Merge branch 'main' into pylint-48855-C-type-disallowed-name

Author: stellalin7

asv_bench/benchmarks/io/sql.py

@@ -38,7 +38,7 @@ def setup(self, connection):
             },
             index=tm.makeStringIndex(N),
         )
-        self.df.loc[1000:3000, "float_with_nan"] = np.nan
+        self.df.iloc[1000:3000, 1] = np.nan
         self.df["date"] = self.df["datetime"].dt.date
         self.df["time"] = self.df["datetime"].dt.time
         self.df["datetime_string"] = self.df["datetime"].astype(str)
@@ -88,7 +88,7 @@ def setup(self, connection, dtype):
             },
             index=tm.makeStringIndex(N),
         )
-        self.df.loc[1000:3000, "float_with_nan"] = np.nan
+        self.df.iloc[1000:3000, 1] = np.nan
         self.df["date"] = self.df["datetime"].dt.date
         self.df["time"] = self.df["datetime"].dt.time
         self.df["datetime_string"] = self.df["datetime"].astype(str)
@@ -117,7 +117,7 @@ def setup(self):
             },
             index=tm.makeStringIndex(N),
         )
-        self.df.loc[1000:3000, "float_with_nan"] = np.nan
+        self.df.iloc[1000:3000, 1] = np.nan
         self.df["date"] = self.df["datetime"].dt.date
         self.df["time"] = self.df["datetime"].dt.time
         self.df["datetime_string"] = self.df["datetime"].astype(str)
@@ -164,7 +164,7 @@ def setup(self, dtype):
             },
             index=tm.makeStringIndex(N),
         )
-        self.df.loc[1000:3000, "float_with_nan"] = np.nan
+        self.df.iloc[1000:3000, 1] = np.nan
         self.df["date"] = self.df["datetime"].dt.date
         self.df["time"] = self.df["datetime"].dt.time
         self.df["datetime_string"] = self.df["datetime"].astype(str)

doc/source/getting_started/intro_tutorials/09_timeseries.rst

@@ -144,7 +144,7 @@ I want to add a new column to the ``DataFrame`` containing only the month of the
 
 By using ``Timestamp`` objects for dates, a lot of time-related
 properties are provided by pandas. For example the ``month``, but also
-``year``, ``weekofyear``, ``quarter``,… All of these properties are
+``year``, ``quarter``,… All of these properties are
 accessible by the ``dt`` accessor.
 
 .. raw:: html

doc/source/reference/indexing.rst

@@ -343,8 +343,6 @@ Time/date components
    DatetimeIndex.timetz
    DatetimeIndex.dayofyear
    DatetimeIndex.day_of_year
-   DatetimeIndex.weekofyear
-   DatetimeIndex.week
    DatetimeIndex.dayofweek
    DatetimeIndex.day_of_week
    DatetimeIndex.weekday

doc/source/reference/series.rst

@@ -311,8 +311,6 @@ Datetime properties
    Series.dt.second
    Series.dt.microsecond
    Series.dt.nanosecond
-   Series.dt.week
-   Series.dt.weekofyear
    Series.dt.dayofweek
    Series.dt.day_of_week
    Series.dt.weekday

doc/source/user_guide/categorical.rst

@@ -353,11 +353,6 @@ Renaming categories is done by using the
 
     In contrast to R's ``factor``, categorical data can have categories of other types than string.
 
-.. note::
-
-    Be aware that assigning new categories is an inplace operation, while most other operations
-    under ``Series.cat`` per default return a new ``Series`` of dtype ``category``.
-
 Categories must be unique or a ``ValueError`` is raised:
 
 .. ipython:: python
@@ -952,7 +947,6 @@ categorical (categories and ordering). So if you read back the CSV file you have
 relevant columns back to ``category`` and assign the right categories and categories ordering.
 
 .. ipython:: python
-    :okwarning:
 
     import io
 
@@ -969,8 +963,8 @@ relevant columns back to ``category`` and assign the right categories and catego
     df2["cats"]
     # Redo the category
     df2["cats"] = df2["cats"].astype("category")
-    df2["cats"].cat.set_categories(
-        ["very bad", "bad", "medium", "good", "very good"], inplace=True
+    df2["cats"] = df2["cats"].cat.set_categories(
+        ["very bad", "bad", "medium", "good", "very good"]
     )
     df2.dtypes
     df2["cats"]
@@ -1162,16 +1156,12 @@ Constructing a ``Series`` from a ``Categorical`` will not copy the input
 change the original ``Categorical``:
 
 .. ipython:: python
-    :okwarning:
 
     cat = pd.Categorical([1, 2, 3, 10], categories=[1, 2, 3, 4, 10])
     s = pd.Series(cat, name="cat")
     cat
     s.iloc[0:2] = 10
     cat
-    df = pd.DataFrame(s)
-    df["cat"].cat.categories = [1, 2, 3, 4, 5]
-    cat
 
 Use ``copy=True`` to prevent such a behaviour or simply don't reuse ``Categoricals``:
 

doc/source/whatsnew/v0.15.0.rst

@@ -70,7 +70,6 @@ For full docs, see the :ref:`categorical introduction <categorical>` and the
 :ref:`API documentation <api.arrays.categorical>`.
 
