From eed8b3322f3a1476f873ae9dbe207eda22702fc0 Mon Sep 17 00:00:00 2001
From: parthiban <parthimyself90@gmail.com>
Date: Tue, 23 Jan 2024 15:23:08 +0530
Subject: [PATCH 1/4] BUG: Fix inconsistency when constructing a Series with
 large integers in a int64 masked array

- Refered code from PR#50757 similar issue for non masked ints
---
 pandas/core/construction.py | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/pandas/core/construction.py b/pandas/core/construction.py
index e6d99ab773db9..06f7f02db679a 100644
--- a/pandas/core/construction.py
+++ b/pandas/core/construction.py
@@ -48,6 +48,8 @@
     maybe_promote,
 )
 from pandas.core.dtypes.common import (
+    is_float_dtype,
+    is_integer_dtype,
     is_list_like,
     is_object_dtype,
     is_string_dtype,
@@ -502,11 +504,22 @@ def sanitize_masked_array(data: ma.MaskedArray) -> np.ndarray:
     Convert numpy MaskedArray to ensure mask is softened.
     """
     mask = ma.getmaskarray(data)
+    original = data
+    original_dtype = data.dtype
     if mask.any():
         dtype, fill_value = maybe_promote(data.dtype, np.nan)
         dtype = cast(np.dtype, dtype)
         data = ma.asarray(data.astype(dtype, copy=True))
         data.soften_mask()  # set hardmask False if it was True
+        if not mask.all():
+            idx = np.unravel_index(np.nanargmax(data, axis=None), data.shape)
+            if not mask[idx] and int(data[idx]) != original[idx]:
+                if (
+                    is_integer_dtype(original_dtype)
+                    and is_float_dtype(data.dtype)
+                    and len(data) > 0
+                ):
+                    data = ma.asarray(original, "object")
         data[mask] = fill_value
     else:
         data = data.copy()

From 0c6d59a00983f9fb37646551f08f1320d22fd897 Mon Sep 17 00:00:00 2001
From: parthiban <parthimyself90@gmail.com>
Date: Tue, 23 Jan 2024 15:24:02 +0530
Subject: [PATCH 2/4] TST: Add test cases

---
 pandas/tests/series/test_constructors.py | 30 ++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/pandas/tests/series/test_constructors.py b/pandas/tests/series/test_constructors.py
index 68737e86f0c6a..11628d76536f4 100644
--- a/pandas/tests/series/test_constructors.py
+++ b/pandas/tests/series/test_constructors.py
@@ -2155,6 +2155,36 @@ def test_inference_on_pandas_objects(self):
             result = Series(idx)
         assert result.dtype != np.object_
 
+    def test_series_constructor_maskedarray_int_overflow(self):
+        # GH#56566
+        mx = ma.masked_array(
+            [
+                4873214862074861312,
+                4875446630161458944,
+                4824652147895424384,
+                0,
+                3526420114272476800,
+            ],
+            mask=[0, 0, 0, 1, 0],
+        )
+        result = Series(mx, dtype="Int64")
+        expected = Series(
+            IntegerArray(
+                np.array(
+                    [
+                        4873214862074861312,
+                        4875446630161458944,
+                        4824652147895424384,
+                        0,
+                        3526420114272476800,
+                    ],
+                    dtype="int64",
+                ),
+                np.array([0, 0, 0, 1, 0], dtype=np.bool_),
+            )
+        )
+        tm.assert_series_equal(result, expected)
+
 
 class TestSeriesConstructorIndexCoercion:
     def test_series_constructor_datetimelike_index_coercion(self):

From 260fc18f9ab8c97c6e8794f784071d4205a58b6e Mon Sep 17 00:00:00 2001
From: parthiban <parthimyself90@gmail.com>
Date: Tue, 9 Apr 2024 22:15:55 +0530
Subject: [PATCH 3/4] TST: Change expected

---
 pandas/tests/series/test_constructors.py | 25 ++++++++++--------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/pandas/tests/series/test_constructors.py b/pandas/tests/series/test_constructors.py
index 11628d76536f4..58fdfd30dde90 100644
--- a/pandas/tests/series/test_constructors.py
+++ b/pandas/tests/series/test_constructors.py
@@ -2168,22 +2168,17 @@ def test_series_constructor_maskedarray_int_overflow(self):
             mask=[0, 0, 0, 1, 0],
         )
         result = Series(mx, dtype="Int64")
-        expected = Series(
-            IntegerArray(
-                np.array(
-                    [
-                        4873214862074861312,
-                        4875446630161458944,
-                        4824652147895424384,
-                        0,
-                        3526420114272476800,
-                    ],
-                    dtype="int64",
-                ),
-                np.array([0, 0, 0, 1, 0], dtype=np.bool_),
-            )
+        expected = np.array(
+            [
+                4873214862074861312,
+                4875446630161458944,
+                4824652147895424384,
+                3526420114272476800,
+            ],
+            dtype="int64",
         )
-        tm.assert_series_equal(result, expected)
+        result = np.array(result.dropna(ignore_index=True).values)
+        assert np.all(expected == result)
 
 
 class TestSeriesConstructorIndexCoercion:

From ab025e1f1e2e56bfc4c0984a56ed68b7534fbad1 Mon Sep 17 00:00:00 2001
From: parthiban <parthimyself90@gmail.com>
Date: Tue, 9 Apr 2024 22:20:45 +0530
Subject: [PATCH 4/4] BUG: Remove len check

---
 pandas/core/construction.py | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/pandas/core/construction.py b/pandas/core/construction.py
index 06f7f02db679a..09240ffc831a6 100644
--- a/pandas/core/construction.py
+++ b/pandas/core/construction.py
@@ -514,11 +514,7 @@ def sanitize_masked_array(data: ma.MaskedArray) -> np.ndarray:
         if not mask.all():
             idx = np.unravel_index(np.nanargmax(data, axis=None), data.shape)
             if not mask[idx] and int(data[idx]) != original[idx]:
-                if (
-                    is_integer_dtype(original_dtype)
-                    and is_float_dtype(data.dtype)
-                    and len(data) > 0
-                ):
+                if is_integer_dtype(original_dtype) and is_float_dtype(data.dtype):
                     data = ma.asarray(original, "object")
         data[mask] = fill_value
     else: