updates

Author: TomAugspurger

pandas/core/dtypes/dtypes.py

@@ -121,26 +121,6 @@ class CategoricalDtype(ExtensionDtype):
     categories : list or None
     ordered : bool, default False
 
-    Notes
-    -----
-    An instance of ``CategoricalDtype`` compares equal with any other
-    instance of ``CategoricalDtype``, regardless of categories or ordered.
-    In addition they compare equal to the string ``'category'``.
-
-    To check whether two instances of a ``CategoricalDtype`` exactly,
-    use the ``is`` operator.
-
-    >>> t1 = CategoricalDtype(['a', 'b'], ordered=True)
-    >>> t2 = CategoricalDtype(['a', 'c'], ordered=False)
-    >>> t1 == t2
-    True
-    >>> t1 == 'category'
-    True
-    >>> t1 is t2
-    False
-    >>> t1 is CategoricalDtype(['a', 'b'], ordered=True)
-    True
-
     Examples
     --------
     >>> t = CategoricalDtype(categories=['b', 'a'], ordered=True)
@@ -160,17 +140,16 @@ class CategoricalDtype(ExtensionDtype):
     kind = 'O'
     str = '|O08'
     base = np.dtype('O')
-    _metadata = []
+    _metadata = ['categories', 'ordered']
     _cache = weakref.WeakValueDictionary()
 
     def __new__(cls, categories=None, ordered=False, fastpath=False):
         from pandas.core.indexes.base import Index
         if categories is not None:
             categories = Index(categories)
-            # Can just inline _validate_* if needed
+            # validation
             cls._validate_categories(categories, fastpath=fastpath)
             cls._validate_ordered(ordered)
-
             # We have a choice when hashing pandas unordered categoricals
             # We can completely ignore the order, or not. I.e. should
             # [a, b, c] hash the same as [b, a, c], when both are unordered?
@@ -184,7 +163,15 @@ def __new__(cls, categories=None, ordered=False, fastpath=False):
             hashed = cls._hash_categories(categories, ordered=True)
         else:
             hashed = None
-        return cls._get_or_create(categories, ordered, hashed)
+
+        try:
+            return cls._cache[(hashed, ordered)]
+        except KeyError:
+            categorical = object.__new__(cls)
+            categorical._categories = categories
+            categorical._ordered = ordered
+            cls._cache[(hashed, ordered)] = categorical
+            return categorical
 
     def __hash__(self):
         # _hash_categories returns a uint64, so use the negative
@@ -237,18 +224,6 @@ def _hash_categories(categories, ordered=True):
         hashed = np.bitwise_xor.reduce(hashed)
         return hashed
 
-    @classmethod
-    def _get_or_create(cls, categories, ordered, hashed):
-
-        try:
-            return cls._cache[(hashed, ordered)]
-        except KeyError:
-            categorical = object.__new__(cls)
-            categorical._categories = categories
-            categorical._ordered = ordered
-            cls._cache[(hashed, ordered)] = categorical
-            return categorical
-
     @classmethod
     def construct_from_string(cls, string):
         """ attempt to construct this type from a string, raise a TypeError if

pandas/core/util/hashing.py

@@ -260,7 +260,7 @@ def hash_array(vals, encoding='utf8', hash_key=None, categorize=True):
 
     # For categoricals, we hash the categories, then remap the codes to the
     # hash values. (This check is above the complex check so that we don't ask
-    # numpy if categorical is a subdtype of complex, as it will choke.
+    # numpy if categorical is a subdtype of complex, as it will choke).
     if is_categorical_dtype(dtype):
         return _hash_categorical(vals, encoding, hash_key)