is normalization step needed in feature preparation?

yinlou / mltk

Machine Learning Tool Kit

BSD 3-Clause "New" or "Revised" License

136 stars 74 forks source link

is normalization step needed in feature preparation? #23

Open donganlei opened 3 years ago

donganlei commented 3 years ago

If the original features are at different ranges other than [-1, 1], do we need to normalize/calibrate their values before running mltk.predictor.gam.GAMLearner? Or, GAMLearner will take care of it?

Another question is: for mltk.predictor.evaluation.Evaluator, does can we find its metric output? I don't see the metric numbers displayed in output display or saved in any output file?

yinlou commented 3 years ago

No, you don't need to do any special preprocessing for features. Features of different scales are fine for GAM and GA2M, although you do need to discretize them first (https://github.com/yinlou/mltk/wiki/Dataset-Transformation#discretization).

You can find Evaluator's documentation here: https://github.com/yinlou/mltk/wiki/Model-Selection%2C-Evaluation-and-Prediction#model-evaluation