// 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.RawRowViewer)
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.RawRowView(i), featurizedInputs.RawRowView(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.RawRowView(i))
}
}
}
common.ParallelFor(nSamples, common.GetGrainSize(nSamples, minGrain, maxGrain), f)
return featurizedInputs
}
func (k *KMeans) Train(inputs *common.RowMatrix) {
nSamples, inputDim := inputs.Dims()
centroids := make([][]float64, k.Clusters)
// Assign the centroids to random data point to start
perm := rand.Perm(nSamples)
for i := 0; i < k.Clusters; i++ {
data := make([]float64, inputDim)
idx := perm[i]
inputs.Row(data, idx)
centroids[i] = data
}
distances := mat64.NewDense(nSamples, k.Clusters, nil)
row := make([]float64, inputDim)
for i := 0; i < nSamples; i++ {
inputs.Row(row, i)
for j := 0; j < k.Clusters; j++ {
d := floats.Distance(row, centroids[j])
distances.Set(i, j, d)
}
}
}
func BatchPredict(batch BatchPredictor, inputs common.RowMatrix, outputs common.MutableRowMatrix, inputDim, outputDim int, grainSize int) (common.MutableRowMatrix, error) {
// TODO: Add in something about error
// Check that the inputs and outputs are the right sizes
nSamples, dimInputs := inputs.Dims()
if inputDim != dimInputs {
return outputs, errors.New("predict batch: input dimension mismatch")
}
if outputs == nil {
outputs = mat64.NewDense(nSamples, outputDim, nil)
} else {
nOutputSamples, dimOutputs := outputs.Dims()
if dimOutputs != outputDim {
return outputs, errors.New("predict batch: output dimension mismatch")
}
if nSamples != nOutputSamples {
return outputs, errors.New("predict batch: rows mismatch")
}
}
// Perform predictions in parallel. For each parallel call, form a new predictor so that
// memory allocations are saved and no race condition happens.
// If the input and/or output is a RowViewer, save time by avoiding a copy
inputRVer, inputIsRowViewer := inputs.(mat64.RawRowViewer)
outputRVer, outputIsRowViewer := outputs.(mat64.RawRowViewer)
var f func(start, end int)
// wrapper function to allow parallel prediction. Uses RowView if the type has it
switch {
default:
panic("Shouldn't be here")
case inputIsRowViewer, outputIsRowViewer:
f = func(start, end int) {
p := batch.NewPredictor()
for i := start; i < end; i++ {
p.Predict(inputRVer.RawRowView(i), outputRVer.RawRowView(i))
}
}
case inputIsRowViewer && !outputIsRowViewer:
f = func(start, end int) {
p := batch.NewPredictor()
output := make([]float64, outputDim)
for i := start; i < end; i++ {
outputs.Row(output, i)
p.Predict(inputRVer.RawRowView(i), output)
outputs.SetRow(i, output)
}
}
case !inputIsRowViewer && outputIsRowViewer:
f = func(start, end int) {
p := batch.NewPredictor()
input := make([]float64, inputDim)
for i := start; i < end; i++ {
inputs.Row(input, i)
p.Predict(input, outputRVer.RawRowView(i))
}
}
case !inputIsRowViewer && !outputIsRowViewer:
f = func(start, end int) {
p := batch.NewPredictor()
input := make([]float64, inputDim)
output := make([]float64, outputDim)
for i := start; i < end; i++ {
inputs.Row(input, i)
outputs.Row(output, i)
p.Predict(input, output)
outputs.SetRow(i, output)
}
}
}
common.ParallelFor(nSamples, grainSize, f)
return outputs, nil
}
