Maintain consistent hash values for equal objects

rapidsai · Jan 6, 2021 · 6ccd860 · 6ccd860
1 parent bdc5c21
commit 6ccd860
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 4 deletions.
diff --git a/python/cudf/cudf/core/column/lists.py b/python/cudf/cudf/core/column/lists.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2020, NVIDIA CORPORATION.
+# Copyright (c) 2020-2021, NVIDIA CORPORATION.
 
 import pickle
 

diff --git a/python/cudf/cudf/core/dtypes.py b/python/cudf/cudf/core/dtypes.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2020, NVIDIA CORPORATION.
+# Copyright (c) 2020-2021, NVIDIA CORPORATION.
 
 import decimal
 import pickle
@@ -166,7 +166,7 @@ def __repr__(self):
             return f"ListDtype({self.element_type})"
 
     def __hash__(self):
-        return id(self)
+        return hash(self._typ)
 
 
 class StructDtype(ExtensionDtype):

diff --git a/python/cudf/cudf/tests/test_list.py b/python/cudf/cudf/tests/test_list.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2020, NVIDIA CORPORATION.
+# Copyright (c) 2020-2021, NVIDIA CORPORATION.
 
 import pandas as pd
 import pyarrow as pa
@@ -78,3 +78,14 @@ def test_list_to_pandas_nullable_true():
     expected = pd.DataFrame({"a": pd.Series([[1, 2, 3]])})
 
     assert_eq(actual, expected)
+
+
+def test_listdtype_hash():
+    a = cudf.core.dtypes.ListDtype("int64")
+    b = cudf.core.dtypes.ListDtype("int64")
+
+    assert hash(a) == hash(b)
+
+    c = cudf.core.dtypes.ListDtype("int32")
+
+    assert hash(a) != hash(c)