About the feature selection

[ChairManMeow-SY]

Hi，

I wonder if we need first normalize the features before using the sequential feature selection. As the regression model takes SVR, which requires the normalized input.

I checked the source code. The SFS will not automatically call the minmax norm within it. I notice in your script the SFS input is not normalized. Why ?

[vztu]

Hmm, good point. I think I might have done it wrong. But telling from my final results, it didn't affect too much. Applying normalization before each iteration should be more rigorous. Actually every time you run feature selection, you will get a different resulting model. All these models should give similar performance, though.