cudf-polars-cu12 25.2.2__py3-none-any.whl → 25.6.0__py3-none-any.whl

cudf_polars/testing/plugin.py

@@ -31,9 +31,12 @@ def pytest_addoption(parser: pytest.Parser) -> None:
 def pytest_configure(config: pytest.Config) -> None:
     """Enable use of this module as a pytest plugin to enable GPU collection."""
     no_fallback = config.getoption("--cudf-polars-no-fallback")
-    collect = polars.LazyFrame.collect
-    engine = polars.GPUEngine(raise_on_fail=no_fallback)
-    polars.LazyFrame.collect = partialmethod(collect, engine=engine)
+    if no_fallback:
+        collect = polars.LazyFrame.collect
+        engine = polars.GPUEngine(raise_on_fail=no_fallback)
+        polars.LazyFrame.collect = partialmethod(collect, engine=engine)
+    else:
+        polars.Config.set_engine_affinity("gpu")
     config.addinivalue_line(
         "filterwarnings",
         "ignore:.*GPU engine does not support streaming or background collection",
@@ -51,22 +54,56 @@ EXPECTED_FAILURES: Mapping[str, str | tuple[str, bool]] = {
     "tests/unit/io/test_delta.py::test_scan_delta_relative": "Need to expose hive partitioning",
     "tests/unit/io/test_delta.py::test_read_delta_version": "Need to expose hive partitioning",
     "tests/unit/io/test_lazy_count_star.py::test_count_compressed_csv_18057": "Need to determine if file is compressed",
+    "tests/unit/io/test_lazy_count_star.py::test_count_csv[foods1.csv-27]": "Need fast count for CSV scan",
+    "tests/unit/io/test_lazy_count_star.py::test_count_csv[foods*.csv-135]": "Need fast count for CSV scan",
+    "tests/unit/io/test_lazy_count_star.py::test_count_parquet[small.parquet-4]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_lazy_count_star.py::test_count_parquet[foods*.parquet-54]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_lazy_count_star.py::test_commented_csv": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_lazy_count_star.py::test_count_ndjson[foods1.ndjson-27]": "Need fast count for JSON scan",
+    "tests/unit/io/test_lazy_count_star.py::test_count_ndjson[foods*.ndjson-54]": "Need fast count for JSON scan",
+    "tests/unit/io/test_lazy_count_star.py::test_count_compressed_ndjson": "Need fast count for JSON scan",
     "tests/unit/io/test_lazy_csv.py::test_scan_csv_slice_offset_zero": "Integer overflow in sliced read",
-    "tests/unit/io/test_lazy_parquet.py::test_dsl2ir_cached_metadata[False]": "cudf-polars doesn't use metadata read by rust preprocessing",
     "tests/unit/io/test_lazy_parquet.py::test_parquet_is_in_statistics": "Debug output on stderr doesn't match",
     "tests/unit/io/test_lazy_parquet.py::test_parquet_statistics": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_lazy_parquet.py::test_parquet_different_schema[False]": "Needs cudf#16394",
-    "tests/unit/io/test_lazy_parquet.py::test_parquet_schema_arg[False-columns]": "Correctly raises but different error",
-    "tests/unit/io/test_lazy_parquet.py::test_parquet_schema_arg[False-row_groups]": "Correctly raises but different error",
-    "tests/unit/io/test_lazy_parquet.py::test_parquet_schema_arg[False-prefiltered]": "Correctly raises but different error",
-    "tests/unit/io/test_lazy_parquet.py::test_parquet_schema_arg[False-none]": "Correctly raises but different error",
-    "tests/unit/io/test_lazy_parquet.py::test_parquet_schema_mismatch_panic_17067[False]": "Needs cudf#16394",
+    "tests/unit/io/test_partition.py::test_partition_to_memory[io_type0]": "partition sinks not yet supported in standard engine.",
+    "tests/unit/io/test_partition.py::test_partition_to_memory[io_type1]": "partition sinks not yet supported in standard engine.",
+    "tests/unit/io/test_partition.py::test_partition_to_memory[io_type2]": "partition sinks not yet supported in standard engine.",
+    "tests/unit/io/test_partition.py::test_partition_to_memory[io_type3]": "partition sinks not yet supported in standard engine.",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-1-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-1-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-4-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-4-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-5-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-5-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-6-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-6-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-7-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[1-7-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-1-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-1-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-4-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-4-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-5-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-5-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-6-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-6-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-7-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[2-7-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-1-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-1-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-4-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-4-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-5-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-5-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-6-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-6-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-7-io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition[3-7-io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition_lambda[io_type1]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
+    "tests/unit/io/test_partition.py::test_max_size_partition_lambda[io_type2]": "Need fast count for Parquet scan: https://github.com/rapidsai/cudf/pull/18463",
     "tests/unit/io/test_lazy_parquet.py::test_scan_parquet_ignores_dtype_mismatch_for_non_projected_columns_19249[False-False]": "Needs some variant of cudf#16394",
     "tests/unit/io/test_lazy_parquet.py::test_scan_parquet_ignores_dtype_mismatch_for_non_projected_columns_19249[True-False]": "Needs some variant of cudf#16394",
-    "tests/unit/io/test_lazy_parquet.py::test_parquet_slice_pushdown_non_zero_offset[False]": "Thrift data not handled correctly/slice pushdown wrong?",
     "tests/unit/io/test_lazy_parquet.py::test_parquet_unaligned_schema_read[False]": "Incomplete handling of projected reads with mismatching schemas, cudf#16394",
-    "tests/unit/io/test_lazy_parquet.py::test_parquet_unaligned_schema_read_dtype_mismatch[False]": "Different exception raised, but correctly raises an exception",
-    "tests/unit/io/test_lazy_parquet.py::test_parquet_unaligned_schema_read_missing_cols_from_first[False]": "Different exception raised, but correctly raises an exception",
     "tests/unit/io/test_parquet.py::test_read_parquet_only_loads_selected_columns_15098": "Memory usage won't be correct due to GPU",
     "tests/unit/io/test_parquet.py::test_allow_missing_columns[projection0-False-none]": "Mismatching column read cudf#16394",
     "tests/unit/io/test_parquet.py::test_allow_missing_columns[projection1-False-none]": "Mismatching column read cudf#16394",
@@ -84,48 +121,7 @@ EXPECTED_FAILURES: Mapping[str, str | tuple[str, bool]] = {
     "tests/unit/io/test_parquet.py::test_allow_missing_columns[projection1-True-row_groups]": "Mismatching column read cudf#16394",
     "tests/unit/io/test_parquet.py::test_allow_missing_columns[projection0-True-columns]": "Mismatching column read cudf#16394",
     "tests/unit/io/test_parquet.py::test_allow_missing_columns[projection1-True-columns]": "Mismatching column read cudf#16394",
