BLD, TST: Build and test Pyodide wheels for pandas in CI (pandas-de…

…v#57896)

* Create initial Pyodide workflow

* Do not import pandas folder from the repo

* Install hypothesis for testing

* Add pytest decorator to skip tests on WASM

* Skip `time.tzset()` tests on WASM platforms

* Skip file system access tests on WASM

* Skip two more tzset test failures

* Skip two more FS failures on WASM

* Resolve last two tzset failures on WASM

* Add a `WASM` constant for Emscripten platform checks

* Fix floating point imprecision with `np.timedelta64`

* Mark tz OverflowError as xfail on WASM

* Try to fix OverflowError with date ranges

* Move job to unit tests workflow, withdraw env vars

* Fix up a few style errors, use WASM variable

* Bump Pyodide to `0.25.1`

See pyodide/pyodide#4654 for
more discussion. This commit resolves a build error
coming from the `pyodide build` command which
broke due to a new `build` release by PyPA.

* Use shorter job name

* Skip test where warning is not raised properly

* Don't run `test_date_time` loc check on WASM

* Don't run additional loc checks in `test_sas7bdat`

* Disable WASM OverflowError

* Skip tests requiring fp exception support

* xfail tests that require stricter tolerances

* xfail test where `OverflowError`s are received

* Remove upper-pin from `pydantic`

* Better skip messages via `pytest.skipif` decorator

* Import `WASM` var via public API where possible

* Unpin `pytest` for Pyodide job

* Add reason attr when using boolean to skip test

* Don't xfail, skip tests that bring `OverflowError`s

* Skip timedelta test that runs well only on 64-bit

* Skip tests that use `np.timedelta64`

---------

Co-authored-by: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>

.github/workflows/unit-tests.yml

@@ -314,7 +314,7 @@ jobs:
     timeout-minutes: 90
 
     concurrency:
-      #https://github.community/t/concurrecy-not-work-for-push/183068/7
+      # https://github.community/t/concurrecy-not-work-for-push/183068/7
       group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-${{ matrix.pytest_target }}-dev
       cancel-in-progress: true
 
@@ -346,3 +346,62 @@ jobs:
 
       - name: Run Tests
         uses: ./.github/actions/run-tests
+
+  emscripten:
+    # Note: the Python version, Emscripten toolchain version are determined
+    # by the Pyodide version. The appropriate versions can be found in the
+    # Pyodide repodata.json "info" field, or in the Makefile.envs file:
+    # https://github.com/pyodide/pyodide/blob/stable/Makefile.envs#L2
+    # The Node.js version can be determined via Pyodide:
+    # https://pyodide.org/en/stable/usage/index.html#node-js
+    name: Pyodide build
+    runs-on: ubuntu-22.04
+    concurrency:
+      # https://github.community/t/concurrecy-not-work-for-push/183068/7
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-wasm
+      cancel-in-progress: true
+    steps:
+      - name: Checkout pandas Repo
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python for Pyodide
+        id: setup-python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11.3'
+
+      - name: Set up Emscripten toolchain
+        uses: mymindstorm/setup-emsdk@v14
+        with:
+          version: '3.1.46'
+          actions-cache-folder: emsdk-cache
+
+      - name: Install pyodide-build
+        run: pip install "pyodide-build==0.25.1"
+
+      - name: Build pandas for Pyodide
+        run: |
+          pyodide build
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '18'
+
+      - name: Set up Pyodide virtual environment
+        run: |
+          pyodide venv .venv-pyodide
+          source .venv-pyodide/bin/activate
+          pip install dist/*.whl
+
+      - name: Test pandas for Pyodide
+        env:
+          PANDAS_CI: 1
+        run: |
+          source .venv-pyodide/bin/activate
+          pip install pytest hypothesis
+          # do not import pandas from the checked out repo
+          cd ..
+          python -c 'import pandas as pd; pd.test(extra_args=["-m not clipboard and not single_cpu and not slow and not network and not db"])'

