Backport PR #45581 on branch 1.4.x (CI: Fix actions-310 testing 3.9 instead of 3.10)

ci/deps/actions-310.yaml

@@ -2,7 +2,7 @@ name: pandas-dev
 channels:
   - conda-forge
 dependencies:
-  - python=3.9
+  - python=3.10
 
   # test dependencies
   - cython=0.29.24

pandas/tests/io/test_fsspec.py

@@ -3,6 +3,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import PY310
 from pandas.compat._optional import VERSIONS
 
 from pandas import (
@@ -181,6 +182,7 @@ def test_arrowparquet_options(fsspectest):
 
 @td.skip_array_manager_not_yet_implemented  # TODO(ArrayManager) fastparquet
 @td.skip_if_no("fastparquet")
+@pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
 def test_fastparquet_options(fsspectest):
     """Regression test for writing to a not-yet-existent GCS Parquet file."""
     df = DataFrame({"a": [0]})

pandas/tests/io/test_parquet.py

@@ -13,6 +13,7 @@
 
 from pandas._config import get_option
 
+from pandas.compat import PY310
 from pandas.compat.pyarrow import (
     pa_version_under2p0,
     pa_version_under5p0,
@@ -261,6 +262,7 @@ def test_options_py(df_compat, pa):
         check_round_trip(df_compat)
 
 
+@pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
 def test_options_fp(df_compat, fp):
     # use the set option
 
@@ -338,6 +340,7 @@ def test_get_engine_auto_error_message():
                 get_engine("auto")
 
 
+@pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
 def test_cross_engine_pa_fp(df_cross_compat, pa, fp):
     # cross-compat with differing reading/writing engines
 
@@ -404,7 +407,11 @@ def test_error(self, engine):
             msg = "to_parquet only supports IO with DataFrames"
             self.check_error_on_write(obj, engine, ValueError, msg)
 
-    def test_columns_dtypes(self, engine):
+    def test_columns_dtypes(self, request, engine):
+        if PY310 and engine == "fastparquet":
+            request.node.add_marker(
+                pytest.mark.xfail(reason="fastparquet failing on 3.10")
+            )
         df = pd.DataFrame({"string": list("abc"), "int": list(range(1, 4))})
 
         # unicode
@@ -431,27 +438,39 @@ def test_columns_dtypes_invalid(self, engine):
         self.check_error_on_write(df, engine, ValueError, msg)
 
     @pytest.mark.parametrize("compression", [None, "gzip", "snappy", "brotli"])
-    def test_compression(self, engine, compression):
+    def test_compression(self, engine, compression, request):
 
         if compression == "snappy":
             pytest.importorskip("snappy")
 
         elif compression == "brotli":
             pytest.importorskip("brotli")
 
+        if PY310 and engine == "fastparquet":
+            request.node.add_marker(
+                pytest.mark.xfail(reason="fastparquet failing on 3.10")
+            )
         df = pd.DataFrame({"A": [1, 2, 3]})
         check_round_trip(df, engine, write_kwargs={"compression": compression})
 
-    def test_read_columns(self, engine):
+    def test_read_columns(self, engine, request):
         # GH18154
+        if PY310 and engine == "fastparquet":
+            request.node.add_marker(
+                pytest.mark.xfail(reason="fastparquet failing on 3.10")
+            )
         df = pd.DataFrame({"string": list("abc"), "int": list(range(1, 4))})
 
         expected = pd.DataFrame({"string": list("abc")})
         check_round_trip(
             df, engine, expected=expected, read_kwargs={"columns": ["string"]}
         )
 
-    def test_write_index(self, engine):
+    def test_write_index(self, engine, request):
+        if PY310 and engine == "fastparquet":
+            request.node.add_marker(
+                pytest.mark.xfail(reason="fastparquet failing on 3.10")
+            )
         check_names = engine != "fastparquet"
 
         df = pd.DataFrame({"A": [1, 2, 3]})
@@ -500,9 +519,13 @@ def test_multiindex_with_columns(self, pa):
                 df, engine, read_kwargs={"columns": ["A", "B"]}, expected=df[["A", "B"]]
             )
 
