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 2024/01/15 07:11:14 UTC
(spark) branch master updated: [SPARK-46719][PS][TESTS] Rebalance `pyspark_pandas` and `pyspark_pandas_slow`
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 ee0d243f0141 [SPARK-46719][PS][TESTS] Rebalance `pyspark_pandas` and `pyspark_pandas_slow`
ee0d243f0141 is described below
commit ee0d243f014176ede9d8cf8296f9a2df1798920b
Author: Ruifeng Zheng <ru...@apache.org>
AuthorDate: Mon Jan 15 15:10:55 2024 +0800
[SPARK-46719][PS][TESTS] Rebalance `pyspark_pandas` and `pyspark_pandas_slow`
### What changes were proposed in this pull request?
Rebalance `pyspark_pandas` and `pyspark_pandas_slow`
### Why are the changes needed?
before:
`pyspark_pandas`: `Tests passed in 1849 seconds`
`pyspark_pandas-slow`: `Tests passed in 3538 seconds`
after:
`pyspark_pandas`: `Tests passed in 2733 seconds`
`pyspark_pandas-slow`: `Tests passed in 2804 seconds`
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
ci, https://github.com/zhengruifeng/spark/actions/runs/7524159324/job/20478674209
### Was this patch authored or co-authored using generative AI tooling?
no
Closes #44731 from zhengruifeng/infra_rebalance_ps_test.
Authored-by: Ruifeng Zheng <ru...@apache.org>
Signed-off-by: Ruifeng Zheng <ru...@apache.org>
---
dev/sparktestsupport/modules.py | 158 ++++++++++++++++++++--------------------
1 file changed, 79 insertions(+), 79 deletions(-)
diff --git a/dev/sparktestsupport/modules.py b/dev/sparktestsupport/modules.py
index 9cdbe4d250ca..202263febc93 100644
--- a/dev/sparktestsupport/modules.py
+++ b/dev/sparktestsupport/modules.py
@@ -699,6 +699,40 @@ pyspark_pandas = Module(
"pyspark.pandas.spark.utils",
"pyspark.pandas.typedef.typehints",
# unittests
+ "pyspark.pandas.tests.test_categorical",
+ "pyspark.pandas.tests.test_config",
+ "pyspark.pandas.tests.test_extension",
+ "pyspark.pandas.tests.test_frame_spark",
+ "pyspark.pandas.tests.test_generic_functions",
+ "pyspark.pandas.tests.test_indexops_spark",
+ "pyspark.pandas.tests.test_internal",
+ "pyspark.pandas.tests.test_namespace",
+ "pyspark.pandas.tests.test_numpy_compat",
+ "pyspark.pandas.tests.test_repr",
+ "pyspark.pandas.tests.test_spark_functions",
+ "pyspark.pandas.tests.test_scalars",
+ "pyspark.pandas.tests.test_sql",
+ "pyspark.pandas.tests.test_typedef",
+ "pyspark.pandas.tests.test_utils",
+ "pyspark.pandas.tests.computation.test_any_all",
+ "pyspark.pandas.tests.computation.test_apply_func",
+ "pyspark.pandas.tests.computation.test_binary_ops",
+ "pyspark.pandas.tests.computation.test_combine",
+ "pyspark.pandas.tests.computation.test_compute",
+ "pyspark.pandas.tests.computation.test_corr",
+ "pyspark.pandas.tests.computation.test_corrwith",
+ "pyspark.pandas.tests.computation.test_cov",
+ "pyspark.pandas.tests.computation.test_cumulative",
+ "pyspark.pandas.tests.computation.test_describe",
+ "pyspark.pandas.tests.computation.test_eval",
+ "pyspark.pandas.tests.computation.test_melt",
+ "pyspark.pandas.tests.computation.test_missing_data",
+ "pyspark.pandas.tests.computation.test_pivot",
