The Alpha158 handler get NAN in y["label"]["LABEL0"] in other instruments except csi300
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 48.7k
- Forks
- 7.7k
- PR merge metrics
- No merged PRs in 30d
Description
❓ Questions and Help
After changing market from default "csi300" to other specific code like market = ["SH600519"] in example tutorial workflow_by_code.ipynb
I got 0 loss in model.fit(dataset)
After debug, I find that the output of y["LABEL0"] in
are all NAN
and using default ”csi300“ is work fine with
So how do i do model fit in such specific stock id，rather than sci300？
I'd appreciate it if someone can tell me Why is that happen and how to solve it?
Contributor guide
No contributing guide indexed for this repository
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
Reproduce the issue in workflow_by_code.ipynb using market = ["SH600519"], then inspect the LABEL0 output at qlib/contrib/model/gbdt.py around lines 40–41. Trace how Alpha158 labels are generated for a single instrument and compare them with the csi300 case. Done means the cause is identified and model.fit receives valid labels for the specific stock, with a regression check if the relevant test location is found.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook, python
- Domain
- fintech-quant, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 28/100