DEPR: xlwt for writing excel files (#38317)

Author: rhshadrach

doc/source/user_guide/io.rst

@@ -3200,6 +3200,13 @@ pandas supports writing Excel files to buffer-like objects such as ``StringIO``
 Excel writer engines
 ''''''''''''''''''''
 
+.. deprecated:: 1.2.0
+
+   As the `xlwt <https://pypi.org/project/xlwt/>`__ package is no longer
+   maintained, the ``xlwt`` engine will be removed from a future version
+   of pandas. This is the only engine in pandas that supports writing to
+   ``.xls`` files.
+
 pandas chooses an Excel writer via two methods:
 
 1. the ``engine`` keyword argument

doc/source/user_guide/options.rst

@@ -432,6 +432,16 @@ display.html.use_mathjax                True         When True, Jupyter notebook
                                                      dollar symbol.
 io.excel.xls.writer                     xlwt         The default Excel writer engine for
                                                      'xls' files.
+
+                                                     .. deprecated:: 1.2.0
+
+                                                        As `xlwt <https://pypi.org/project/xlwt/>`__
+                                                        package is no longer maintained, the ``xlwt``
+                                                        engine will be removed in a future version of
+                                                        pandas. Since this is the only engine in pandas
+                                                        that supports writing to ``.xls`` files,
+                                                        this option will also be removed.
+
 io.excel.xlsm.writer                    openpyxl     The default Excel writer engine for
                                                      'xlsm' files. Available options:
                                                      'openpyxl' (the default).

doc/source/whatsnew/v1.2.0.rst

@@ -10,12 +10,27 @@ including other versions of pandas.
 
 .. warning::
 
+   The packages `xlrd <https://xlrd.readthedocs.io/en/latest/>`_ for reading excel
+   files and `xlwt <https://xlwt.readthedocs.io/en/latest/>`_ for
+   writing excel files are no longer maintained. These are the only engines in pandas
+   that support the xls format.
+
    Previously, the default argument ``engine=None`` to ``pd.read_excel``
-   would result in using the `xlrd <https://xlrd.readthedocs.io/en/latest/>`_ engine in
-   many cases. The engine ``xlrd`` is no longer maintained, and is not supported with
-   python >= 3.9. If `openpyxl <https://pypi.org/project/openpyxl/>`_  is installed,
-   many of these  cases will now default to using the ``openpyxl`` engine. See the
-   :func:`read_excel` documentation for more details.
+   would result in using the ``xlrd`` engine in many cases. If
+   `openpyxl <https://openpyxl.readthedocs.io/en/stable/>`_  is installed,
+   many of these cases will now default to using the ``openpyxl`` engine.
+   See the :func:`read_excel` documentation for more details. Attempting to read
+   ``.xls`` files or specifying ``engine="xlrd"`` to ``pd.read_excel`` will not
+   raise a warning. However users should be aware that ``xlrd`` is already
+   broken with certain package configurations, for example with Python 3.9
+   when `defusedxml <https://github.com/tiran/defusedxml/>`_ is installed, and
+   is anticipated to be unusable in the future.
+
+   Attempting to use the the ``xlwt`` engine will raise a ``FutureWarning``
+   unless the option :attr:`io.excel.xls.writer` is set to ``"xlwt"``.
+   While this option is now deprecated and will also raise a ``FutureWarning``,
+   it can be globally set and the warning suppressed. Users are recommended to
+   write ``.xlsx`` files using the ``openpyxl`` engine instead.
 
 .. ---------------------------------------------------------------------------
 

pandas/core/config_init.py

@@ -581,6 +581,13 @@ def use_inf_as_na_cb(key):
         writer_engine_doc.format(ext="xls", others=", ".join(_xls_options)),
         validator=str,
     )
+cf.deprecate_option(
+    "io.excel.xls.writer",
+    msg="As the xlwt package is no longer maintained, the xlwt engine will be "
+    "removed in a future version of pandas. This is the only engine in pandas that "
+    "supports writing in the xls format. Install openpyxl and write to an "
+    "xlsx file instead.",
+)
 
 with cf.config_prefix("io.excel.xlsm"):
     cf.register_option(

pandas/core/generic.py

@@ -2093,6 +2093,13 @@ def to_excel(
             Write engine to use, 'openpyxl' or 'xlsxwriter'. You can also set this
             via the options ``io.excel.xlsx.writer``, ``io.excel.xls.writer``, and
             ``io.excel.xlsm.writer``.
+
+            .. deprecated:: 1.2.0
+
+                As the `xlwt <https://pypi.org/project/xlwt/>`__ package is no longer
+                maintained, the ``xlwt`` engine will be removed in a future version
+                of pandas.
+
         merge_cells : bool, default True
             Write MultiIndex and Hierarchical Rows as merged cells.
         encoding : str, optional