+ "pyspark.pandas.tests.computation.test_pivot_table",
+ "pyspark.pandas.tests.computation.test_pivot_table_adv",
+ "pyspark.pandas.tests.computation.test_pivot_table_multi_idx",
+ "pyspark.pandas.tests.computation.test_pivot_table_multi_idx_adv",
+ "pyspark.pandas.tests.computation.test_stats",
"pyspark.pandas.tests.data_type_ops.test_as_type",
"pyspark.pandas.tests.data_type_ops.test_base",
"pyspark.pandas.tests.data_type_ops.test_binary_ops",
@@ -717,42 +751,26 @@ pyspark_pandas = Module(
"pyspark.pandas.tests.data_type_ops.test_string_ops",
"pyspark.pandas.tests.data_type_ops.test_udt_ops",
"pyspark.pandas.tests.data_type_ops.test_timedelta_ops",
- "pyspark.pandas.tests.indexes.test_category",
- "pyspark.pandas.tests.indexes.test_timedelta",
"pyspark.pandas.tests.plot.test_frame_plot",
"pyspark.pandas.tests.plot.test_frame_plot_matplotlib",
"pyspark.pandas.tests.plot.test_frame_plot_plotly",
"pyspark.pandas.tests.plot.test_series_plot",
"pyspark.pandas.tests.plot.test_series_plot_matplotlib",
"pyspark.pandas.tests.plot.test_series_plot_plotly",
- "pyspark.pandas.tests.test_categorical",
- "pyspark.pandas.tests.test_config",
- "pyspark.pandas.tests.indexes.test_default",
- "pyspark.pandas.tests.window.test_expanding",
- "pyspark.pandas.tests.window.test_expanding_adv",
- "pyspark.pandas.tests.window.test_expanding_error",
- "pyspark.pandas.tests.window.test_groupby_expanding",
- "pyspark.pandas.tests.window.test_groupby_expanding_adv",
- "pyspark.pandas.tests.test_extension",
- "pyspark.pandas.tests.window.test_ewm_error",
- "pyspark.pandas.tests.window.test_ewm_mean",
- "pyspark.pandas.tests.window.test_groupby_ewm_mean",
- "pyspark.pandas.tests.test_frame_spark",
- "pyspark.pandas.tests.test_generic_functions",
"pyspark.pandas.tests.frame.test_interpolate",
"pyspark.pandas.tests.frame.test_interpolate_error",
+ "pyspark.pandas.tests.frame.test_attrs",
+ "pyspark.pandas.tests.frame.test_axis",
+ "pyspark.pandas.tests.frame.test_constructor",
+ "pyspark.pandas.tests.frame.test_conversion",
+ "pyspark.pandas.tests.frame.test_reindexing",
+ "pyspark.pandas.tests.frame.test_reshaping",
+ "pyspark.pandas.tests.frame.test_spark",
+ "pyspark.pandas.tests.frame.test_take",
+ "pyspark.pandas.tests.frame.test_take_adv",
+ "pyspark.pandas.tests.frame.test_time_series",
+ "pyspark.pandas.tests.frame.test_truncate",
"pyspark.pandas.tests.series.test_interpolate",
- "pyspark.pandas.tests.test_indexops_spark",
- "pyspark.pandas.tests.test_internal",
- "pyspark.pandas.tests.test_namespace",
- "pyspark.pandas.tests.test_numpy_compat",
- "pyspark.pandas.tests.diff_frames_ops.test_groupby_expanding",
- "pyspark.pandas.tests.diff_frames_ops.test_groupby_expanding_adv",
- "pyspark.pandas.tests.diff_frames_ops.test_groupby_expanding_count",
- "pyspark.pandas.tests.diff_frames_ops.test_groupby_rolling",
- "pyspark.pandas.tests.diff_frames_ops.test_groupby_rolling_adv",
- "pyspark.pandas.tests.diff_frames_ops.test_groupby_rolling_count",
- "pyspark.pandas.tests.test_repr",
"pyspark.pandas.tests.resample.test_on",
