BUG: Fix incompatible return value type in pandas/core/generic.py (pandas-dev#52897)

Co-authored-by: HappyHorse <[email protected]>

Author: 2 people

doc/source/whatsnew/v2.1.0.rst

@@ -332,10 +332,12 @@ Numeric
 - Bug in :meth:`Series.corr` and :meth:`Series.cov` raising ``AttributeError`` for masked dtypes (:issue:`51422`)
 - Bug in :meth:`Series.mean`, :meth:`DataFrame.mean` with object-dtype values containing strings that can be converted to numbers (e.g. "2") returning incorrect numeric results; these now raise ``TypeError`` (:issue:`36703`, :issue:`44008`)
 - Bug in :meth:`DataFrame.corrwith` raising ``NotImplementedError`` for pyarrow-backed dtypes (:issue:`52314`)
+- Bug in :meth:`DataFrame.size` and :meth:`Series.size` returning 64-bit integer instead of int (:issue:`52897`)
 - Bug in :meth:`Series.corr` and :meth:`Series.cov` raising ``AttributeError`` for masked dtypes (:issue:`51422`)
 - Bug in :meth:`Series.median` and :meth:`DataFrame.median` with object-dtype values containing strings that can be converted to numbers (e.g. "2") returning incorrect numeric results; these now raise ``TypeError`` (:issue:`34671`)
 -
 
+
 Conversion
 ^^^^^^^^^^
 - Bug in :func:`DataFrame.style.to_latex` and :func:`DataFrame.style.to_html` if the DataFrame contains integers with more digits than can be represented by floating point double precision (:issue:`52272`)

pandas/core/generic.py

@@ -657,9 +657,8 @@ def size(self) -> int:
         >>> df.size
         4
         """
-        # error: Incompatible return value type (got "signedinteger[_64Bit]",
-        # expected "int")  [return-value]
-        return np.prod(self.shape)  # type: ignore[return-value]
+
+        return int(np.prod(self.shape))
 
     def set_axis(
         self,

pandas/tests/frame/methods/test_size.py

@@ -0,0 +1,21 @@
+import numpy as np
+import pytest
+
+from pandas import DataFrame
+
+
+@pytest.mark.parametrize(
+    "data, index, expected",
+    [
+        ({"col1": [1], "col2": [3]}, None, 2),
+        ({}, None, 0),
+        ({"col1": [1, np.nan], "col2": [3, 4]}, None, 4),
+        ({"col1": [1, 2], "col2": [3, 4]}, [["a", "b"], [1, 2]], 4),
+        ({"col1": [1, 2, 3, 4], "col2": [3, 4, 5, 6]}, ["x", "y", "a", "b"], 8),
+    ],
+)
+def test_size(data, index, expected):
+    # GH#52897
+    df = DataFrame(data, index=index)
+    assert df.size == expected
+    assert isinstance(df.size, int)

pandas/tests/series/methods/test_size.py

@@ -0,0 +1,22 @@
+import pytest
+
+from pandas import Series
+
+
+@pytest.mark.parametrize(
+    "data, index, expected",
+    [
+        ([1, 2, 3], None, 3),
+        ({"a": 1, "b": 2, "c": 3}, None, 3),
+        ([1, 2, 3], ["x", "y", "z"], 3),
+        ([1, 2, 3, 4, 5], ["x", "y", "z", "w", "n"], 5),
+        ([1, 2, 3], None, 3),
+        ([1, 2, 3], ["x", "y", "z"], 3),
+        ([1, 2, 3, 4], ["x", "y", "z", "w"], 4),
+    ],
+)
+def test_series(data, index, expected):
+    # GH#52897
+    ser = Series(data, index=index)
+    assert ser.size == expected
+    assert isinstance(ser.size, int)