initial format support

Co-Authored-By: MarcoGorelli <>
Co-Authored-By: FDRocha <>

Author: nikitaved

asv_bench/asv.conf.json

@@ -54,7 +54,6 @@
         "openpyxl": [],
         "xlsxwriter": [],
         "xlrd": [],
-        "xlwt": [],
         "odfpy": [],
         "jinja2": [],
     },

asv_bench/benchmarks/io/excel.py

@@ -33,7 +33,7 @@ def _generate_dataframe():
 
 class WriteExcel:
 
-    params = ["openpyxl", "xlsxwriter", "xlwt"]
+    params = ["openpyxl", "xlsxwriter"]
     param_names = ["engine"]
 
     def setup(self, engine):
@@ -68,10 +68,9 @@ def time_write_excel_style(self, engine):
 
 class ReadExcel:
 
-    params = ["xlrd", "openpyxl", "odf"]
+    params = ["openpyxl", "odf"]
     param_names = ["engine"]
     fname_excel = "spreadsheet.xlsx"
-    fname_excel_xls = "spreadsheet.xls"
     fname_odf = "spreadsheet.ods"
 
     def _create_odf(self):
@@ -92,13 +91,10 @@ def setup_cache(self):
         self.df = _generate_dataframe()
 
         self.df.to_excel(self.fname_excel, sheet_name="Sheet1")
-        self.df.to_excel(self.fname_excel_xls, sheet_name="Sheet1")
         self._create_odf()
 
     def time_read_excel(self, engine):
-        if engine == "xlrd":
-            fname = self.fname_excel_xls
-        elif engine == "odf":
+        if engine == "odf":
             fname = self.fname_odf
         else:
             fname = self.fname_excel
@@ -107,9 +103,7 @@ def time_read_excel(self, engine):
 
 class ReadExcelNRows(ReadExcel):
     def time_read_excel(self, engine):
-        if engine == "xlrd":
-            fname = self.fname_excel_xls
-        elif engine == "odf":
+        if engine == "odf":
             fname = self.fname_odf
         else:
             fname = self.fname_excel

ci/code_checks.sh

@@ -47,7 +47,7 @@ import pandas
 
 blocklist = {'bs4', 'gcsfs', 'html5lib', 'http', 'ipython', 'jinja2', 'hypothesis',
              'lxml', 'matplotlib', 'openpyxl', 'py', 'pytest', 's3fs', 'scipy',
-             'tables', 'urllib.request', 'xlrd', 'xlsxwriter', 'xlwt'}
+             'tables', 'urllib.request', 'xlrd', 'xlsxwriter'}
 
 # GH#28227 for some of these check for top-level modules, while others are
 #  more specific (e.g. urllib.request)

ci/deps/actions-310.yaml

@@ -51,5 +51,4 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard

ci/deps/actions-38-downstream_compat.yaml

@@ -51,7 +51,6 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard
 
   # downstream packages

ci/deps/actions-38-minimum_versions.yaml

@@ -53,5 +53,4 @@ dependencies:
   - xarray=0.19.0
   - xlrd=2.0.1
   - xlsxwriter=1.4.3
-  - xlwt=1.3.0
   - zstandard=0.15.2

ci/deps/actions-38.yaml

@@ -50,5 +50,4 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard

ci/deps/actions-39.yaml

@@ -51,5 +51,4 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard

ci/deps/circle-38-arm64.yaml

@@ -51,5 +51,4 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard

doc/source/getting_started/install.rst

@@ -336,7 +336,6 @@ Can be managed as optional_extra with ``pandas[excel]``.
 Dependency                Minimum Version    optional_extra  Notes
 ========================= ================== =============== =============================================================
 xlrd                      2.0.1              excel           Reading Excel
-xlwt                      1.3.0              excel           Writing Excel
 xlsxwriter                1.4.3              excel           Writing Excel
 openpyxl                  3.0.7              excel           Reading / writing for xlsx files
 pyxlsb                    1.0.8              excel           Reading for xlsb files

doc/source/user_guide/io.rst

@@ -3466,8 +3466,6 @@ See the :ref:`cookbook<cookbook.excel>` for some advanced strategies.
 
 .. warning::
 
-   The `xlwt <https://xlwt.readthedocs.io/en/latest/>`__ package for writing old-style ``.xls``
-   excel files is no longer maintained.
    The `xlrd <https://xlrd.readthedocs.io/en/latest/>`__ package is now only for reading
    old-style ``.xls`` files.
 