-    "tests/unit/io/test_scan.py::test_scan[single-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_limit[single-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_filter[single-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_filter_and_limit[single-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_limit_and_filter[single-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_and_limit[single-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_and_filter[single-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_limit_and_filter[single-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan[glob-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_limit[glob-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_filter[glob-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_filter_and_limit[glob-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_limit_and_filter[glob-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_and_limit[glob-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_and_filter[glob-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_limit_and_filter[glob-csv-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_limit[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_filter[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_filter_and_limit[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_limit_and_filter[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_and_limit[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_and_filter[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_limit_and_filter[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_projected_out[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_filter_and_limit[glob-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_limit[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_filter[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_filter_and_limit[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_limit_and_filter[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_and_limit[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_and_filter[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_limit_and_filter[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_projected_out[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_with_row_index_filter_and_limit[single-parquet-async]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_include_file_name[False-scan_parquet-write_parquet]": "Need to add include_file_path to IR",
-    "tests/unit/io/test_scan.py::test_scan_include_file_name[False-scan_csv-write_csv]": "Need to add include_file_path to IR",
-    "tests/unit/io/test_scan.py::test_scan_include_file_paths[False-scan_parquet-write_parquet]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_include_file_paths[False-scan_csv-write_csv]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_include_file_paths[False-scan_ndjson-write_ndjson]": "Debug output on stderr doesn't match",
-    "tests/unit/io/test_scan.py::test_scan_include_file_name[False-scan_ndjson-write_ndjson]": "Need to add include_file_path to IR",
+    "tests/unit/io/test_parquet.py::test_scan_parquet_filter_statistics_load_missing_column_21391": "Mismatching column read cudf#16394",
     "tests/unit/io/test_write.py::test_write_async[read_parquet-write_parquet]": "Need to add include_file_path to IR",
     "tests/unit/io/test_write.py::test_write_async[<lambda>-write_csv]": "Need to add include_file_path to IR",
     "tests/unit/io/test_write.py::test_write_async[read_parquet-<lambda>]": "Need to add include_file_path to IR",
@@ -136,8 +132,6 @@ EXPECTED_FAILURES: Mapping[str, str | tuple[str, bool]] = {
     "tests/unit/lazyframe/test_lazyframe.py::test_round[dtype1-123.55-1-123.6]": "Rounding midpoints is handled incorrectly",
     "tests/unit/lazyframe/test_lazyframe.py::test_cast_frame": "Casting that raises not supported on GPU",
     "tests/unit/lazyframe/test_lazyframe.py::test_lazy_cache_hit": "Debug output on stderr doesn't match",
-    "tests/unit/operations/aggregation/test_aggregations.py::test_duration_function_literal": "Broadcasting inside groupby-agg not supported",
-    "tests/unit/operations/aggregation/test_aggregations.py::test_sum_empty_and_null_set": "libcudf sums column of all nulls to null, not zero",
     "tests/unit/operations/aggregation/test_aggregations.py::test_binary_op_agg_context_no_simplify_expr_12423": "groupby-agg of just literals should not produce collect_list",
     "tests/unit/operations/aggregation/test_aggregations.py::test_nan_inf_aggregation": "treatment of nans and nulls together is different in libcudf and polars in groupby-agg context",
     "tests/unit/operations/arithmetic/test_list_arithmetic.py::test_list_arithmetic_values[func0-func0-none]": "cudf-polars doesn't nullify division by zero",
@@ -165,6 +159,7 @@ EXPECTED_FAILURES: Mapping[str, str | tuple[str, bool]] = {
     "tests/unit/operations/arithmetic/test_list.py::test_list_arithmetic_values[exec_op_with_expr_no_type_coercion-broadcast_both-none]": "cudf-polars doesn't nullify division by zero",
     "tests/unit/operations/arithmetic/test_list.py::test_list_arithmetic_values[exec_op_with_expr_no_type_coercion-broadcast_none-none]": "cudf-polars doesn't nullify division by zero",
     "tests/unit/operations/test_abs.py::test_abs_duration": "Need to raise for unsupported uops on timelike values",
+    "tests/unit/operations/test_group_by.py::test_group_by_shorthand_quantile": "libcudf quantiles are round to nearest ties to even, polars quantiles are round to nearest ties away from zero",
     "tests/unit/operations/test_group_by.py::test_group_by_mean_by_dtype[input7-expected7-Float32-Float32]": "Mismatching dtypes, needs cudf#15852",
     "tests/unit/operations/test_group_by.py::test_group_by_mean_by_dtype[input10-expected10-Date-output_dtype10]": "Unsupported groupby-agg for a particular dtype",
     "tests/unit/operations/test_group_by.py::test_group_by_mean_by_dtype[input11-expected11-input_dtype11-output_dtype11]": "Unsupported groupby-agg for a particular dtype",
@@ -180,26 +175,30 @@ EXPECTED_FAILURES: Mapping[str, str | tuple[str, bool]] = {
     "tests/unit/operations/test_group_by.py::test_group_by_median_by_dtype[input16-expected16-input_dtype16-output_dtype16]": "Unsupported groupby-agg for a particular dtype",
     "tests/unit/operations/test_group_by.py::test_group_by_binary_agg_with_literal": "Incorrect broadcasting of literals in groupby-agg",
     "tests/unit/operations/test_group_by.py::test_group_by_lit_series": "Incorrect broadcasting of literals in groupby-agg",
-    "tests/unit/operations/test_group_by.py::test_aggregated_scalar_elementwise_15602": "Unsupported boolean function/dtype combination in groupby-agg",
-    "tests/unit/operations/test_group_by.py::test_schemas[data1-expr1-expected_select1-expected_gb1]": "Mismatching dtypes, needs cudf#15852",
     "tests/unit/operations/test_join.py::test_cross_join_slice_pushdown": "Need to implement slice pushdown for cross joins",
+    "tests/unit/operations/test_rolling.py::test_rolling_group_by_empty_groups_by_take_6330": "Ordering difference, might be polars bug",
     "tests/unit/sql/test_cast.py::test_cast_errors[values0-values::uint8-conversion from `f64` to `u64` failed]": "Casting that raises not supported on GPU",
     "tests/unit/sql/test_cast.py::test_cast_errors[values1-values::uint4-conversion from `i64` to `u32` failed]": "Casting that raises not supported on GPU",
     "tests/unit/sql/test_cast.py::test_cast_errors[values2-values::int1-conversion from `i64` to `i8` failed]": "Casting that raises not supported on GPU",
     "tests/unit/sql/test_cast.py::test_cast_errors[values5-values::int4-conversion from `str` to `i32` failed]": "Cast raises, but error user receives is wrong",
     "tests/unit/sql/test_miscellaneous.py::test_read_csv": "Incorrect handling of missing_is_null in read_csv",
     "tests/unit/sql/test_wildcard_opts.py::test_select_wildcard_errors": "Raises correctly but with different exception",
-    "tests/unit/streaming/test_streaming_io.py::test_parquet_eq_statistics": "Debug output on stderr doesn't match",
     "tests/unit/test_cse.py::test_cse_predicate_self_join": "Debug output on stderr doesn't match",
+    "tests/unit/test_cse.py::test_nested_cache_no_panic_16553": "Needs https://github.com/rapidsai/cudf/issues/18630",
     "tests/unit/test_empty.py::test_empty_9137": "Mismatching dtypes, needs cudf#15852",
     "tests/unit/test_errors.py::test_error_on_empty_group_by": "Incorrect exception raised",
-    # Maybe flaky, order-dependent?
-    "tests/unit/test_projections.py::test_schema_full_outer_join_projection_pd_13287": "Order-specific result check, query is correct but in different order",
-    "tests/unit/test_queries.py::test_group_by_agg_equals_zero_3535": "libcudf sums all nulls to null, not zero",
+    "tests/unit/streaming/test_streaming_io.py::test_sink_phases[parquet]": "Debug output on stderr doesn't match",
+    "tests/unit/streaming/test_streaming_io.py::test_sink_phases[ndjson]": "Debug output on stderr doesn't match",
+    "tests/unit/io/test_scan.py::test_async_read_21945[scan_type0]": "Debug output on stderr doesn't match",
+    "tests/unit/io/test_scan.py::test_async_read_21945[scan_type1]": "Debug output on stderr doesn't match",
+    "tests/unit/io/test_scan.py::test_async_read_21945[scan_type2]": "Debug output on stderr doesn't match",
+    "tests/unit/io/test_scan.py::test_async_read_21945[scan_type3]": "Debug output on stderr doesn't match",
+    "tests/unit/io/test_multiscan.py::test_multiscan_row_index[scan_csv-write_csv-csv]": "Debug output on stderr doesn't match",
 }
 
