You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ru...@apache.org on 2023/05/23 01:25:15 UTC
[spark] branch master updated: [SPARK-42996][CONNECT][PS][ML] Create & assign proper JIRA tickets for all failing tests
This is an automated email from the ASF dual-hosted git repository.
ruifengz pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new e1949f05b92 [SPARK-42996][CONNECT][PS][ML] Create & assign proper JIRA tickets for all failing tests
e1949f05b92 is described below
commit e1949f05b92bfce2b3254ed5d57665c6d29a282f
Author: itholic <ha...@databricks.com>
AuthorDate: Tue May 23 09:24:53 2023 +0800
[SPARK-42996][CONNECT][PS][ML] Create & assign proper JIRA tickets for all failing tests
### What changes were proposed in this pull request?
This PR proposes to add comments for all pandas-on-Spark with Spark Connect failing tests, with related JIRA tickets.
Created all tickets for pandas API on Spark with Spark Connect are here: SPARK-42497
### Why are the changes needed?
To assign appropriate tasks to efficiently fix the failing tests.
### Does this PR introduce _any_ user-facing change?
No, it's dev-only.
### How was this patch tested?
The existing CI should pass
Closes #41255 from itholic/SPARK-42996.
Authored-by: itholic <ha...@databricks.com>
Signed-off-by: Ruifeng Zheng <ru...@apache.org>
---
python/pyspark/pandas/internal.py | 1 +
.../data_type_ops/test_parity_binary_ops.py | 10 +--
.../data_type_ops/test_parity_boolean_ops.py | 18 +---
.../data_type_ops/test_parity_categorical_ops.py | 14 +--
.../connect/data_type_ops/test_parity_date_ops.py | 18 +---
.../data_type_ops/test_parity_datetime_ops.py | 10 +--
.../connect/data_type_ops/test_parity_null_ops.py | 14 +--
.../connect/data_type_ops/test_parity_num_ops.py | 18 ++--
.../data_type_ops/test_parity_string_ops.py | 18 ++--
.../data_type_ops/test_parity_timedelta_ops.py | 14 +--
.../connect/data_type_ops/test_parity_udt_ops.py | 32 +++++--
.../tests/connect/indexes/test_parity_base.py | 18 ++--
.../tests/connect/indexes/test_parity_category.py | 18 ++--
.../tests/connect/indexes/test_parity_datetime.py | 8 +-
.../tests/connect/indexes/test_parity_timedelta.py | 2 +-
.../tests/connect/plot/test_parity_frame_plot.py | 4 +-
.../plot/test_parity_frame_plot_matplotlib.py | 4 +-
.../connect/plot/test_parity_frame_plot_plotly.py | 6 +-
.../plot/test_parity_series_plot_matplotlib.py | 12 +--
.../connect/plot/test_parity_series_plot_plotly.py | 4 +-
.../tests/connect/test_parity_categorical.py | 16 ++--
.../pandas/tests/connect/test_parity_dataframe.py | 89 ++++++++++--------
.../tests/connect/test_parity_dataframe_slow.py | 66 ++++++++------
.../tests/connect/test_parity_default_index.py | 12 ++-
.../pandas/tests/connect/test_parity_ewm.py | 4 +-
.../pandas/tests/connect/test_parity_expanding.py | 80 ++++++++++++-----
.../tests/connect/test_parity_frame_spark.py | 8 +-
.../tests/connect/test_parity_generic_functions.py | 10 ++-
.../pandas/tests/connect/test_parity_groupby.py | 50 ++++++++---
.../tests/connect/test_parity_groupby_slow.py | 14 ++-
.../pandas/tests/connect/test_parity_internal.py | 2 +-
.../pandas/tests/connect/test_parity_namespace.py | 10 ++-
.../tests/connect/test_parity_numpy_compat.py | 8 +-
.../test_parity_ops_on_diff_frames_groupby.py | 36 +++++---
..._parity_ops_on_diff_frames_groupby_expanding.py | 28 ++++--
...st_parity_ops_on_diff_frames_groupby_rolling.py | 28 ++++--
.../connect/test_parity_ops_on_diff_frames_slow.py | 26 ++++--
.../pandas/tests/connect/test_parity_resample.py | 4 +-
.../pandas/tests/connect/test_parity_reshape.py | 4 +-
.../pandas/tests/connect/test_parity_rolling.py | 80 ++++++++++++-----
.../pandas/tests/connect/test_parity_series.py | 100 ++++++++++++++-------
.../tests/connect/test_parity_series_string.py | 4 +-
.../pandas/tests/connect/test_parity_sql.py | 8 +-
.../pandas/tests/connect/test_parity_stats.py | 32 +++++--
44 files changed, 618 insertions(+), 344 deletions(-)
diff --git a/python/pyspark/pandas/internal.py b/python/pyspark/pandas/internal.py
index d17d9be5114..1daae6bf07b 100644
--- a/python/pyspark/pandas/internal.py
+++ b/python/pyspark/pandas/internal.py
@@ -935,6 +935,7 @@ class InternalFrame:
)
return sdf.select(sequential_index.alias(column_name), *scols)
+ # TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect.
