PERF: For GH23814, return early in Categorical.__init__

Author: erikoveson

asv_bench/benchmarks/categoricals.py

@@ -46,6 +46,7 @@ def setup(self):
         self.values_some_nan = list(np.tile(self.categories + [np.nan], N))
         self.values_all_nan = [np.nan] * len(self.values)
         self.values_all_int8 = np.ones(N, 'int8')
+        self.categorical = pd.Categorical(self.values, self.categories)
 
     def time_regular(self):
         pd.Categorical(self.values, self.categories)
@@ -68,6 +69,9 @@ def time_all_nan(self):
     def time_from_codes_all_int8(self):
         pd.Categorical.from_codes(self.values_all_int8, self.categories)
 
+    def time_existing_categorical(self):
+        pd.Categorical(self.categorical)
+
 
 class ValueCounts(object):
 

pandas/core/arrays/categorical.py

@@ -314,6 +314,16 @@ class Categorical(ExtensionArray, PandasObject):
     def __init__(self, values, categories=None, ordered=None, dtype=None,
                  fastpath=False):
 
+        # GH23814, for perf, if no optional params used and values already an
+        # instance of Categorical, simply return the same dtype/codes
+        if categories is None and ordered is None and dtype is None:
+            if isinstance(values, (ABCSeries, ABCIndexClass)):
+                values = values._values
+            if isinstance(values, type(self)):
+                self._dtype = values.dtype
+                self._codes = values.codes.copy()
+                return
+
         # Ways of specifying the dtype (prioritized ordered)
         # 1. dtype is a CategoricalDtype
         #    a.) with known categories, use dtype.categories