BUG: Bug on reset_index for a MultiIndex of all NaNs

closes pandas-dev#6322

Author: tzinckgraf <[email protected]>

Closes pandas-dev#15466 from tzinckgraf/GH6322 and squashes the following commits:

35f97f4 [tzinckgraf] GH6322, Bug on reset_index for a MultiIndex of all NaNs

Author: tzinckgraf

doc/source/whatsnew/v0.20.0.txt

@@ -575,6 +575,7 @@ Bug Fixes
 - Incorrect dtyped ``Series`` was returned by comparison methods (e.g., ``lt``, ``gt``, ...) against a constant for an empty ``DataFrame`` (:issue:`15077`)
 - Bug in ``Series.dt.round`` inconsistent behaviour on NAT's with different arguments (:issue:`14940`)
 - Bug in ``DataFrame.fillna()`` where the argument ``downcast`` was ignored when fillna value was of type ``dict`` (:issue:`15277`)
+- Bug in ``.reset_index()`` when an all ``NaN`` level of a ``MultiIndex`` would fail (:issue:`6322`)
 
 
 

pandas/core/frame.py

@@ -2973,10 +2973,17 @@ def _maybe_casted_values(index, labels=None):
             # if we have the labels, extract the values with a mask
             if labels is not None:
                 mask = labels == -1
-                values = values.take(labels)
-                if mask.any():
-                    values, changed = _maybe_upcast_putmask(values, mask,
-                                                            np.nan)
+
+                # we can have situations where the whole mask is -1,
+                # meaning there is nothing found in labels, so make all nan's
+                if mask.all():
+                    values = np.empty(len(mask))
+                    values.fill(np.nan)
+                else:
+                    values = values.take(labels)
+                    if mask.any():
+                        values, changed = _maybe_upcast_putmask(values, mask,
+                                                                np.nan)
             return values
 
         new_index = _default_index(len(new_obj))

pandas/tests/frame/test_alter_axes.py

@@ -624,6 +624,33 @@ def test_reset_index_multiindex_col(self):
                                 ['a', 'mean', 'median', 'mean']])
         assert_frame_equal(rs, xp)
 
+    def test_reset_index_multiindex_nan(self):
+        # GH6322, testing reset_index on MultiIndexes
+        # when we have a nan or all nan
+        df = pd.DataFrame({'A': ['a', 'b', 'c'],
+                           'B': [0, 1, np.nan],
+                           'C': np.random.rand(3)})
+        rs = df.set_index(['A', 'B']).reset_index()
+        assert_frame_equal(rs, df)
+
+        df = pd.DataFrame({'A': [np.nan, 'b', 'c'],
+                           'B': [0, 1, 2],
+                           'C': np.random.rand(3)})
+        rs = df.set_index(['A', 'B']).reset_index()
+        assert_frame_equal(rs, df)
+
+        df = pd.DataFrame({'A': ['a', 'b', 'c'],
+                           'B': [0, 1, 2],
+                           'C': [np.nan, 1.1, 2.2]})
+        rs = df.set_index(['A', 'B']).reset_index()
+        assert_frame_equal(rs, df)
+
+        df = pd.DataFrame({'A': ['a', 'b', 'c'],
+                           'B': [np.nan, np.nan, np.nan],
+                           'C': np.random.rand(3)})
+        rs = df.set_index(['A', 'B']).reset_index()
+        assert_frame_equal(rs, df)
+
     def test_reset_index_with_datetimeindex_cols(self):
         # GH5818
         #