pandas/io/excel/_base.py

@@ -587,6 +587,13 @@ class ExcelWriter(metaclass=abc.ABCMeta):
         Engine to use for writing. If None, defaults to
         ``io.excel.<extension>.writer``.  NOTE: can only be passed as a keyword
         argument.
+
+        .. deprecated:: 1.2.0
+
+            As the `xlwt <https://pypi.org/project/xlwt/>`__ package is no longer
+            maintained, the ``xlwt`` engine will be removed in a future
+            version of pandas.
+
     date_format : str, default None
         Format string for dates written into Excel files (e.g. 'YYYY-MM-DD').
     datetime_format : str, default None
@@ -691,11 +698,31 @@ def __new__(cls, path, engine=None, **kwargs):
                     ext = "xlsx"
 
                 try:
-                    engine = config.get_option(f"io.excel.{ext}.writer")
+                    engine = config.get_option(f"io.excel.{ext}.writer", silent=True)
                     if engine == "auto":
                         engine = get_default_writer(ext)
                 except KeyError as err:
                     raise ValueError(f"No engine for filetype: '{ext}'") from err
+
+            if engine == "xlwt":
+                xls_config_engine = config.get_option(
+                    "io.excel.xls.writer", silent=True
+                )
+                # Don't warn a 2nd time if user has changed the default engine for xls
+                if xls_config_engine != "xlwt":
+                    warnings.warn(
+                        "As the xlwt package is no longer maintained, the xlwt "
+                        "engine will be removed in a future version of pandas. "
+                        "This is the only engine in pandas that supports writing "
+                        "in the xls format. Install openpyxl and write to an xlsx "
+                        "file instead. You can set the option io.excel.xls.writer "
+                        "to 'xlwt' to silence this warning. While this option is "
+                        "deprecated and will also raise a warning, it can "
+                        "be globally set and the warning suppressed.",
+                        FutureWarning,
+                        stacklevel=4,
+                    )
+
             cls = get_writer(engine)
 
         return object.__new__(cls)

pandas/io/formats/excel.py

@@ -805,6 +805,13 @@ def write(
             write engine to use if writer is a path - you can also set this
             via the options ``io.excel.xlsx.writer``, ``io.excel.xls.writer``,
             and ``io.excel.xlsm.writer``.
+
+            .. deprecated:: 1.2.0
+
+                As the `xlwt <https://pypi.org/project/xlwt/>`__ package is no longer
+                maintained, the ``xlwt`` engine will be removed in a future
+                version of pandas.
+
         {storage_options}
 
             .. versionadded:: 1.2.0

pandas/tests/io/excel/__init__.py

@@ -9,4 +9,8 @@
     pytest.mark.filterwarnings(
         "ignore:This method will be removed in future versions:DeprecationWarning"
     ),
+    # GH 26552
+    pytest.mark.filterwarnings(
+        "ignore:As the xlwt package is no longer maintained:FutureWarning"
+    ),
 ]

pandas/tests/io/excel/test_xlwt.py

@@ -1,7 +1,7 @@
 import numpy as np
 import pytest
 
-from pandas import DataFrame, MultiIndex
+from pandas import DataFrame, MultiIndex, options
 import pandas._testing as tm
 
 from pandas.io.excel import ExcelWriter, _XlwtWriter
@@ -69,3 +69,24 @@ def test_write_append_mode_raises(ext):
     with tm.ensure_clean(ext) as f:
         with pytest.raises(ValueError, match=msg):
             ExcelWriter(f, engine="xlwt", mode="a")
+
+
+def test_to_excel_xlwt_warning(ext):
+    # GH 26552
+    df = DataFrame(np.random.randn(3, 10))
+    with tm.ensure_clean(ext) as path:
+        with tm.assert_produces_warning(
+            FutureWarning,
+            match="As the xlwt package is no longer maintained",
+        ):
+            df.to_excel(path)
+
+
+def test_option_xls_writer_deprecated(ext):
+    # GH 26552
+    with tm.assert_produces_warning(
+        FutureWarning,
+        match="As the xlwt package is no longer maintained",
+        check_stacklevel=False,
+    ):
+        options.io.excel.xls.writer = "xlwt"