Merge branch 'main' into bugfix-spss-kwargs

Author: astronights

ci/code_checks.sh

@@ -294,34 +294,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.UnsupportedFunctionCall SA01" \
         -i "pandas.errors.ValueLabelTypeMismatch SA01" \
         -i "pandas.infer_freq SA01" \
-        -i "pandas.io.formats.style.Styler.apply RT03" \
-        -i "pandas.io.formats.style.Styler.apply_index RT03" \
-        -i "pandas.io.formats.style.Styler.background_gradient RT03" \
-        -i "pandas.io.formats.style.Styler.bar RT03,SA01" \
-        -i "pandas.io.formats.style.Styler.clear SA01" \
-        -i "pandas.io.formats.style.Styler.concat RT03,SA01" \
-        -i "pandas.io.formats.style.Styler.export RT03" \
-        -i "pandas.io.formats.style.Styler.from_custom_template SA01" \
-        -i "pandas.io.formats.style.Styler.hide RT03,SA01" \
-        -i "pandas.io.formats.style.Styler.highlight_between RT03" \
-        -i "pandas.io.formats.style.Styler.highlight_max RT03" \
-        -i "pandas.io.formats.style.Styler.highlight_min RT03" \
-        -i "pandas.io.formats.style.Styler.highlight_null RT03" \
-        -i "pandas.io.formats.style.Styler.highlight_quantile RT03" \
-        -i "pandas.io.formats.style.Styler.map RT03" \
-        -i "pandas.io.formats.style.Styler.map_index RT03" \
-        -i "pandas.io.formats.style.Styler.set_caption RT03,SA01" \
-        -i "pandas.io.formats.style.Styler.set_properties RT03,SA01" \
-        -i "pandas.io.formats.style.Styler.set_sticky RT03,SA01" \
-        -i "pandas.io.formats.style.Styler.set_table_attributes PR07,RT03" \
-        -i "pandas.io.formats.style.Styler.set_table_styles RT03" \
-        -i "pandas.io.formats.style.Styler.set_td_classes RT03" \
-        -i "pandas.io.formats.style.Styler.set_tooltips RT03,SA01" \
-        -i "pandas.io.formats.style.Styler.set_uuid PR07,RT03,SA01" \
-        -i "pandas.io.formats.style.Styler.text_gradient RT03" \
-        -i "pandas.io.formats.style.Styler.to_excel PR01" \
-        -i "pandas.io.formats.style.Styler.to_string SA01" \
-        -i "pandas.io.formats.style.Styler.use RT03" \
         -i "pandas.io.json.build_table_schema PR07,RT03,SA01" \
         -i "pandas.io.stata.StataReader.data_label SA01" \
         -i "pandas.io.stata.StataReader.value_labels RT03,SA01" \

doc/source/whatsnew/v3.0.0.rst

@@ -506,6 +506,7 @@ Performance improvements
 - Performance improvement in :meth:`DataFrame.join` for sorted but non-unique indexes (:issue:`56941`)
 - Performance improvement in :meth:`DataFrame.join` when left and/or right are non-unique and ``how`` is ``"left"``, ``"right"``, or ``"inner"`` (:issue:`56817`)
 - Performance improvement in :meth:`DataFrame.join` with ``how="left"`` or ``how="right"`` and ``sort=True`` (:issue:`56919`)
+- Performance improvement in :meth:`DataFrame.to_csv` when ``index=False`` (:issue:`59312`)
 - Performance improvement in :meth:`DataFrameGroupBy.ffill`, :meth:`DataFrameGroupBy.bfill`, :meth:`SeriesGroupBy.ffill`, and :meth:`SeriesGroupBy.bfill` (:issue:`56902`)
 - Performance improvement in :meth:`Index.join` by propagating cached attributes in cases where the result matches one of the inputs (:issue:`57023`)
 - Performance improvement in :meth:`Index.take` when ``indices`` is a full range indexer from zero to length of index (:issue:`56806`)
@@ -555,6 +556,7 @@ Datetimelike
 - Bug in :meth:`DatetimeIndex.union` and :meth:`DatetimeIndex.intersection` when ``unit`` was non-nanosecond (:issue:`59036`)
 - Bug in :meth:`Series.dt.microsecond` producing incorrect results for pyarrow backed :class:`Series`. (:issue:`59154`)
 - Bug in :meth:`to_datetime` not respecting dayfirst if an uncommon date string was passed. (:issue:`58859`)
+- Bug in :meth:`to_datetime` reports incorrect index in case of any failure scenario. (:issue:`58298`)
 - Bug in setting scalar values with mismatched resolution into arrays with non-nanosecond ``datetime64``, ``timedelta64`` or :class:`DatetimeTZDtype` incorrectly truncating those scalars (:issue:`56410`)
 
 Timedelta

pandas/_libs/tslib.pyx

@@ -439,7 +439,7 @@ cpdef array_to_datetime(
                 raise TypeError(f"{type(val)} is not convertible to datetime")
 
         except (TypeError, OverflowError, ValueError) as ex:
-            ex.args = (f"{ex}, at position {i}",)
+            ex.args = (f"{ex}",)
             if is_coerce:
                 iresult[i] = NPY_NAT
                 continue

pandas/_libs/tslibs/strptime.pyx

@@ -536,7 +536,7 @@ def array_strptime(
 
         except ValueError as ex:
             ex.args = (
-                f"{str(ex)}, at position {i}. You might want to try:\n"
+                f"{str(ex)}. You might want to try:\n"
                 "    - passing `format` if your strings have a consistent format;\n"
                 "    - passing `format='ISO8601'` if your strings are "
                 "all ISO8601 but not necessarily in exactly the same format;\n"

pandas/core/generic.py

@@ -2123,11 +2123,13 @@ def _repr_data_resource_(self):
         klass="object",
         storage_options=_shared_docs["storage_options"],
         storage_options_versionadded="1.2.0",
+        encoding_parameter="",
+        verbose_parameter="",
         extra_parameters=textwrap.dedent(
             """\
         engine_kwargs : dict, optional
             Arbitrary keyword arguments passed to excel engine.
-    """
+        """
         ),
     )
     def to_excel(
@@ -2196,9 +2198,11 @@ def to_excel(
 
         merge_cells : bool, default True
             Write MultiIndex and Hierarchical Rows as merged cells.
+        {encoding_parameter}
         inf_rep : str, default 'inf'
             Representation for infinity (there is no native representation for
             infinity in Excel).
+        {verbose_parameter}
         freeze_panes : tuple of int (length 2), optional
             Specifies the one-based bottommost row and rightmost column that
             is to be frozen.

pandas/io/formats/csvs.py

@@ -320,7 +320,11 @@ def _save_chunk(self, start_i: int, end_i: int) -> None:
         res = df._get_values_for_csv(**self._number_format)
         data = list(res._iter_column_arrays())
 
-        ix = self.data_index[slicer]._get_values_for_csv(**self._number_format)
+        ix = (
+            self.data_index[slicer]._get_values_for_csv(**self._number_format)
+            if self.nlevels != 0
+            else np.empty(end_i - start_i)
+        )
         libwriters.write_csv_rows(
             data,
             ix,