CLN: assorted (#55618)

Author: jbrockmendel

pandas/_libs/tslibs/np_datetime.pyx

@@ -484,7 +484,6 @@ import operator
 
 
 cdef int op_to_op_code(op):
-    # TODO: should exist somewhere?
     if op is operator.eq:
         return Py_EQ
     if op is operator.ne:

pandas/core/arrays/categorical.py

@@ -2165,7 +2165,7 @@ def __contains__(self, key) -> bool:
     # Rendering Methods
 
     def _formatter(self, boxed: bool = False):
-        # Defer to CategoricalFormatter's formatter.
+        # Returning None here will cause format_array to do inference.
         return None
 
     def _repr_categories(self) -> list[str]:

pandas/core/arrays/datetimelike.py

@@ -2013,8 +2013,9 @@ def freq(self, value) -> None:
 
         self._freq = value
 
+    @final
     @classmethod
-    def _validate_frequency(cls, index, freq, **kwargs):
+    def _validate_frequency(cls, index, freq: BaseOffset, **kwargs):
         """
         Validate that a frequency is compatible with the values of a given
         Datetime Array/Index or Timedelta Array/Index

pandas/core/arrays/datetimes.py

@@ -2266,7 +2266,8 @@ def _sequence_to_dt64ns(
 
     elif lib.is_np_dtype(data_dtype, "M"):
         # tz-naive DatetimeArray or ndarray[datetime64]
-        data = getattr(data, "_ndarray", data)
+        if isinstance(data, DatetimeArray):
+            data = data._ndarray
         new_dtype = data.dtype
         data_unit = get_unit_from_dtype(new_dtype)
         if not is_supported_unit(data_unit):

pandas/core/dtypes/dtypes.py

@@ -55,6 +55,7 @@
 from pandas.core.dtypes.generic import (
     ABCCategoricalIndex,
     ABCIndex,
+    ABCRangeIndex,
 )
 from pandas.core.dtypes.inference import (
     is_bool,
@@ -464,8 +465,7 @@ def __repr__(self) -> str_type:
             dtype = "None"
         else:
             data = self.categories._format_data(name=type(self).__name__)
-            if data is None:
-                # self.categories is RangeIndex
+            if isinstance(self.categories, ABCRangeIndex):
                 data = str(self.categories._range)
             data = data.rstrip(", ")
             dtype = self.categories.dtype

pandas/core/indexes/base.py

@@ -127,6 +127,7 @@
     ABCIntervalIndex,
     ABCMultiIndex,
     ABCPeriodIndex,
+    ABCRangeIndex,
     ABCSeries,
     ABCTimedeltaIndex,
 )
@@ -1292,11 +1293,6 @@ def __repr__(self) -> str_t:
         attrs_str = [f"{k}={v}" for k, v in attrs]
         prepr = ", ".join(attrs_str)
 
-        # no data provided, just attributes
-        if data is None:
-            # i.e. RangeIndex
-            data = ""
-
         return f"{klass_name}({data}{prepr})"
 
     @property
@@ -1306,6 +1302,7 @@ def _formatter_func(self):
         """
         return default_pprint
 
+    @final
     def _format_data(self, name=None) -> str_t:
         """
         Return the formatted data as a unicode string.
@@ -1319,6 +1316,9 @@ def _format_data(self, name=None) -> str_t:
             self = cast("CategoricalIndex", self)
             if is_object_dtype(self.categories.dtype):
                 is_justify = False
+        elif isinstance(self, ABCRangeIndex):
+            # We will do the relevant formatting via attrs
+            return ""
 
         return format_object_summary(
             self,
@@ -6961,6 +6961,7 @@ def drop(
             indexer = indexer[~mask]
         return self.delete(indexer)
 
+    @final
     def infer_objects(self, copy: bool = True) -> Index:
         """
         If we have an object dtype, try to infer a non-object dtype.
@@ -6992,6 +6993,7 @@ def infer_objects(self, copy: bool = True) -> Index:
             result._references.add_index_reference(result)
         return result
 
+    @final
     def diff(self, periods: int = 1) -> Self:
         """
         Computes the difference between consecutive values in the Index object.
@@ -7020,6 +7022,7 @@ def diff(self, periods: int = 1) -> Self:
         """
         return self._constructor(self.to_series().diff(periods))
 
+    @final
     def round(self, decimals: int = 0) -> Self:
         """
         Round each value in the Index to the given number of decimals.

pandas/core/indexes/datetimes.py

@@ -417,8 +417,10 @@ def _is_comparable_dtype(self, dtype: DtypeObj) -> bool:
     # --------------------------------------------------------------------
     # Rendering Methods
 
