PERF: fix pandas-dev#32976 slow group by for categorical columns

Aggregate categorical codes with fast cython aggregation for select
`how` operations.

Author: rtlee9

pandas/core/groupby/generic.py

@@ -44,6 +44,7 @@
     ensure_int64,
     ensure_platform_int,
     is_bool,
+    is_categorical_dtype,
     is_integer_dtype,
     is_interval_dtype,
     is_numeric_dtype,
@@ -59,6 +60,7 @@
     normalize_keyword_aggregation,
 )
 import pandas.core.algorithms as algorithms
+from pandas.core.arrays.categorical import Categorical
 from pandas.core.base import DataError, SpecificationError
 import pandas.core.common as com
 from pandas.core.construction import create_series_with_explicit_dtype
@@ -1056,9 +1058,22 @@ def _cython_agg_blocks(
             result = no_result
             locs = block.mgr_locs.as_array
             try:
-                result, _ = self.grouper.aggregate(
-                    block.values, how, axis=1, min_count=min_count
-                )
+
+                if is_categorical_dtype(block.values) and how in ('first', 'last'):
+                    # perf improvement: aggregate categorical codes with fast cython agg
+                    # for select `how` operations
+                    result_codes, _ = self.grouper.aggregate(
+                        block.values.codes, how, axis=1, min_count=min_count
+                    )
+                    result = Categorical.from_codes(
+                        result_codes,
+                        categories=block.values.categories,
+                        ordered=block.values.ordered,
+                    )
+                else:
+                    result, _ = self.grouper.aggregate(
+                        block.values, how, axis=1, min_count=min_count
+                    )
             except NotImplementedError:
                 # generally if we have numeric_only=False
                 # and non-applicable functions