added validate_dtype and changed code using fastpaath paremeter

Author: kaichogami

pandas/core/categorical.py

@@ -25,6 +25,7 @@
     is_timedelta64_dtype,
     is_categorical,
     is_categorical_dtype,
+    is_integer_dtype,
     is_list_like, is_sequence,
     is_scalar,
     is_dict_like)
@@ -244,44 +245,8 @@ class Categorical(PandasObject):
     def __init__(self, values, categories=None, ordered=None, dtype=None,
                  fastpath=False):
 
-        # Ways of specifying the dtype (prioritized ordered)
-        # 1. dtype is a CategoricalDtype
-        #    a.) with known categories, use dtype.categories
-        #    b.) else with Categorical values, use values.dtype
-        #    c.) else, infer from values
-        #    d.) specifying dtype=CategoricalDtype and categories is an error
-        # 2. dtype is a string 'category'
-        #    a.) use categories, ordered
-        #    b.) use values.dtype
-        #    c.) infer from values
-        # 3. dtype is None
-        #    a.) use categories, ordered
-        #    b.) use values.dtype
-        #    c.) infer from values
-
-        if dtype is not None:
-            # The dtype argument takes precedence over values.dtype (if any)
-            if isinstance(dtype, compat.string_types):
-                if dtype == 'category':
-                    dtype = CategoricalDtype(categories, ordered)
-                else:
-                    msg = "Unknown `dtype` {dtype}"
-                    raise ValueError(msg.format(dtype=dtype))
-            elif categories is not None or ordered is not None:
-                raise ValueError("Cannot specify both `dtype` and `categories`"
-                                 " or `ordered`.")
-
-            categories = dtype.categories
-            ordered = dtype.ordered
-
-        elif is_categorical(values):
-            # If no "dtype" was passed, use the one from "values", but honor
-            # the "ordered" and "categories" arguments
-            dtype = values.dtype._from_categorical_dtype(values.dtype,
-                                                         categories, ordered)
-        else:
-            # If dtype=None and values is not categorical, create a new dtype
-            dtype = CategoricalDtype(categories, ordered)
+        categories, ordered, dtype = validate_dtype(values, categories,
+                                                    ordered, dtype)
 
         # At this point, dtype is always a CategoricalDtype
         # if dtype.categories is None, we are inferring
@@ -347,6 +312,13 @@ def __init__(self, values, categories=None, ordered=None, dtype=None,
                                            dtype.categories)
 
         else:
+            # there were two ways if categories are present
+            # - the old one, where each value is a int pointer to the levels
+            #   array -> not anymore possible, but code outside of pandas could
+            #   call us like that, so make some checks
+            # - the new one, where each value is also in the categories array
+            #   (or np.nan)
+
             codes = _get_codes_for_values(values, dtype.categories)
 
         if null_mask.any():
@@ -875,6 +847,11 @@ def set_categories(self, new_categories, ordered=None, rename=False,
     def rename_categories(self, new_categories, inplace=False):
         """ Renames categories.
 
+        The new categories can be either a list-like dict-like object.
+        If it is list-like, all items must be unique and the number of items
+        in the new categories must be the same as the number of items in the
+        old categories.
+
         Raises
         ------
         ValueError
@@ -915,33 +892,10 @@ def rename_categories(self, new_categories, inplace=False):
         remove_categories
         remove_unused_categories
         set_categories
-
-        Examples
-        --------
-        >>> c = Categorical(['a', 'a', 'b'])
-        >>> c.rename_categories([0, 1])
-        [0, 0, 1]
-        Categories (2, int64): [0, 1]
-
-        For dict-like ``new_categories``, extra keys are ignored and
-        categories not in the dictionary are passed through
-
-        >>> c.rename_categories({'a': 'A', 'c': 'C'})
-        [A, A, b]
-        Categories (2, object): [A, b]
         """
         inplace = validate_bool_kwarg(inplace, 'inplace')
         cat = self if inplace else self.copy()
 
-        if isinstance(new_categories, ABCSeries):
-            msg = ("Treating Series 'new_categories' as a list-like and using "
-                   "the values. In a future version, 'rename_categories' will "
-                   "treat Series like a dictionary.\n"
-                   "For dict-like, use 'new_categories.to_dict()'\n"
-                   "For list-like, use 'new_categories.values'.")
-            warn(msg, FutureWarning, stacklevel=2)
-            new_categories = list(new_categories)
-
         if is_dict_like(new_categories):
             cat.categories = [new_categories.get(item, item)
                               for item in cat.categories]