@staticmethod
def attach_distributed_column(sdf: PySparkDataFrame, column_name: str) -> PySparkDataFrame:
scols = [scol_for(sdf, column) for column in sdf.columns]
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_binary_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_binary_ops.py
index 71bf32771e5..7d941c4c788 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_binary_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_binary_ops.py
@@ -25,23 +25,23 @@ from pyspark.testing.connectutils import ReusedConnectTestCase
class BinaryOpsParityTests(
BinaryOpsTestsMixin, PandasOnSparkTestUtils, OpsTestBase, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43666): Fix BinaryOps.ge to work with Spark Connect Column.")
def test_ge(self):
super().test_ge()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43667): Fix BinaryOps.gt to work with Spark Connect Column.")
def test_gt(self):
super().test_gt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43667): Fix BinaryOps.le to work with Spark Connect Column.")
def test_le(self):
super().test_le()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43667): Fix BinaryOps.lt to work with Spark Connect Column.")
def test_lt(self):
super().test_lt()
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_boolean_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_boolean_ops.py
index 5bd68ce683b..52d517967eb 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_boolean_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_boolean_ops.py
@@ -30,26 +30,10 @@ class BooleanOpsParityTests(
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_ge(self):
- super().test_ge()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_gt(self):
- super().test_gt()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_le(self):
- super().test_le()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_lt(self):
- super().test_lt()
-
if __name__ == "__main__":
from pyspark.pandas.tests.connect.data_type_ops.test_parity_boolean_ops import * # noqa: F401
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_categorical_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_categorical_ops.py
index be418992d47..dc196060bfc 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_categorical_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_categorical_ops.py
@@ -30,31 +30,31 @@ class CategoricalOpsParityTests(
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43670): Enable CategoricalOps.eq to work with Spark Connect.")
def test_eq(self):
super().test_eq()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43671): Enable CategoricalOps.ge to work with Spark Connect.")
def test_ge(self):
super().test_ge()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43672): Enable CategoricalOps.gt to work with Spark Connect.")
def test_gt(self):
super().test_gt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43673): Enable CategoricalOps.le to work with Spark Connect.")
def test_le(self):
super().test_le()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43674): Enable CategoricalOps.lt to work with Spark Connect.")
def test_lt(self):
super().test_lt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43675): Enable CategoricalOps.ne to work with Spark Connect.")
def test_ne(self):
super().test_ne()
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_date_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_date_ops.py
index 9e9020b2d06..e7b1c7de70d 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_date_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_date_ops.py
@@ -30,26 +30,10 @@ class DateOpsParityTests(
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_ge(self):
- super().test_ge()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_gt(self):
- super().test_gt()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_le(self):
- super().test_le()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_lt(self):
- super().test_lt()
-
if __name__ == "__main__":
from pyspark.pandas.tests.connect.data_type_ops.test_parity_date_ops import * # noqa: F401
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_datetime_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_datetime_ops.py
index 4f5be453207..697c191b743 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_datetime_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_datetime_ops.py
@@ -30,23 +30,23 @@ class DatetimeOpsParityTests(
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43676): Fix DatetimeOps.ge to work with Spark Connect Column.")
def test_ge(self):
super().test_ge()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43677): Fix DatetimeOps.gt to work with Spark Connect Column.")
def test_gt(self):
super().test_gt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43678): Fix DatetimeOps.le to work with Spark Connect Column.")
def test_le(self):
super().test_le()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43679): Fix DatetimeOps.lt to work with Spark Connect Column.")
def test_lt(self):
super().test_lt()
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_null_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_null_ops.py
index eb97e0f1cb0..00bfb75087a 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_null_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_null_ops.py
@@ -25,31 +25,31 @@ from pyspark.testing.connectutils import ReusedConnectTestCase
class NullOpsParityTests(
NullOpsTestsMixin, PandasOnSparkTestUtils, OpsTestBase, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43684): Fix NullOps.eq to work with Spark Connect Column.")
def test_eq(self):
super().test_eq()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43680): Fix NullOps.ge to work with Spark Connect Column.")
def test_ge(self):
super().test_ge()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43681): Fix NullOps.gt to work with Spark Connect Column.")
def test_gt(self):
super().test_gt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43682): Fix NullOps.le to work with Spark Connect Column.")
def test_le(self):
super().test_le()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43683): Fix NullOps.lt to work with Spark Connect Column.")
def test_lt(self):
super().test_lt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43685): Fix NullOps.ne to work with Spark Connect Column.")
def test_ne(self):
super().test_ne()
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_num_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_num_ops.py
index 4ec71d2598e..1726b9a9e97 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_num_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_num_ops.py
@@ -30,35 +30,37 @@ class NumOpsParityTests(
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43686): Enable NumOpsParityTests.test_eq.")
def test_eq(self):
super().test_eq()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43687): Enable NumOpsParityTests.test_ge.")
def test_ge(self):
super().test_ge()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43688): Enable NumOpsParityTests.test_gt.")
def test_gt(self):
super().test_gt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43689): Enable NumOpsParityTests.test_le.")
def test_le(self):
super().test_le()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43690): Enable NumOpsParityTests.test_lt.")
def test_lt(self):
super().test_lt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43621): Enable pyspark.pandas.spark.functions.repeat in Spark Connect."
+ )
def test_mul(self):
super().test_mul()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43691): Enable NumOpsParityTests.test_ne.")
def test_ne(self):
super().test_ne()
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_string_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_string_ops.py
index af63790b544..9abfe1d1e09 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_string_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_string_ops.py
@@ -30,31 +30,35 @@ class StringOpsParityTests(
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43692): Fix StringOps.ge to work with Spark Connect.")
def test_ge(self):
super().test_ge()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43693): Fix StringOps.gt to work with Spark Connect.")
def test_gt(self):
super().test_gt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43694): Fix StringOps.le to work with Spark Connect.")
def test_le(self):
super().test_le()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43695): Fix StringOps.lt to work with Spark Connect.")
def test_lt(self):
super().test_lt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43621): Enable pyspark.pandas.spark.functions.repeat in Spark Connect."
