EpistasisLab / EpistasisLab/tpot
MLPRegressor in TPOT configuration dictionary
Open
need contributor
question
- Dominant language
- Jupyter Notebook
- Stars
- 10.1k
- Forks
- 1.6k
- PR merge metrics
- No merged PRs in 30d
Description
I include MLPRegressor in TPOT config and finally get the best pipeline ['standardscaler', 'MLPRegressor']. It is so reasonable that the best pipeline includes standardscaler as data preprocessing and modeling with MLPRegressor.
However, I met a problem is that MLP is sensitive to feature scaling. If I would like use the best pipeline to do prediction. The results are far away the expectation.
Could someone to help me come up with a good solution to do prediction while the best pipeline include MLP?
Does #104 can help on this issue?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.