BUG: item_cache invalidation

doc/source/whatsnew/v1.3.0.rst

@@ -104,7 +104,7 @@ Timezones
 
 Numeric
 ^^^^^^^
-
+- Bug in :meth:`DataFrame.quantile`, :meth:`DataFrame.sort_values` causing incorrect subsequent indexing behavior (:issue:`38351`)
 -
 -
 

pandas/core/internals/managers.py

@@ -442,7 +442,6 @@ def apply(
     def quantile(
         self,
         axis: int = 0,
-        consolidate: bool = True,
         transposed: bool = False,
         interpolation="linear",
         qs=None,
@@ -472,9 +471,6 @@ def quantile(
         #  simplify some of the code here and in the blocks
         assert self.ndim >= 2
 
-        if consolidate:
-            self._consolidate_inplace()
-
         def get_axe(block, qs, axes):
             # Because Series dispatches to DataFrame, we will always have
             #  block.ndim == 2
@@ -1455,7 +1451,6 @@ def take(self, indexer, axis: int = 1, verify: bool = True, convert: bool = True
         """
         Take items along any axis.
         """
-        self._consolidate_inplace()
         indexer = (
             np.arange(indexer.start, indexer.stop, indexer.step, dtype="int64")
             if isinstance(indexer, slice)
@@ -1472,7 +1467,11 @@ def take(self, indexer, axis: int = 1, verify: bool = True, convert: bool = True
 
         new_labels = self.axes[axis].take(indexer)
         return self.reindex_indexer(
-            new_axis=new_labels, indexer=indexer, axis=axis, allow_dups=True
+            new_axis=new_labels,
+            indexer=indexer,
+            axis=axis,
+            allow_dups=True,
+            consolidate=False,
         )
 
     def equals(self, other: object) -> bool:

pandas/tests/frame/methods/test_quantile.py

@@ -517,3 +517,15 @@ def test_quantile_empty_no_columns(self):
         expected = DataFrame([], index=[0.5], columns=[])
         expected.columns.name = "captain tightpants"
         tm.assert_frame_equal(result, expected)
+
+    def test_quantile_item_cache(self):
+        # previous behavior incorrect retained an invalid _item_cache entry
+        df = DataFrame(np.random.randn(4, 3), columns=["A", "B", "C"])
+        df["D"] = df["A"] * 2
+        ser = df["A"]
+        assert len(df._mgr.blocks) == 2
+
+        df.quantile(numeric_only=False)
+        ser.values[0] = 99
+
+        assert df.iloc[0, 0] == df["A"][0]

pandas/tests/frame/methods/test_sort_values.py

@@ -544,6 +544,18 @@ def test_sort_values_nat_na_position_default(self):
         result = expected.sort_values(["A", "date"])
         tm.assert_frame_equal(result, expected)
 
+    def test_sort_values_item_cache(self):
+        # previous behavior incorrect retained an invalid _item_cache entry
+        df = DataFrame(np.random.randn(4, 3), columns=["A", "B", "C"])
+        df["D"] = df["A"] * 2
+        ser = df["A"]
+        assert len(df._mgr.blocks) == 2
+
+        df.sort_values(by="A")
+        ser.values[0] = 99
+
+        assert df.iloc[0, 0] == df["A"][0]
+
 
 class TestDataFrameSortKey:  # test key sorting (issue 27237)
     def test_sort_values_inplace_key(self, sort_by_key):