+ )
def test_mul(self):
super().test_mul()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43621): Enable pyspark.pandas.spark.functions.repeat in Spark Connect."
+ )
def test_rmul(self):
super().test_rmul()
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_timedelta_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_timedelta_ops.py
index 1fdd80d783a..badb32f08b4 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_timedelta_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_timedelta_ops.py
@@ -25,31 +25,31 @@ from pyspark.testing.connectutils import ReusedConnectTestCase
class TimedeltaOpsParityTests(
TimedeltaOpsTestsMixin, PandasOnSparkTestUtils, OpsTestBase, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43696): Fix TimedeltaOps.ge to work with Spark Connect.")
def test_ge(self):
super().test_ge()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43697): Fix TimedeltaOps.gt to work with Spark Connect.")
def test_gt(self):
super().test_gt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43698): Fix TimedeltaOps.le to work with Spark Connect.")
def test_le(self):
super().test_le()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43699): Fix TimedeltaOps.lt to work with Spark Connect.")
def test_lt(self):
super().test_lt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43700): Fix TimedeltaOps.rsub to work with Spark Connect.")
def test_rsub(self):
super().test_rsub()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43701): Fix TimedeltaOps.sub to work with Spark Connect.")
def test_sub(self):
super().test_sub()
diff --git a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_udt_ops.py b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_udt_ops.py
index 6ea91ce8536..81511829c06 100644
--- a/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_udt_ops.py
+++ b/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_udt_ops.py
@@ -25,35 +25,51 @@ from pyspark.testing.connectutils import ReusedConnectTestCase
class UDTOpsParityTests(
UDTOpsTestsMixin, PandasOnSparkTestUtils, OpsTestBase, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43702): Fix pyspark.sql.pandas.types.to_arrow_type to work with Spark Connect."
+ )
def test_eq(self):
super().test_eq()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43702): Fix pyspark.sql.pandas.types.to_arrow_type to work with Spark Connect."
+ )
def test_from_to_pandas(self):
super().test_from_to_pandas()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43702): Fix pyspark.sql.pandas.types.to_arrow_type to work with Spark Connect."
+ )
def test_ge(self):
super().test_ge()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43702): Fix pyspark.sql.pandas.types.to_arrow_type to work with Spark Connect."
+ )
def test_gt(self):
super().test_gt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43702): Fix pyspark.sql.pandas.types.to_arrow_type to work with Spark Connect."
+ )
def test_isnull(self):
super().test_isnull()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43702): Fix pyspark.sql.pandas.types.to_arrow_type to work with Spark Connect."
+ )
def test_le(self):
super().test_le()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43702): Fix pyspark.sql.pandas.types.to_arrow_type to work with Spark Connect."
+ )
def test_lt(self):
super().test_lt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43702): Fix pyspark.sql.pandas.types.to_arrow_type to work with Spark Connect."
+ )
def test_ne(self):
super().test_ne()
diff --git a/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py b/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
index 0582412c87e..d5ae0a39b5b 100644
--- a/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
+++ b/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py
@@ -29,27 +29,33 @@ class IndexesParityTests(
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_append(self):
super().test_append()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_drop_duplicates(self):
super().test_drop_duplicates()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_factorize(self):
super().test_factorize()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_index_drop_duplicates(self):
super().test_index_drop_duplicates()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43703): Enable IndexesParityTests.test_monotonic.")
def test_monotonic(self):
super().test_monotonic()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43704): Enable IndexesParityTests.test_to_series.")
def test_to_series(self):
super().test_to_series()
diff --git a/python/pyspark/pandas/tests/connect/indexes/test_parity_category.py b/python/pyspark/pandas/tests/connect/indexes/test_parity_category.py
index b61c531687f..d99d013306f 100644
--- a/python/pyspark/pandas/tests/connect/indexes/test_parity_category.py
+++ b/python/pyspark/pandas/tests/connect/indexes/test_parity_category.py
@@ -24,39 +24,39 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class CategoricalIndexParityTests(
CategoricalIndexTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_append(self):
super().test_append()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_factorize(self):
super().test_factorize()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_intersection(self):
super().test_intersection()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_remove_categories(self):
super().test_remove_categories()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_remove_unused_categories(self):
super().test_remove_unused_categories()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_reorder_categories(self):
super().test_reorder_categories()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_set_categories(self):
super().test_set_categories()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_union(self):
super().test_union()
diff --git a/python/pyspark/pandas/tests/connect/indexes/test_parity_datetime.py b/python/pyspark/pandas/tests/connect/indexes/test_parity_datetime.py
index 75649f0fb53..aa035d1d608 100644
--- a/python/pyspark/pandas/tests/connect/indexes/test_parity_datetime.py
+++ b/python/pyspark/pandas/tests/connect/indexes/test_parity_datetime.py
@@ -24,11 +24,15 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class DatetimeIndexParityTests(
DatetimeIndexTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_indexer_at_time(self):
super().test_indexer_at_time()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_indexer_between_time(self):
super().test_indexer_between_time()
diff --git a/python/pyspark/pandas/tests/connect/indexes/test_parity_timedelta.py b/python/pyspark/pandas/tests/connect/indexes/test_parity_timedelta.py
index 2289f24777b..9dadad756c4 100644
--- a/python/pyspark/pandas/tests/connect/indexes/test_parity_timedelta.py
+++ b/python/pyspark/pandas/tests/connect/indexes/test_parity_timedelta.py
@@ -24,7 +24,7 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class TimedeltaIndexParityTests(
TimedeltaIndexTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43710): Support functions.date_part for Spark Connect.")
