Group by a categorical Series of unequal length

doc/source/whatsnew/v1.4.0.rst

@@ -593,7 +593,7 @@ Groupby/resample/rolling
 - Fixed bug in :meth:`Series.rolling` and :meth:`DataFrame.rolling` for centered datetimelike windows with uneven nanosecond (:issue:`43997`)
 - Bug in :meth:`GroupBy.nth` failing on ``axis=1`` (:issue:`43926`)
 - Fixed bug in :meth:`Series.rolling` and :meth:`DataFrame.rolling` not respecting right bound on centered datetime-like windows, if the index contain duplicates (:issue:`#3944`)
-
+- Enabled grouping by a :class:`Series` that has a categorical data type and length unequal to the axis of grouping (:issue:`44179`); also, with this fix, the ``ValueError`` raised when grouping by a :class:`Categorical` with unequal length now has the same message as when grouping by other sequences
 
 Reshaping
 ^^^^^^^^^

pandas/core/groupby/grouper.py

@@ -887,12 +887,6 @@ def is_in_obj(gpr) -> bool:
         else:
             in_axis = False
 
-        if is_categorical_dtype(gpr) and len(gpr) != obj.shape[axis]:
-            raise ValueError(
-                f"Length of grouper ({len(gpr)}) and axis ({obj.shape[axis]}) "
-                "must be same length"
-            )
-
         # create the Grouping
         # allow us to passing the actual Grouping as the gpr
         ping = (
@@ -938,7 +932,7 @@ def _convert_grouper(axis: Index, grouper):
             return grouper.reindex(axis)._values
     elif isinstance(grouper, MultiIndex):
         return grouper._values
-    elif isinstance(grouper, (list, tuple, Series, Index, np.ndarray)):
+    elif isinstance(grouper, (list, tuple, Index, Categorical, np.ndarray)):
         if len(grouper) != len(axis):
             raise ValueError("Grouper and axis must be same length")
 

pandas/tests/groupby/test_categorical.py

@@ -668,11 +668,32 @@ def test_bins_unequal_len():
     bins = pd.cut(series.dropna().values, 4)
 
     # len(bins) != len(series) here
-    msg = r"Length of grouper \(8\) and axis \(10\) must be same length"
-    with pytest.raises(ValueError, match=msg):
+    with pytest.raises(ValueError, match=r"Grouper and axis must be same length"):
         series.groupby(bins).mean()
 
 
+@pytest.mark.parametrize(
+    ["series", "data"],
+    [
+        # Group a series with length and index equal to those of the grouper.
+        (Series(range(4)), {"A": [0, 3], "B": [1, 2]}),
+        # Group a series with length equal to that of the grouper and index unequal to
+        # that of the grouper.
+        (Series(range(4)).rename(lambda idx: idx + 1), {"A": [2], "B": [0, 1]}),
+        # GH44179: Group a series with length unequal to that of the grouper.
+        (Series(range(7)), {"A": [0, 3], "B": [1, 2]}),
+    ],
+)
+def test_categorical_series(series, data):
+    # Group the given series by a series with categorical data type such that group A
+    # takes indices 0 and 3 and group B indices 1 and 2, obtaining the values mapped in
+    # the given data.
+    groupby = series.groupby(Series(list("ABBA"), dtype="category"))
+    tm.assert_series_equal(
+        groupby.aggregate(list), Series(data, index=CategoricalIndex(data.keys()))
+    )
+
+
 def test_as_index():
     # GH13204
     df = DataFrame(