ibzib commented on a change in pull request #13853:
URL: https://github.com/apache/beam/pull/13853#discussion_r571321954
##########
File path: sdks/python/apache_beam/dataframe/frames_test.py
##########
@@ -182,14 +194,53 @@ def test_groupby_project(self):
self._run_test(lambda df: df.groupby('group')['foo'].median(), df)
self._run_test(lambda df: df.groupby('group')['baz'].median(), df)
self._run_test(lambda df: df.groupby('group')[['bar', 'baz']].median(), df)
+
+ def test_groupby_errors(self):
+ df = pd.DataFrame({
+ 'group': ['a' if i % 5 == 0 or i % 3 == 0 else 'b' for i in
range(100)],
+ 'foo': [None if i % 11 == 0 else i for i in range(100)],
+ 'bar': [None if i % 7 == 0 else 99 - i for i in range(100)],
+ 'baz': [None if i % 13 == 0 else i * 2 for i in range(100)],
+ })
+
+ # non-existent projection column
self._run_test(
lambda df: df.groupby('group')[['bar', 'baz']].bar.median(),
df,
expect_error=True)
self._run_test(
- lambda df: df.groupby('group')[['bat']].median(), df,
expect_error=True)
+ lambda df: df.groupby('group')[['bad']].median(), df,
expect_error=True)
+
+ self._run_test(
+ lambda df: df.groupby('group').bad.median(), df, expect_error=True)
+
+ # non-existent grouping label
+ self._run_test(
+ lambda df: df.groupby(['really_bad', 'foo', 'bad']).foo.sum(),
+ df,
+ expect_error=True)
+ self._run_test(
+ lambda df: df.groupby('bad').foo.sum(), df, expect_error=True)
+
+ def test_set_index(self):
+ df = pd.DataFrame({
+ # Generate some unique columns to use for indexes
Review comment:
Thanks, 20 is a lot more manageable. I'm curious though, isn't there a
way to force partitions even on small inputs?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