"pyspark.pandas.tests.resample.test_error",
"pyspark.pandas.tests.resample.test_frame",
@@ -765,6 +783,14 @@ pyspark_pandas = Module(
"pyspark.pandas.tests.reshape.test_get_dummies_object",
"pyspark.pandas.tests.reshape.test_get_dummies_prefix",
"pyspark.pandas.tests.reshape.test_merge_asof",
+ "pyspark.pandas.tests.window.test_expanding",
+ "pyspark.pandas.tests.window.test_expanding_adv",
+ "pyspark.pandas.tests.window.test_expanding_error",
+ "pyspark.pandas.tests.window.test_groupby_expanding",
+ "pyspark.pandas.tests.window.test_groupby_expanding_adv",
+ "pyspark.pandas.tests.window.test_ewm_error",
+ "pyspark.pandas.tests.window.test_ewm_mean",
+ "pyspark.pandas.tests.window.test_groupby_ewm_mean",
"pyspark.pandas.tests.window.test_missing",
"pyspark.pandas.tests.window.test_rolling",
"pyspark.pandas.tests.window.test_rolling_adv",
@@ -773,14 +799,26 @@ pyspark_pandas = Module(
"pyspark.pandas.tests.window.test_groupby_rolling",
"pyspark.pandas.tests.window.test_groupby_rolling_adv",
"pyspark.pandas.tests.window.test_groupby_rolling_count",
- "pyspark.pandas.tests.test_scalars",
"pyspark.pandas.tests.series.test_datetime",
"pyspark.pandas.tests.series.test_string_ops_adv",
"pyspark.pandas.tests.series.test_string_ops_basic",
- "pyspark.pandas.tests.test_spark_functions",
- "pyspark.pandas.tests.test_sql",
- "pyspark.pandas.tests.test_typedef",
- "pyspark.pandas.tests.test_utils",
+ "pyspark.pandas.tests.series.test_all_any",
+ "pyspark.pandas.tests.series.test_arg_ops",
+ "pyspark.pandas.tests.series.test_as_of",
+ "pyspark.pandas.tests.series.test_as_type",
+ "pyspark.pandas.tests.series.test_compute",
+ "pyspark.pandas.tests.series.test_conversion",
+ "pyspark.pandas.tests.series.test_cumulative",
+ "pyspark.pandas.tests.series.test_index",
+ "pyspark.pandas.tests.series.test_missing_data",
+ "pyspark.pandas.tests.series.test_series",
+ "pyspark.pandas.tests.series.test_sort",
+ "pyspark.pandas.tests.series.test_stat",
+ "pyspark.pandas.tests.io.test_io",
+ "pyspark.pandas.tests.io.test_csv",
+ "pyspark.pandas.tests.io.test_dataframe_conversion",
+ "pyspark.pandas.tests.io.test_dataframe_spark_io",
+ "pyspark.pandas.tests.io.test_series_conversion",
],
excluded_python_implementations=[
"PyPy" # Skip these tests under PyPy since they require numpy, pandas, and pyarrow and
@@ -798,6 +836,9 @@ pyspark_pandas_slow = Module(
"pyspark.pandas.generic",
"pyspark.pandas.series",
# unittests
+ "pyspark.pandas.tests.indexes.test_default",
+ "pyspark.pandas.tests.indexes.test_category",
+ "pyspark.pandas.tests.indexes.test_timedelta",
"pyspark.pandas.tests.indexes.test_basic",
"pyspark.pandas.tests.indexes.test_getattr",
"pyspark.pandas.tests.indexes.test_name",
@@ -841,41 +882,6 @@ pyspark_pandas_slow = Module(
"pyspark.pandas.tests.indexes.test_reindex",
"pyspark.pandas.tests.indexes.test_rename",
"pyspark.pandas.tests.indexes.test_reset_index",
- "pyspark.pandas.tests.computation.test_any_all",
- "pyspark.pandas.tests.computation.test_apply_func",
- "pyspark.pandas.tests.computation.test_binary_ops",
- "pyspark.pandas.tests.computation.test_combine",