 
 TESTS_TO_SKIP: Mapping[str, str] = {
+    "tests/unit/operations/test_profile.py::test_profile_with_cse": "Shape assertion won't match",
     # On Ubuntu 20.04, the tzdata package contains a bunch of symlinks
     # for obsolete timezone names. However, the chrono_tz package that
     # polars uses doesn't read /usr/share/zoneinfo, instead packaging
@@ -209,15 +208,19 @@ TESTS_TO_SKIP: Mapping[str, str] = {
     # polars that the requested timezone is unknown.
     # Since this is random, just skip it, rather than xfailing.
     "tests/unit/lazyframe/test_serde.py::test_lf_serde_roundtrip_binary": "chrono_tz doesn't have all tzdata symlink names",
+    # Tests performance difference of CPU engine
+    "tests/unit/operations/test_join.py::test_join_where_eager_perf_21145": "Tests performance bug in CPU engine",
     # The test may segfault with the legacy streaming engine. We should
     # remove this skip when all polars tests use the new streaming engine.
     "tests/unit/streaming/test_streaming_group_by.py::test_streaming_group_by_literal[1]": "May segfault w/the legacy streaming engine",
     # Fails in CI, but passes locally
     "tests/unit/streaming/test_streaming.py::test_streaming_streamable_functions": "RuntimeError: polars_python::sql::PySQLContext is unsendable, but is being dropped on another thread",
-    # TODO: Remove once when we support polars 1.23
-    "tests/unit/io/database/test_read.py::test_read_database[uri: connectorx]": "ValueError: arrow2",
-    "tests/unit/io/database/test_read.py::test_read_database_cx_credentials[fakedb://123:456@account/database/schema?warehouse=warehouse&role=role]": "ValueError: arrow2",
-    "tests/unit/io/database/test_read.py::test_read_database_cx_credentials[fakedb://my#%us3r:p433w0rd@not_a_real_host:9999/database]": "ValueError: arrow2",
+    # Remove when polars supports Pydantic V3
+    "tests/unit/constructors/test_constructors.py::test_init_structured_objects": "pydantic deprecation warning",
+    "tests/unit/constructors/test_constructors.py::test_init_pydantic_2x": "pydantic deprecation warning",
+    "tests/unit/constructors/test_constructors.py::test_init_structured_objects_nested[_TestFooPD-_TestBarPD-_TestBazPD]": "pydantic deprecation warning",
+    "tests/unit/series/test_series.py::test_init_structured_objects": "pydantic deprecation warning",
+    "tests/unit/streaming/test_streaming.py::test_streaming_apply": "https://github.com/pola-rs/polars/issues/22558",
 }
 
