Merged

Author: cmazzullo

doc/source/whatsnew/v0.22.0.txt

@@ -28,10 +28,11 @@ Other Enhancements
 
 .. _whatsnew_0220.api_breaking:
 
+
 Backwards incompatible API changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
--
+- When created with duplicate labels, ``MultiIndex`` now raises a ``ValueError``. (:issue:`17464`)
 -
 -
 

pandas/tests/indexes/test_multi.py

@@ -1573,7 +1573,6 @@ def test_is_(self):
         # shouldn't change
         assert mi2.is_(mi)
         mi4 = mi3.view()
-        # GH 17464 - Remove duplicate MultiIndex levels
         mi4.set_levels([lrange(10), lrange(10)], inplace=True)
         assert not mi4.is_(mi3)
         mi5 = mi.view()
@@ -2376,7 +2375,6 @@ def test_level_setting_resets_attributes(self):
             ['A', 'A', 'B', 'B', 'B'], [1, 2, 1, 2, 3]
         ])
         assert ind.is_monotonic
-        # GH 17464 - Remove duplicate MultiIndex levels
         ind.set_levels([['A', 'B'], [1, 3, 2]], inplace=True)
         # if this fails, probably didn't reset the cache correctly.
         assert not ind.is_monotonic
@@ -2980,3 +2978,15 @@ def test_nan_stays_float(self):
         assert pd.isna(df0.index.get_level_values(1)).all()
         # the following failed in 0.14.1
         assert pd.isna(dfm.index.get_level_values(1)[:-1]).all()
+
+    def test_duplicate_multiindex_labels(self):
+        # GH 17464
+        # Make sure that a MultiIndex with duplicate levels throws a ValueError
+        with pytest.raises(ValueError):
+            ind = pd.MultiIndex([['A'] * 10, range(10)], [[0] * 10, range(10)])
+        # And that using set_levels with duplicate levels fails
+        ind = MultiIndex.from_arrays([['A', 'A', 'B', 'B', 'B'],
+                                      [1, 2, 1, 2, 3]])
+        with pytest.raises(ValueError):
+            ind.set_levels([['A', 'B', 'A', 'A', 'B'], [2, 1, 3, -2, 5]],
+                           inplace=True)