QuantConnect / QuantConnect/Lean
[Library Upgrade] ray
Nobody has claimed this yet.
- Dominant language
- C#
- Stars
- 21.7k
- Forks
- 5.3k
- Avg merge
- 2d 22h
- Merged PRs (30d)
- 34
Description
Expected Behavior
autogluon.tabular.TabularPredictor doesn't raise exception. We probably need to upgrade ray and maybe autogluon
Actual Behavior
FATAL UNHANDLED EXCEPTION when we use "high_quality"
predictor = predictor.fit(
train_data=train_df,
presets="high_quality",
hyperparameters={"GBM": {}},
)
Full code:
https://www.quantconnect.cloud/backtest/9a7197ec020b382b1330f0f1bd56dddc/?theme=chrome
Potential Solution
Upgrade ray since the exception comes from this library
Checklist
- I have completely filled out this template
- I have confirmed that this issue exists on the current
masterbranch - I have confirmed that this is not a duplicate issue by searching issues
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the failure with autogluon.tabular.TabularPredictor.fit using the “high_quality” preset and the GBM hyperparameters shown in the issue, using the linked backtest as context. Check the project’s dependency configuration for the ray and autogluon versions involved. Done means the same training path no longer produces the reported FATAL UNHANDLED EXCEPTION.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100