fixed up append

Author: jreback

pandas/core/categorical.py

@@ -233,6 +233,10 @@ def __init__(self, values, categories=None, ordered=False, name=None, fastpath=F
             cat = values
             if isinstance(values, ABCSeries):
                 cat = values.values
+            if isinstance(values, ABCCategoricalIndex):
+                ordered = values.ordered
+                cat = values.values
+
             if categories is None:
                 categories = cat.categories
             values = values.__array__()

pandas/core/index.py

@@ -963,17 +963,13 @@ def __getitem__(self, key):
         else:
             return result
 
-    def append(self, other):
+    def _ensure_compat_append(self, other):
         """
-        Append a collection of Index options together
-
-        Parameters
-        ----------
-        other : Index or list/tuple of indices
+        prepare the append
 
         Returns
         -------
-        appended : Index
+        list of to_concat, name of result Index
         """
         name = self.name
         to_concat = [self]
@@ -991,7 +987,21 @@ def append(self, other):
         to_concat = self._ensure_compat_concat(to_concat)
         to_concat = [x.values if isinstance(x, Index) else x
                      for x in to_concat]
+        return to_concat, name
+
+    def append(self, other):
+        """
+        Append a collection of Index options together
 
+        Parameters
+        ----------
+        other : Index or list/tuple of indices
+
+        Returns
+        -------
+        appended : Index
+        """
+        to_concat, name = self._ensure_compat_append(other)
         return Index(np.concatenate(to_concat), name=name)
 
     @staticmethod
@@ -2628,6 +2638,10 @@ def codes(self):
     def categories(self):
         return self._data.categories
 
+    @property
+    def ordered(self):
+        return self._data.ordered
+
     def __contains__(self, key):
         hash(key)
         return key in self.categories
@@ -2760,11 +2774,48 @@ def insert(self, loc, item):
 
         from pandas import Categorical
         codes = self.codes
-        idx = np.concatenate(
+        codes = np.concatenate(
             (codes[:loc], code, codes[loc:]))
-        cat = Categorical.from_codes(idx, categories=self.categories)
+        cat = Categorical.from_codes(codes, categories=self.categories)
         return CategoricalIndex(cat, name=self.name)
 
+    def append(self, other):
+        """
+        Append a collection of CategoricalIndex options together
+
+        Parameters
+        ----------
+        other : Index or list/tuple of indices
+
+        Returns
+        -------
+        appended : Index
+
+        Raises
+        ------
+        ValueError if other is not in the categories
+        """
+        from pandas import Categorical
+        categories = self.categories
+        to_concat, name = self._ensure_compat_append(other)
+
+        def convert(c):
+            """ make sure that we have the same categories exactly """
+            if is_categorical_dtype(c):
+                if not c.categories.equals(categories):
+                    raise ValueError("categories must match existing categories when appending")
+            else:
+                c = Categorical(c, categories)
+                if isnull(c).any():
+                    raise ValueError("cannot append a non-category item to a CategoricalIndex")
+
+            return c
+
+        to_concat = [ convert(c) for c in to_concat ]
+
+        codes = np.concatenate([ c.codes for c in to_concat ])
+        cat = Categorical.from_codes(codes, categories=categories)
+        return CategoricalIndex(cat, name=name)
 
 CategoricalIndex._add_numeric_methods_disabled()
 CategoricalIndex._add_logical_methods_disabled()

pandas/tests/test_categorical.py

@@ -11,7 +11,7 @@
 import numpy as np
 import pandas as pd
 
-from pandas import Categorical, Index, Series, DataFrame, PeriodIndex, Timestamp
+from pandas import Categorical, Index, Series, DataFrame, PeriodIndex, Timestamp, CategoricalIndex
 
 from pandas.core.config import option_context
 import pandas.core.common as com
@@ -221,6 +221,11 @@ def f():
             c_old2 = Categorical([0, 1, 2, 0, 1, 2], [1, 2, 3])
             cat = Categorical([1,2], categories=[1,2,3])
 
+    def test_constructor_with_categorical_index(self):
+
+        ci = CategoricalIndex(list('aabbca'),categories=list('cab'))
+        self.assertTrue(ci.values.equals(Categorical(ci)))
+
     def test_constructor_with_generator(self):
         # This was raising an Error in isnull(single_val).any() because isnull returned a scalar
         # for a generator

pandas/tests/test_index.py

@@ -1392,7 +1392,8 @@ def test_append(self):
         result = ci.append([])
         self.assertTrue(result.equals(ci))
 
-        # appending with different categories
+        # appending with different categories or reoreded is not ok
+        self.assertRaises(ValueError, lambda : ci.append(ci.values.set_categories(list('abcd'))))
         self.assertRaises(ValueError, lambda : ci.append(ci.values.reorder_categories(list('abc'))))
 
         # with objects