BLD: Add pyproject.toml to wheels (#50330)

* BLD: Add pyproject.toml to wheels

* Make strict-data-files opt out

* Fixed backwards condition

* Actually fix

* Maybe fix all

* Adjust options for other wheel builds

* Error on unknown mark warning

* Update pyproject.toml

* Apply suggestions from code review

Co-authored-by: Matthew Roeschke <[email protected]>

* revert #48924

* update

* fix syntax

* fix warnings

* Update test_nlargest.py

* Update pyproject.toml

---------

Co-authored-by: Matthew Roeschke <[email protected]>

Author: lithomas1

.github/workflows/wheels.yml

@@ -173,8 +173,8 @@ jobs:
           pip install hypothesis>=6.34.2 pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17
           cd .. # Not a good idea to test within the src tree
           python -c "import pandas; print(pandas.__version__);
-          pandas.test(extra_args=['-m not clipboard and not single_cpu and not slow and not network and not db', '-n 2']);
-          pandas.test(extra_args=['-m not clipboard and single_cpu and not slow and not network and not db'])"
+          pandas.test(extra_args=['-m not clipboard and not single_cpu and not slow and not network and not db', '-n 2', '--no-strict-data-files']);
+          pandas.test(extra_args=['-m not clipboard and single_cpu and not slow and not network and not db', '--no-strict-data-files'])"
       - uses: actions/upload-artifact@v3
         with:
           name: sdist

ci/test_wheels.py

@@ -41,10 +41,12 @@
     multi_args = [
         "-m not clipboard and not single_cpu and not slow and not network and not db",
         "-n 2",
+        "--no-strict-data-files",
     ]
     pd.test(extra_args=multi_args)
     pd.test(
         extra_args=[
             "-m not clipboard and single_cpu and not slow and not network and not db",
+            "--no-strict-data-files",
         ]
     )

ci/test_wheels_windows.bat

@@ -1,6 +1,6 @@
 set test_command=import pandas as pd; print(pd.__version__); ^
-pd.test(extra_args=['-m not clipboard and not single_cpu and not slow and not network and not db', '-n 2']); ^
-pd.test(extra_args=['-m not clipboard and single_cpu and not slow and not network and not db'])
+pd.test(extra_args=['-m not clipboard and not single_cpu and not slow and not network and not db', '--no-strict-data-files', '-n=2']); ^
+pd.test(extra_args=['-m not clipboard and single_cpu and not slow and not network and not db', '--no-strict-data-files'])
 
 python --version
 pip install pytz six numpy python-dateutil tzdata>=2022.1

pandas/conftest.py

@@ -103,9 +103,9 @@
 
 def pytest_addoption(parser) -> None:
     parser.addoption(
-        "--strict-data-files",
-        action="store_true",
-        help="Fail if a test is skipped for missing data file.",
+        "--no-strict-data-files",
+        action="store_false",
+        help="Don't fail if a test is skipped for missing data file.",
     )
 
 
@@ -1112,9 +1112,9 @@ def all_numeric_accumulations(request):
 @pytest.fixture
 def strict_data_files(pytestconfig):
     """
-    Returns the configuration for the test setting `--strict-data-files`.
+    Returns the configuration for the test setting `--no-strict-data-files`.
     """
-    return pytestconfig.getoption("--strict-data-files")
+    return pytestconfig.getoption("--no-strict-data-files")
 
 
 @pytest.fixture
@@ -1134,7 +1134,7 @@ def datapath(strict_data_files: str) -> Callable[..., str]:
     Raises
     ------
     ValueError
-        If the path doesn't exist and the --strict-data-files option is set.
+        If the path doesn't exist and the --no-strict-data-files option is not set.
     """
     BASE_PATH = os.path.join(os.path.dirname(__file__), "tests")
 
@@ -1143,7 +1143,7 @@ def deco(*args):
         if not os.path.exists(path):
             if strict_data_files:
                 raise ValueError(
-                    f"Could not find file {path} and --strict-data-files is set."
+                    f"Could not find file {path} and --no-strict-data-files is not set."
                 )
             pytest.skip(f"Could not find {path}.")
         return path

pandas/tests/frame/indexing/test_setitem.py

@@ -61,7 +61,8 @@ class mystring(str):
         "dtype", ["int32", "int64", "uint32", "uint64", "float32", "float64"]
     )
     def test_setitem_dtype(self, dtype, float_frame):
-        arr = np.random.randn(len(float_frame))
+        # Use randint since casting negative floats to uints is undefined
+        arr = np.random.randint(1, 10, len(float_frame))
 
         float_frame[dtype] = np.array(arr, dtype=dtype)
         assert float_frame[dtype].dtype.name == dtype

pandas/tests/series/methods/test_nlargest.py

@@ -217,7 +217,12 @@ def test_nlargest_boolean(self, data, expected):
     def test_nlargest_nullable(self, any_numeric_ea_dtype):
         # GH#42816
         dtype = any_numeric_ea_dtype
-        arr = np.random.randn(10).astype(dtype.lower(), copy=False)
+        if dtype.startswith("UInt"):
+            # Can't cast from negative float to uint on some platforms
+            arr = np.random.randint(1, 10, 10)
+        else:
+            arr = np.random.randn(10)
+        arr = arr.astype(dtype.lower(), copy=False)
 
         ser = Series(arr.copy(), dtype=dtype)
         ser[1] = pd.NA

pandas/tests/test_common.py

@@ -1,5 +1,6 @@
 import collections
 from functools import partial
+import os
 import string
 
 import numpy as np
@@ -174,6 +175,12 @@ def test_version_tag():
         )
 
 
+def test_pyproject_present():
+    # Check pyproject.toml is present(relevant for wheels)
+    pyproject_loc = os.path.join(os.path.dirname(__file__), "../../pyproject.toml")
+    assert os.path.exists(pyproject_loc)
+
+
 @pytest.mark.parametrize(
     "obj", [(obj,) for obj in pd.__dict__.values() if callable(obj)]
 )

pyproject.toml

@@ -125,6 +125,9 @@ include-package-data = true
 include = ["pandas", "pandas.*"]
 namespaces = false
 
+[tool.setuptools.package-data]
+pandas = ["../pyproject.toml"]
+
 [tool.setuptools.exclude-package-data]
 "*" = ["*.c", "*.h"]
 
@@ -406,7 +409,7 @@ disable = [
 [tool.pytest.ini_options]
 # sync minversion with pyproject.toml & install.rst
 minversion = "7.0"
-addopts = "--strict-data-files --strict-markers --strict-config --capture=no --durations=30 --junitxml=test-data.xml"
+addopts = "--strict-markers --strict-config --capture=no --durations=30 --junitxml=test-data.xml"
 empty_parameter_set_mark = "fail_at_collect"
 xfail_strict = true
 testpaths = "pandas"
@@ -416,6 +419,7 @@ doctest_optionflags = [
   "ELLIPSIS",
 ]
 filterwarnings = [
+  "error::_pytest.warning_types.PytestUnknownMarkWarning",
   "error:::pandas",
   "error::ResourceWarning",
   "error::pytest.PytestUnraisableExceptionWarning",