pandas/compat/__init__.py

@@ -22,6 +22,7 @@
     PY311,
     PY312,
     PYPY,
+    WASM,
 )
 import pandas.compat.compressors
 from pandas.compat.numpy import is_numpy_dev
@@ -207,4 +208,5 @@ def get_bz2_file() -> type[pandas.compat.compressors.BZ2File]:
     "PY311",
     "PY312",
     "PYPY",
+    "WASM",
 ]

pandas/compat/_constants.py

@@ -17,6 +17,7 @@
 PY311 = sys.version_info >= (3, 11)
 PY312 = sys.version_info >= (3, 12)
 PYPY = platform.python_implementation() == "PyPy"
+WASM = (sys.platform == "emscripten") or (platform.machine() in ["wasm32", "wasm64"])
 ISMUSL = "musl" in (sysconfig.get_config_var("HOST_GNU_TYPE") or "")
 REF_COUNT = 2 if PY311 else 3
 
@@ -27,4 +28,5 @@
     "PY311",
     "PY312",
     "PYPY",
+    "WASM",
 ]

pandas/tests/apply/test_str.py

@@ -4,6 +4,8 @@
 import numpy as np
 import pytest
 
+from pandas.compat import WASM
+
 from pandas.core.dtypes.common import is_number
 
 from pandas import (
@@ -54,6 +56,7 @@ def test_apply_np_reducer(op, how):
     tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.skipif(WASM, reason="No fp exception support in wasm")
 @pytest.mark.parametrize(
     "op", ["abs", "ceil", "cos", "cumsum", "exp", "log", "sqrt", "square"]
 )

pandas/tests/arithmetic/test_timedelta64.py

@@ -8,6 +8,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import WASM
 from pandas.errors import OutOfBoundsDatetime
 
 import pandas as pd
@@ -1741,6 +1742,7 @@ def test_td64_div_object_mixed_result(self, box_with_array):
     # ------------------------------------------------------------------
     # __floordiv__, __rfloordiv__
 
+    @pytest.mark.skipif(WASM, reason="no fp exception support in wasm")
     def test_td64arr_floordiv_td64arr_with_nat(self, box_with_array):
         # GH#35529
         box = box_with_array

pandas/tests/indexes/datetimes/methods/test_normalize.py

@@ -2,6 +2,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import WASM
 import pandas.util._test_decorators as td
 
 from pandas import (
@@ -70,6 +71,9 @@ def test_normalize_tz(self):
         assert not rng.is_normalized
 
     @td.skip_if_windows
+    @pytest.mark.skipif(
+        WASM, reason="tzset is available only on Unix-like systems, not WASM"
+    )
     @pytest.mark.parametrize(
         "timezone",
         [

pandas/tests/indexes/datetimes/methods/test_resolution.py

@@ -1,7 +1,10 @@
 from dateutil.tz import tzlocal
 import pytest
 
-from pandas.compat import IS64
+from pandas.compat import (
+    IS64,
+    WASM,
+)
 
 from pandas import date_range
 
@@ -20,9 +23,10 @@
         ("us", "microsecond"),
     ],
 )
+@pytest.mark.skipif(WASM, reason="OverflowError received on WASM")
 def test_dti_resolution(request, tz_naive_fixture, freq, expected):
     tz = tz_naive_fixture
-    if freq == "YE" and not IS64 and isinstance(tz, tzlocal):
+    if freq == "YE" and ((not IS64) or WASM) and isinstance(tz, tzlocal):
         request.applymarker(
             pytest.mark.xfail(reason="OverflowError inside tzlocal past 2038")
         )

pandas/tests/io/parser/common/test_file_buffer_url.py

@@ -15,6 +15,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import WASM
 from pandas.errors import (
     EmptyDataError,
     ParserError,
@@ -80,6 +81,7 @@ def test_path_path_lib(all_parsers):
     tm.assert_frame_equal(df, result)
 
 
+@pytest.mark.skipif(WASM, reason="limited file system access on WASM")
 def test_nonexistent_path(all_parsers):
     # gh-2428: pls no segfault
     # gh-14086: raise more helpful FileNotFoundError
@@ -93,6 +95,7 @@ def test_nonexistent_path(all_parsers):
     assert path == e.value.filename
 