@@ -3481,12 +3479,6 @@ See the :ref:`cookbook<cookbook.excel>` for some advanced strategies.
    **Please do not report issues when using ``xlrd`` to read ``.xlsx`` files.**
    This is no longer supported, switch to using ``openpyxl`` instead.
 
-   Attempting to use 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.
-
 .. _io.excel_reader:
 
 Reading Excel files
@@ -3788,7 +3780,7 @@ written. For example:
 
    df.to_excel("path_to_file.xlsx", sheet_name="Sheet1")
 
-Files with a ``.xls`` extension will be written using ``xlwt`` and those with a
+Files with a
 ``.xlsx`` extension will be written using ``xlsxwriter`` (if available) or
 ``openpyxl``.
 
@@ -3849,35 +3841,26 @@ 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
 2. the filename extension (via the default specified in config options)
 
 By default, pandas uses the `XlsxWriter`_  for ``.xlsx``, `openpyxl`_
-for ``.xlsm``, and `xlwt`_ for ``.xls`` files. If you have multiple
+for ``.xlsm``. If you have multiple
 engines installed, you can set the default engine through :ref:`setting the
 config options <options>` ``io.excel.xlsx.writer`` and
 ``io.excel.xls.writer``. pandas will fall back on `openpyxl`_ for ``.xlsx``
 files if `Xlsxwriter`_ is not available.
 
 .. _XlsxWriter: https://xlsxwriter.readthedocs.io
 .. _openpyxl: https://openpyxl.readthedocs.io/
-.. _xlwt: http://www.python-excel.org
 
 To specify which writer you want to use, you can pass an engine keyword
 argument to ``to_excel`` and to ``ExcelWriter``. The built-in engines are:
 
 * ``openpyxl``: version 2.4 or higher is required
 * ``xlsxwriter``
-* ``xlwt``
 
 .. code-block:: python
 

doc/source/user_guide/missing_data.rst

@@ -472,7 +472,7 @@ at the new values.
 
 .. _scipy: https://scipy.org/
 .. _documentation: https://docs.scipy.org/doc/scipy/reference/interpolate.html#univariate-interpolation
-.. _guide: https://docs.scipy.org/doc/scipy/reference/tutorial/interpolate.html
+.. _guide: https://docs.scipy.org/doc/scipy/tutorial/interpolate.html
 
 .. _missing_data.interp_limits:
 

