ENH: Clarify error message when reindexing fails (pandas-dev#42000) (pandas-dev#42007)

Author: aberres

doc/source/user_guide/indexing.rst

@@ -701,7 +701,7 @@ Having a duplicated index will raise for a ``.reindex()``:
 .. code-block:: ipython
 
    In [17]: s.reindex(labels)
-   ValueError: cannot reindex from a duplicate axis
+   ValueError: cannot reindex on an axis with duplicate labels
 
 Generally, you can intersect the desired labels with the current
 axis, and then reindex.
@@ -717,7 +717,7 @@ However, this would *still* raise if your resulting index is duplicated.
    In [41]: labels = ['a', 'd']
 
    In [42]: s.loc[s.index.intersection(labels)].reindex(labels)
-   ValueError: cannot reindex from a duplicate axis
+   ValueError: cannot reindex on an axis with duplicate labels
 
 
 .. _indexing.basics.partial_setting:

pandas/core/indexes/base.py

@@ -3737,7 +3737,7 @@ def _validate_can_reindex(self, indexer: np.ndarray) -> None:
         """
         # trying to reindex on an axis with duplicates
         if not self._index_as_unique and len(indexer):
-            raise ValueError("cannot reindex from a duplicate axis")
+            raise ValueError("cannot reindex on an axis with duplicate labels")
 
     def reindex(
         self, target, method=None, level=None, limit=None, tolerance=None

pandas/tests/frame/indexing/test_getitem.py

@@ -299,7 +299,7 @@ def test_getitem_boolean_frame_unaligned_with_duplicate_columns(self, df_dup_col
 
         # boolean with the duplicate raises
         df = df_dup_cols
-        msg = "cannot reindex from a duplicate axis"
+        msg = "cannot reindex on an axis with duplicate labels"
         with pytest.raises(ValueError, match=msg):
             df[df.A > 6]
 

pandas/tests/frame/indexing/test_setitem.py

@@ -68,7 +68,7 @@ def test_setitem_error_msmgs(self):
             index=Index(["a", "b", "c", "a"], name="foo"),
             name="fiz",
         )
-        msg = "cannot reindex from a duplicate axis"
+        msg = "cannot reindex on an axis with duplicate labels"
         with pytest.raises(ValueError, match=msg):
             df["newcol"] = ser
 

pandas/tests/frame/methods/test_reindex.py

@@ -658,7 +658,7 @@ def test_reindex_dups(self):
         tm.assert_frame_equal(result, expected)
 
         # reindex fails
-        msg = "cannot reindex from a duplicate axis"
+        msg = "cannot reindex on an axis with duplicate labels"
         with pytest.raises(ValueError, match=msg):
             df.reindex(index=list(range(len(df))))
 
@@ -668,7 +668,7 @@ def test_reindex_with_duplicate_columns(self):
         df = DataFrame(
             [[1, 5, 7.0], [1, 5, 7.0], [1, 5, 7.0]], columns=["bar", "a", "a"]
         )
-        msg = "cannot reindex from a duplicate axis"
+        msg = "cannot reindex on an axis with duplicate labels"
         with pytest.raises(ValueError, match=msg):
             df.reindex(columns=["bar"])
         with pytest.raises(ValueError, match=msg):
@@ -942,7 +942,7 @@ def test_reindex_with_categoricalindex(self):
             index=CategoricalIndex(list("aabbca"), dtype=CDT(list("cabe")), name="B"),
         )
         # passed duplicate indexers are not allowed
-        msg = "cannot reindex from a duplicate axis"
+        msg = "cannot reindex on an axis with duplicate labels"
         with pytest.raises(ValueError, match=msg):
             df2.reindex(["a", "b"])
 

pandas/tests/resample/test_datetime_index.py

@@ -692,7 +692,7 @@ def test_asfreq_non_unique():
     rng2 = rng.repeat(2).values
     ts = Series(np.random.randn(len(rng2)), index=rng2)
 
-    msg = "cannot reindex from a duplicate axis"
+    msg = "cannot reindex on an axis with duplicate labels"
     with pytest.raises(ValueError, match=msg):
         ts.asfreq("B")