Backport PR #59046: TST: Fix some test builds for numpy 2.0 (#59086)

Author: mroeschke

ci/deps/actions-311-pyarrownightly.yaml

@@ -18,7 +18,7 @@ dependencies:
 
   # required dependencies
   - python-dateutil
-  - numpy
+  - numpy<2
   - pytz
   - pip
 

pandas/compat/__init__.py

@@ -31,6 +31,7 @@
     pa_version_under14p0,
     pa_version_under14p1,
     pa_version_under16p0,
+    pa_version_under17p0,
 )
 
 if TYPE_CHECKING:
@@ -188,6 +189,7 @@ def get_bz2_file() -> type[pandas.compat.compressors.BZ2File]:
     "pa_version_under14p0",
     "pa_version_under14p1",
     "pa_version_under16p0",
+    "pa_version_under17p0",
     "IS64",
     "ISMUSL",
     "PY310",

pandas/compat/numpy/__init__.py

@@ -12,7 +12,7 @@
 np_version_gte1p24 = _nlv >= Version("1.24")
 np_version_gte1p24p3 = _nlv >= Version("1.24.3")
 np_version_gte1p25 = _nlv >= Version("1.25")
-np_version_gt2 = _nlv >= Version("2.0.0.dev0")
+np_version_gt2 = _nlv >= Version("2.0.0")
 is_numpy_dev = _nlv.dev is not None
 _min_numpy_ver = "1.22.4"
 

pandas/compat/pyarrow.py

@@ -16,6 +16,7 @@
     pa_version_under14p1 = _palv < Version("14.0.1")
     pa_version_under15p0 = _palv < Version("15.0.0")
     pa_version_under16p0 = _palv < Version("16.0.0")
+    pa_version_under17p0 = _palv < Version("17.0.0")
 except ImportError:
     pa_version_under10p1 = True
     pa_version_under11p0 = True
@@ -25,3 +26,4 @@
     pa_version_under14p1 = True
     pa_version_under15p0 = True
     pa_version_under16p0 = True
+    pa_version_under17p0 = True

pandas/core/dtypes/cast.py

@@ -39,7 +39,6 @@
     is_supported_dtype,
 )
 from pandas._libs.tslibs.timedeltas import array_to_timedelta64
-from pandas.compat.numpy import np_version_gt2
 from pandas.errors import (
     IntCastingNaNError,
     LossySetitemError,
@@ -1647,13 +1646,11 @@ def maybe_cast_to_integer_array(arr: list | np.ndarray, dtype: np.dtype) -> np.n
             with warnings.catch_warnings():
                 # We already disallow dtype=uint w/ negative numbers
                 # (test_constructor_coercion_signed_to_unsigned) so safe to ignore.
-                if not np_version_gt2:
-                    warnings.filterwarnings(
-                        "ignore",
-                        "NumPy will stop allowing conversion of "
-                        "out-of-bound Python int",
-                        DeprecationWarning,
-                    )
+                warnings.filterwarnings(
+                    "ignore",
+                    "NumPy will stop allowing conversion of out-of-bound Python int",
+                    DeprecationWarning,
+                )
                 casted = np.asarray(arr, dtype=dtype)
         else:
             with warnings.catch_warnings():

pandas/tests/indexes/datetimelike_/test_indexing.py

@@ -19,7 +19,7 @@
 @pytest.mark.parametrize("ldtype", dtlike_dtypes)
 @pytest.mark.parametrize("rdtype", dtlike_dtypes)
 def test_get_indexer_non_unique_wrong_dtype(ldtype, rdtype):
-    vals = np.tile(3600 * 10**9 * np.arange(3), 2)
+    vals = np.tile(3600 * 10**9 * np.arange(3, dtype=np.int64), 2)
 
     def construct(dtype):
         if dtype is dtlike_dtypes[-1]:

pandas/tests/io/test_parquet.py

@@ -16,6 +16,7 @@
     pa_version_under11p0,
     pa_version_under13p0,
     pa_version_under15p0,
+    pa_version_under17p0,
 )
 
 import pandas as pd
@@ -1063,6 +1064,9 @@ def test_read_dtype_backend_pyarrow_config_index(self, pa):
             expected=expected,
         )
 
+    @pytest.mark.xfail(
+        pa_version_under17p0, reason="pa.pandas_compat passes 'datetime64' to .astype"
+    )
     def test_columns_dtypes_not_invalid(self, pa):
         df = pd.DataFrame({"string": list("abc"), "int": list(range(1, 4))})
 

pandas/tests/scalar/timedelta/test_arithmetic.py

@@ -418,7 +418,7 @@ def test_td_mul_numeric_ndarray(self):
 
     def test_td_mul_numeric_ndarray_0d(self):
         td = Timedelta("1 day")
-        other = np.array(2)
+        other = np.array(2, dtype=np.int64)
         assert other.ndim == 0
         expected = Timedelta("2 days")
 

pandas/tests/tools/test_to_datetime.py

@@ -3407,7 +3407,18 @@ def test_invalid_origin(self, unit):
         with pytest.raises(ValueError, match=msg):
             to_datetime("2005-01-01", origin="1960-01-01", unit=unit)
 
-    def test_epoch(self, units, epochs, epoch_1960, units_from_epochs):
+    @pytest.mark.parametrize(
+        "epochs",
+        [
+            Timestamp(1960, 1, 1),
+            datetime(1960, 1, 1),
+            "1960-01-01",
+            np.datetime64("1960-01-01"),
+        ],
+    )
+    def test_epoch(self, units, epochs):
+        epoch_1960 = Timestamp(1960, 1, 1)
+        units_from_epochs = np.arange(5, dtype=np.int64)
         expected = Series(
             [pd.Timedelta(x, unit=units) + epoch_1960 for x in units_from_epochs]
         )