doc/source/whatsnew/v2.0.0.rst

@@ -192,10 +192,24 @@ Removal of prior version deprecations/changes
 - Removed argument ``sort_columns`` in :meth:`DataFrame.plot` and :meth:`Series.plot` (:issue:`47563`)
 - Removed argument ``is_copy`` from :meth:`DataFrame.take` and :meth:`Series.take` (:issue:`30615`)
 - Removed argument ``kind`` from :meth:`Index.get_slice_bound`, :meth:`Index.slice_indexer` and :meth:`Index.slice_locs` (:issue:`41378`)
+- Disallow subclass-specific keywords (e.g. "freq", "tz", "names", "closed") in the :class:`Index` constructor (:issue:`38597`)
 - Removed argument ``inplace`` from :meth:`Categorical.remove_unused_categories` (:issue:`37918`)
 - Disallow passing non-round floats to :class:`Timestamp` with ``unit="M"`` or ``unit="Y"`` (:issue:`47266`)
 - Remove keywords ``convert_float`` and ``mangle_dupe_cols`` from :func:`read_excel` (:issue:`41176`)
 - Disallow passing non-keyword arguments to :func:`read_excel` except ``io`` and ``sheet_name`` (:issue:`34418`)
+- Disallow passing non-keyword arguments to :meth:`DataFrame.drop_duplicates` except for ``subset`` (:issue:`41485`)
+- Disallow passing non-keyword arguments to :meth:`DataFrame.sort_index` and :meth:`Series.sort_index` (:issue:`41506`)
+- Disallow passing non-keyword arguments to :meth:`DataFrame.interpolate` and :meth:`Series.interpolate` except for ``method`` (:issue:`41510`)
+- Disallow passing non-keyword arguments to :meth:`DataFrame.any` and :meth:`Series.any` (:issue:`44896`)
+- Disallow passing non-keyword arguments to :meth:`Index.set_names` except for ``names`` (:issue:`41551`)
+- Disallow passing non-keyword arguments to :meth:`Index.join` except for ``other`` (:issue:`46518`)
+- Disallow passing non-keyword arguments to :func:`concat` except for ``objs`` (:issue:`41485`)
+- Disallow passing non-keyword arguments to :func:`pivot` except for ``data`` (:issue:`48301`)
+- Disallow passing non-keyword arguments to :meth:`DataFrame.pivot` (:issue:`48301`)
+- Disallow passing non-keyword arguments to :func:`read_json` except for ``path_or_buf`` (:issue:`27573`)
+- Disallow passing non-keyword arguments to :func:`read_sas` except for ``filepath_or_buffer`` (:issue:`47154`)
+- Disallow passing non-keyword arguments to :func:`read_stata` except for ``filepath_or_buffer`` (:issue:`48128`)
+- Disallow passing non-keyword arguments to :func:`read_xml` except for ``path_or_buffer`` (:issue:`45133`)
 - Disallow passing non-keyword arguments to :meth:`Series.mask` and :meth:`DataFrame.mask` except ``cond`` and ``other`` (:issue:`41580`)
 - Disallow passing non-keyword arguments to :meth:`DataFrame.to_stata` except for ``path`` (:issue:`48128`)
 - Disallow passing non-keyword arguments to :meth:`DataFrame.where` and :meth:`Series.where` except for ``cond`` and ``other`` (:issue:`41523`)
@@ -228,16 +242,21 @@ Removal of prior version deprecations/changes
 - Removed ``pandas.util.testing`` in favor of ``pandas.testing`` (:issue:`30745`)
 - Removed :meth:`Series.str.__iter__` (:issue:`28277`)
 - Removed ``pandas.SparseArray`` in favor of :class:`arrays.SparseArray` (:issue:`30642`)
-- Removed ``pandas.SparseSeries`` and ``pandas.SparseDataFrame`` (:issue:`30642`)
+- Removed ``pandas.SparseSeries`` and ``pandas.SparseDataFrame``, including pickle support. (:issue:`30642`)
 - Enforced disallowing a string column label into ``times`` in :meth:`DataFrame.ewm` (:issue:`43265`)
 - Enforced disallowing a tuple of column labels into :meth:`.DataFrameGroupBy.__getitem__` (:issue:`30546`)
 - Removed setting Categorical._codes directly (:issue:`41429`)
 - Enforced :meth:`Rolling.count` with ``min_periods=None`` to default to the size of the window (:issue:`31302`)
 - Renamed ``fname`` to ``path`` in :meth:`DataFrame.to_parquet`, :meth:`DataFrame.to_stata` and :meth:`DataFrame.to_feather` (:issue:`30338`)
+- Enforced disallowing indexing a :class:`Series` with a single item list with a slice (e.g. ``ser[[slice(0, 2)]]``). Either convert the list to tuple, or pass the slice directly instead (:issue:`31333`)
 - Enforced the ``display.max_colwidth`` option to not accept negative integers (:issue:`31569`)
 - Removed the ``display.column_space`` option in favor of ``df.to_string(col_space=...)`` (:issue:`47280`)
 - Removed the deprecated method ``mad`` from pandas classes (:issue:`11787`)
 - Removed the deprecated method ``tshift`` from pandas classes (:issue:`11631`)
+- Changed the behavior of :func:`to_datetime` with argument "now" with ``utc=False`` to match ``Timestamp("now")`` (:issue:`18705`)
+- Changed behavior of :class:`DataFrame` constructor given floating-point ``data`` and an integer ``dtype``, when the data cannot be cast losslessly, the floating point dtype is retained, matching :class:`Series` behavior (:issue:`41170`)
+- Changed behavior of :class:`DataFrame` constructor when passed a ``dtype`` (other than int) that the data cannot be cast to; it now raises instead of silently ignoring the dtype (:issue:`41733`)
+- Changed the behavior of :class:`Series` constructor, it will no longer infer a datetime64 or timedelta64 dtype from string entries (:issue:`41731`)
 - Changed behavior of :class:`Index` constructor when passed a ``SparseArray`` or ``SparseDtype`` to retain that dtype instead of casting to ``numpy.ndarray`` (:issue:`43930`)
 
