.
Adopted from xlrd: https://github.com/python-excel/xlrd.
Parameters
----------
content_or_path : str or file-like object
Path to file or content of file to inspect. May be a URL.
{storage_options}
Returns
-------
str or None
Format of file if it can be determined.
Raises
------
ValueError
If resulting stream is empty.
BadZipFile
If resulting stream does not have an XLS signature and is not a valid zipfile.
"""
if isinstance(content_or_path, bytes):
content_or_path = BytesIO(content_or_path)
with get_handle(
content_or_path, "rb", storage_options=storage_options, is_text=False
) as handle:
stream = handle.handle
stream.seek(0)
buf = stream.read(PEEK_SIZE)
if buf is None:
raise ValueError("stream is empty")
assert isinstance(buf, bytes)
peek = buf
stream.seek(0)
if any(peek.startswith(sig) for sig in XLS_SIGNATURES):
return "xls"
elif not peek.startswith(ZIP_SIGNATURE):
return None
with zipfile.ZipFile(stream) as zf:
# Workaround for some third party files that use forward slashes and
# lower case names.
component_names = [
name.replace("\\", "/").lower() for name in zf.namelist()
]
if "xl/workbook.xml" in component_names:
return "xlsx"
if "xl/workbook.bin" in component_names:
return "xlsb"
if "content.xml" in component_names:
return "ods"
return "zip"
class ExcelFile:
"""
Class for parsing tabular Excel sheets into DataFrame objects.
See read_excel for more documentation.
Parameters
----------
path_or_buffer : str, bytes, path object (pathlib.Path or py._path.local.LocalPath),
A file-like object, xlrd workbook or openpyxl workbook.
If a string or path object, expected to be a path to a
.xls, .xlsx, .xlsb, .xlsm, .odf, .ods, or .odt file.
engine : str, default None
If io is not a buffer or path, this must be set to identify io.
Supported engines: ``xlrd``, ``openpyxl``, ``odf``, ``pyxlsb``, ``calamine``
Engine compatibility :
- ``xlrd`` supports old-style Excel files (.xls).
- ``openpyxl`` supports newer Excel file formats.
- ``odf`` supports OpenDocument file formats (.odf, .ods, .odt).
- ``pyxlsb`` supports Binary Excel files.
- ``calamine`` supports Excel (.xls, .xlsx, .xlsm, .xlsb)
and OpenDocument (.ods) file formats.
.. versionchanged:: 1.2.0
The engine `xlrd <https://xlrd.readthedocs.io/en/latest/>`_
now only supports old-style ``.xls`` files.
When ``engine=None``, the following logic will be
used to determine the engine:
- If ``path_or_buffer`` is an OpenDocument format (.odf, .ods, .odt),
then `odf <https://pypi.org/project/odfpy/>`_ will be used.
- Otherwise if ``path_or_buffer`` is an xls format,
``xlrd`` will be used.
- Otherwise if ``path_or_buffer`` is in xlsb format,
`pyxlsb <https://pypi.org/project/pyxlsb/>`_ will be used.
.. versionadded:: 1.3.0
- Otherwise if `openpyxl <https://pypi.org/project/openpyxl/>`_ is installed,
then ``openpyxl`` will be used.
- Otherwise if ``xlrd >= 2.0`` is installed, a ``ValueError`` will be raised.
.. warning::
Please do not report issues when using ``xlrd`` to read ``.xlsx`` files.
This is not supported, switch to using ``openpyxl`` instead.
engine_kwargs : dict, optional
Arbitrary keyword arguments passed to excel engine.
