ci: test pi-thon (#3218)

Author: MarcoGorelli

.github/workflows/pytest.yml

@@ -52,13 +52,13 @@ jobs:
           cache-suffix: pytest-windows-${{ matrix.python-version }}
           cache-dependency-glob: "pyproject.toml"
       - name: install-reqs
-        # we are not testing pyspark on Windows here because it is very slow
-        run: uv pip install -e ".[dask, modin, ibis]" --group core-tests --group extra --system
+        # we are not testing pyspark, modin, or dask on Windows here because nobody got time for that
+        run: uv pip install -e ".[ibis]" --group core-tests --group extra --system
       - name: show-deps
         run: uv pip freeze
       - name: Run pytest
         run: |
-          pytest tests --cov=narwhals --cov=tests --runslow --cov-fail-under=95 --constructors=pandas,pandas[nullable],pandas[pyarrow],pyarrow,modin[pyarrow],polars[eager],polars[lazy],dask,duckdb,sqlframe,ibis --durations=30
+          pytest tests --cov=narwhals --cov=tests --runslow --cov-fail-under=95 --constructors=pandas,pandas[nullable],pandas[pyarrow],pyarrow,polars[eager],polars[lazy],duckdb,sqlframe,ibis --durations=30
 
   pytest-full-coverage:
     strategy:
@@ -112,8 +112,73 @@ jobs:
           cache-suffix: pytest-narrower-deps-${{ matrix.python-version }}
           cache-dependency-glob: "pyproject.toml"
       - name: install-reqs
-        run: uv pip install -e ".[pandas, pyarrow]" --group tests --system
+        run: uv pip install -e ".[pandas]" --group tests --system
+      - name: show-deps
+        run: uv pip freeze
+      - name: Run pytest
+        run: pytest tests --runslow --constructors=pandas,pandas[nullable]
+      - name: install-more-reqs
+        run: uv pip install -U pyarrow --system
+      - name: show-deps
+        run: uv pip freeze
+      - name: Run pytest
+        run: pytest tests --runslow --constructors=pandas[pyarrow],pyarrow
+
+  python-314:
+    strategy:
+      matrix:
+        python-version: ["3.14"]
+        os: [ubuntu-latest]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v5
+      - uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: "true"
+          cache-suffix: python-314-${{ matrix.python-version }}
+          cache-dependency-glob: "pyproject.toml"
+      - name: install pyarrow nightly
+        run: |
+          uv pip uninstall pyarrow --system
+          uv pip install -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple pyarrow -U --system
+      - name: install-reqs
+        # Use `--pre` as duckdb stable not compatible with 3.14
+        run: uv pip install -e . --group tests --pre pandas polars duckdb sqlframe  --system
+      - name: show-deps
+        run: uv pip freeze
+      - name: Run pytest
+        run: pytest tests --cov=narwhals --cov=tests --runslow --durations=30 --constructors=pandas,pandas[nullable],pandas[pyarrow],pyarrow,polars[eager],polars[lazy],duckdb,sqlframe --cov-fail-under=50
+
+  python-314t:
+    strategy:
+      matrix:
+        python-version: ["3.14t"]
+        os: [ubuntu-latest]
+    runs-on: ${{ matrix.os }}
+    env:
+        PYTHON_GIL: 0
+    steps:
+      - uses: actions/checkout@v5
+      - uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: "true"
+          cache-suffix: python-314t-${{ matrix.python-version }}
+          cache-dependency-glob: "pyproject.toml"
+      - name: install pyarrow nightly
+        run: |
+          uv pip uninstall pyarrow --system
+          uv pip install -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple pyarrow -U --system
+      - name: install-reqs
+        run: uv pip install -e . --group tests --pre pandas --system
       - name: show-deps
         run: uv pip freeze
       - name: Run pytest
-        run: pytest tests --runslow --constructors=pandas,pandas[nullable],pandas[pyarrow],pyarrow
+        run: pytest tests --cov=narwhals --cov=tests --runslow --durations=30 --constructors=pandas,pandas[nullable],pandas[pyarrow],pyarrow --cov-fail-under=50