 .. ---------------------------------------------------------------------------
@@ -314,6 +333,7 @@ Conversion
 - Bug in :meth:`Series.convert_dtypes` not converting dtype to nullable dtype when :class:`Series` contains ``NA`` and has dtype ``object`` (:issue:`48791`)
 - Bug where any :class:`ExtensionDtype` subclass with ``kind="M"`` would be interpreted as a timezone type (:issue:`34986`)
 - Bug in :class:`.arrays.ArrowExtensionArray` that would raise ``NotImplementedError`` when passed a sequence of strings or binary (:issue:`49172`)
+- Bug in :func:`to_datetime` was not respecting ``exact`` argument when ``format`` was an ISO8601 format (:issue:`12649`)
 
 Strings
 ^^^^^^^

environment.yml

@@ -53,7 +53,6 @@ dependencies:
   - xarray
   - xlrd
   - xlsxwriter
-  - xlwt
   - zstandard
 
   # downstream packages

pandas/_libs/lib.pyi

@@ -158,7 +158,7 @@ def ensure_string_array(
 ) -> npt.NDArray[np.object_]: ...
 def infer_datetimelike_array(
     arr: npt.NDArray[np.object_],
-) -> tuple[str, bool]: ...
+) -> str: ...
 def convert_nans_to_NA(
     arr: npt.NDArray[np.object_],
 ) -> npt.NDArray[np.object_]: ...

pandas/_libs/lib.pyx

@@ -95,7 +95,6 @@ from pandas._libs.util cimport (
     is_nan,
 )
 
-from pandas._libs.tslib import array_to_datetime
 from pandas._libs.tslibs import (
     OutOfBoundsDatetime,
     OutOfBoundsTimedelta,
@@ -1583,25 +1582,19 @@ def infer_datetimelike_array(arr: ndarray[object]) -> tuple[str, bool]:
     Returns
     -------
     str: {datetime, timedelta, date, nat, mixed}
-    bool
     """
     cdef:
         Py_ssize_t i, n = len(arr)
         bint seen_timedelta = False, seen_date = False, seen_datetime = False
         bint seen_tz_aware = False, seen_tz_naive = False
-        bint seen_nat = False, seen_str = False
+        bint seen_nat = False
         bint seen_period = False, seen_interval = False
-        list objs = []
         object v
 
     for i in range(n):
         v = arr[i]
         if isinstance(v, str):
-            objs.append(v)
-            seen_str = True
-
-            if len(objs) == 3:
-                break
+            return "mixed"
 
         elif v is None or util.is_nan(v):
             # nan or None
@@ -1619,7 +1612,7 @@ def infer_datetimelike_array(arr: ndarray[object]) -> tuple[str, bool]:
                 seen_tz_aware = True
 
             if seen_tz_naive and seen_tz_aware:
-                return "mixed", seen_str
+                return "mixed"
         elif util.is_datetime64_object(v):
             # np.datetime64
             seen_datetime = True
@@ -1635,43 +1628,30 @@ def infer_datetimelike_array(arr: ndarray[object]) -> tuple[str, bool]:
             seen_interval = True
             break
         else:
-            return "mixed", seen_str
+            return "mixed"
 
     if seen_period:
         if is_period_array(arr):
-            return "period", seen_str
-        return "mixed", seen_str
+            return "period"
+        return "mixed"
 
     if seen_interval:
         if is_interval_array(arr):
-            return "interval", seen_str
-        return "mixed", seen_str
+            return "interval"
+        return "mixed"
 
     if seen_date and not (seen_datetime or seen_timedelta):
-        return "date", seen_str
+        return "date"
     elif seen_datetime and not seen_timedelta:
-        return "datetime", seen_str
+        return "datetime"
     elif seen_timedelta and not seen_datetime:
-        return "timedelta", seen_str
+        return "timedelta"
+    elif seen_datetime and seen_timedelta:
+        return "mixed"
     elif seen_nat:
-        return "nat", seen_str
+        return "nat"
 
-    # short-circuit by trying to
-    # actually convert these strings
-    # this is for performance as we don't need to try
-    # convert *every* string array
-    if len(objs):
-        try:
-            # require_iso8601 as in maybe_infer_to_datetimelike
-            array_to_datetime(objs, errors="raise", require_iso8601=True)
-            return "datetime", seen_str
-        except (ValueError, TypeError):
-            pass
-
-        # we are *not* going to infer from strings
-        # for timedelta as too much ambiguity
-
-    return "mixed", seen_str
+    return "mixed"
 
 
 cdef inline bint is_timedelta(object o):