- "pyspark.pandas.tests.computation.test_compute",
- "pyspark.pandas.tests.computation.test_corr",
- "pyspark.pandas.tests.computation.test_corrwith",
- "pyspark.pandas.tests.computation.test_cov",
- "pyspark.pandas.tests.computation.test_cumulative",
- "pyspark.pandas.tests.computation.test_describe",
- "pyspark.pandas.tests.computation.test_eval",
- "pyspark.pandas.tests.computation.test_melt",
- "pyspark.pandas.tests.computation.test_missing_data",
- "pyspark.pandas.tests.computation.test_pivot",
- "pyspark.pandas.tests.computation.test_pivot_table",
- "pyspark.pandas.tests.computation.test_pivot_table_adv",
- "pyspark.pandas.tests.computation.test_pivot_table_multi_idx",
- "pyspark.pandas.tests.computation.test_pivot_table_multi_idx_adv",
- "pyspark.pandas.tests.computation.test_stats",
- "pyspark.pandas.tests.frame.test_attrs",
- "pyspark.pandas.tests.frame.test_axis",
- "pyspark.pandas.tests.frame.test_constructor",
- "pyspark.pandas.tests.frame.test_conversion",
- "pyspark.pandas.tests.frame.test_reindexing",
- "pyspark.pandas.tests.frame.test_reshaping",
- "pyspark.pandas.tests.frame.test_spark",
- "pyspark.pandas.tests.frame.test_take",
- "pyspark.pandas.tests.frame.test_take_adv",
- "pyspark.pandas.tests.frame.test_time_series",
- "pyspark.pandas.tests.frame.test_truncate",
- "pyspark.pandas.tests.io.test_io",
- "pyspark.pandas.tests.io.test_csv",
- "pyspark.pandas.tests.io.test_dataframe_conversion",
- "pyspark.pandas.tests.io.test_dataframe_spark_io",
- "pyspark.pandas.tests.io.test_series_conversion",
"pyspark.pandas.tests.groupby.test_aggregate",
"pyspark.pandas.tests.groupby.test_apply_func",
"pyspark.pandas.tests.groupby.test_cumulative",
@@ -936,18 +942,12 @@ pyspark_pandas_slow = Module(
"pyspark.pandas.tests.diff_frames_ops.test_groupby_shift",
"pyspark.pandas.tests.diff_frames_ops.test_groupby_split_apply_combine",
"pyspark.pandas.tests.diff_frames_ops.test_groupby_transform",
- "pyspark.pandas.tests.series.test_all_any",
- "pyspark.pandas.tests.series.test_arg_ops",
- "pyspark.pandas.tests.series.test_as_of",
- "pyspark.pandas.tests.series.test_as_type",
- "pyspark.pandas.tests.series.test_compute",
- "pyspark.pandas.tests.series.test_conversion",
- "pyspark.pandas.tests.series.test_cumulative",
- "pyspark.pandas.tests.series.test_index",
- "pyspark.pandas.tests.series.test_missing_data",
- "pyspark.pandas.tests.series.test_series",
- "pyspark.pandas.tests.series.test_sort",
- "pyspark.pandas.tests.series.test_stat",
+ "pyspark.pandas.tests.diff_frames_ops.test_groupby_expanding",
+ "pyspark.pandas.tests.diff_frames_ops.test_groupby_expanding_adv",
+ "pyspark.pandas.tests.diff_frames_ops.test_groupby_expanding_count",
+ "pyspark.pandas.tests.diff_frames_ops.test_groupby_rolling",
+ "pyspark.pandas.tests.diff_frames_ops.test_groupby_rolling_adv",
+ "pyspark.pandas.tests.diff_frames_ops.test_groupby_rolling_count",
],
excluded_python_implementations=[
"PyPy" # Skip these tests under PyPy since they require numpy, pandas, and pyarrow and
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org