 
+@pytest.mark.skipif(WASM, reason="limited file system access on WASM")
 @td.skip_if_windows  # os.chmod does not work in windows
 def test_no_permission(all_parsers):
     # GH 23784

pandas/tests/io/parser/test_c_parser_only.py

@@ -18,6 +18,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import WASM
 from pandas.compat.numpy import np_version_gte1p24
 from pandas.errors import (
     ParserError,
@@ -94,15 +95,16 @@ def test_dtype_and_names_error(c_parser_only):
 """
     # fallback casting, but not castable
     warning = RuntimeWarning if np_version_gte1p24 else None
-    with pytest.raises(ValueError, match="cannot safely convert"):
-        with tm.assert_produces_warning(warning, check_stacklevel=False):
-            parser.read_csv(
-                StringIO(data),
-                sep=r"\s+",
-                header=None,
-                names=["a", "b"],
-                dtype={"a": np.int32},
-            )
+    if not WASM:  # no fp exception support in wasm
+        with pytest.raises(ValueError, match="cannot safely convert"):
+            with tm.assert_produces_warning(warning, check_stacklevel=False):
+                parser.read_csv(
+                    StringIO(data),
+                    sep=r"\s+",
+                    header=None,
+                    names=["a", "b"],
+                    dtype={"a": np.int32},
+                )
 
 
 @pytest.mark.parametrize(
@@ -550,6 +552,7 @@ def test_chunk_whitespace_on_boundary(c_parser_only):
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.skipif(WASM, reason="limited file system access on WASM")
 def test_file_handles_mmap(c_parser_only, csv1):
     # gh-14418
     #

pandas/tests/io/sas/test_sas7bdat.py

@@ -7,7 +7,10 @@
 import numpy as np
 import pytest
 
-from pandas.compat import IS64
+from pandas.compat._constants import (
+    IS64,
+    WASM,
+)
 from pandas.errors import EmptyDataError
 
 import pandas as pd
@@ -168,6 +171,7 @@ def test_airline(datapath):
     tm.assert_frame_equal(df, df0)
 
 
+@pytest.mark.skipif(WASM, reason="Pyodide/WASM has 32-bitness")
 def test_date_time(datapath):
     # Support of different SAS date/datetime formats (PR #15871)
     fname = datapath("io", "sas", "data", "datetime.sas7bdat")
@@ -253,6 +257,7 @@ def test_corrupt_read(datapath):
         pd.read_sas(fname)
 
 
+@pytest.mark.xfail(WASM, reason="failing with currently set tolerances on WASM")
 def test_max_sas_date(datapath):
     # GH 20927
     # NB. max datetime in SAS dataset is 31DEC9999:23:59:59.999
@@ -292,6 +297,7 @@ def test_max_sas_date(datapath):
     tm.assert_frame_equal(df, expected)
 
 
+@pytest.mark.xfail(WASM, reason="failing with currently set tolerances on WASM")
 def test_max_sas_date_iterator(datapath):
     # GH 20927
     # when called as an iterator, only those chunks with a date > pd.Timestamp.max
@@ -337,6 +343,7 @@ def test_max_sas_date_iterator(datapath):
     tm.assert_frame_equal(results[1], expected[1])
 
 
+@pytest.mark.skipif(WASM, reason="Pyodide/WASM has 32-bitness")
 def test_null_date(datapath):
     fname = datapath("io", "sas", "data", "dates_null.sas7bdat")
     df = pd.read_sas(fname, encoding="utf-8")

pandas/tests/io/test_common.py

@@ -19,7 +19,10 @@
 import numpy as np
 import pytest
 
-from pandas.compat import is_platform_windows
+from pandas.compat import (
+    WASM,
+    is_platform_windows,
+)
 
 import pandas as pd
 import pandas._testing as tm
@@ -163,6 +166,7 @@ def test_iterator(self):
             tm.assert_frame_equal(first, expected.iloc[[0]])
             tm.assert_frame_equal(pd.concat(it), expected.iloc[1:])
 