-    def test_write_ignoring_index(self, engine):
+    def test_write_ignoring_index(self, engine, request):
         # ENH 20768
         # Ensure index=False omits the index from the written Parquet file.
+        if PY310 and engine == "fastparquet":
+            request.node.add_marker(
+                pytest.mark.xfail(reason="fastparquet failing on 3.10")
+            )
         df = pd.DataFrame({"a": [1, 2, 3], "b": ["q", "r", "s"]})
 
         write_kwargs = {"compression": None, "index": False}
@@ -958,6 +981,7 @@ def test_read_parquet_manager(self, pa, using_array_manager):
 
 
 class TestParquetFastParquet(Base):
+    @pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
     def test_basic(self, fp, df_full):
         df = df_full
 
@@ -975,6 +999,7 @@ def test_duplicate_columns(self, fp):
         msg = "Cannot create parquet dataset with duplicate column names"
         self.check_error_on_write(df, fp, ValueError, msg)
 
+    @pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
     def test_bool_with_none(self, fp):
         df = pd.DataFrame({"a": [True, None, False]})
         expected = pd.DataFrame({"a": [1.0, np.nan, 0.0]}, dtype="float16")
@@ -994,10 +1019,12 @@ def test_unsupported(self, fp):
         msg = "Can't infer object conversion type"
         self.check_error_on_write(df, fp, ValueError, msg)
 
+    @pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
     def test_categorical(self, fp):
         df = pd.DataFrame({"a": pd.Categorical(list("abc"))})
         check_round_trip(df, fp)
 
+    @pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
     def test_filter_row_groups(self, fp):
         d = {"a": list(range(0, 3))}
         df = pd.DataFrame(d)
@@ -1016,6 +1043,7 @@ def test_s3_roundtrip(self, df_compat, s3_resource, fp, s3so):
             write_kwargs={"compression": None, "storage_options": s3so},
         )
 
+    @pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
     def test_partition_cols_supported(self, fp, df_full):
         # GH #23283
         partition_cols = ["bool", "int"]
@@ -1033,6 +1061,7 @@ def test_partition_cols_supported(self, fp, df_full):
             actual_partition_cols = fastparquet.ParquetFile(path, False).cats
             assert len(actual_partition_cols) == 2
 
+    @pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
     def test_partition_cols_string(self, fp, df_full):
         # GH #27117
         partition_cols = "bool"
@@ -1050,6 +1079,7 @@ def test_partition_cols_string(self, fp, df_full):
             actual_partition_cols = fastparquet.ParquetFile(path, False).cats
             assert len(actual_partition_cols) == 1
 
+    @pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
     def test_partition_on_supported(self, fp, df_full):
         # GH #23283
         partition_cols = ["bool", "int"]
@@ -1085,13 +1115,15 @@ def test_error_on_using_partition_cols_and_partition_on(self, fp, df_full):
                     partition_cols=partition_cols,
                 )
 
+    @pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
     def test_empty_dataframe(self, fp):
         # GH #27339
         df = pd.DataFrame()
         expected = df.copy()
         expected.index.name = "index"
         check_round_trip(df, fp, expected=expected)
 
+    @pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10")
     def test_timezone_aware_index(self, fp, timezone_aware_date_list):
         idx = 5 * [timezone_aware_date_list]
 

pandas/tests/io/test_user_agent.py

@@ -11,6 +11,7 @@
 
 import pytest
 
+from pandas.compat import PY310
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -242,7 +243,10 @@ def responder(request):
             pd.read_parquet,
             "fastparquet",
             # TODO(ArrayManager) fastparquet
-            marks=td.skip_array_manager_not_yet_implemented,
+            marks=[
+                td.skip_array_manager_not_yet_implemented,
+                pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10"),
+            ],
         ),
         (PickleUserAgentResponder, pd.read_pickle, None),
         (StataUserAgentResponder, pd.read_stata, None),
@@ -277,7 +281,10 @@ def test_server_and_default_headers(responder, read_method, parquet_engine):
             pd.read_parquet,
             "fastparquet",
             # TODO(ArrayManager) fastparquet
-            marks=td.skip_array_manager_not_yet_implemented,
+            marks=[
+                td.skip_array_manager_not_yet_implemented,
+                pytest.mark.xfail(PY310, reason="fastparquet failing on 3.10"),
+            ],
         ),
         (PickleUserAgentResponder, pd.read_pickle, None),
         (StataUserAgentResponder, pd.read_stata, None),