search

WillKoehrsen / feature-selector

Feature selector is a tool for dimensionality reduction of machine learning datasets
GNU General Public License v3.0
2.23k stars 768 forks source link

Remove stratify for regression splits #29

Closed ashtou closed 1 year ago

ashtou commented 5 years ago

Hey Will!

  1. The current code results in the following error for regression tasks: ValueError: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2. It's because stratify works based on class labels, hence only for classification. This would not affect your Jupyter notebooks, as it leaves your classification example untouched.

  2. I'd also set the random_state parameter to get the same train/test split every time, but that's up to you.

et2010 commented 4 years ago

I have also bumped into this error. This seems to be a proper fix. Any ideas? @WillKoehrsen

AleksandrovichK commented 4 years ago

Today have faced the same error. Could you please fix the current behavior with regression? @WillKoehrsen

florence27 commented 4 years ago

Any news on this fix? @WillKoehrsen