// Creates the features from the inputs. Features must be nSamples x nFeatures or nil
func FeaturizeTrainable(t Trainable, inputs common.RowMatrix, featurizedInputs *mat64.Dense) *mat64.Dense {
nSamples, nDim := inputs.Dims()
if featurizedInputs == nil {
nFeatures := t.NumFeatures()
featurizedInputs = mat64.NewDense(nSamples, nFeatures, nil)
}
rowViewer, isRowViewer := inputs.(mat64.RowViewer)
var f func(start, end int)
if isRowViewer {
f = func(start, end int) {
featurizer := t.NewFeaturizer()
for i := start; i < end; i++ {
featurizer.Featurize(rowViewer.RowView(i), featurizedInputs.RowView(i))
}
}
} else {
f = func(start, end int) {
featurizer := t.NewFeaturizer()
input := make([]float64, nDim)
for i := start; i < end; i++ {
inputs.Row(input, i)
featurizer.Featurize(input, featurizedInputs.RowView(i))
}
}
}
common.ParallelFor(nSamples, common.GetGrainSize(nSamples, minGrain, maxGrain), f)
return featurizedInputs
}
// UnscaleData is a wrapper for unscaling data in parallel.
// TODO: Make this work better so that if there is an error somewhere data isn't changed
func UnscaleData(scaler Scaler, data *mat64.Dense) error {
m := &sync.Mutex{}
var e ErrorList
f := func(start, end int) {
for r := start; r < end; r++ {
errTmp := scaler.Unscale(data.RowView(r))
if errTmp != nil {
m.Lock()
e = append(e, &SliceError{Header: "scale", Idx: r, Err: errTmp})
m.Unlock()
}
}
}
nSamples, _ := data.Dims()
grain := common.GetGrainSize(nSamples, 1, 500)
common.ParallelFor(nSamples, grain, f)
if len(e) != 0 {
return e
}
return nil
}