Intelligent Feature Selection (with SVM or PCA)

[rodrigo.constanzo]

Indeed. As it is all those numbers seem super duper arbitrary.

I tried building a thing with this now and it seems like I’ve run into a bug/problem, so will see what comes of that.

Hopefully this is not some native dict thing where you can’t view arrays or something awful like that.

@tedmoore

…instead of using only the first n principle components, maybe try using all them but create a weighted sum, where the weights are the explained variance ratios so that all are accounted for but the first few will contribute more to the final summed curve.

And to make sure I understand, by this you mean taking each column from the array and summing them together (ala an iterative vexpr $f1 + $f2)?