def test_properties(self):
super().test_properties()
diff --git a/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot.py b/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot.py
index db004cd8d86..24392eaf27c 100644
--- a/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot.py
+++ b/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot.py
@@ -24,11 +24,11 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class DataFramePlotParityTests(
DataFramePlotTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43711): Fix Transformer.transform to work with Spark Connect.")
def test_compute_hist_multi_columns(self):
super().test_compute_hist_multi_columns()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43711): Fix Transformer.transform to work with Spark Connect.")
def test_compute_hist_single_column(self):
super().test_compute_hist_single_column()
diff --git a/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_matplotlib.py b/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_matplotlib.py
index 0a6da179c1a..98da8858a03 100644
--- a/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_matplotlib.py
+++ b/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_matplotlib.py
@@ -24,11 +24,11 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class DataFramePlotMatplotlibParityTests(
DataFramePlotMatplotlibTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43711): Fix Transformer.transform to work with Spark Connect.")
def test_hist_plot(self):
super().test_hist_plot()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43629): Enable RDD with Spark Connect.")
def test_kde_plot(self):
super().test_kde_plot()
diff --git a/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_plotly.py b/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_plotly.py
index a7075b5ab15..7a3efee06df 100644
--- a/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_plotly.py
+++ b/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_plotly.py
@@ -24,15 +24,15 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class DataFramePlotPlotlyParityTests(
DataFramePlotPlotlyTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43711): Fix Transformer.transform to work with Spark Connect.")
def test_hist_layout_kwargs(self):
super().test_hist_layout_kwargs()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43711): Fix Transformer.transform to work with Spark Connect.")
def test_hist_plot(self):
super().test_hist_plot()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43629): Enable RDD with Spark Connect.")
def test_kde_plot(self):
super().test_kde_plot()
diff --git a/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_matplotlib.py b/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_matplotlib.py
index 69b46ce2f6b..18cdac7a162 100644
--- a/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_matplotlib.py
+++ b/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_matplotlib.py
@@ -24,27 +24,27 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class SeriesPlotMatplotlibParityTests(
SeriesPlotMatplotlibTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43711): Fix Transformer.transform to work with Spark Connect.")
def test_hist(self):
super().test_hist()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43711): Fix Transformer.transform to work with Spark Connect.")
def test_hist_plot(self):
super().test_hist_plot()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43629): Enable RDD with Spark Connect.")
def test_kde_plot(self):
super().test_kde_plot()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43712): Enable SeriesPlotMatplotlibParityTests.test_line_plot.")
def test_line_plot(self):
super().test_line_plot()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43713): Enable SeriesPlotMatplotlibParityTests.test_pie_plot.")
def test_pie_plot(self):
super().test_pie_plot()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43711): Fix Transformer.transform to work with Spark Connect.")
def test_single_value_hist(self):
super().test_single_value_hist()
diff --git a/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_plotly.py b/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_plotly.py
index 256f1a555f0..5ced8cb226e 100644
--- a/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_plotly.py
+++ b/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_plotly.py
@@ -24,11 +24,11 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class SeriesPlotPlotlyParityTests(
SeriesPlotPlotlyTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43711): Fix Transformer.transform to work with Spark Connect.")
def test_hist_plot(self):
super().test_hist_plot()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43629): Enable RDD with Spark Connect.")
def test_kde_plot(self):
super().test_kde_plot()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_categorical.py b/python/pyspark/pandas/tests/connect/test_parity_categorical.py
index ef62440e597..3e05eb2c0f3 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_categorical.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_categorical.py
@@ -29,31 +29,33 @@ class CategoricalParityTests(
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_astype(self):
super().test_astype()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_factorize(self):
super().test_factorize()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_remove_categories(self):
super().test_remove_categories()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_remove_unused_categories(self):
super().test_remove_unused_categories()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_reorder_categories(self):
super().test_reorder_categories()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_set_categories(self):
super().test_set_categories()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_unstack(self):
super().test_unstack()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_dataframe.py b/python/pyspark/pandas/tests/connect/test_parity_dataframe.py
index 63452f8bd12..c1b9ae2ee11 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_dataframe.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_dataframe.py
@@ -27,98 +27,117 @@ class DataFrameParityTests(DataFrameTestsMixin, PandasOnSparkTestUtils, ReusedCo
def psdf(self):
return ps.from_pandas(self.pdf)
- # "Spark Connect does not depend on JVM but the tests depend on SparkSession._jvm."
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_aggregate(self):
super().test_aggregate()
- # TODO(SPARK-41876): Implement DataFrame `toLocalIterator`
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-41876): Implement DataFrame `toLocalIterator`")
def test_iterrows(self):
super().test_iterrows()
- # TODO(SPARK-41876): Implement DataFrame `toLocalIterator`
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-41876): Implement DataFrame `toLocalIterator`")
def test_itertuples(self):
super().test_itertuples()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummax(self):
super().test_cummax()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummax_multiindex_columns(self):
super().test_cummax_multiindex_columns()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummin(self):
super().test_cummin()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummin_multiindex_columns(self):
super().test_cummin_multiindex_columns()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumprod(self):
super().test_cumprod()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumprod_multiindex_columns(self):
super().test_cumprod_multiindex_columns()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumsum(self):
super().test_cumsum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumsum_multiindex_columns(self):
super().test_cumsum_multiindex_columns()
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_cummax(self):
- super().test_cummax()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_cummax(self):
- super().test_cummax()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_cummax(self):
- super().test_cummax()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43616): Enable pyspark.pandas.spark.functions.repeat in Spark Connect."
