kmeans new functionalities - classes done, with help+doc+examples in progress

release-packaging/Classes/FluidKMeans.sc

@@ -59,6 +59,50 @@ FluidKMeans : FluidRealTimeModel {
 		this.prSendMsg(this.predictPointMsg(buffer))
 	}
 
+	fitTransformMsg{|srcDataSet, dstDataSet|
+		^this.prMakeMsg(\fitTransform, id, srcDataSet.id, dstDataSet.id)
+	}
+
+	fitTransform{|srcDataSet, dstDataSet,action|
+		actions[\fitTransform] = [nil,action];
+		this.prSendMsg(this.fitTransformMsg(srcDataSet,dstDataSet));
+	}
+
+	transformMsg{|srcDataSet, dstDataSet|
+		^this.prMakeMsg(\transform, id, srcDataSet.id, dstDataSet.id)
+	}
+
+	transform{ |srcDataSet, dstDataSet, action|
+		actions[\transform] = [nil,action];
+		this.prSendMsg(this.transformMsg(srcDataSet,dstDataSet));
+	}
+
+	transformPointMsg{ |sourceBuffer, targetBuffer|
+		^this.prMakeMsg(\transformPoint, id,
+			this.prEncodeBuffer(sourceBuffer),
+            this.prEncodeBuffer(targetBuffer),
+            ["/b_query", targetBuffer.asUGenInput]);
+    }
+
+	transformPoint { |sourceBuffer, targetBuffer, action|
+		actions[\transformPoint] = [nil,{action.value(targetBuffer)}];
+		this.prSendMsg(this.transformPointMsg(sourceBuffer, targetBuffer));
+	}
+
+	getMeansMsg{|dataSet| ^this.prMakeMsg(\getMeans, id, dataSet.asUGenInput) }
+
+    getMeans{ |dataSet, action|
+        actions[\getMeans] = [nil, action];
+		this.prSendMsg(this.getMeansMsg(dataSet));
+	}
+
+	setMeansMsg{|dataSet| ^this.prMakeMsg(\setMeans, id, dataSet.asUGenInput) }
+
+    setMeans{ |dataSet, action|
+        actions[\setMeans] = [nil, action];
+		this.prSendMsg(this.setMeansMsg(dataSet));
+	}
+
 	kr{|trig, inputBuffer,outputBuffer|
 		^FluidKMeansQuery.kr(K2A.ar(trig),
 			this, clusters, maxiter,

release-packaging/HelpSource/Classes/FluidKMeans.schelp

@@ -65,6 +65,46 @@ A link::Classes/FluidLabelSet:: to contain assignments.
 ARGUMENT:: action
 A function to run when complete, taking an array of the counts for each category as its argument.
 
+METHOD:: fitTransform
+Run link::Classes/FluidKMeans#*fit:: and link::Classes/FluidKMeans#*predict:: in a single pass: i.e. train the model on the incoming link::Classes/FluidDataSet:: and then return the learned clustering to the passed link::Classes/FluidLabelSet::
+ARGUMENT:: srcDataSet
+a link::Classes/FluidDataSet:: containing the data to fit and predict.
+ARGUMENT:: dstDataSet
+a link::Classes/FluidLabelSet:: to retrieve the predicted clusters.
+ARGUMENT:: action
+A function to run when the server responds
+
+METHOD:: transformPoint
+Given a trained object, return the cluster ID for a data point in a link::Classes/Buffer::
+ARGUMENT:: sourceBuffer
+a link::Classes/Buffer:: containing a data point.
+ARGUMENT:: targetBuffer
+a link::Classes/Buffer:: containing a data point.
+ARGUMENT:: action
+A function to run when the server responds, taking the ID of the cluster as its argument.
+
+METHOD:: transform
+Report cluster assignments for previously unseen data.
+ARGUMENT:: srcDataSet
+A link::Classes/FluidDataSet:: of data points.
+ARGUMENT:: dstDataSet
+A link::Classes/FluidLabelSet:: to contain assignments.
+ARGUMENT:: action
+A function to run when complete, taking an array of the counts for each category as its argument.
+
+METHOD:: getMeans
+Report cluster assignments for previously unseen data.
+ARGUMENT:: dataSet
+A link::Classes/FluidDataSet:: of data points.
+ARGUMENT:: action
+A function to run when complete, taking an array of the counts for each category as its argument.
+
+METHOD:: setMeans
+Report cluster assignments for previously unseen data.
+ARGUMENT:: dataSet
+A link::Classes/FluidDataSet:: of data points.
+ARGUMENT:: action
+A function to run when complete, taking an array of the counts for each category as its argument.
 
 EXAMPLES::
 code::
@@ -147,6 +187,38 @@ w.front;
 ~kmeans.predictPoint(~inbuf,{|x|x.postln;});
 ::
 
+subsection:: Accessing the means
+
+We can get and set the means for each cluster, their centroid.
+
+code::
+~centroids = FluidDataSet(s);
+~kmeans.getMeans(~centroids, {~centroids.print});
+
+
+
+~centroids.load(Dictionary.newFrom([\cols, 2, \data, Dictionary.newFrom([\0, [0.5,0.5], \1, [-0.5,0.5], \2, [0.5,-0.5], \3, [-0.5,-0.5]])]));
+~centroids.print
+~kmeans.setMeans(~centroids, {~kmeans.predict(~dataSet,~clusters,{~clusters.dump{|x|var count = 0.dup(4); x["data"].keysValuesDo{|k,v|count[v[0].asInteger] = count[v[0].asInteger] + 1;};count.postln}})});
+
+~kmeans.free
+~kmeans = FluidKMeans(s);
+~kmeans.predict(~dataSet,~clusters)
+
+::
+
+subsection:: Cluster-distance Space
+
+You can get the euclidian distance of a given point to each cluster.
+
+code::
+b = Buffer.sendCollection(s,[0.5,0.5])
+c = Buffer(s)
+
+~kmeans.transformPoint(b,c,{|x|x.query;x.getn(0,x.numFrames,{|y|y.postln})})
+
+::
+
 subsection:: Queries in a Synth
 
 This is the equivalent of predictPoint, but wholly on the server