From 8093a25586988f4d9237df0c181be176263c8106 Mon Sep 17 00:00:00 2001 From: Fidorc80 <114183964+Fidorc80@users.noreply.github.com> Date: Mon, 8 Dec 2025 15:05:58 -0800 Subject: [PATCH 1/4] inline docstrings for read_excel and storage options decorators in pandas/io/excel/_base.py. --- pandas/io/excel/_base.py | 585 ++++++++++++++++++++------------------- 1 file changed, 304 insertions(+), 281 deletions(-) diff --git a/pandas/io/excel/_base.py b/pandas/io/excel/_base.py index a171b1229f7bb..35a3155d96d5a 100644 --- a/pandas/io/excel/_base.py +++ b/pandas/io/excel/_base.py @@ -11,7 +11,6 @@ from decimal import Decimal from functools import partial import os -from textwrap import fill from typing import ( IO, TYPE_CHECKING, @@ -30,15 +29,12 @@ 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, set_module, ) from pandas.util._exceptions import find_stack_level @@ -54,7 +50,6 @@ ) 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 ( @@ -88,274 +83,6 @@ StorageOptions, WriteExcelBuffer, ) -_read_excel_doc = ( - """ -Read an Excel file into a ``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, 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. - When ``None``, will return a dictionary containing DataFrames for each sheet. - - 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``: Returns a dictionary containing DataFrames for each sheet.. - -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 `_ 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. Does not include header rows. -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_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). -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'}} - Back-end data type applied to the resultant :class:`DataFrame` - (still experimental). If not specified, the default behavior - is to not use nullable data types. If specified, the behavior - is as follows: - - * ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame` - * ``"pyarrow"``: returns pyarrow-backed nullable - :class:`ArrowDtype` :class:`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 ` - -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 @@ -433,8 +160,6 @@ def read_excel( @set_module("pandas") -@doc(storage_options=_shared_docs["storage_options"]) -@Appender(_read_excel_doc) def read_excel( io, sheet_name: str | int | list[IntStrT] | None = 0, @@ -469,6 +194,283 @@ def read_excel( dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default, engine_kwargs: dict | None = None, ) -> DataFrame | dict[IntStrT, DataFrame]: + """ + Read an Excel file into a ``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, 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. + When ``None``, will return a dictionary containing DataFrames for each sheet. + + 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``: Returns a dictionary containing DataFrames for each sheet.. + + 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 `_ 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. Does not include header rows. + 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: '', '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN', '-NaN', '-nan', + '1.#IND', '1.#QNAN', '', 'N/A', 'NA', 'NULL', 'NaN', 'None', + 'n/a', 'nan', 'null'. + 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_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). + 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 : dict, optional + Extra options that make sense for a particular storage connection, e.g. + host, port, username, password, etc. For HTTP(S) URLs the key-value pairs + are forwarded to ``urllib.request.Request`` as header options. For other + URLs (e.g. starting with "s3://", and "gcs://") the key-value pairs are + forwarded to ``fsspec.open``. Please see ``fsspec`` and ``urllib`` for more + details, and for more examples on storage options refer `here + `_. + + dtype_backend : {'numpy_nullable', 'pyarrow'} + Back-end data type applied to the resultant :class:`DataFrame` + (still experimental). If not specified, the default behavior + is to not use nullable data types. If specified, the behavior + is as follows: + + * ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame` + * ``"pyarrow"``: returns pyarrow-backed nullable + :class:`ArrowDtype` :class:`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 ` + + 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 + """ check_dtype_backend(dtype_backend) should_close = False if engine_kwargs is None: @@ -951,7 +953,6 @@ def _parse_sheet( @set_module("pandas") -@doc(storage_options=_shared_docs["storage_options"]) class ExcelWriter(Generic[_WorkbookT]): """ Class for writing DataFrame objects into excel sheets. @@ -982,7 +983,15 @@ class ExcelWriter(Generic[_WorkbookT]): (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} + storage_options : dict, optional + Extra options that make sense for a particular storage connection, e.g. + host, port, username, password, etc. For HTTP(S) URLs the key-value pairs + are forwarded to ``urllib.request.Request`` as header options. For other + URLs (e.g. starting with "s3://", and "gcs://") the key-value pairs are + forwarded to ``fsspec.open``. Please see ``fsspec`` and ``urllib`` for more + details, and for more examples on storage options refer `here + `_. if_sheet_exists : {{'error', 'new', 'replace', 'overlay'}}, default 'error' How to behave when trying to write to a sheet that already @@ -1405,7 +1414,6 @@ def close(self) -> None: 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, @@ -1419,7 +1427,15 @@ def inspect_excel_format( ---------- content_or_path : str or file-like object Path to file or content of file to inspect. May be a URL. - {storage_options} + storage_options : dict, optional + Extra options that make sense for a particular storage connection, e.g. + host, port, username, password, etc. For HTTP(S) URLs the key-value pairs + are forwarded to ``urllib.request.Request`` as header options. For other + URLs (e.g. starting with "s3://", and "gcs://") the key-value pairs are + forwarded to ``fsspec.open``. Please see ``fsspec`` and ``urllib`` for more + details, and for more examples on storage options refer `here + `_. Returns ------- @@ -1467,7 +1483,6 @@ def inspect_excel_format( @set_module("pandas") -@doc(storage_options=_shared_docs["storage_options"]) class ExcelFile: """ Class for parsing tabular Excel sheets into DataFrame objects. @@ -1511,7 +1526,15 @@ class ExcelFile: Please do not report issues when using ``xlrd`` to read ``.xlsx`` files. This is not supported, switch to using ``openpyxl`` instead. - {storage_options} + storage_options : dict, optional + Extra options that make sense for a particular storage connection, e.g. + host, port, username, password, etc. For HTTP(S) URLs the key-value pairs + are forwarded to ``urllib.request.Request`` as header options. For other + URLs (e.g. starting with "s3://", and "gcs://") the key-value pairs are + forwarded to ``fsspec.open``. Please see ``fsspec`` and ``urllib`` for more + details, and for more examples on storage options refer `here + `_. engine_kwargs : dict, optional Arbitrary keyword arguments passed to excel engine. From 6c1470f7020cde98c587faf278cb42264577a054 Mon Sep 17 00:00:00 2001 From: Fidorc80 <114183964+Fidorc80@users.noreply.github.com> Date: Mon, 8 Dec 2025 15:31:09 -0800 Subject: [PATCH 2/4] Fixed formatting errors --- pandas/io/excel/_base.py | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/pandas/io/excel/_base.py b/pandas/io/excel/_base.py index 35a3155d96d5a..c93ad21faa5f2 100644 --- a/pandas/io/excel/_base.py +++ b/pandas/io/excel/_base.py @@ -229,7 +229,7 @@ def read_excel( * ``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` + as a dict of `DataFrame` * ``None``: Returns a dictionary containing DataFrames for each sheet.. header : int, list of int, default 0 @@ -253,13 +253,13 @@ def read_excel( 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. + 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). + (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``. + 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 @@ -315,13 +315,13 @@ def read_excel( 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. + ``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. + 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. + 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. + 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. @@ -336,11 +336,11 @@ def read_excel( * ``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. + 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. + a single date column. * ``dict``, e.g. {'foo' : [1, 3]} -> parse columns 1, 3 as date and call - result 'foo' + 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 @@ -350,11 +350,12 @@ def read_excel( Note: A fast-path exists for iso8601-formatted dates. 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. + 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 - .. 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, @@ -389,6 +390,7 @@ def read_excel( * ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame` * ``"pyarrow"``: returns pyarrow-backed nullable + :class:`ArrowDtype` :class:`DataFrame` .. versionadded:: 2.0 From 842a5dd05893d77f957eee4d751b642e55b5c441 Mon Sep 17 00:00:00 2001 From: Fidorc80 <114183964+Fidorc80@users.noreply.github.com> Date: Mon, 8 Dec 2025 16:18:50 -0800 Subject: [PATCH 3/4] Addressed formatting errors --- pandas/io/excel/_base.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/pandas/io/excel/_base.py b/pandas/io/excel/_base.py index c93ad21faa5f2..b8843e65c1fd6 100644 --- a/pandas/io/excel/_base.py +++ b/pandas/io/excel/_base.py @@ -230,7 +230,7 @@ def read_excel( * ``"Sheet1"``: Load sheet with name "Sheet1" * ``[0, 1, "Sheet5"]``: Load first, second and sheet named "Sheet5" as a dict of `DataFrame` - * ``None``: Returns a dictionary containing DataFrames for each sheet.. + * ``None``: Returns a dictionary containing DataFrames for each sheet. header : int, list of int, default 0 Row (0-indexed) to use for the column labels of the parsed @@ -275,7 +275,7 @@ def read_excel( - ``openpyxl`` supports newer Excel file formats. - ``calamine`` supports Excel (.xls, .xlsx, .xlsm, .xlsb) - and OpenDocument (.ods) file formats. + 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). @@ -283,10 +283,11 @@ def read_excel( 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 `_ will be used. + then `odf `_ 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 From 6373448af5585fecb0f514aab9eba3a617caaac6 Mon Sep 17 00:00:00 2001 From: Fidorc80 <114183964+Fidorc80@users.noreply.github.com> Date: Tue, 9 Dec 2025 12:37:38 -0800 Subject: [PATCH 4/4] Applied requested format changes --- pandas/io/excel/_base.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/pandas/io/excel/_base.py b/pandas/io/excel/_base.py index b8843e65c1fd6..fcd5b05465fe9 100644 --- a/pandas/io/excel/_base.py +++ b/pandas/io/excel/_base.py @@ -423,13 +423,13 @@ def read_excel( 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 + 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 + Unnamed: 0 Name Value 0 0 string1 1 1 1 string2 2 2 2 #Comment 3 @@ -437,7 +437,7 @@ def read_excel( 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 1 2 0 NaN Name Value 1 0.0 string1 1 2 1.0 string2 2 @@ -448,7 +448,7 @@ def read_excel( >>> pd.read_excel( ... "tmp.xlsx", index_col=0, dtype={"Name": str, "Value": float} ... ) # doctest: +SKIP - Name Value + Name Value 0 string1 1.0 1 string2 2.0 2 #Comment 3.0 @@ -460,7 +460,7 @@ def read_excel( >>> pd.read_excel( ... "tmp.xlsx", index_col=0, na_values=["string1", "string2"] ... ) # doctest: +SKIP - Name Value + Name Value 0 NaN 1 1 NaN 2 2 #Comment 3 @@ -469,7 +469,7 @@ def read_excel( ``comment`` kwarg. >>> pd.read_excel("tmp.xlsx", index_col=0, comment="#") # doctest: +SKIP - Name Value + Name Value 0 string1 1.0 1 string2 2.0 2 None NaN