FluidPCA and FluidMDS updates and help files
Owen Green
6 years ago
parent
a109652612
commit
b58360d4d4
@ -1,17 +1,23 @@
|
||||
FluidMDS : FluidManipulationClient {
|
||||
var id;
|
||||
classvar < manhattan = 0;
|
||||
classvar < euclidean = 1;
|
||||
classvar < sqeuclidean = 2;
|
||||
classvar < max = 3;
|
||||
classvar < min = 4;
|
||||
classvar < kl = 5;
|
||||
classvar < cosine = 5;
|
||||
|
||||
*new {|server|
|
||||
*new {|server|
|
||||
var uid = UniqueID.next;
|
||||
^super.new(server,uid).init(uid);
|
||||
^super.new(server,uid)!?{|inst|inst.init(uid);inst}
|
||||
}
|
||||
|
||||
init {|uid|
|
||||
id = uid;
|
||||
}
|
||||
|
||||
fitTransform{|sourceDataset, k, dist, destDataset, action|
|
||||
this.pr_sendMsg(\fitTransform,[sourceDataset.asString, k, dist, destDataset.asString],action);
|
||||
}
|
||||
fitTransform{|sourceDataset, destDataset, k, dist, action|
|
||||
this.prSendMsg(\fitTransform,[sourceDataset.asSymbol, destDataset.asSymbol, k, dist],action);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@ -0,0 +1,139 @@
|
||||
TITLE:: FluidMDS
|
||||
summary:: Dimensionality Reduction with Multidimensional Scaling
|
||||
categories:: Dimensionality Reduction, Data Processing
|
||||
related:: Classes/FluidMDS, Classes/FluidDataSet
|
||||
|
||||
DESCRIPTION::
|
||||
|
||||
https://scikit-learn.org/stable/modules/manifold.html#multi-dimensional-scaling-mds
|
||||
|
||||
|
||||
CLASSMETHODS::
|
||||
|
||||
|
||||
METHOD:: new
|
||||
Make a new instance
|
||||
ARGUMENT:: server
|
||||
The server on which to run this model
|
||||
|
||||
METHOD:: euclidean
|
||||
Euclidean distance (default)
|
||||
|
||||
METHOD:: sqeuclidean
|
||||
Squared Euclidean distance
|
||||
|
||||
METHOD:: manhattan
|
||||
Manhattan distance
|
||||
|
||||
METHOD:: max
|
||||
Minowski max
|
||||
|
||||
METHOD:: min
|
||||
Minowski max
|
||||
|
||||
METHOD:: kl
|
||||
Symmetric Kulback Leiber divergance (only makes sense with non-negative data)
|
||||
|
||||
METHOD:: cosine
|
||||
Cosine distance
|
||||
|
||||
INSTANCEMETHODS::
|
||||
|
||||
PRIVATE:: init
|
||||
|
||||
METHOD:: fitTransform
|
||||
Fit the model to a link::Classes/FluidDataSet:: and write the new projected data to a destination FluidDataSet.
|
||||
ARGUMENT:: sourceDataset
|
||||
Source data, or the dataset name
|
||||
ARGUMENT:: destDataset
|
||||
Destination data, or the dataset name
|
||||
ARGUMENT:: k
|
||||
The number of dimensions to reduce to
|
||||
ARGUMENT:: dist
|
||||
The distance metric to use (integer, 0-6, see flags above)
|
||||
ARGUMENT:: action
|
||||
Run when done
|
||||
|
||||
EXAMPLES::
|
||||
|
||||
code::
|
||||
//Preliminaries: we want some audio, a couple of FluidDataSets, some Buffers, a FluidStandardize and a FluidMDS
|
||||
(
|
||||
~audiofile = File.realpath(FluidBufPitch.class.filenameSymbol).dirname +/+ "../AudioFiles/Tremblay-ASWINE-ScratchySynth-M.wav";
|
||||
~raw = FluidDataSet(s,\mds_help_12D);
|
||||
~reduced = FluidDataSet(s,\mds_help_2D);
|
||||
~audio = Buffer.read(s,~audiofile);
|
||||
~mfcc_feature = Buffer.new(s);
|
||||
~stats = Buffer.new(s);
|
||||
~datapoint = Buffer.alloc(s,12);
|
||||
~standardizer = FluidStandardize(s);
|
||||
~mds = FluidMDS(s);
|
||||
)
|
||||
|
||||
// Do a mfcc analysis on the audio, which gives us 13 points, and we'll throw the 0th away
|
||||
// Divide the time series in to 100, and take the mean of each segment and add this as a point to
|
||||
// the 'raw' FluidDataSet
|
||||
(
|
||||
~raw.clear;
|
||||
~norm.clear;
|
||||
FluidBufMFCC.process(s,~audio,features:~mfcc_feature,action:{
|
||||
"MFCC analysis.complete. Doing stats".postln;
|
||||
fork{
|
||||
var chunkLen = (~mfcc_feature.numFrames / 100).asInteger;
|
||||
100.do{ |i|
|
||||
s.sync; FluidBufStats.process(s,~mfcc_feature,startFrame:i*chunkLen,numFrames:chunkLen,startChan:1, stats:~stats, action:{
|
||||
~stats.loadToFloatArray(action:{ |statsdata|
|
||||
[statsdata[0],statsdata[1]].postln;
|
||||
~datapoint.setn(0,[statsdata[0],statsdata[1]]);
|
||||
s.sync;
|
||||
("Adding point" ++ i).postln;
|
||||
~raw.addPoint(i,~datapoint);
|
||||
})
|
||||
});
|
||||
if(i == 99) {"Analysis done, dataset ready".postln}
|
||||
}
|
||||
}
|
||||
});
|
||||
)
|
||||
|
||||
//First standardize our dataset, so that the MFCC dimensions are on comensurate scales
|
||||
//Then apply the MDS in-place on the standardized data to get 2 dimensions, using a Euclidean distance metric
|
||||
//Download the dataset contents into an array for plotting
|
||||
(
|
||||
~standardizer.fit(~raw);
|
||||
~standardizer.transform(~raw, ~reduced);
|
||||
~mds.fitTransform(~raw,~reduced,2, FluidMDS.euclidean);
|
||||
~reducedarray= Array.new(100);
|
||||
fork{
|
||||
100.do{|i|
|
||||
~reduced.getPoint(i,~datapoint,{
|
||||
|
||||
~datapoint.loadToFloatArray(action:{|a| ~reducedarray.add(Array.newFrom(a))})
|
||||
});
|
||||
s.sync;
|
||||
if(i==99){"Data downloaded".postln};
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
//Visualise the 2D projection of our original 12D data
|
||||
(
|
||||
d = ~reducedarray.flatten(1).unlace.deepCollect(1, { |x| x.normalize});
|
||||
// d = [20.collect{1.0.rand}, 20.collect{1.0.rand}];
|
||||
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;
|
||||
)
|
||||
|
||||
::
|
||||
Loading…
Reference in New Issue