 
@@ -229,18 +232,17 @@ def pytest_collection_modifyitems(
         # Don't xfail tests if running without fallback
         return
     for item in items:
-        if item.nodeid in TESTS_TO_SKIP:
-            item.add_marker(pytest.mark.skip(reason=TESTS_TO_SKIP[item.nodeid]))
-        elif item.nodeid in EXPECTED_FAILURES:
-            if isinstance(EXPECTED_FAILURES[item.nodeid], tuple):
+        if (reason := TESTS_TO_SKIP.get(item.nodeid, None)) is not None:
+            item.add_marker(pytest.mark.skip(reason=reason))
+        elif (entry := EXPECTED_FAILURES.get(item.nodeid, None)) is not None:
+            if isinstance(entry, tuple):
                 # the second entry in the tuple is the condition to xfail on
+                reason, condition = entry
                 item.add_marker(
                     pytest.mark.xfail(
-                        condition=EXPECTED_FAILURES[item.nodeid][1],
-                        reason=EXPECTED_FAILURES[item.nodeid][0],
+                        condition=condition,
+                        reason=reason,
                     ),
                 )
             else:
-                item.add_marker(
-                    pytest.mark.xfail(reason=EXPECTED_FAILURES[item.nodeid])
-                )
+                item.add_marker(pytest.mark.xfail(reason=entry))