pyproject.toml

@@ -246,23 +246,34 @@ filterwarnings = [
   'ignore:.*defaulting to pandas implementation:Warning:modin',
   'ignore:.*implementation has mismatches with pandas:Warning:modin',
   'ignore:.*You are using pyarrow version',
+
+  # https://discuss.python.org/t/types-uniontype-was-merged-with-wrong-class-not-even-a-class/102275/31
+  "ignore:.*'_UnionGenericAlias' is deprecated:DeprecationWarning",
+
   # This warning was temporarily raised by pandas but then reverted.
   'ignore:.*Passing a BlockManager to DataFrame:DeprecationWarning',
+
   # This warning was temporarily raised by Polars but then reverted.
   'ignore:.*The default coalesce behavior of left join will change:DeprecationWarning',
+
   'ignore: unclosed <socket.socket',
   'ignore:.*The distutils package is deprecated and slated for removal in Python 3.12:DeprecationWarning:pyspark',
   'ignore:.*distutils Version classes are deprecated. Use packaging.version instead.*:DeprecationWarning',
   'ignore:.*is_datetime64tz_dtype is deprecated and will be removed in a future version.*:DeprecationWarning:pyspark',
+
   # Warning raised by PyArrow nightly just by importing pandas
   'ignore:.*Python binding for RankQuantileOptions not exposed:RuntimeWarning:pyarrow',
+
   'ignore:.*pandas only supports SQLAlchemy:UserWarning:sqlframe',
   'ignore:.*numpy.core is deprecated and has been renamed to numpy._core.*:DeprecationWarning:sqlframe',
   "ignore:.*__array__ implementation doesn't accept a copy keyword, so passing copy=False failed:DeprecationWarning:modin",
+
   # raised internally by pandas
   "ignore:.*np.find_common_type is deprecated:DeprecationWarning:pandas",
+
   # Warning raised when calling PandasLikeNamespace.from_arrow with old pyarrow
   "ignore:.*is_sparse is deprecated and will be removed in a future version.*:DeprecationWarning:pyarrow",
+
   'ignore:.*invalid value encountered in cast:RuntimeWarning:pandas',
 ]
 xfail_strict = true

tests/conftest.py

@@ -102,6 +102,7 @@ def pandas_nullable_constructor(obj: Data) -> pd.DataFrame:
 
 
 def pandas_pyarrow_constructor(obj: Data) -> pd.DataFrame:
+    pytest.importorskip("pyarrow")
     import pandas as pd
 
     return pd.DataFrame(obj).convert_dtypes(dtype_backend="pyarrow")
@@ -143,6 +144,8 @@ def polars_lazy_constructor(obj: Data) -> pl.LazyFrame:
 
 
 def duckdb_lazy_constructor(obj: Data) -> duckdb.DuckDBPyRelation:
+    pytest.importorskip("duckdb")
+    pytest.importorskip("pyarrow")
     import duckdb
     import polars as pl
 
@@ -165,6 +168,7 @@ def dask_lazy_p2_constructor(obj: Data) -> NativeLazyFrame:  # pragma: no cover
 
 
 def pyarrow_table_constructor(obj: dict[str, Any]) -> pa.Table:
+    pytest.importorskip("pyarrow")
     import pyarrow as pa
 
     return pa.table(obj)
@@ -201,6 +205,8 @@ def _constructor(obj: Data) -> PySparkDataFrame:
 
 
 def sqlframe_pyspark_lazy_constructor(obj: Data) -> SQLFrameDataFrame:  # pragma: no cover
+    pytest.importorskip("sqlframe")
+    pytest.importorskip("duckdb")
     session = sqlframe_session()
     return session.createDataFrame([*zip(*obj.values())], schema=[*obj.keys()])
 
@@ -214,6 +220,8 @@ def _ibis_backend() -> IbisDuckDBBackend:  # pragma: no cover
 
 
 def ibis_lazy_constructor(obj: Data) -> ibis.Table:  # pragma: no cover
+    pytest.importorskip("ibis")
+    pytest.importorskip("polars")
     import polars as pl
 
     ldf = pl.from_dict(obj).lazy()

tests/dtypes_test.py

@@ -7,7 +7,6 @@
 
 import numpy as np
 import pandas as pd
-import pyarrow as pa
 import pytest
 
 import narwhals as nw
@@ -159,6 +158,8 @@ def test_2d_array(constructor: Constructor, request: pytest.FixtureRequest) -> N
     for condition, reason in version_conditions:
         if condition:
             pytest.skip(reason)
+    if "pandas" in str(constructor):
+        pytest.importorskip("pyarrow")
 
     if any(x in str(constructor) for x in ("dask", "cudf", "pyspark")):
         request.applymarker(
@@ -176,6 +177,9 @@ def test_2d_array(constructor: Constructor, request: pytest.FixtureRequest) -> N
 
 
 def test_second_time_unit() -> None:
+    pytest.importorskip("pyarrow")
+    import pyarrow as pa
+
     s: IntoSeries = pd.Series(np.array([np.datetime64("2020-01-01", "s")]))
     result = nw.from_native(s, series_only=True)
     expected_unit: Literal["ns", "us", "ms", "s"] = (
@@ -216,6 +220,8 @@ def test_pandas_inplace_modification_1267() -> None:
 
 
 def test_pandas_fixed_offset_1302() -> None:
+    pytest.importorskip("pyarrow")
+
     result = nw.from_native(
         pd.Series(pd.to_datetime(["2020-01-01T00:00:00.000000000+01:00"])),
         series_only=True,
@@ -398,9 +404,10 @@ def test_huge_int_to_native() -> None:
 def test_cast_decimal_to_native() -> None:
     pytest.importorskip("duckdb")
     pytest.importorskip("polars")
-
+    pytest.importorskip("pyarrow")
     import duckdb
     import polars as pl
+    import pyarrow as pa
 
     data = {"a": [1, 2, 3]}
 

tests/expr_and_series/cast_test.py

@@ -268,8 +268,10 @@ def test_cast_struct(request: pytest.FixtureRequest, constructor: Constructor) -
     if any(backend in str(constructor) for backend in ("dask", "cudf", "sqlframe")):
         request.applymarker(pytest.mark.xfail)
 
