Remove random_state arg from get_pipelines in AutoMLSearch #1719
Conversation
Codecov Report
@@ Coverage Diff @@
## main #1719 +/- ##
=========================================
+ Coverage 100.0% 100.0% +0.1%
=========================================
Files 243 243
Lines 19435 19445 +10
=========================================
+ Hits 19426 19436 +10
Misses 9 9
Continue to review full report at Codecov.
|
bchen1116
requested review from
ParthivNaresh,
angela97lin,
christopherbunn,
chukarsten,
dsherry,
freddyaboulton and
jeremyliweishih
|
Will need to resolve this issue to remove support for |
freddyaboulton
left a comment
freddyaboulton
left a comment
There was a problem hiding this comment.
@bchen1116 Awesome! 🤩
| assert row['parameters']['Decision Tree Classifier']['max_depth'] == 1 | ||
|
|
||
|
|
||
| @pytest.mark.parametrize("random_state", [0, 1, 9]) |
There was a problem hiding this comment.
So fresh and so clean. Awesome.
| automl.search() | ||
|
|
||
| for i, row in automl.rankings.iterrows(): | ||
| if 'Base' not in list(row['parameters'].keys())[0]: |
There was a problem hiding this comment.
O same question as other PR LOL, why the check for Base here :o
There was a problem hiding this comment.
The baseline pipeline isn't initialized with a random_state arg, so we can't check for random state here
fix #1638