GH#15420 added support for na_option when ranking categorical

Author: jeet63

doc/source/whatsnew/v0.20.0.txt

@@ -627,3 +627,4 @@ Bug Fixes
 - Bug in ``Series.replace`` and ``DataFrame.replace`` which failed on empty replacement dicts (:issue:`15289`)
 - Bug in ``pd.melt()`` where passing a tuple value for ``value_vars`` caused a ``TypeError`` (:issue:`15348`)
 - Bug in ``.eval()`` which caused multiline evals to fail with local variables not on the first line (:issue:`15342`)
+- Bug in ``.rank()`` rank incorrectly orders ordered categories

pandas/core/algorithms.py

@@ -989,9 +989,10 @@ def _get_data_algo(values, func_map):
         f = func_map['uint64']
         values = _ensure_uint64(values)
 
-    elif is_categorical_dtype(values):
-        f = func_map['int64']
-        values = _ensure_int64(values.codes)
+    elif is_categorical_dtype(values) and values.ordered:
+        nanMapper = np.vectorize(lambda t: np.NaN if t == -1 else t*1.)
+        f = func_map['float64']
+        values = _ensure_float64(nanMapper(values.codes))
 
     else:
         values = _ensure_object(values)

pandas/tests/series/test_analytics.py

@@ -1057,6 +1057,59 @@ def test_rank(self):
         iranks = iseries.rank()
         assert_series_equal(iranks, exp)
 
+        # GH issue #15420 rank incorrectly orders ordered categories
+        
+        # Test ascending/descending ranking for ordered categoricals
+        exp = pd.Series([1., 2., 3., 4., 5., 6.])
+        exp_desc = pd.Series([6., 5., 4., 3., 2., 1.])
+        ser = pd.Series(
+            ['first', 'second', 'third', 'fourth', 'fifth', 'sixth']
+        )
+        ordered = ser.astype('category', ).cat.set_categories(
+            ['first', 'second', 'third', 'fourth', 'fifth', 'sixth'],
+            ordered=True
+        )
+        assert_series_equal(ordered.rank(), exp)
+        assert_series_equal(ordered.rank(ascending=False), exp_desc)
+
+        # Unordered categoricals should be ranked as objects
+        unordered = ser.astype('category', ).cat.set_categories(
+            ['first', 'second', 'third', 'fourth', 'fifth', 'sixth'],
+            ordered=False
+        )
+        res = unordered.rank()
+        assert_series_equal(res, unordered.astype(object).rank())
+
+        # Test na_option for rank data
+        na_ser = pd.Series(
+            ['first', 'second', 'third', 'fourth', 'fifth', 'sixth', np.NaN]
+        ).astype('category', ).cat.set_categories(
+            [
+                'first', 'second', 'third', 'fourth',
+                'fifth', 'sixth', 'seventh'
+            ],
+            ordered=True
+        )
+
+        exp_top = pd.Series([2., 3., 4., 5., 6., 7., 1.])
+        exp_bot = pd.Series([1., 2., 3., 4., 5., 6., 7.])
+        exp_keep = pd.Series([1., 2., 3., 4., 5., 6., np.NaN])
+
+        assert_series_equal(
+            na_ser.rank(na_option='top'),
+            exp_top
+        )
+
+        assert_series_equal(
+            na_ser.rank(na_option='bottom'),
+            exp_bot
+        )
+
+        assert_series_equal(
+            na_ser.rank(na_option='keep'),
+            exp_keep
+        )
+
     def test_rank_signature(self):
         s = Series([0, 1])
         s.rank(method='average')

pandas/tests/test_categorical.py

@@ -4549,14 +4549,6 @@ def test_concat_categorical(self):
                             'h': [None] * 6 + cat_values})
         tm.assert_frame_equal(res, exp)
 
-    def test_rank_categorical(self):
-        exp = pd.Series([1., 2., 3., 4., 5., 6.], name='A')
-        dframe = pd.DataFrame(['first', 'second', 'third', 'fourth', 'fifth', 'sixth'], columns=['A'])
-        dframe['A'] = dframe['A'].astype('category', ).cat.set_categories(
-                ['first', 'second', 'third', 'fourth', 'fifth', 'sixth'], ordered=True)
-        res = dframe['A'].rank()
-        tm.assert_series_equal(res, exp)
-
 class TestCategoricalSubclassing(tm.TestCase):
 
     def test_constructor(self):