Merge pull request #10464 from sinhrks/categorical_map

BUG: Series.map using categorical Series raises AttributeError

Author: sinhrks

doc/source/whatsnew/v0.17.0.txt

@@ -124,8 +124,8 @@ Bug Fixes
 
 
 - Bug in ``test_categorical`` on big-endian builds (:issue:`10425`)
-
-
+- Bug in ``Series.map`` using categorical ``Series`` raises ``AttributeError`` (:issue:`10324`)
+- Bug in ``MultiIndex.get_level_values`` including ``Categorical`` raises ``AttributeError`` (:issue:`10460`)
 
 - Bug that caused segfault when resampling an empty Series (:issue:`10228`)
 - Bug in ``DatetimeIndex`` and ``PeriodIndex.value_counts`` resets name from its result, but retains in result's ``Index``. (:issue:`10150`)

pandas/core/common.py

@@ -782,6 +782,11 @@ def take_nd(arr, indexer, axis=0, out=None, fill_value=np.nan,
         will be done.  This short-circuits computation of a mask.  Result is
         undefined if allow_fill == False and -1 is present in indexer.
     """
+
+    if is_categorical(arr):
+        return arr.take_nd(indexer, fill_value=fill_value,
+                           allow_fill=allow_fill)
+
     if indexer is None:
         indexer = np.arange(arr.shape[axis], dtype=np.int64)
         dtype, fill_value = arr.dtype, arr.dtype.type()

pandas/tests/test_groupby.py

@@ -3476,6 +3476,13 @@ def test_groupby_categorical(self):
         expected.index.names = ['myfactor', None]
         assert_frame_equal(desc_result, expected)
 
+        # GH 10460
+        expc = Categorical.from_codes(np.arange(4).repeat(8), levels, name='myfactor', ordered=True)
+        exp = CategoricalIndex(expc, name='myfactor')
+        self.assert_index_equal(desc_result.index.get_level_values(0), exp)
+        exp = Index(['count', 'mean', 'std', 'min', '25%', '50%', '75%', 'max'] * 4)
+        self.assert_index_equal(desc_result.index.get_level_values(1), exp)
+
     def test_groupby_datetime_categorical(self):
         # GH9049: ensure backward compatibility
         levels = pd.date_range('2014-01-01', periods=4)
@@ -3488,7 +3495,8 @@ def test_groupby_datetime_categorical(self):
 
         expected = data.groupby(np.asarray(cats)).mean()
         expected = expected.reindex(levels)
-        expected.index = CategoricalIndex(expected.index,categories=expected.index,name='myfactor',ordered=True)
+        expected.index = CategoricalIndex(expected.index, categories=expected.index,
+                                          name='myfactor', ordered=True)
 
         assert_frame_equal(result, expected)
         self.assertEqual(result.index.name, cats.name)
@@ -3503,6 +3511,14 @@ def test_groupby_datetime_categorical(self):
         expected.index.names = ['myfactor', None]
         assert_frame_equal(desc_result, expected)
 
+        # GH 10460
+        expc = Categorical.from_codes(np.arange(4).repeat(8), levels, name='myfactor', ordered=True)
+        exp = CategoricalIndex(expc, name='myfactor')
+        self.assert_index_equal(desc_result.index.get_level_values(0), exp)
+        exp = Index(['count', 'mean', 'std', 'min', '25%', '50%', '75%', 'max'] * 4)
+        self.assert_index_equal(desc_result.index.get_level_values(1), exp)
+
+
     def test_groupby_categorical_index(self):
 
         levels = ['foo', 'bar', 'baz', 'qux']

pandas/tests/test_index.py

@@ -3534,6 +3534,16 @@ def test_get_level_values(self):
         expected = self.index.get_level_values(0)
         self.assert_numpy_array_equal(result, expected)
 
+        # GH 10460
+        index = MultiIndex(levels=[CategoricalIndex(['A', 'B']),
+                                   CategoricalIndex([1, 2, 3])],
+                           labels=[np.array([0, 0, 0, 1, 1, 1]),
+                                   np.array([0, 1, 2, 0, 1, 2])])
+        exp = CategoricalIndex(['A', 'A', 'A', 'B', 'B', 'B'])
+        self.assert_index_equal(index.get_level_values(0), exp)
+        exp = CategoricalIndex([1, 2 ,3, 1, 2, 3])
+        self.assert_index_equal(index.get_level_values(1), exp)
+
     def test_get_level_values_na(self):
         arrays = [['a', 'b', 'b'], [1, np.nan, 2]]
         index = pd.MultiIndex.from_arrays(arrays)

pandas/tests/test_series.py

@@ -5753,6 +5753,35 @@ def test_map(self):
         result = self.ts.map(lambda x: x * 2)
         self.assert_numpy_array_equal(result, self.ts * 2)
 
+        # GH 10324
+        a = Series([1, 2, 3, 4])
+        b = Series(["even", "odd", "even", "odd"], dtype="category")
+        c = Series(["even", "odd", "even", "odd"])
+
+        exp = Series(["odd", "even", "odd", np.nan], dtype="category")
+        self.assert_series_equal(a.map(b), exp)
+        exp = Series(["odd", "even", "odd", np.nan])
+        self.assert_series_equal(a.map(c), exp)
+
+        a = Series(['a', 'b', 'c', 'd'])
+        b = Series([1, 2, 3, 4], index=pd.CategoricalIndex(['b', 'c', 'd', 'e']))
+        c = Series([1, 2, 3, 4], index=Index(['b', 'c', 'd', 'e']))
+
+        exp = Series([np.nan, 1, 2, 3])
+        self.assert_series_equal(a.map(b), exp)
+        exp = Series([np.nan, 1, 2, 3])
+        self.assert_series_equal(a.map(c), exp)
+
+        a = Series(['a', 'b', 'c', 'd'])
+        b = Series(['B', 'C', 'D', 'E'], dtype='category',
+                   index=pd.CategoricalIndex(['b', 'c', 'd', 'e']))
+        c = Series(['B', 'C', 'D', 'E'], index=Index(['b', 'c', 'd', 'e']))
+
+        exp = Series([np.nan, 'B', 'C', 'D'], dtype='category')
+        self.assert_series_equal(a.map(b), exp)
+        exp = Series([np.nan, 'B', 'C', 'D'])
+        self.assert_series_equal(a.map(c), exp)
+
     def test_map_compat(self):
         # related GH 8024
         s = Series([True,True,False],index=[1,2,3])