-    @property
+    @cache_readonly
     def _formatter_func(self):
+        # Note this is equivalent to the DatetimeIndexOpsMixin method but
+        #  uses the maybe-cached self._is_dates_only instead of re-computing it.
         from pandas.io.formats.format import get_format_datetime64
 
         formatter = get_format_datetime64(is_dates_only=self._is_dates_only)

pandas/core/indexes/range.py

@@ -240,7 +240,7 @@ def _data(self) -> np.ndarray:  # type: ignore[override]
         """
         return np.arange(self.start, self.stop, self.step, dtype=np.int64)
 
-    def _get_data_as_items(self):
+    def _get_data_as_items(self) -> list[tuple[str, int]]:
         """return a list of tuples of start, stop, step"""
         rng = self._range
         return [("start", rng.start), ("stop", rng.stop), ("step", rng.step)]
@@ -257,15 +257,11 @@ def _format_attrs(self):
         """
         Return a list of tuples of the (attr, formatted_value)
         """
-        attrs = self._get_data_as_items()
+        attrs = cast("list[tuple[str, str | int]]", self._get_data_as_items())
         if self._name is not None:
             attrs.append(("name", ibase.default_pprint(self._name)))
         return attrs
 
-    def _format_data(self, name=None):
-        # we are formatting thru the attributes
-        return None
-
     def _format_with_header(self, *, header: list[str], na_rep: str) -> list[str]:
         # Equivalent to Index implementation, but faster
         if not len(self._range):

pandas/core/resample.py

@@ -189,6 +189,7 @@ def __init__(
         else:
             self.exclusions = frozenset()
 
+    @final
     def __str__(self) -> str:
         """
         Provide a nice str repr of our rolling object.
@@ -200,6 +201,7 @@ def __str__(self) -> str:
         )
         return f"{type(self).__name__} [{', '.join(attrs)}]"
 
+    @final
     def __getattr__(self, attr: str):
         if attr in self._internal_names_set:
             return object.__getattribute__(self, attr)
@@ -210,6 +212,7 @@ def __getattr__(self, attr: str):
 
         return object.__getattribute__(self, attr)
 
+    @final
     @property
     def _from_selection(self) -> bool:
         """
@@ -249,6 +252,7 @@ def _get_binner(self):
         bin_grouper = BinGrouper(bins, binlabels, indexer=self._indexer)
         return binner, bin_grouper
 
+    @final
     @Substitution(
         klass="Resampler",
         examples="""
@@ -334,6 +338,7 @@ def pipe(
     """
     )
 
+    @final
     @doc(
         _shared_docs["aggregate"],
         see_also=_agg_see_also_doc,
@@ -352,6 +357,7 @@ def aggregate(self, func=None, *args, **kwargs):
     agg = aggregate
     apply = aggregate
 
+    @final
     def transform(self, arg, *args, **kwargs):
         """
         Call function producing a like-indexed Series on each group.
@@ -471,6 +477,7 @@ def _groupby_and_aggregate(self, how, *args, **kwargs):
 
         return self._wrap_result(result)
 
+    @final
     def _get_resampler_for_grouping(
         self, groupby: GroupBy, key, include_groups: bool = True
     ):
@@ -506,6 +513,7 @@ def _wrap_result(self, result):
 
         return result
 
+    @final
     def ffill(self, limit: int | None = None):
         """
         Forward fill the values.
@@ -574,6 +582,7 @@ def ffill(self, limit: int | None = None):
         """
         return self._upsample("ffill", limit=limit)
 
+    @final
     def nearest(self, limit: int | None = None):
         """
         Resample by using the nearest value.
@@ -634,6 +643,7 @@ def nearest(self, limit: int | None = None):
         """
         return self._upsample("nearest", limit=limit)
 
+    @final
     def bfill(self, limit: int | None = None):
         """
         Backward fill the new missing values in the resampled data.
@@ -736,6 +746,7 @@ def bfill(self, limit: int | None = None):
         """
         return self._upsample("bfill", limit=limit)
 
+    @final
     def fillna(self, method, limit: int | None = None):
         """
         Fill missing values introduced by upsampling.
@@ -903,6 +914,7 @@ def fillna(self, method, limit: int | None = None):
         )
         return self._upsample(method, limit=limit)
 
+    @final
     def interpolate(
         self,
         method: InterpolateOptions = "linear",
@@ -1084,6 +1096,7 @@ def interpolate(
             **kwargs,
         )
 
