Fix pandas-dev#12564 for Categorical: consistent result if comparing as DataFrame

Author: facaiy

doc/source/whatsnew/v0.18.1.txt

@@ -207,7 +207,9 @@ Bug Fixes
 
 
 - Bug in ``pivot_table`` when ``margins=True`` and ``dropna=True`` where nulls still contributed to margin count (:issue:`12577`)
+
 - Bug in ``Series.name`` when ``name`` attribute can be a hashable type (:issue:`12610`)
 - Bug in ``.describe()`` resets categorical columns information (:issue:`11558`)
 - Bug where ``loffset`` argument was not applied when calling ``resample().count()`` on a timeseries (:issue:`12725`)
 - ``pd.read_excel()`` now accepts path objects (e.g. ``pathlib.Path``, ``py.path.local``) for the file path, in line with other ``read_*`` functions (:issue:`12655`)
+- Bug in ``CategoricalBlock`` when Categoricals equality check raises ValueError in DataFrame (:issue:`12564`)

pandas/core/internals.py

@@ -1874,6 +1874,17 @@ def _slice(self, slicer):
         # return same dims as we currently have
         return self.values._slice(slicer)
 
+    def _try_coerce_result(self, result):
+        """ reverse of try_coerce_args """
+
+        # fix issue #12564: CategoricalBlock is 1-dim only, while category
+        # datarame can be more.
+        if ((not com.is_categorical_dtype(result)) and
+                isinstance(result, np.ndarray)):
+            result = _block_shape(result, ndim=self.ndim)
+
+        return result
+
     def fillna(self, value, limit=None, inplace=False, downcast=None,
                mgr=None):
         # we may need to upcast our fill to match our dtype

pandas/tests/indexing/test_indexing.py

@@ -936,6 +936,22 @@ def check(target, indexers, value, compare_fn, expected=None):
             check(target=df, indexers=(df.index, df.columns), value=df,
                   compare_fn=assert_frame_equal, expected=copy)
 
+    def test_indexing_with_category(self):
+
+        # https://github.com/pydata/pandas/issues/12564#issuecomment-194022792
+        # consistent result if comparing as Dataframe
+
+        cat = DataFrame({'A': ['foo', 'bar', 'baz']})
+        exp = DataFrame({'A': [True, False, False]})
+
+        res = (cat[['A']] == 'foo')
+        tm.assert_frame_equal(res, exp)
+
+        cat['A'] = cat['A'].astype('category')
+
+        res = (cat[['A']] == 'foo')
+        tm.assert_frame_equal(res, exp)
+
     def test_indexing_with_datetime_tz(self):
 
         # 8260