cudf_polars/typing/__init__.py

@@ -1,26 +1,40 @@
-# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES.
+# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES.
 # SPDX-License-Identifier: Apache-2.0
 
 """Typing utilities for cudf_polars."""
 
 from __future__ import annotations
 
-from collections.abc import Hashable, Mapping
-from typing import TYPE_CHECKING, Any, Literal, Protocol, TypeVar, Union
+from collections.abc import Hashable, MutableMapping
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Literal,
+    NewType,
+    Protocol,
+    TypeVar,
+    TypedDict,
+    Union,
+)
 
 from polars.polars import _expr_nodes as pl_expr, _ir_nodes as pl_ir
 
 import pylibcudf as plc
 
 if TYPE_CHECKING:
-    from collections.abc import Callable
+    from collections.abc import Callable, Mapping
     from typing import TypeAlias
 
     import polars as pl
 
+    from cudf_polars.containers import DataFrame
     from cudf_polars.dsl import expr, ir, nodebase
 
 __all__: list[str] = [
+    "ClosedInterval",
+    "ColumnHeader",
+    "ColumnOptions",
+    "DataFrameHeader",
     "ExprTransformer",
     "GenericTransformer",
     "IRTransformer",
@@ -28,6 +42,8 @@ __all__: list[str] = [
     "OptimizationArgs",
     "PolarsExpr",
     "PolarsIR",
+    "Schema",
+    "Slice",
 ]
 
 PolarsIR: TypeAlias = Union[
@@ -66,7 +82,15 @@ PolarsExpr: TypeAlias = Union[
     pl_expr.PyExprIR,
 ]
 
-Schema: TypeAlias = Mapping[str, plc.DataType]
+Schema: TypeAlias = dict[str, plc.DataType]
+
+Slice: TypeAlias = tuple[int, int | None]
+
+CSECache: TypeAlias = MutableMapping[int, tuple["DataFrame", int]]
+
+ClosedInterval: TypeAlias = Literal["left", "right", "both", "none"]
+
+Duration = NewType("Duration", tuple[int, int, int, int, bool, bool])
 
 
 class NodeTraverser(Protocol):
@@ -84,7 +108,7 @@ class NodeTraverser(Protocol):
         """Convert current plan node to python rep."""
         ...
 
-    def get_schema(self) -> Mapping[str, pl.DataType]:
+    def get_schema(self) -> Schema:
         """Get the schema of the current plan node."""
         ...
 
@@ -145,3 +169,32 @@ ExprTransformer: TypeAlias = GenericTransformer["expr.Expr", "expr.Expr"]
 
 IRTransformer: TypeAlias = GenericTransformer["ir.IR", "ir.IR"]
 """Protocol for transformation of IR nodes."""
+
+
+class ColumnOptions(TypedDict):
+    """
+    Column constructor options.
+
+    Notes
+    -----
+    Used to serialize Column and DataFrame containers.
+    """
+
+    is_sorted: plc.types.Sorted
+    order: plc.types.Order
+    null_order: plc.types.NullOrder
+    name: str | None
+
+
+class ColumnHeader(TypedDict):
+    """Column serialization header."""
+
+    column_kwargs: ColumnOptions
+    frame_count: int
+
+
+class DataFrameHeader(TypedDict):
+    """DataFrame serialization header."""
+
+    columns_kwargs: list[ColumnOptions]
+    frame_count: int