REF: collect methods by topic (pandas-dev#36173)

Author: jbrockmendel

pandas/core/arrays/categorical.py

@@ -393,56 +393,6 @@ def __init__(
         self._dtype = self._dtype.update_dtype(dtype)
         self._codes = coerce_indexer_dtype(codes, dtype.categories)
 
-    @property
-    def categories(self):
-        """
-        The categories of this categorical.
-
-        Setting assigns new values to each category (effectively a rename of
-        each individual category).
-
-        The assigned value has to be a list-like object. All items must be
-        unique and the number of items in the new categories must be the same
-        as the number of items in the old categories.
-
-        Assigning to `categories` is a inplace operation!
-
-        Raises
-        ------
-        ValueError
-            If the new categories do not validate as categories or if the
-            number of new categories is unequal the number of old categories
-
-        See Also
-        --------
-        rename_categories : Rename categories.
-        reorder_categories : Reorder categories.
-        add_categories : Add new categories.
-        remove_categories : Remove the specified categories.
-        remove_unused_categories : Remove categories which are not used.
-        set_categories : Set the categories to the specified ones.
-        """
-        return self.dtype.categories
-
-    @categories.setter
-    def categories(self, categories):
-        new_dtype = CategoricalDtype(categories, ordered=self.ordered)
-        if self.dtype.categories is not None and len(self.dtype.categories) != len(
-            new_dtype.categories
-        ):
-            raise ValueError(
-                "new categories need to have the same number of "
-                "items as the old categories!"
-            )
-        self._dtype = new_dtype
-
-    @property
-    def ordered(self) -> Ordered:
-        """
-        Whether the categories have an ordered relationship.
-        """
-        return self.dtype.ordered
-
     @property
     def dtype(self) -> CategoricalDtype:
         """
@@ -458,10 +408,6 @@ def _constructor(self) -> Type["Categorical"]:
     def _from_sequence(cls, scalars, dtype=None, copy=False):
         return Categorical(scalars, dtype=dtype)
 
-    def _formatter(self, boxed=False):
-        # Defer to CategoricalFormatter's formatter.
-        return None
-
     def astype(self, dtype: Dtype, copy: bool = True) -> ArrayLike:
         """
         Coerce this type to another dtype
@@ -640,6 +586,59 @@ def from_codes(cls, codes, categories=None, ordered=None, dtype=None):
 
         return cls(codes, dtype=dtype, fastpath=True)
 
+    # ------------------------------------------------------------------
+    # Categories/Codes/Ordered
+
+    @property
+    def categories(self):
+        """
+        The categories of this categorical.
+
+        Setting assigns new values to each category (effectively a rename of
+        each individual category).
+
+        The assigned value has to be a list-like object. All items must be
+        unique and the number of items in the new categories must be the same
+        as the number of items in the old categories.
+
+        Assigning to `categories` is a inplace operation!
+
+        Raises
+        ------
+        ValueError
+            If the new categories do not validate as categories or if the
+            number of new categories is unequal the number of old categories
+
+        See Also
+        --------
+        rename_categories : Rename categories.
+        reorder_categories : Reorder categories.
+        add_categories : Add new categories.
+        remove_categories : Remove the specified categories.
+        remove_unused_categories : Remove categories which are not used.
+        set_categories : Set the categories to the specified ones.
+        """
+        return self.dtype.categories
+
+    @categories.setter
+    def categories(self, categories):
+        new_dtype = CategoricalDtype(categories, ordered=self.ordered)
+        if self.dtype.categories is not None and len(self.dtype.categories) != len(
+            new_dtype.categories
+        ):
+            raise ValueError(
+                "new categories need to have the same number of "
+                "items as the old categories!"
+            )
+        self._dtype = new_dtype
+
+    @property
+    def ordered(self) -> Ordered:
+        """
+        Whether the categories have an ordered relationship.
+        """
+        return self.dtype.ordered
+
     @property
     def codes(self) -> np.ndarray:
         """
@@ -1104,6 +1103,8 @@ def remove_unused_categories(self, inplace=False):
         if not inplace:
             return cat
 
+    # ------------------------------------------------------------------
+
     def map(self, mapper):
         """
         Map categories using input correspondence (dict, Series, or function).
@@ -1192,6 +1193,9 @@ def map(self, mapper):
     __le__ = _cat_compare_op(operator.le)
     __ge__ = _cat_compare_op(operator.ge)
 
+    # -------------------------------------------------------------
+    # Validators; ideally these can be de-duplicated
+
     def _validate_insert_value(self, value) -> int:
         code = self.categories.get_indexer([value])
         if (code == -1) and not (is_scalar(value) and isna(value)):
@@ -1241,6 +1245,8 @@ def _validate_fill_value(self, fill_value):
             )
         return fill_value
 
