REF: Move Categorical logic from Grouping (#46203)

Author: NickCrews

pandas/core/groupby/categorical.py

@@ -1,14 +1,68 @@
 from __future__ import annotations
+import dataclasses
+from typing import final
 
 import numpy as np
 
+from pandas._typing import ArrayLike
 from pandas.core.algorithms import unique1d
 from pandas.core.arrays.categorical import (
     Categorical,
     CategoricalDtype,
     recode_for_categories,
 )
-from pandas.core.indexes.api import CategoricalIndex
+from pandas.core.indexes.api import (
+    Index,
+    CategoricalIndex,
+)
+
+
+@final
+@dataclasses.dataclass
+class CategoricalGrouper:
+    original_grouping_vector: Categorical
+    new_grouping_vector: Categorical
+    observed: bool
+    sort: bool
+
+    def result_index(self, new_index: Index) -> Index:
+        if self.original_grouping_vector is None:
+            return new_index
+        assert isinstance(new_index, CategoricalIndex)
+        return recode_from_groupby(self.original_grouping_vector, self.sort, new_index)
+
+    def group_index(self):
+        return self.original_grouping_vector
+
+    @classmethod
+    def make(cls, grouping_vector, sort: bool, observed: bool) -> "CategoricalGrouper":
+        new_grouping_vector, original_grouping_vector = recode_for_groupby(
+            grouping_vector, sort, observed
+        )
+        return cls(
+            original_grouping_vector=original_grouping_vector,
+            new_grouping_vector=new_grouping_vector,
+            observed=observed,
+            sort=sort,
+        )
+
+    def codes_and_uniques(self, cat: Categorical) -> tuple[np.ndarray, ArrayLike]:
+        # we make a CategoricalIndex out of the cat grouper
+        # preserving the categories / ordered attributes
+        categories = cat.categories
+
+        if self.observed:
+            ucodes = unique1d(cat.codes)
+            ucodes = ucodes[ucodes != -1]
+            if self.sort or cat.ordered:
+                ucodes = np.sort(ucodes)
+        else:
+            ucodes = np.arange(len(categories))
+
+        uniques = Categorical.from_codes(
+            codes=ucodes, categories=categories, ordered=cat.ordered
+        )
+        return cat.codes, uniques
 
 
 def recode_for_groupby(

pandas/core/groupby/grouper.py

@@ -38,12 +38,8 @@
 import pandas.core.common as com
 from pandas.core.frame import DataFrame
 from pandas.core.groupby import ops
-from pandas.core.groupby.categorical import (
-    recode_for_groupby,
-    recode_from_groupby,
-)
+from pandas.core.groupby.categorical import CategoricalGrouper
 from pandas.core.indexes.api import (
-    CategoricalIndex,
     Index,
     MultiIndex,
 )
@@ -461,8 +457,7 @@ class Grouping:
 
     _codes: npt.NDArray[np.signedinteger] | None = None
     _group_index: Index | None = None
-    _passed_categorical: bool
-    _all_grouper: Categorical | None
+    _cat_info: CategoricalGrouper | None = None
     _index: Index
 
     def __init__(
@@ -479,16 +474,12 @@ def __init__(
         self.level = level
         self._orig_grouper = grouper
         self.grouping_vector = _convert_grouper(index, grouper)
-        self._all_grouper = None
         self._index = index
         self._sort = sort
         self.obj = obj
-        self._observed = observed
         self.in_axis = in_axis
         self._dropna = dropna
 
-        self._passed_categorical = False
-
         # we have a single grouper which may be a myriad of things,
         # some of which are dependent on the passing in level
 
@@ -527,13 +518,10 @@ def __init__(
                 self.grouping_vector = Index(ng, name=newgrouper.result_index.name)
 
         elif is_categorical_dtype(self.grouping_vector):
-            # a passed Categorical
-            self._passed_categorical = True
-
-            self.grouping_vector, self._all_grouper = recode_for_groupby(
-                self.grouping_vector, sort, observed
+            self._cat_info = CategoricalGrouper.make(
+                self.grouping_vector, sort, observed, dropna=dropna
             )
-
+            self.grouping_vector = self._cat_info.new_grouping_vector
         elif not isinstance(
             self.grouping_vector, (Series, Index, ExtensionArray, np.ndarray)
         ):
@@ -631,20 +619,23 @@ def group_arraylike(self) -> ArrayLike:
             # _group_index is set in __init__ for MultiIndex cases
             return self._group_index._values
 
-        elif self._all_grouper is not None:
+        elif (
+            self._cat_info is not None
+            and self._cat_info.original_grouping_vector is not None
+        ):
             # retain dtype for categories, including unobserved ones
             return self.result_index._values
 
         return self._codes_and_uniques[1]
 
     @cache_readonly
     def result_index(self) -> Index:
-        # result_index retains dtype for categories, including unobserved ones,
-        #  which group_index does not
-        if self._all_grouper is not None:
-            group_idx = self.group_index
-            assert isinstance(group_idx, CategoricalIndex)
-            return recode_from_groupby(self._all_grouper, self._sort, group_idx)
+        """
+        result_index retains dtype for categories, including unobserved ones,
+        which group_index does not
+        """
+        if self._cat_info is not None:
+            return self._cat_info.result_index(self.group_index)
         return self.group_index
 
     @cache_readonly
@@ -658,25 +649,8 @@ def group_index(self) -> Index:
 
     @cache_readonly
     def _codes_and_uniques(self) -> tuple[npt.NDArray[np.signedinteger], ArrayLike]:
-        if self._passed_categorical:
-            # we make a CategoricalIndex out of the cat grouper
-            # preserving the categories / ordered attributes
-            cat = self.grouping_vector
-            categories = cat.categories
-
-            if self._observed:
-                ucodes = algorithms.unique1d(cat.codes)
-                ucodes = ucodes[ucodes != -1]
-                if self._sort or cat.ordered:
-                    ucodes = np.sort(ucodes)
-            else:
-                ucodes = np.arange(len(categories))
-
-            uniques = Categorical.from_codes(
-                codes=ucodes, categories=categories, ordered=cat.ordered
-            )
-            return cat.codes, uniques
-
+        if self._cat_info is not None:
+            return self._cat_info.codes_and_uniques(self.grouping_vector)
         elif isinstance(self.grouping_vector, ops.BaseGrouper):
             # we have a list of groupers
             codes = self.grouping_vector.codes_info