Hello all,
Using lassoCV to select the optimal regularization I get an extremely high
alpha (1x10^6), which produces all zero weighted features when training the
model.
What I would like to know is if I can infer from such a high parameter that
there is insufficient information contained in the features to predict
outcomes before testing with it?
I have tested with this parameter, which indeed yield non-significant
prediction, but I am more interested in what type of inferences can be made
from the high regularization parameter per se.
Regards,
Steve
------------------------------------------------------------------------------
Own the Future-Intel® Level Up Game Demo Contest 2013
Rise to greatness in Intel's independent game demo contest.
Compete for recognition, cash, and the chance to get your game
on Steam. $5K grand prize plus 10 genre and skill prizes.
Submit your demo by 6/6/13. http://p.sf.net/sfu/intel_levelupd2d
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
