BUG: Raise a ValueError when index and data lengths don't match (pandas-dev#26911)

* Raise a ValueError when index and data lengths don't match

Author: krsnik93

doc/source/whatsnew/v0.25.0.rst

@@ -673,6 +673,8 @@ Indexing
 ^^^^^^^^
 
 - Improved exception message when calling :meth:`DataFrame.iloc` with a list of non-numeric objects (:issue:`25753`).
+- Improved exception message when calling ``.iloc`` or ``.loc`` with a boolean indexer with different length (:issue:`26658`).
+- Bug in ``.iloc`` and ``.loc`` with a boolean indexer not raising an ``IndexError`` when too few items are passed (:issue:`26658`).
 - Bug in :meth:`DataFrame.loc` and :meth:`Series.loc` where ``KeyError`` was not raised for a ``MultiIndex`` when the key was less than or equal to the number of levels in the :class:`MultiIndex` (:issue:`14885`).
 - Bug in which :meth:`DataFrame.append` produced an erroneous warning indicating that a ``KeyError`` will be thrown in the future when the data to be appended contains new columns (:issue:`22252`).
 - Bug in which :meth:`DataFrame.to_csv` caused a segfault for a reindexed data frame, when the indices were single-level :class:`MultiIndex` (:issue:`26303`).

pandas/core/indexing.py

@@ -2407,29 +2407,54 @@ def convert_to_index_sliceable(obj, key):
     return None
 
 
-def check_bool_indexer(ax, key):
-    # boolean indexing, need to check that the data are aligned, otherwise
-    # disallowed
+def check_bool_indexer(index: Index, key) -> np.ndarray:
+    """
+    Check if key is a valid boolean indexer for an object with such index and
+    perform reindexing or conversion if needed.
+
+    This function assumes that is_bool_indexer(key) == True.
+
+    Parameters
+    ----------
+    index : Index
+        Index of the object on which the indexing is done
+    key : list-like
+        Boolean indexer to check
 
-    # this function assumes that is_bool_indexer(key) == True
+    Returns
+    -------
+    result: np.array
+        Resulting key
 
+    Raises
+    ------
+    IndexError
+        If the key does not have the same length as index
+
+    IndexingError
+        If the index of the key is unalignable to index
+
+    """
     result = key
-    if isinstance(key, ABCSeries) and not key.index.equals(ax):
-        result = result.reindex(ax)
+    if isinstance(key, ABCSeries) and not key.index.equals(index):
+        result = result.reindex(index)
         mask = isna(result._values)
         if mask.any():
             raise IndexingError('Unalignable boolean Series provided as '
                                 'indexer (index of the boolean Series and of '
-                                'the indexed object do not match')
+                                'the indexed object do not match).')
         result = result.astype(bool)._values
-    elif is_sparse(result):
-        result = result.to_dense()
-        result = np.asarray(result, dtype=bool)
     else:
-        # is_bool_indexer has already checked for nulls in the case of an
-        # object array key, so no check needed here
+        if is_sparse(result):
+            result = result.to_dense()
         result = np.asarray(result, dtype=bool)
 
+        # GH26658
+        if len(result) != len(index):
+            raise IndexError(
+                'Item wrong length {} instead of {}.'.format(len(result),
+                                                             len(index)))
+
     return result
 
 

pandas/tests/indexing/test_iloc.py

@@ -265,6 +265,16 @@ def test_iloc_getitem_bool(self):
                           typs=['labels', 'mixed', 'ts', 'floats', 'empty'],
                           fails=IndexError)
 
+    @pytest.mark.parametrize('index', [[True, False],
+                                       [True, False, True, False]])
+    def test_iloc_getitem_bool_diff_len(self, index):
+        # GH26658
+        s = Series([1, 2, 3])
+        with pytest.raises(IndexError,
+                           match=('Item wrong length {} instead of {}.'.format(
+                               len(index), len(s)))):
+            _ = s.iloc[index]
+
     def test_iloc_getitem_slice(self):
 
         # slices
@@ -614,10 +624,10 @@ def test_iloc_mask(self):
                                  'cannot use an indexable as a mask'),
             ('locs', ''): 'Unalignable boolean Series provided as indexer '
                           '(index of the boolean Series and of the indexed '
-                          'object do not match',
+                          'object do not match).',
             ('locs', '.loc'): 'Unalignable boolean Series provided as indexer '
                               '(index of the boolean Series and of the '
-                              'indexed object do not match',
+                              'indexed object do not match).',
             ('locs', '.iloc'): ('iLocation based boolean indexing on an '
                                 'integer type is not available'),
         }

pandas/tests/indexing/test_loc.py

@@ -194,7 +194,17 @@ def test_loc_getitem_bool(self):
                           typs=['ints', 'uints', 'labels',
                                 'mixed', 'ts', 'floats'])
         self.check_result('bool', 'loc', b, 'ix', b, typs=['empty'],
-                          fails=KeyError)
+                          fails=IndexError)
+
+    @pytest.mark.parametrize('index', [[True, False],
+                                       [True, False, True, False]])
+    def test_loc_getitem_bool_diff_len(self, index):
+        # GH26658
+        s = Series([1, 2, 3])
+        with pytest.raises(IndexError,
+                           match=('Item wrong length {} instead of {}.'.format(
+                               len(index), len(s)))):
+            _ = s.loc[index]
 
     def test_loc_getitem_int_slice(self):