+    @pytest.mark.skipif(WASM, reason="limited file system access on WASM")
     @pytest.mark.parametrize(
         "reader, module, error_class, fn_ext",
         [
@@ -228,6 +232,7 @@ def test_write_missing_parent_directory(self, method, module, error_class, fn_ex
         ):
             method(dummy_frame, path)
 
+    @pytest.mark.skipif(WASM, reason="limited file system access on WASM")
     @pytest.mark.parametrize(
         "reader, module, error_class, fn_ext",
         [
@@ -382,6 +387,7 @@ def mmap_file(datapath):
 
 
 class TestMMapWrapper:
+    @pytest.mark.skipif(WASM, reason="limited file system access on WASM")
     def test_constructor_bad_file(self, mmap_file):
         non_file = StringIO("I am not a file")
         non_file.fileno = lambda: -1
@@ -404,6 +410,7 @@ def test_constructor_bad_file(self, mmap_file):
         with pytest.raises(ValueError, match=msg):
             icom._maybe_memory_map(target, True)
 
+    @pytest.mark.skipif(WASM, reason="limited file system access on WASM")
     def test_next(self, mmap_file):
         with open(mmap_file, encoding="utf-8") as target:
             lines = target.readlines()
@@ -587,6 +594,7 @@ def test_bad_encdoing_errors():
             icom.get_handle(path, "w", errors="bad")
 
 
+@pytest.mark.skipif(WASM, reason="limited file system access on WASM")
 def test_errno_attribute():
     # GH 13872
     with pytest.raises(FileNotFoundError, match="\\[Errno 2\\]") as err:

pandas/tests/io/xml/test_xml.py

@@ -14,6 +14,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import WASM
 from pandas.compat._optional import import_optional_dependency
 from pandas.errors import (
     EmptyDataError,
@@ -485,6 +486,7 @@ def test_empty_string_etree(val):
         read_xml(data, parser="etree")
 
 
+@pytest.mark.skipif(WASM, reason="limited file system access on WASM")
 def test_wrong_file_path(parser):
     filename = os.path.join("does", "not", "exist", "books.xml")
 

pandas/tests/scalar/timestamp/methods/test_replace.py

@@ -11,6 +11,7 @@
     conversion,
 )
 from pandas._libs.tslibs.dtypes import NpyDatetimeUnit
+from pandas.compat import WASM
 import pandas.util._test_decorators as td
 
 import pandas._testing as tm
@@ -99,13 +100,15 @@ def test_replace_integer_args(self, tz_aware_fixture):
         with pytest.raises(ValueError, match=msg):
             ts.replace(hour=0.1)
 
+    @pytest.mark.skipif(WASM, reason="tzset is not available on WASM")
     def test_replace_tzinfo_equiv_tz_localize_none(self):
         # GH#14621, GH#7825
         # assert conversion to naive is the same as replacing tzinfo with None
         ts = Timestamp("2013-11-03 01:59:59.999999-0400", tz="US/Eastern")
         assert ts.tz_localize(None) == ts.replace(tzinfo=None)
 
     @td.skip_if_windows
+    @pytest.mark.skipif(WASM, reason="tzset is not available on WASM")
     def test_replace_tzinfo(self):
         # GH#15683
         dt = datetime(2016, 3, 27, 1)

pandas/tests/scalar/timestamp/methods/test_timestamp_method.py

@@ -1,16 +1,19 @@
 # NB: This is for the Timestamp.timestamp *method* specifically, not
 # the Timestamp class in general.
 
+import pytest
 from pytz import utc
 
 from pandas._libs.tslibs import Timestamp
+from pandas.compat import WASM
 import pandas.util._test_decorators as td
 
 import pandas._testing as tm
 
 
 class TestTimestampMethod:
     @td.skip_if_windows
+    @pytest.mark.skipif(WASM, reason="tzset is not available on WASM")
     def test_timestamp(self, fixed_now_ts):
         # GH#17329
         # tz-naive --> treat it as if it were UTC for purposes of timestamp()