+ )
def test_binary_operator_multiply(self):
super().test_binary_operator_multiply()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43622): Enable pyspark.pandas.spark.functions.var in Spark Connect.")
def test_dataframe(self):
super().test_dataframe()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_fillna(self):
return super().test_fillna()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_pivot_table(self):
super().test_pivot_table()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_pivot_table_dtypes(self):
super().test_pivot_table_dtypes()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_reset_index_with_default_index_types(self):
super().test_reset_index_with_default_index_types()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_transpose(self):
super().test_transpose()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_unstack(self):
super().test_unstack()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_append(self):
super().test_append()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_dataframe_slow.py b/python/pyspark/pandas/tests/connect/test_parity_dataframe_slow.py
index 898247da6e3..5876be3b4d0 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_dataframe_slow.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_dataframe_slow.py
@@ -29,75 +29,87 @@ class DataFrameSlowParityTests(
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_at_time(self):
super().test_at_time()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_backfill(self):
super().test_backfill()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_between_time(self):
super().test_between_time()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_bfill(self):
super().test_bfill()
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_cache(self):
- super().test_cache()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43613): Enable pyspark.pandas.spark.functions.covar in Spark Connect."
+ )
def test_cov(self):
super().test_cov()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_diff(self):
super().test_diff()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43615): Enable DataFrameSlowParityTests.test_eval.")
def test_eval(self):
super().test_eval()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_ffill(self):
super().test_ffill()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43616): Enable pyspark.pandas.spark.functions.mode in Spark Connect."
+ )
def test_mode(self):
super().test_mode()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_pad(self):
super().test_pad()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_pct_change(self):
super().test_pct_change()
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_persist(self):
- super().test_persist()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43617): Enable pyspark.pandas.spark.functions.product in Spark Connect."
+ )
def test_product(self):
super().test_product()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43618): Fix pyspark.sq.column._unary_op to work with Spark Connect.")
def test_rank(self):
super().test_rank()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_shift(self):
super().test_shift()
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_style(self):
- super().test_style()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43619): Enable DataFrameSlowParityTests.test_udt.")
def test_udt(self):
super().test_udt()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_default_index.py b/python/pyspark/pandas/tests/connect/test_parity_default_index.py
index 2cb5591c923..9d8ebc5eb33 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_default_index.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_default_index.py
@@ -24,15 +24,21 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class DefaultIndexParityTests(
DefaultIndexTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_default_index_distributed(self):
super().test_default_index_distributed()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_default_index_sequence(self):
super().test_default_index_sequence()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43623): Enable DefaultIndexParityTests.test_index_distributed_sequence_cleanup."
+ )
def test_index_distributed_sequence_cleanup(self):
super().test_index_distributed_sequence_cleanup()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_ewm.py b/python/pyspark/pandas/tests/connect/test_parity_ewm.py
index 10686f3bdfc..0e13306fd79 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_ewm.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_ewm.py
@@ -22,11 +22,11 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class EWMParityTests(EWMTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase, TestUtils):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43624): Enable ExponentialMovingLike.mean with Spark Connect.")
def test_ewm_mean(self):
super().test_ewm_mean()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43624): Enable ExponentialMovingLike.mean with Spark Connect.")
def test_groupby_ewm_func(self):
super().test_groupby_ewm_func()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_expanding.py b/python/pyspark/pandas/tests/connect/test_parity_expanding.py
index bdbc29e9e14..d970530db29 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_expanding.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_expanding.py
@@ -24,83 +24,123 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class ExpandingParityTests(
ExpandingTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_expanding_count(self):
super().test_expanding_count()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43626): Enable pyspark.pandas.spark.functions.kurt in Spark Connect."
+ )
def test_expanding_kurt(self):
super().test_expanding_kurt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_expanding_max(self):
super().test_expanding_max()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_expanding_mean(self):
super().test_expanding_mean()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_expanding_min(self):
super().test_expanding_min()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_expanding_quantile(self):
super().test_expanding_quantile()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43627): Enable pyspark.pandas.spark.functions.skew in Spark Connect."
+ )
def test_expanding_skew(self):
super().test_expanding_skew()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_expanding_std(self):
super().test_expanding_std()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_expanding_sum(self):
super().test_expanding_sum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_expanding_var(self):
super().test_expanding_var()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_count(self):
super().test_groupby_expanding_count()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43626): Enable pyspark.pandas.spark.functions.kurt in Spark Connect."
+ )
def test_groupby_expanding_kurt(self):
super().test_groupby_expanding_kurt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_max(self):
super().test_groupby_expanding_max()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_mean(self):
super().test_groupby_expanding_mean()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_min(self):
super().test_groupby_expanding_min()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_quantile(self):
super().test_groupby_expanding_quantile()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43627): Enable pyspark.pandas.spark.functions.skew in Spark Connect."