+    # -------------------------------------------------------------
+
     def __array__(self, dtype=None) -> np.ndarray:
         """
         The numpy array interface.
@@ -1758,6 +1764,10 @@ def __contains__(self, key) -> bool:
     # ------------------------------------------------------------------
     # Rendering Methods
 
+    def _formatter(self, boxed=False):
+        # Defer to CategoricalFormatter's formatter.
+        return None
+
     def _tidy_repr(self, max_vals=10, footer=True) -> str:
         """
         a short repr displaying only max_vals and an optional (but default
@@ -1987,7 +1997,9 @@ def _reverse_indexer(self) -> Dict[Hashable, np.ndarray]:
         result = dict(zip(categories, _result))
         return result
 
-    # reduction ops #
+    # ------------------------------------------------------------------
+    # Reductions
+
     def _reduce(self, name: str, skipna: bool = True, **kwargs):
         func = getattr(self, name, None)
         if func is None:
@@ -2090,6 +2102,9 @@ def mode(self, dropna=True):
         codes = sorted(htable.mode_int64(ensure_int64(codes), dropna))
         return self._constructor(values=codes, dtype=self.dtype, fastpath=True)
 
+    # ------------------------------------------------------------------
+    # ExtensionArray Interface
+
     def unique(self):
         """
         Return the ``Categorical`` which ``categories`` and ``codes`` are
@@ -2179,6 +2194,18 @@ def equals(self, other: object) -> bool:
             return np.array_equal(self._codes, other_codes)
         return False
 
+    @property
+    def _can_hold_na(self):
+        return True
+
+    @classmethod
+    def _concat_same_type(self, to_concat):
+        from pandas.core.dtypes.concat import union_categoricals
+
+        return union_categoricals(to_concat)
+
+    # ------------------------------------------------------------------
+
     def is_dtype_equal(self, other):
         """
         Returns True if categoricals are the same dtype
@@ -2217,17 +2244,6 @@ def describe(self):
 
         return result
 
-    # Implement the ExtensionArray interface
-    @property
-    def _can_hold_na(self):
-        return True
-
-    @classmethod
-    def _concat_same_type(self, to_concat):
-        from pandas.core.dtypes.concat import union_categoricals
-
-        return union_categoricals(to_concat)
-
     def isin(self, values) -> np.ndarray:
         """
         Check whether `values` are contained in Categorical.

pandas/core/indexes/category.py

@@ -433,11 +433,6 @@ def _to_safe_for_reshape(self):
         """ convert to object if we are a categorical """
         return self.astype("object")
 
-    def _maybe_cast_indexer(self, key):
-        code = self.categories.get_loc(key)
-        code = self.codes.dtype.type(code)
-        return code
-
     @doc(Index.where)
     def where(self, cond, other=None):
         # TODO: Investigate an alternative implementation with
@@ -537,6 +532,14 @@ def _reindex_non_unique(self, target):
 
         return new_target, indexer, new_indexer
 
+    # --------------------------------------------------------------------
+    # Indexing Methods
+
+    def _maybe_cast_indexer(self, key):
+        code = self.categories.get_loc(key)
+        code = self.codes.dtype.type(code)
+        return code
+
     @Appender(_index_shared_docs["get_indexer"] % _index_doc_kwargs)
     def get_indexer(self, target, method=None, limit=None, tolerance=None):
         method = missing.clean_reindex_fill_method(method)
@@ -619,6 +622,15 @@ def _convert_arr_indexer(self, keyarr):
     def _convert_index_indexer(self, keyarr):
         return self._shallow_copy(keyarr)
 
+    @doc(Index._maybe_cast_slice_bound)
+    def _maybe_cast_slice_bound(self, label, side, kind):
+        if kind == "loc":
+            return label
+
+        return super()._maybe_cast_slice_bound(label, side, kind)
+
+    # --------------------------------------------------------------------
+
     def take_nd(self, *args, **kwargs):
         """Alias for `take`"""
         warnings.warn(
@@ -628,13 +640,6 @@ def take_nd(self, *args, **kwargs):
         )
         return self.take(*args, **kwargs)
 
-    @doc(Index._maybe_cast_slice_bound)
-    def _maybe_cast_slice_bound(self, label, side, kind):
-        if kind == "loc":
-            return label
-
-        return super()._maybe_cast_slice_bound(label, side, kind)
-
     def map(self, mapper):
         """
         Map values using input correspondence (a dict, Series, or function).

pandas/core/indexes/datetimes.py

@@ -509,6 +509,9 @@ def snap(self, freq="S"):
         dta = DatetimeArray(snapped, dtype=self.dtype)
         return DatetimeIndex._simple_new(dta, name=self.name)
 
+    # --------------------------------------------------------------------
+    # Indexing Methods
+
     def _parsed_string_to_bounds(self, reso: Resolution, parsed: datetime):
         """
         Calculate datetime bounds for parsed time string and its resolution.