+    @final
     def asfreq(self, fill_value=None):
         """
         Return the values at the new freq, essentially a reindex.
@@ -1122,6 +1135,7 @@ def asfreq(self, fill_value=None):
         """
         return self._upsample("asfreq", fill_value=fill_value)
 
+    @final
     def sum(
         self,
         numeric_only: bool = False,
@@ -1169,6 +1183,7 @@ def sum(
         nv.validate_resampler_func("sum", args, kwargs)
         return self._downsample("sum", numeric_only=numeric_only, min_count=min_count)
 
+    @final
     def prod(
         self,
         numeric_only: bool = False,
@@ -1216,6 +1231,7 @@ def prod(
         nv.validate_resampler_func("prod", args, kwargs)
         return self._downsample("prod", numeric_only=numeric_only, min_count=min_count)
 
+    @final
     def min(
         self,
         numeric_only: bool = False,
@@ -1250,6 +1266,7 @@ def min(
         nv.validate_resampler_func("min", args, kwargs)
         return self._downsample("min", numeric_only=numeric_only, min_count=min_count)
 
+    @final
     def max(
         self,
         numeric_only: bool = False,
@@ -1283,6 +1300,7 @@ def max(
         nv.validate_resampler_func("max", args, kwargs)
         return self._downsample("max", numeric_only=numeric_only, min_count=min_count)
 
+    @final
     @doc(GroupBy.first)
     def first(
         self,
@@ -1295,6 +1313,7 @@ def first(
         nv.validate_resampler_func("first", args, kwargs)
         return self._downsample("first", numeric_only=numeric_only, min_count=min_count)
 
+    @final
     @doc(GroupBy.last)
     def last(
         self,
@@ -1307,12 +1326,14 @@ def last(
         nv.validate_resampler_func("last", args, kwargs)
         return self._downsample("last", numeric_only=numeric_only, min_count=min_count)
 
+    @final
     @doc(GroupBy.median)
     def median(self, numeric_only: bool = False, *args, **kwargs):
         maybe_warn_args_and_kwargs(type(self), "median", args, kwargs)
         nv.validate_resampler_func("median", args, kwargs)
         return self._downsample("median", numeric_only=numeric_only)
 
+    @final
     def mean(
         self,
         numeric_only: bool = False,
@@ -1356,6 +1377,7 @@ def mean(
         nv.validate_resampler_func("mean", args, kwargs)
         return self._downsample("mean", numeric_only=numeric_only)
 
+    @final
     def std(
         self,
         ddof: int = 1,
@@ -1403,6 +1425,7 @@ def std(
         nv.validate_resampler_func("std", args, kwargs)
         return self._downsample("std", ddof=ddof, numeric_only=numeric_only)
 
+    @final
     def var(
         self,
         ddof: int = 1,
@@ -1456,6 +1479,7 @@ def var(
         nv.validate_resampler_func("var", args, kwargs)
         return self._downsample("var", ddof=ddof, numeric_only=numeric_only)
 
+    @final
     @doc(GroupBy.sem)
     def sem(
         self,
@@ -1468,6 +1492,7 @@ def sem(
         nv.validate_resampler_func("sem", args, kwargs)
         return self._downsample("sem", ddof=ddof, numeric_only=numeric_only)
 
+    @final
     @doc(GroupBy.ohlc)
     def ohlc(
         self,
@@ -1495,6 +1520,7 @@ def ohlc(
 
         return self._downsample("ohlc")
 
+    @final
     @doc(SeriesGroupBy.nunique)
     def nunique(
         self,
@@ -1505,6 +1531,7 @@ def nunique(
         nv.validate_resampler_func("nunique", args, kwargs)
         return self._downsample("nunique")
 
+    @final
     @doc(GroupBy.size)
     def size(self):
         result = self._downsample("size")
@@ -1524,6 +1551,7 @@ def size(self):
             result = Series([], index=result.index, dtype="int64", name=name)
         return result
 
+    @final
     @doc(GroupBy.count)
     def count(self):
         result = self._downsample("count")
@@ -1541,6 +1569,7 @@ def count(self):
 
         return result
 
+    @final
     def quantile(self, q: float | list[float] | AnyArrayLike = 0.5, **kwargs):
         """
         Return value at the given quantile.

pandas/core/series.py

@@ -1047,7 +1047,7 @@ def _ixs(self, i: int, axis: AxisInt = 0) -> Any:
 
         Returns
         -------
-        scalar (int) or Series (slice, sequence)
+        scalar
         """
         return self._values[i]