EpistasisLab / EpistasisLab/tpot

MLPRegressor in TPOT configuration dictionary

Open
#984 2 comments 0 reactions 0 assignees View on GitHub
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.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.