-    if "pandas" in str(constructor) and PANDAS_VERSION < (2, 2):
-        pytest.skip()
+    if "pandas" in str(constructor):
+        if PANDAS_VERSION < (2, 2):
+            pytest.skip()
+        pytest.importorskip("pyarrow")
 
     data = {
         "a": [{"movie ": "Cars", "rating": 4.5}, {"movie ": "Toy Story", "rating": 4.9}]
@@ -318,8 +320,10 @@ def test_raise_if_polars_dtype(constructor: Constructor) -> None:
 
 
 def test_cast_time(request: pytest.FixtureRequest, constructor: Constructor) -> None:
-    if "pandas" in str(constructor) and PANDAS_VERSION < (2, 2):
-        pytest.skip()
+    if "pandas" in str(constructor):
+        if PANDAS_VERSION < (2, 2):
+            pytest.skip()
+        pytest.importorskip("pyarrow")
 
     if any(backend in str(constructor) for backend in ("dask", "pyspark", "cudf")):
         request.applymarker(pytest.mark.xfail)
@@ -331,8 +335,10 @@ def test_cast_time(request: pytest.FixtureRequest, constructor: Constructor) ->
 
 
 def test_cast_binary(request: pytest.FixtureRequest, constructor: Constructor) -> None:
-    if "pandas" in str(constructor) and PANDAS_VERSION < (2, 2):
-        pytest.skip()
+    if "pandas" in str(constructor):
+        if PANDAS_VERSION < (2, 2):
+            pytest.skip()
+        pytest.importorskip("pyarrow")
 
     if any(backend in str(constructor) for backend in ("cudf", "dask")):
         request.applymarker(pytest.mark.xfail)
@@ -402,6 +408,7 @@ def test_cast_typing_invalid() -> None:
 
 @pytest.mark.skipif(PANDAS_VERSION < (2,), reason="too old for pyarrow")
 def test_pandas_pyarrow_dtypes() -> None:
+    pytest.importorskip("pyarrow")
     s = nw.from_native(
         pd.Series([123, None]).convert_dtypes(dtype_backend="pyarrow"), series_only=True
     ).cast(nw.String)

tests/expr_and_series/cat/get_categories_test.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import pyarrow as pa
 import pytest
 
 import narwhals as nw
@@ -25,6 +24,9 @@ def test_get_categories(constructor_eager: ConstructorEager) -> None:
 
 
 def test_get_categories_pyarrow() -> None:
+    pytest.importorskip("pyarrow")
+    import pyarrow as pa
+
     # temporary test until we have `cast` in pyarrow - later, fuse
     # this with test above
     table = pa.table(

tests/expr_and_series/concat_str_test.py

@@ -2,12 +2,14 @@
 
 from typing import Callable
 
-import pyarrow as pa
 import pytest
 
 import narwhals as nw
 from tests.utils import POLARS_VERSION, Constructor, assert_equal_data
 
+pytest.importorskip("pyarrow")
+import pyarrow as pa
+
 data = {"a": [1, 2, 3], "b": ["dogs", "cats", None], "c": ["play", "swim", "walk"]}
 
 

tests/expr_and_series/dt/datetime_duration_test.py

@@ -4,8 +4,6 @@
 from typing import Literal
 
 import numpy as np
-import pyarrow as pa
-import pyarrow.compute as pc
 import pytest
 
 import narwhals as nw
@@ -102,6 +100,10 @@ def test_duration_attributes_series(
 def test_pyarrow_units(
     unit: Literal["s", "ms", "us", "ns"], attribute: str, expected: int
 ) -> None:
+    pytest.importorskip("pyarrow")
+    import pyarrow as pa
+    import pyarrow.compute as pc
+
     data = [None, timedelta(minutes=1, seconds=10)]
     arr = pc.cast(pa.array(data), pa.duration(unit))
     df = nw.from_native(pa.table({"a": arr}), eager_only=True)

tests/expr_and_series/dt/offset_by_test.py

@@ -250,6 +250,7 @@ def test_offset_by_invalid_interval(constructor: Constructor) -> None:
 @pytest.mark.skipif(PANDAS_VERSION < (2, 2), reason="too old for pyarrow date type")
 def test_offset_by_date_pandas() -> None:
     pytest.importorskip("pandas")
+    pytest.importorskip("pyarrow")
     import pandas as pd
 
     df = nw.from_native(pd.DataFrame({"a": [date(2020, 1, 1)]}, dtype="date32[pyarrow]"))

tests/expr_and_series/dt/ordinal_day_test.py

@@ -17,6 +17,7 @@
 @pytest.mark.skipif(PANDAS_VERSION < (2, 0, 0), reason="pyarrow dtype not available")
 @pytest.mark.slow
 def test_ordinal_day(dates: datetime) -> None:
+    pytest.importorskip("pyarrow")
     result_pd = nw.from_native(pd.Series([dates]), series_only=True).dt.ordinal_day()[0]
     result_pdms = nw.from_native(
         pd.Series([dates]).dt.as_unit("ms"), series_only=True