Examples
--------
>>> file = pd.ExcelFile('myfile.xlsx') # doctest: +SKIP
>>> with pd.ExcelFile("myfile.xls") as xls: # doctest: +SKIP
... df1 = pd.read_excel(xls, "Sheet1") # doctest: +SKIP
"""
from pandas.io.excel._calamine import CalamineReader
from pandas.io.excel._odfreader import ODFReader
from pandas.io.excel._openpyxl import OpenpyxlReader
from pandas.io.excel._pyxlsb import PyxlsbReader
from pandas.io.excel._xlrd import XlrdReader
_engines: Mapping[str, Any] = {
"xlrd": XlrdReader,
"openpyxl": OpenpyxlReader,
"odf": ODFReader,
"pyxlsb": PyxlsbReader,
"calamine": CalamineReader,
}
def __init__(
self,
path_or_buffer,
engine: str | None = None,
storage_options: StorageOptions | None = None,
engine_kwargs: dict | None = None,
) -> None:
if engine_kwargs is None:
engine_kwargs = {}
if engine is not None and engine not in self._engines:
raise ValueError(f"Unknown engine: {engine}")
# First argument can also be bytes, so create a buffer
if isinstance(path_or_buffer, bytes):
path_or_buffer = BytesIO(path_or_buffer)
warnings.warn(
"Passing bytes to 'read_excel' is deprecated and "
"will be removed in a future version. To read from a "
"byte string, wrap it in a `BytesIO` object.",
FutureWarning,
stacklevel=find_stack_level(),
)
# Could be a str, ExcelFile, Book, etc.
self.io = path_or_buffer
# Always a string
self._io = stringify_path(path_or_buffer)
# Determine xlrd version if installed
if import_optional_dependency("xlrd", errors="ignore") is None:
xlrd_version = None
else:
import xlrd
xlrd_version = Version(get_version(xlrd))
if engine is None:
# Only determine ext if it is needed
ext: str | None
if xlrd_version is not None and isinstance(path_or_buffer, xlrd.Book):
ext = "xls"
else:
ext = inspect_excel_format(
content_or_path=path_or_buffer, storage_options=storage_options
)
if ext is None:
raise ValueError(
"Excel file format cannot be determined, you must specify "
"an engine manually."
)
engine = config.get_option(f"io.excel.{ext}.reader", silent=True)
if engine == "auto":
engine = get_default_engine(ext, mode="reader")
assert engine is not None
self.engine = engine
self.storage_options = storage_options
self._reader = self._engines[engine](
self._io,
storage_options=storage_options,
engine_kwargs=engine_kwargs,
)
def __fspath__(self):
return self._io
def parse(
self,
sheet_name: str | int | list[int] | list[str] | None = 0,
header: int | Sequence[int] | None = 0,
names: SequenceNotStr[Hashable] | range | None = None,
index_col: int | Sequence[int] | None = None,
usecols=None,
converters=None,
true_values: Iterable[Hashable] | None = None,
false_values: Iterable[Hashable] | None = None,
skiprows: Sequence[int] | int | Callable[[int], object] | None = None,
nrows: int | None = None,
na_values=None,
parse_dates: list | dict | bool = False,
date_parser: Callable | lib.NoDefault = lib.no_default,
date_format: str | dict[Hashable, str] | None = None,
thousands: str | None = None,
comment: str | None = None,
skipfooter: int = 0,
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
**kwds,
) -> DataFrame | dict[str, DataFrame] | dict[int, DataFrame]:
"""
Parse specified sheet(s) into a DataFrame.
Equivalent to read_excel(ExcelFile, ...) See the read_excel
docstring for more info on accepted parameters.
Returns
-------
DataFrame or dict of DataFrames
DataFrame from the passed in Excel file.
Examples
--------
>>> df = pd.DataFrame([[1, 2, 3], [4, 5, 6]], columns=['A', 'B', 'C'])
>>> df.to_excel('myfile.xlsx') # doctest: +SKIP
>>> file = pd.ExcelFile('myfile.xlsx') # doctest: +SKIP
>>> file.parse() # doctest: +SKIP
"""
return self._reader.parse(
sheet_name=sheet_name,
header=header,
names=names,
index_col=index_col,
usecols=usecols,
converters=converters,
true_values=true_values,
false_values=false_values,
skiprows=skiprows,
nrows=nrows,
na_values=na_values,
parse_dates=parse_dates,
date_parser=date_parser,
date_format=date_format,
thousands=thousands,
comment=comment,
skipfooter=skipfooter,
dtype_backend=dtype_backend,
**kwds,
)
@property
def book(self):
return self._reader.book
@property
def sheet_names(self):
return self._reader.sheet_names
def close(self) -> None:
"""close io if necessary"""
self._reader.close()
def __enter__(self) -> Self:
return self
def __exit__(
self,
exc_type: type[BaseException] | None,
exc_value: BaseException | None,
traceback: TracebackType | None,
) -> None:
self.close()
|