+ )
def test_groupby_expanding_skew(self):
super().test_groupby_expanding_skew()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_std(self):
super().test_groupby_expanding_std()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_sum(self):
super().test_groupby_expanding_sum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_var(self):
super().test_groupby_expanding_var()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_frame_spark.py b/python/pyspark/pandas/tests/connect/test_parity_frame_spark.py
index 0be30f43860..986ddde4db0 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_frame_spark.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_frame_spark.py
@@ -24,19 +24,19 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class SparkFrameMethodsParityTests(
SparkFrameMethodsTestsMixin, TestUtils, PandasOnSparkTestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43628): Enable SparkContext with Spark Connect.")
def test_checkpoint(self):
super().test_checkpoint()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43629): Enable RDD with Spark Connect.")
def test_coalesce(self):
super().test_coalesce()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43630): Implement `localCheckpoint` for Spark Connect DataFrame.")
def test_local_checkpoint(self):
super().test_local_checkpoint()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43629): Enable RDD with Spark Connect.")
def test_repartition(self):
super().test_repartition()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_generic_functions.py b/python/pyspark/pandas/tests/connect/test_parity_generic_functions.py
index 669e078f23c..39934798533 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_generic_functions.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_generic_functions.py
@@ -24,15 +24,19 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class GenericFunctionsParityTests(
GenericFunctionsTestsMixin, TestUtils, PandasOnSparkTestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43631): Enable Series.interpolate with Spark Connect.")
def test_interpolate(self):
super().test_interpolate()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43617): Enable pyspark.pandas.spark.functions.product in Spark Connect."
+ )
def test_prod_precision(self):
super().test_prod_precision()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43617): Enable pyspark.pandas.spark.functions.product in Spark Connect."
+ )
def test_stat_functions(self):
super().test_stat_functions()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_groupby.py b/python/pyspark/pandas/tests/connect/test_parity_groupby.py
index f6f9c1dac7c..b7a1cfa9e9f 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_groupby.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_groupby.py
@@ -24,55 +24,79 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class GroupByParityTests(
GroupByTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43628): Enable SparkContext with Spark Connect.")
def test_apply_with_side_effect(self):
super().test_apply_with_side_effect()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43622): Enable pyspark.pandas.spark.functions.covar in Spark Connect."
+ )
def test_basic_stat_funcs(self):
super().test_basic_stat_funcs()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_bfill(self):
super().test_bfill()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumcount(self):
super().test_cumcount()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummax(self):
super().test_cummax()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummin(self):
super().test_cummin()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumprod(self):
super().test_cumprod()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumsum(self):
super().test_cumsum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43645): Enable pyspark.pandas.spark.functions.stddev in Spark Connect."
+ )
def test_ddof(self):
super().test_ddof()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_ffill(self):
super().test_ffill()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_fillna(self):
super().test_fillna()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43617): Enable pyspark.pandas.spark.functions.product in Spark Connect."
+ )
def test_prod(self):
super().test_prod()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_shift(self):
super().test_shift()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_groupby_slow.py b/python/pyspark/pandas/tests/connect/test_parity_groupby_slow.py
index 375dc703d95..797a9622874 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_groupby_slow.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_groupby_slow.py
@@ -24,19 +24,25 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class GroupBySlowParityTests(
GroupBySlowTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_diff(self):
super().test_diff()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43645): Enable pyspark.pandas.spark.functions.stddev in Spark Connect."
+ )
def test_dropna(self):
super().test_dropna()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43652): Enable GroupBy.rank with Spark Connect.")
def test_rank(self):
super().test_rank()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43653): Enable GroupBySlowParityTests.test_split_apply_combine_on_series."
+ )
def test_split_apply_combine_on_series(self):
super().test_split_apply_combine_on_series()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_internal.py b/python/pyspark/pandas/tests/connect/test_parity_internal.py
index 65147bd3d44..d586fec57f7 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_internal.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_internal.py
@@ -24,7 +24,7 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class InternalFrameParityTests(
InternalFrameTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43654): Enable InternalFrameParityTests.test_from_pandas.")
def test_from_pandas(self):
super().test_from_pandas()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_namespace.py b/python/pyspark/pandas/tests/connect/test_parity_namespace.py
index e056c7dee1e..72f638ca23c 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_namespace.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_namespace.py
@@ -22,15 +22,19 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class NamespaceParityTests(NamespaceTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_concat_index_axis(self):
super().test_concat_index_axis()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_concat_multiindex_sort(self):
super().test_concat_multiindex_sort()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43655): Enable NamespaceParityTests.test_get_index_map.")
def test_get_index_map(self):
super().test_get_index_map()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_numpy_compat.py b/python/pyspark/pandas/tests/connect/test_parity_numpy_compat.py
index 5544866236d..1bfeda035a4 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_numpy_compat.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_numpy_compat.py
@@ -35,11 +35,15 @@ class NumPyCompatParityTests(NumPyCompatTestsMixin, PandasOnSparkTestUtils, Reus
def psdf(self):
return ps.from_pandas(self.pdf)
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43656): Fix pyspark.sql.column._to_java_column to accept Connect Column."
+ )
def test_np_spark_compat_frame(self):
super().test_np_spark_compat_frame()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43656): Fix pyspark.sql.column._to_java_column to accept Connect Column."