 .. ipython:: python
-    :okwarning:
 
     df = pd.DataFrame({"id": [1, 2, 3, 4, 5, 6],
                        "raw_grade": ['a', 'b', 'b', 'a', 'a', 'e']})
@@ -79,7 +78,7 @@ For full docs, see the :ref:`categorical introduction <categorical>` and the
     df["grade"]
 
     # Rename the categories
-    df["grade"].cat.categories = ["very good", "good", "very bad"]
+    df["grade"] = df["grade"].cat.rename_categories(["very good", "good", "very bad"])
 
     # Reorder the categories and simultaneously add the missing categories
     df["grade"] = df["grade"].cat.set_categories(["very bad", "bad",

doc/source/whatsnew/v0.19.0.rst

@@ -271,12 +271,12 @@ Individual columns can be parsed as a ``Categorical`` using a dict specification
    such as :func:`to_datetime`.
 
    .. ipython:: python
-      :okwarning:
 
       df = pd.read_csv(StringIO(data), dtype="category")
       df.dtypes
       df["col3"]
-      df["col3"].cat.categories = pd.to_numeric(df["col3"].cat.categories)
+      new_categories = pd.to_numeric(df["col3"].cat.categories)
+      df["col3"] = df["col3"].cat.rename_categories(new_categories)
       df["col3"]
 
 .. _whatsnew_0190.enhancements.union_categoricals:

