flucoma-sc/release-packaging/HelpSource/Classes/FluidPCA.schelp

TITLE:: FluidPCA
summary:: Dimensionality Reduction with Principal Component Analysis
categories:: Dimensionality Reduction, Data Processing
related:: Classes/FluidMDS, Classes/FluidDataSet

DESCRIPTION::

Principal Components Analysis of a link::Classes/FluidDataSet::

https://scikit-learn.org/stable/modules/decomposition.html#principal-component-analysis-pca

CLASSMETHODS::

METHOD:: new
Make a new instance
ARGUMENT:: server
The server on which to run this model
ARGUMENT:: numDimensions
The number of dimensions to reduce to

INSTANCEMETHODS::

PRIVATE:: init

METHOD:: fit
Train this model on a link::Classes/FluidDataSet:: but don't transform the data
ARGUMENT:: dataSet
A link::Classes/FluidDataSet:: to analyse
ARGUMENT:: action
Run when done

METHOD:: transform
Given a trained model, apply the reduction to a source link::Classes/FluidDataSet:: and write to a destination. Can be the same for both (in-place)
ARGUMENT:: sourceDataSet
Source data, or the DataSet name
ARGUMENT:: destDataSet
Destination data, or the DataSet name
ARGUMENT:: action
Run when done. The variance is passed as an argument, aka the error of the new representation: a lower value means a higher fidelity to the original.

METHOD:: fitTransform
link::Classes/FluidPCA#fit:: and link::Classes/FluidPCA#transform:: in a single pass
ARGUMENT:: sourceDataSet
Source data, or the DataSet name
ARGUMENT:: destDataSet
Destination data, or the DataSet name
ARGUMENT:: action
Run when done. The variance is passed as an argument, aka the error of the new representation: a lower value means a higher fidelity to the original.

METHOD:: transformPoint
Given a trained model, transform the data point in a link::Classes/Buffer:: and write to an output
ARGUMENT:: sourceBuffer
Input data
ARGUMENT:: destBuffer
Output data
ARGUMENT:: action
Run when done. The variance is passed as an argument, aka the error of the new representation: a lower value means a higher fidelity to the original.

EXAMPLES::

code::
s.boot;
//Preliminaries: we want some audio, a couple of FluidDataSets, some Buffers, a FluidStandardize and a FluidPCA
(
~audiofile = File.realpath(FluidBufPitch.class.filenameSymbol).dirname +/+ "../AudioFiles/Tremblay-ASWINE-ScratchySynth-M.wav";
~raw = FluidDataSet(s,\pca_help_12D);
~standardized = FluidDataSet(s,\pca_help_12Ds);
~reduced = FluidDataSet(s,\pca_help_2D);
~audio = Buffer.read(s,~audiofile);
~mfcc_feature = Buffer.new(s);
~stats = Buffer.alloc(s, 7, 12);
~datapoint = Buffer.alloc(s, 12);
~standardizer  = FluidStandardize(s);
~pca = FluidPCA(s,2);
)


// Load audio and run an mfcc analysis, which gives us 13 points (we'll throw the 0th away)
(
~audio = Buffer.read(s,~audiofile);
FluidBufMFCC.process(s,~audio, features: ~mfcc_feature);
)

// Divide the time series in 100, and take the mean of each segment and add this as a point to
// the 'raw' FluidDataSet
(
{
	var trig = LocalIn.kr(1, 1);
	var buf =  LocalBuf(12, 1);
    var count = PulseCount.kr(trig) - 1;
	var chunkLen = (~mfcc_feature.numFrames / 100).asInteger;
	var stats = FluidBufStats.kr(
			source: ~mfcc_feature, startFrame: count * chunkLen,
		    startChan:1, numFrames: chunkLen, stats: ~stats, trig: trig
	);
	var rd = BufRd.kr(12, ~stats, DC.kr(0), 0, 1);
	var bufWr, dsWr;
	12.do{|i|
		bufWr = BufWr.kr(rd[i], buf, DC.kr(i));
	};
	dsWr = FluidDataSetWr.kr(\pca_help_12D, buf: buf, trig: Done.kr(stats));
	LocalOut.kr( Done.kr(dsWr));
	FreeSelf.kr(count - 99);
	Poll.kr(trig,count);
}.play;
)
// wait for the post window to acknoledge the job is done.

//First standardize our DataSet, so that the MFCC dimensions are on comensurate scales
//Then apply the PCA in-place on the standardized data
//Download the DataSet contents into an array for plotting
(
~reducedarray = Array.new(100);
~standardizer.fitTransform(~raw, ~standardized);
~pca.fitTransform(~standardized, ~reduced, action:{|x|
	x.postln; //pass on the variance
	~reduced.dump{|x| 100.do{|i|
		~reducedarray.add(x["data"][i.asString])
	}};
});
)

//Visualise the 2D projection of our original 12D data
(
d = ~reducedarray.flop.deepCollect(1, { |x| x.normalize});
w = Window("scatter", Rect(128, 64, 200, 200));
w.drawFunc = {
    Pen.use {
        d[0].size.do{|i|
            var x = (d[0][i]*200);
            var y = (d[1][i]*200);
            var r = Rect(x,y,5,5);
            Pen.fillColor = Color.blue;
            Pen.fillOval(r);
        }
    }
};
w.refresh;
w.front;
)
::

subsection:: Server Side Queries

Let's map our learned PCA dimensions to the controls of a processor

code::

(
~inputPoint = Buffer.alloc(s,12);
~predictPoint = Buffer.alloc(s,2);
~pitchingBus = Bus.control;
~catchingBus = Bus.control;
)

(
~pca.inBus_(~pitchingBus).outBus_(~catchingBus).inBuffer_(~inputPoint).outBuffer_(~predictPoint);

{
	var mapped;
	var audio = BufRd.ar(1,~audio,LFSaw.ar(BufDur.ir(~audio).reciprocal).range(0, BufFrames.ir(~audio)));
	var mfcc = FluidMFCC.kr(audio)[1..12];
	var smoothed = LagUD.kr(mfcc,1*ControlDur.ir,500*ControlDur.ir);
	var trig = Impulse.kr(ControlRate.ir / 2);
	smoothed.collect{|coeff,i| BufWr.kr([coeff],~inputPoint,i)};
	Out.kr(~pitchingBus,[trig]);
	mapped = Latch.kr(BufRd.kr(1,~predictPoint, phase:[0,1]).linlin(-3,3,0,3),In.kr(~catchingBus));
	CombC.ar(audio,3,mapped[0],mapped[1]*3)
}.play(~pca.synth,addAction:\addBefore);

)


::