+ )
def test_np_spark_compat_series(self):
super().test_np_spark_compat_series()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby.py b/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby.py
index daeeda53f52..5d6b6a80b9b 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby.py
@@ -24,39 +24,51 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class OpsOnDiffFramesGroupByParityTests(
OpsOnDiffFramesGroupByTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumcount(self):
super().test_cumcount()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummax(self):
super().test_cummax()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummin(self):
super().test_cummin()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumprod(self):
super().test_cumprod()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumsum(self):
super().test_cumsum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_diff(self):
super().test_diff()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_fillna(self):
super().test_fillna()
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_fillna(self):
- super().test_fillna()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_shift(self):
super().test_shift()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_expanding.py b/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_expanding.py
index dbb5f00a0c6..90fa36f3b98 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_expanding.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_expanding.py
@@ -29,31 +29,45 @@ class OpsOnDiffFramesGroupByExpandingParityTests(
TestUtils,
ReusedConnectTestCase,
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_count(self):
super().test_groupby_expanding_count()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_min(self):
super().test_groupby_expanding_min()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_max(self):
super().test_groupby_expanding_max()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_mean(self):
super().test_groupby_expanding_mean()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_sum(self):
super().test_groupby_expanding_sum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_std(self):
super().test_groupby_expanding_std()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_expanding_var(self):
super().test_groupby_expanding_var()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_rolling.py b/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_rolling.py
index 910ec2c8bd5..dd82e443256 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_rolling.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_rolling.py
@@ -29,31 +29,45 @@ class OpsOnDiffFramesGroupByRollingParityTests(
TestUtils,
ReusedConnectTestCase,
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_count(self):
super().test_groupby_rolling_count()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_min(self):
super().test_groupby_rolling_min()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_max(self):
super().test_groupby_rolling_max()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_mean(self):
super().test_groupby_rolling_mean()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_sum(self):
super().test_groupby_rolling_sum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_std(self):
super().test_groupby_rolling_std()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_var(self):
super().test_groupby_rolling_var()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_slow.py b/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_slow.py
index e14686adf30..c9713d1905d 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_slow.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_slow.py
@@ -24,31 +24,43 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class OpsOnDiffFramesEnabledSlowParityTests(
OpsOnDiffFramesEnabledSlowTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43613): Enable pyspark.pandas.spark.functions.covar in Spark Connect."
+ )
def test_cov(self):
super().test_cov()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_diff(self):
super().test_diff()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43658): Fix unexpected `SparkConnectGrpcException` from Spark Connect client."
+ )
def test_frame_iloc_setitem(self):
super().test_frame_iloc_setitem()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43652): Enable GroupBy.rank with Spark Connect.")
def test_rank(self):
super().test_rank()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43659): Enable OpsOnDiffFramesEnabledSlowParityTests.test_series_eq."
+ )
def test_series_eq(self):
super().test_series_eq()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43658): Fix unexpected `SparkConnectGrpcException` from Spark Connect client."
+ )
def test_series_iloc_setitem(self):
super().test_series_iloc_setitem()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_shift(self):
super().test_shift()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_resample.py b/python/pyspark/pandas/tests/connect/test_parity_resample.py
index cd4b125b1b4..ab3e7f4410b 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_resample.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_resample.py
@@ -24,11 +24,11 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class ResampleTestsParityMixin(
ResampleTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43660): Enable `resample` with Spark Connect.")
def test_dataframe_resample(self):
super().test_dataframe_resample()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43660): Enable `resample` with Spark Connect.")
def test_series_resample(self):
super().test_series_resample()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_reshape.py b/python/pyspark/pandas/tests/connect/test_parity_reshape.py
index 2d8f856e9ed..e221ff82fa4 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_reshape.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_reshape.py
@@ -22,11 +22,11 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class ReshapeParityTests(ReshapeTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43661): Enable ReshapeParityTests.test_get_dummies_date_datetime.")
def test_get_dummies_date_datetime(self):
super().test_get_dummies_date_datetime()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43662): Enable ReshapeParityTests.test_merge_asof.")
def test_merge_asof(self):
super().test_merge_asof()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_rolling.py b/python/pyspark/pandas/tests/connect/test_parity_rolling.py
index cb82b4d6dc9..77b56c50b91 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_rolling.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_rolling.py
@@ -24,83 +24,123 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils, TestUtils
class RollingParityTests(
RollingTestsMixin, PandasOnSparkTestUtils, TestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_count(self):
super().test_groupby_rolling_count()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43626): Enable pyspark.pandas.spark.functions.kurt in Spark Connect."
+ )
def test_groupby_rolling_kurt(self):
super().test_groupby_rolling_kurt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_max(self):
super().test_groupby_rolling_max()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_mean(self):
super().test_groupby_rolling_mean()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_min(self):
super().test_groupby_rolling_min()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_quantile(self):
super().test_groupby_rolling_quantile()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43627): Enable pyspark.pandas.spark.functions.skew in Spark Connect."
+ )
def test_groupby_rolling_skew(self):
super().test_groupby_rolling_skew()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_std(self):
super().test_groupby_rolling_std()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_sum(self):
super().test_groupby_rolling_sum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_groupby_rolling_var(self):
super().test_groupby_rolling_var()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_rolling_count(self):
super().test_rolling_count()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43626): Enable pyspark.pandas.spark.functions.kurt in Spark Connect."
+ )
def test_rolling_kurt(self):
super().test_rolling_kurt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_rolling_max(self):
super().test_rolling_max()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_rolling_mean(self):
super().test_rolling_mean()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_rolling_min(self):
super().test_rolling_min()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_rolling_quantile(self):
super().test_rolling_quantile()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43627): Enable pyspark.pandas.spark.functions.skew in Spark Connect."