doc/source/whatsnew/v2.0.0.rst

@@ -49,6 +49,7 @@ Other enhancements
 - Fix ``test`` optional_extra by adding missing test package ``pytest-asyncio`` (:issue:`48361`)
 - :func:`DataFrame.astype` exception message thrown improved to include column name when type conversion is not possible. (:issue:`47571`)
 - :meth:`DataFrame.to_json` now supports a ``mode`` keyword with supported inputs 'w' and 'a'. Defaulting to 'w', 'a' can be used when lines=True and orient='records' to append record oriented json lines to an existing json file. (:issue:`35849`)
+- Added ``name`` parameter to :meth:`IntervalIndex.from_breaks`, :meth:`IntervalIndex.from_arrays` and :meth:`IntervalIndex.from_tuples` (:issue:`48911`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_200.notable_bug_fixes:
@@ -170,6 +171,7 @@ Removal of prior version deprecations/changes
 - Removed deprecated :meth:`Index.to_native_types`, use ``obj.astype(str)`` instead (:issue:`36418`)
 - Removed deprecated :meth:`Series.iteritems`, :meth:`DataFrame.iteritems`, use ``obj.items`` instead (:issue:`45321`)
 - Removed deprecated :meth:`DatetimeIndex.union_many` (:issue:`45018`)
+- Removed deprecated ``weekofyear`` and ``week`` attributes of :class:`DatetimeArray`, :class:`DatetimeIndex` and ``dt`` accessor in favor of ``isocalendar().week`` (:issue:`33595`)
 - Removed deprecated :meth:`RangeIndex._start`, :meth:`RangeIndex._stop`, :meth:`RangeIndex._step`, use ``start``, ``stop``, ``step`` instead (:issue:`30482`)
 - Removed deprecated :meth:`DatetimeIndex.to_perioddelta`, Use ``dtindex - dtindex.to_period(freq).to_timestamp()`` instead (:issue:`34853`)
 - Enforced deprecation disallowing passing a timezone-aware :class:`Timestamp` and ``dtype="datetime64[ns]"`` to :class:`Series` or :class:`DataFrame` constructors (:issue:`41555`)
@@ -236,6 +238,7 @@ Removal of prior version deprecations/changes
 - Removed deprecated :meth:`Timedelta.delta`, :meth:`Timedelta.is_populated`, and :attr:`Timedelta.freq` (:issue:`46430`, :issue:`46476`)
 - Removed deprecated :meth:`Categorical.replace`, use :meth:`Series.replace` instead (:issue:`44929`)
 - Removed the ``numeric_only`` keyword from :meth:`Categorical.min` and :meth:`Categorical.max` in favor of ``skipna`` (:issue:`48821`)
+- Changed behavior of :meth:`DataFrame.median` and :meth:`DataFrame.mean` with ``numeric_only=None`` to not exclude datetime-like columns THIS NOTE WILL BE IRRELEVANT ONCE ``numeric_only=None`` DEPRECATION IS ENFORCED (:issue:`29941`)
 - Removed :func:`is_extension_type` in favor of :func:`is_extension_array_dtype` (:issue:`29457`)
 - Removed ``.ExponentialMovingWindow.vol`` (:issue:`39220`)
 - Removed :meth:`Index.get_value` and :meth:`Index.set_value` (:issue:`33907`, :issue:`28621`)
@@ -256,7 +259,10 @@ Removal of prior version deprecations/changes
 - Enforced disallowing passing an integer ``fill_value`` to :meth:`DataFrame.shift` and :meth:`Series.shift`` with datetime64, timedelta64, or period dtypes (:issue:`32591`)
 - 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`)
+- Enforced disallowing setting values with ``.loc`` using a positional slice. Use ``.loc`` with labels or ``.iloc`` with positions instead (:issue:`31840`)
 - Removed setting Categorical._codes directly (:issue:`41429`)
+- Removed setting Categorical.categories directly (:issue:`47834`)
+- Removed argument ``inplace`` from :meth:`Categorical.add_categories`, :meth:`Categorical.remove_categories`, :meth:`Categorical.set_categories`, :meth:`Categorical.rename_categories`, :meth:`Categorical.reorder_categories`, :meth:`Categorical.set_ordered`, :meth:`Categorical.as_ordered`, :meth:`Categorical.as_unordered` (:issue:`37981`, :issue:`41118`, :issue:`41133`, :issue:`47834`)
 - 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`)
@@ -269,7 +275,9 @@ Removal of prior version deprecations/changes
 - 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`)
+- Removed the deprecated ``base`` and ``loffset`` arguments from :meth:`pandas.DataFrame.resample`, :meth:`pandas.Series.resample` and :class:`pandas.Grouper`. Use ``offset`` or ``origin`` instead (:issue:`31809`)
 - Changed behavior of :meth:`DataFrame.any` and :meth:`DataFrame.all` with ``bool_only=True``; object-dtype columns with all-bool values will no longer be included, manually cast to ``bool`` dtype first (:issue:`46188`)
+- Enforced deprecation of silently dropping columns that raised a ``TypeError`` in :class:`Series.transform` and :class:`DataFrame.transform` when used with a list or dictionary (:issue:`43740`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/_libs/tslibs/parsing.pyx

@@ -1011,10 +1011,11 @@ def guess_datetime_format(dt_str: str, bint dayfirst=False) -> str | None:
                 break
 
     # Only consider it a valid guess if we have a year, month and day,
-    # unless it's %Y which is both common and unambiguous.
+    # unless it's %Y or %Y-%m which conform with ISO8601. Note that we don't
+    # make an exception for %Y%m because it's explicitly not considered ISO8601.
     if (
         len({'year', 'month', 'day'} & found_attrs) != 3
-        and format_guess != ['%Y']
+        and format_guess not in (['%Y'], ['%Y', None, '%m'])
     ):
         return None
 

pandas/core/apply.py

@@ -266,34 +266,9 @@ def transform_dict_like(self, func):
         func = self.normalize_dictlike_arg("transform", obj, func)
 
         results: dict[Hashable, DataFrame | Series] = {}
-        failed_names = []
-        all_type_errors = True
         for name, how in func.items():
             colg = obj._gotitem(name, ndim=1)
-            try:
-                results[name] = colg.transform(how, 0, *args, **kwargs)
-            except Exception as err:
-                if str(err) in {
-                    "Function did not transform",
-                    "No transform functions were provided",
-                }:
-                    raise err
-                else:
-                    if not isinstance(err, TypeError):
-                        all_type_errors = False
-                    failed_names.append(name)
-        # combine results
-        if not results:
-            klass = TypeError if all_type_errors else ValueError
-            raise klass("Transform function failed")
-        if len(failed_names) > 0:
-            warnings.warn(
-                f"{failed_names} did not transform successfully. If any error is "
-                f"raised, this will raise in a future version of pandas. "
-                f"Drop these columns/ops to avoid this warning.",
-                FutureWarning,
-                stacklevel=find_stack_level(),
-            )
+            results[name] = colg.transform(how, 0, *args, **kwargs)
         return concat(results, axis=1)
 
     def transform_str_or_callable(self, func) -> DataFrame | Series: