This is an automated email from the ASF dual-hosted git repository. dongjoon 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 a56ca8a673d7 [SPARK-46271][PS][TESTS] Remove unused properties in `pyspark.pandas.tests.groupby.*` a56ca8a673d7 is described below commit a56ca8a673d7a0ce85a5f01e51c76d8dae81804a Author: Ruifeng Zheng <ruife...@apache.org> AuthorDate: Tue Dec 5 10:17:19 2023 -0800 [SPARK-46271][PS][TESTS] Remove unused properties in `pyspark.pandas.tests.groupby.*` ### What changes were proposed in this pull request? remove unused properties in `pyspark.pandas.tests.groupby.*` ### Why are the changes needed? just code clean up ### Does this PR introduce _any_ user-facing change? no ### How was this patch tested? ci ### Was this patch authored or co-authored using generative AI tooling? no Closes #44188 from zhengruifeng/ps_test_cleanup. Authored-by: Ruifeng Zheng <ruife...@apache.org> Signed-off-by: Dongjoon Hyun <dh...@apple.com> --- python/pyspark/pandas/tests/groupby/test_aggregate.py | 15 --------------- python/pyspark/pandas/tests/groupby/test_apply_func.py | 15 --------------- python/pyspark/pandas/tests/groupby/test_cumulative.py | 15 --------------- python/pyspark/pandas/tests/groupby/test_describe.py | 15 --------------- python/pyspark/pandas/tests/groupby/test_groupby.py | 15 --------------- python/pyspark/pandas/tests/groupby/test_head_tail.py | 15 --------------- python/pyspark/pandas/tests/groupby/test_index.py | 15 --------------- python/pyspark/pandas/tests/groupby/test_missing_data.py | 15 --------------- python/pyspark/pandas/tests/groupby/test_split_apply.py | 15 --------------- 9 files changed, 135 deletions(-) diff --git a/python/pyspark/pandas/tests/groupby/test_aggregate.py b/python/pyspark/pandas/tests/groupby/test_aggregate.py index 9e7f3f6cd113..f6fb37aa9824 100644 --- a/python/pyspark/pandas/tests/groupby/test_aggregate.py +++ b/python/pyspark/pandas/tests/groupby/test_aggregate.py @@ -24,21 +24,6 @@ from pyspark.testing.sqlutils import SQLTestUtils class GroupbyAggregateMixin: - @property - def pdf(self): - return pd.DataFrame( - { - "A": [1, 2, 1, 2], - "B": [3.1, 4.1, 4.1, 3.1], - "C": ["a", "b", "b", "a"], - "D": [True, False, False, True], - } - ) - - @property - def psdf(self): - return ps.from_pandas(self.pdf) - def test_aggregate(self): pdf = pd.DataFrame( {"A": [1, 1, 2, 2], "B": [1, 2, 3, 4], "C": [0.362, 0.227, 1.267, -0.562]} diff --git a/python/pyspark/pandas/tests/groupby/test_apply_func.py b/python/pyspark/pandas/tests/groupby/test_apply_func.py index e7a30ff57b41..d886d8799444 100644 --- a/python/pyspark/pandas/tests/groupby/test_apply_func.py +++ b/python/pyspark/pandas/tests/groupby/test_apply_func.py @@ -26,21 +26,6 @@ from pyspark.testing.sqlutils import SQLTestUtils class GroupbyApplyFuncMixin: - @property - def pdf(self): - return pd.DataFrame( - { - "A": [1, 2, 1, 2], - "B": [3.1, 4.1, 4.1, 3.1], - "C": ["a", "b", "b", "a"], - "D": [True, False, False, True], - } - ) - - @property - def psdf(self): - return ps.from_pandas(self.pdf) - def test_apply(self): pdf = pd.DataFrame( {"a": [1, 2, 3, 4, 5, 6], "b": [1, 1, 2, 3, 5, 8], "c": [1, 4, 9, 16, 25, 36]}, diff --git a/python/pyspark/pandas/tests/groupby/test_cumulative.py b/python/pyspark/pandas/tests/groupby/test_cumulative.py index 64d6812c7bcf..2bcc1ade2d06 100644 --- a/python/pyspark/pandas/tests/groupby/test_cumulative.py +++ b/python/pyspark/pandas/tests/groupby/test_cumulative.py @@ -26,21 +26,6 @@ from pyspark.testing.sqlutils import SQLTestUtils class GroupbyCumulativeMixin: - @property - def pdf(self): - return pd.DataFrame( - { - "A": [1, 2, 1, 2], - "B": [3.1, 4.1, 4.1, 3.1], - "C": ["a", "b", "b", "a"], - "D": [True, False, False, True], - } - ) - - @property - def psdf(self): - return ps.from_pandas(self.pdf) - def test_cumcount(self): pdf = pd.DataFrame( { diff --git a/python/pyspark/pandas/tests/groupby/test_describe.py b/python/pyspark/pandas/tests/groupby/test_describe.py index dcd0e33a3811..ae12aae61ffc 100644 --- a/python/pyspark/pandas/tests/groupby/test_describe.py +++ b/python/pyspark/pandas/tests/groupby/test_describe.py @@ -25,21 +25,6 @@ from pyspark.testing.sqlutils import SQLTestUtils class GroupbyDescribeMixin: - @property - def pdf(self): - return pd.DataFrame( - { - "A": [1, 2, 1, 2], - "B": [3.1, 4.1, 4.1, 3.1], - "C": ["a", "b", "b", "a"], - "D": [True, False, False, True], - } - ) - - @property - def psdf(self): - return ps.from_pandas(self.pdf) - def test_describe(self): # support for numeric type, not support for string type yet datas = [] diff --git a/python/pyspark/pandas/tests/groupby/test_groupby.py b/python/pyspark/pandas/tests/groupby/test_groupby.py index 7499ba7f5a1d..4ef2d1acd811 100644 --- a/python/pyspark/pandas/tests/groupby/test_groupby.py +++ b/python/pyspark/pandas/tests/groupby/test_groupby.py @@ -32,21 +32,6 @@ from pyspark.testing.pandasutils import PandasOnSparkTestCase, TestUtils class GroupByTestsMixin: - @property - def pdf(self): - return pd.DataFrame( - { - "A": [1, 2, 1, 2], - "B": [3.1, 4.1, 4.1, 3.1], - "C": ["a", "b", "b", "a"], - "D": [True, False, False, True], - } - ) - - @property - def psdf(self): - return ps.from_pandas(self.pdf) - def test_groupby_simple(self): pdf = pd.DataFrame( { diff --git a/python/pyspark/pandas/tests/groupby/test_head_tail.py b/python/pyspark/pandas/tests/groupby/test_head_tail.py index 6f69b0bdee00..68a364103e06 100644 --- a/python/pyspark/pandas/tests/groupby/test_head_tail.py +++ b/python/pyspark/pandas/tests/groupby/test_head_tail.py @@ -25,21 +25,6 @@ from pyspark.testing.sqlutils import SQLTestUtils class GroupbyHeadTailMixin: - @property - def pdf(self): - return pd.DataFrame( - { - "A": [1, 2, 1, 2], - "B": [3.1, 4.1, 4.1, 3.1], - "C": ["a", "b", "b", "a"], - "D": [True, False, False, True], - } - ) - - @property - def psdf(self): - return ps.from_pandas(self.pdf) - def test_head(self): pdf = pd.DataFrame( { diff --git a/python/pyspark/pandas/tests/groupby/test_index.py b/python/pyspark/pandas/tests/groupby/test_index.py index 9219a65d2cb4..f83ae615161f 100644 --- a/python/pyspark/pandas/tests/groupby/test_index.py +++ b/python/pyspark/pandas/tests/groupby/test_index.py @@ -24,21 +24,6 @@ from pyspark.testing.sqlutils import SQLTestUtils class GroupbyIndexMixin: - @property - def pdf(self): - return pd.DataFrame( - { - "A": [1, 2, 1, 2], - "B": [3.1, 4.1, 4.1, 3.1], - "C": ["a", "b", "b", "a"], - "D": [True, False, False, True], - } - ) - - @property - def psdf(self): - return ps.from_pandas(self.pdf) - def test_groupby_multiindex_columns(self): pdf = pd.DataFrame( { diff --git a/python/pyspark/pandas/tests/groupby/test_missing_data.py b/python/pyspark/pandas/tests/groupby/test_missing_data.py index e91b77ebf8c9..3d54baf7e84e 100644 --- a/python/pyspark/pandas/tests/groupby/test_missing_data.py +++ b/python/pyspark/pandas/tests/groupby/test_missing_data.py @@ -26,21 +26,6 @@ from pyspark.testing.sqlutils import SQLTestUtils class GroupbyMissingDataMixin: - @property - def pdf(self): - return pd.DataFrame( - { - "A": [1, 2, 1, 2], - "B": [3.1, 4.1, 4.1, 3.1], - "C": ["a", "b", "b", "a"], - "D": [True, False, False, True], - } - ) - - @property - def psdf(self): - return ps.from_pandas(self.pdf) - def test_fillna(self): pdf = pd.DataFrame( { diff --git a/python/pyspark/pandas/tests/groupby/test_split_apply.py b/python/pyspark/pandas/tests/groupby/test_split_apply.py index e8648c9b0a84..13cdae94c0e3 100644 --- a/python/pyspark/pandas/tests/groupby/test_split_apply.py +++ b/python/pyspark/pandas/tests/groupby/test_split_apply.py @@ -24,21 +24,6 @@ from pyspark.testing.sqlutils import SQLTestUtils class GroupbySplitApplyMixin: - @property - def pdf(self): - return pd.DataFrame( - { - "A": [1, 2, 1, 2], - "B": [3.1, 4.1, 4.1, 3.1], - "C": ["a", "b", "b", "a"], - "D": [True, False, False, True], - } - ) - - @property - def psdf(self): - return ps.from_pandas(self.pdf) - def test_split_apply_combine_on_series(self): # TODO(SPARK-45228): Enabling string type columns for `test_split_apply_combine_on_series` # when Pandas regression is fixed --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org