+ )
def test_rolling_skew(self):
super().test_rolling_skew()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_rolling_std(self):
super().test_rolling_std()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_rolling_sum(self):
super().test_rolling_sum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_rolling_var(self):
super().test_rolling_var()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_series.py b/python/pyspark/pandas/tests/connect/test_parity_series.py
index b1b5da3f69f..35a9ba1fca4 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_series.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_series.py
@@ -22,111 +22,151 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class SeriesParityTests(SeriesTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_argsort(self):
super().test_argsort()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_asof(self):
super().test_asof()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_at_time(self):
super().test_at_time()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_backfill(self):
super().test_backfill()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43610): Enable `InternalFrame.attach_distributed_column` in Spark Connect."
+ )
def test_between_time(self):
super().test_between_time()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_bfill(self):
super().test_bfill()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43663): Enable SeriesParityTests.test_compare.")
def test_compare(self):
super().test_compare()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43613): Enable pyspark.pandas.spark.functions.covar in Spark Connect."
+ )
def test_cov(self):
super().test_cov()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummax(self):
super().test_cummax()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cummin(self):
super().test_cummin()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumprod(self):
super().test_cumprod()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_cumsum(self):
super().test_cumsum()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_diff(self):
super().test_diff()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43620): Support `Column` for SparkConnectColumn.__getitem__.")
def test_factorize(self):
super().test_factorize()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_ffill(self):
super().test_ffill()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_fillna(self):
super().test_fillna()
- @unittest.skip("Fails in Spark Connect, should enable.")
- def test_iteritems(self):
- super().test_iteritems()
-
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43616): Enable pyspark.pandas.spark.functions.mode in Spark Connect."
+ )
def test_mode(self):
super().test_mode()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_pad(self):
super().test_pad()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_pct_change(self):
super().test_pct_change()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43617): Enable pyspark.pandas.spark.functions.product in Spark Connect."
+ )
def test_product(self):
super().test_product()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43618): Fix pyspark.sq.column._unary_op to work with Spark Connect.")
def test_rank(self):
super().test_rank()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_replace(self):
super().test_replace()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_reset_index_with_default_index_types(self):
super().test_reset_index_with_default_index_types()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_shift(self):
super().test_shift()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43619): Enable DataFrameSlowParityTests.test_udt.")
def test_udt(self):
super().test_udt()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43611): Fix unexpected `AnalysisException` from Spark Connect client."
+ )
def test_unstack(self):
super().test_unstack()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_series_string.py b/python/pyspark/pandas/tests/connect/test_parity_series_string.py
index 9f170a65494..c8e529d9df0 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_series_string.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_series_string.py
@@ -24,7 +24,9 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class SeriesStringParityTests(
SeriesStringTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase
):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43621): Enable pyspark.pandas.spark.functions.repeat in Spark Connect."
+ )
def test_string_repeat(self):
super().test_string_repeat()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_sql.py b/python/pyspark/pandas/tests/connect/test_parity_sql.py
index 5afda98929f..6c2979f785a 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_sql.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_sql.py
@@ -22,15 +22,17 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class SQLParityTests(SQLTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43664): Fix TABLE_OR_VIEW_NOT_FOUND from SQLParityTests.")
def test_sql_with_index_col(self):
super().test_sql_with_index_col()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip("TODO(SPARK-43664): Fix TABLE_OR_VIEW_NOT_FOUND from SQLParityTests.")
def test_sql_with_pandas_on_spark_objects(self):
super().test_sql_with_pandas_on_spark_objects()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43665): Enable PandasSQLStringFormatter.vformat to work with Spark Connect."
+ )
def test_sql_with_python_objects(self):
super().test_sql_with_python_objects()
diff --git a/python/pyspark/pandas/tests/connect/test_parity_stats.py b/python/pyspark/pandas/tests/connect/test_parity_stats.py
index 0b354b58953..d9a8bf8e31a 100644
--- a/python/pyspark/pandas/tests/connect/test_parity_stats.py
+++ b/python/pyspark/pandas/tests/connect/test_parity_stats.py
@@ -22,35 +22,51 @@ from pyspark.testing.pandasutils import PandasOnSparkTestUtils
class StatsParityTests(StatsTestsMixin, PandasOnSparkTestUtils, ReusedConnectTestCase):
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43626): Enable pyspark.pandas.spark.functions.kurt in Spark Connect."
+ )
def test_axis_on_dataframe(self):
super().test_axis_on_dataframe()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43617): Enable pyspark.pandas.spark.functions.product in Spark Connect."
+ )
def test_product(self):
super().test_product()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43627): Enable pyspark.pandas.spark.functions.skew in Spark Connect."
+ )
def test_skew_kurt_numerical_stability(self):
super().test_skew_kurt_numerical_stability()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43645): Enable pyspark.pandas.spark.functions.stddev in Spark Connect."
+ )
def test_stat_functions(self):
super().test_stat_functions()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43645): Enable pyspark.pandas.spark.functions.stddev in Spark Connect."
+ )
def test_stat_functions_multiindex_column(self):
super().test_stat_functions_multiindex_column()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43617): Enable pyspark.pandas.spark.functions.product in Spark Connect."
+ )
def test_stats_on_boolean_dataframe(self):
super().test_stats_on_boolean_dataframe()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43617): Enable pyspark.pandas.spark.functions.product in Spark Connect."
+ )
def test_stats_on_boolean_series(self):
super().test_stats_on_boolean_series()
- @unittest.skip("Fails in Spark Connect, should enable.")
+ @unittest.skip(
+ "TODO(SPARK-43617): Enable pyspark.pandas.spark.functions.product in Spark Connect."
+ )
def test_stats_on_non_numeric_columns_should_be_discarded_if_numeric_only_is_true(self):
super().test_stats_on_non_numeric_columns_should_be_discarded_if_numeric_only_is_true()
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org