BUG: Fix from_records() column reorder issue, if columns!=None use passed param (#59717)

doc/source/whatsnew/v3.0.0.rst

@@ -619,6 +619,7 @@ I/O
 ^^^
 - Bug in :class:`DataFrame` and :class:`Series` ``repr`` of :py:class:`collections.abc.Mapping`` elements. (:issue:`57915`)
 - Bug in :meth:`.DataFrame.to_json` when ``"index"`` was a value in the :attr:`DataFrame.column` and :attr:`Index.name` was ``None``. Now, this will fail with a ``ValueError`` (:issue:`58925`)
+- Bug in :meth:`DataFrame.from_records` where ``columns`` parameter with numpy structured array was not reordering and filtering out the columns (:issue:`59717`)
 - Bug in :meth:`DataFrame.to_dict` raises unnecessary ``UserWarning`` when columns are not unique and ``orient='tight'``. (:issue:`58281`)
 - Bug in :meth:`DataFrame.to_excel` when writing empty :class:`DataFrame` with :class:`MultiIndex` on both axes (:issue:`57696`)
 - Bug in :meth:`DataFrame.to_stata` when writing :class:`DataFrame` and ``byteorder=`big```. (:issue:`58969`)

pandas/core/internals/construction.py

@@ -750,7 +750,8 @@ def to_arrays(
 
     elif isinstance(data, np.ndarray) and data.dtype.names is not None:
         # e.g. recarray
-        columns = Index(list(data.dtype.names))
+        if columns is None:
+            columns = Index(data.dtype.names)
         arrays = [data[k] for k in columns]
         return arrays, columns
 

pandas/tests/frame/constructors/test_from_records.py

@@ -469,3 +469,26 @@ def test_from_records_empty2(self):
 
         alt = DataFrame(arr)
         tm.assert_frame_equal(alt, expected)
+
+    def test_from_records_structured_array(self):
+        # GH 59717
+        data = np.array(
+            [
+                ("John", 25, "New York", 50000),
+                ("Jane", 30, "San Francisco", 75000),
+                ("Bob", 35, "Chicago", 65000),
+                ("Alice", 28, "Los Angeles", 60000),
+            ],
+            dtype=[("name", "U10"), ("age", "i4"), ("city", "U15"), ("salary", "i4")],
+        )
+
+        actual_result = DataFrame.from_records(data, columns=["name", "salary", "city"])
+
+        modified_data = {
+            "name": ["John", "Jane", "Bob", "Alice"],
+            "salary": np.array([50000, 75000, 65000, 60000], dtype="int32"),
+            "city": ["New York", "San Francisco", "Chicago", "Los Angeles"],
+        }
+        expected_result = DataFrame(modified_data)
+
+        tm.assert_frame_equal(actual_result, expected_result)

pandas/tests/frame/methods/test_to_arrays.py

@@ -0,0 +1,34 @@
+import numpy as np
+from numpy import array
+
+import pandas._testing as tm
+from pandas.core.indexes.api import ensure_index
+from pandas.core.internals.construction import to_arrays
+
+
+def test_to_arrays():
+    # GH 59717
+    data = np.array(
+        [
+            ("John", 25, "New York", 50000),
+            ("Jane", 30, "San Francisco", 75000),
+            ("Bob", 35, "Chicago", 65000),
+            ("Alice", 28, "Los Angeles", 60000),
+        ],
+        dtype=[("name", "U10"), ("age", "i4"), ("city", "U15"), ("salary", "i4")],
+    )
+
+    columns = ["name", "salary", "city"]
+    indexed_columns = ensure_index(columns)
+
+    actual_arrays, actual_cols = to_arrays(data, indexed_columns)
+    expected_arrays = [
+        array(["John", "Jane", "Bob", "Alice"], dtype="<U10"),
+        array([50000, 75000, 65000, 60000], dtype="int32"),
+        array(["New York", "San Francisco", "Chicago", "Los Angeles"], dtype="<U15"),
+    ]
+
+    for actual, expected in zip(actual_arrays, expected_arrays):
+        tm.assert_numpy_array_equal(actual, expected)
+
+    assert actual_cols.equals(indexed_columns)