lcoogan
/
flucoma-sc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

KMeans review

Browse Source
nix
Gerard 6 years ago
parent 8381580885
commit 48ee95f77c
2 changed files with 81 additions and 81 deletions
Show Stats Download Patch File Download Diff File

56
release-packaging/Classes/FluidKMeans.sc
Unescape Escape View File

@ -1,33 +1,43 @@
FluidKMeans : FluidManipulationClient { FluidKMeans : FluidManipulationClient {
var <>k; var <>k;
*new {|server| *new {|server|
var uid = UniqueID.next; var uid = UniqueID.next;
^super.new(server,uid)!?{|inst|inst.init(uid);inst} ^super.new(server,uid)!?{|inst|inst.init(uid);inst}
} }
init {|uid| init {|uid|
id = uid; id = uid;
} }
fit{|dataset,k, maxIter = 100, buffer, action| fit{|dataset,k, maxIter = 100, action|
buffer = buffer ? -1; this.k = k;
this.k = k; this.prSendMsg(\fit,
// this.prSendMsg(\fit,[dataset.asSymbol, k,maxIter, buffer.asUGenInput],action,[numbers(FluidMessageResponse,_,k,_)]); [dataset.asSymbol, k,maxIter], action,
this.prSendMsg(\fit,[dataset.asSymbol, k,maxIter],action,[numbers(FluidMessageResponse,_,k,_)]); [numbers(FluidMessageResponse,_,k,_)]
);
} }
fitPredict{|dataset,labelset, k, maxIter = 100, action| fitPredict{|dataset, labelset, k, maxIter = 100, action|
this.k = k; this.k = k;
this.prSendMsg(\fitPredict,[dataset.asSymbol,labelset.asSymbol, k,maxIter],action,[numbers(FluidMessageResponse,_,k,_)]); this.prSendMsg(\fitPredict,
} [dataset.asSymbol,labelset.asSymbol, k,maxIter],
action,[numbers(FluidMessageResponse,_,k,_)]
);
}
predict{ |dataset, labelset,action| predict{ |dataset, labelset,action|
this.prSendMsg(\predict,[dataset.asSymbol, labelset.asSymbol],action,[numbers(FluidMessageResponse,_,this.k,_)]); this.prSendMsg(\predict,
} [dataset.asSymbol, labelset.asSymbol], action,
[numbers(FluidMessageResponse,_,this.k,_)]
);
}
predictPoint { |buffer, action| predictPoint { |buffer, action|
this.prSendMsg(\predictPoint,[buffer.asUGenInput],action,[number(FluidMessageResponse,_,_)]); this.prSendMsg(\predictPoint,
} [buffer.asUGenInput], action,
[number(FluidMessageResponse,_,_)]
);
}
} }

106
release-packaging/HelpSource/Classes/FluidKMeans.schelp
Unescape Escape View File

@ -1,7 +1,7 @@
TITLE:: FluidKMeans TITLE:: FluidKMeans
summary:: Cluster data points with K-Means summary:: Cluster data points with K-Means
categories:: FluidManipulation categories:: FluidManipulation
related:: Classes/FluidDataSet, Classes/FluidLabelSet, Classes/FluidKNN related:: Classes/FluidDataSet, Classes/FluidLabelSet, Classes/FluidKNNClassifier, Classes/FluidKNNRegressor
DESCRIPTION:: DESCRIPTION::
Uses the K-Means algorithm to learn clusters from a link::Classes/FluidDataSet:: Uses the K-Means algorithm to learn clusters from a link::Classes/FluidDataSet::
@ -11,9 +11,9 @@ https://scikit-learn.org/stable/tutorial/statistical_inference/unsupervised_lear
CLASSMETHODS:: CLASSMETHODS::
METHOD:: new METHOD:: new
Construct a new K Means model on the passed server Construct a new K Means model on the passed server.
ARGUMENT:: server ARGUMENT:: server
If nil will use Server.default If nil will use Server.default.
INSTANCEMETHODS:: INSTANCEMETHODS::
@ -22,118 +22,108 @@ PRIVATE::k
METHOD:: fit METHOD:: fit
Identify code::k:: clusters in a link::Classes/FluidDataSet:: Identify code::k:: clusters in a link::Classes/FluidDataSet::
ARGUMENT:: dataset ARGUMENT:: dataset
A link::Classes/FluidDataSet:: of data points A link::Classes/FluidDataSet:: of data points.
ARGUMENT:: k ARGUMENT:: k
The number of clusters to identify in the data set The number of clusters to identify in the data set.
ARGUMENT:: maxIter ARGUMENT:: maxIter
Maximum number of iterations to use partitioning the data Maximum number of iterations.
ARGUMENT:: buffer
Seed centroids for clusters WARNING:: Not yet implemented ::
ARGUMENT:: action ARGUMENT:: action
A function to run when fitting is complete, taking as its argument an array with the number of data points for each cluster A function to run when fitting is complete, taking as its argument an array with the number of data points for each cluster.
METHOD:: predict METHOD:: predict
Given a trained object, return the cluster ID for each data point in a dataset to a label set. Given a trained object, return the cluster ID for each data point in a dataset to a label set.
ARGUMENT:: dataset ARGUMENT:: dataset
a link::Classes/FluidDataSet:: containing the data to predict a link::Classes/FluidDataSet:: containing the data to predict.
ARGUMENT:: labelset ARGUMENT:: labelset
a link::Classes/FluidLabelSet:: to reveive the predicted clusters a link::Classes/FluidLabelSet:: to retrieve the predicted clusters.
ARGUMENT:: action ARGUMENT:: action
A function to run when the server responds A function to run when the server responds.
METHOD:: fitPredict METHOD:: fitPredict
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:: 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:: dataset ARGUMENT:: dataset
a link::Classes/FluidDataSet:: containing the data to fit and predict a link::Classes/FluidDataSet:: containing the data to fit and predict.
ARGUMENT:: labelset ARGUMENT:: labelset
a link::Classes/FluidLabelSet:: to reveive the predicted clusters a link::Classes/FluidLabelSet:: to retrieve the predicted clusters.
ARGUMENT:: k ARGUMENT:: k
The number of clusters to identify in the data set The number of clusters.
ARGUMENT:: maxIter ARGUMENT:: maxIter
Maximum number of iterations to use partitioning the data Maximum number of iterations.
ARGUMENT:: action ARGUMENT:: action
A function to run when the server responds A function to run when the server responds
METHOD:: predictPoint METHOD:: predictPoint
Given a trained object, return the cluster ID for a data point in a link::Classes/Buffer:: Given a trained object, return the cluster ID for a data point in a link::Classes/Buffer::
ARGUMENT:: buffer ARGUMENT:: buffer
a link::Classes/Buffer:: containing a data point a link::Classes/Buffer:: containing a data point.
ARGUMENT:: action ARGUMENT:: action
A function to run when the server responds, taking the ID of the cluser as its argument A function to run when the server responds, taking the ID of the cluster as its argument.
METHOD:: predict METHOD:: predict
Report cluster assignments for previously unseen data Report cluster assignments for previously unseen data.
ARGUMENT:: dataset ARGUMENT:: dataset
A link::Classes/FluidDataSet:: of data points A link::Classes/FluidDataSet:: of data points.
ARGUMENT:: labelset ARGUMENT:: labelset
A link::Classes/FluidLabelSet:: to contain assigments A link::Classes/FluidLabelSet:: to contain assignments.
ARGUMENT:: action ARGUMENT:: action
A function to run when complete, taking an array of the counts for each catgegory as its argument A function to run when complete, taking an array of the counts for each category as its argument.
EXAMPLES:: EXAMPLES::
Server.default.options.outDevice = "Built-in Output" Server.default.options.outDevice = "Built-in Output"
code:: code::
//A dataset for our points, a labelset for cluster labels
( (
~dataset= FluidDataSet(s,\kdtree_help_rand2d);
~clusters = FluidLabelSet(s,\kmeans_help_clusters);
)
//Make some clumped 2D points and place into a dataset //Make some clumped 2D points and place into a dataset
( ~points = (4.collect{
~points = (4.collect{64.collect{(1.sum3rand) + [1,-1].choose}.clump(2)}).flatten(1) * 0.5; 64.collect{(1.sum3rand) + [1,-1].choose}.clump(2)
~dataset.clear; }).flatten(1) * 0.5;
~tmpbuf = Buffer.alloc(s,2);
fork{ fork{
~dataset = FluidDataSet.new(s,\kmeans_help_rand2d);
d = Dictionary.with(
*[\cols -> 2,\data -> Dictionary.newFrom(
~points.collect{|x, i| [i, x]}.flatten)]);
s.sync; s.sync;
~points.do{|x,i| ~dataset.load(d, {~dataset.print});
(""++(i+1)++"/128").postln;
~tmpbuf.setn(0,x);
~dataset.addPoint(i,~tmpbuf);
s.sync
}
} }
) )
//Make a new k means model, fit it to the dataset and return the discovered clusters to a labelset
( // Create a KMeans instance and a LabelSet for the cluster labels in the server
fork{ ~clusters = FluidLabelSet(s,\kmeans_help_clusters);
~clusters.clear; ~kmeans = FluidKMeans(s);
~kmeans = FluidKMeans(s);
s.sync; // Fit into 4 clusters
~kmeans.fitPredict(~dataset,~clusters, 4,action: {|c| ~kmeans.fitPredict(~dataset,~clusters, 4, action: {|c|
"Fitted.\n # Points in each cluster:".postln; "Fitted.\n # Points in each cluster:".postln;
c.do{|x,i| c.do{|x,i|
("Cluster" + i + "->" + x.asInteger + "points").postln; ("Cluster" + i + "->" + x.asInteger + "points").postln;
} }
}); });
}
)
//Dims of kmeans should match dataset
~kmeans.cols
//Return labels of clustered points // Cols of kmeans should match dataset, size is the number of clusters
~kmeans.cols;
~kmeans.size;
~kmeans.dump;
// Retrieve labels of clustered points
( (
~assignments = Array.new(128); ~assignments = Array.new(128);
fork{ fork{
128.do{ |i| 128.do{ |i|
~clusters.getLabel(i,{|clusterID| ~clusters.getLabel(i,{|clusterID|
(i.asString+clusterID).postln; (i.asString+clusterID).postln;
~assignments.add(clusterID) ~assignments.add(clusterID)
}); });
s.sync; s.sync;
} }
} }
) )
//Visualise: we're hoping to see colours neatly mapped to quandrants... //Visualise: we're hoping to see colours neatly mapped to quandrants...
( (
d = ((~points + 1) * 0.5).flatten(1).unlace; d = ((~points + 1) * 0.5).flatten(1).unlace;
// d = [20.collect{1.0.rand}, 20.collect{1.0.rand}];
w = Window("scatter", Rect(128, 64, 200, 200)); w = Window("scatter", Rect(128, 64, 200, 200));
~colours = [Color.blue,Color.red,Color.green,Color.magenta]; ~colours = [Color.blue,Color.red,Color.green,Color.magenta];
w.drawFunc = { w.drawFunc = {

Write Preview
Loading…
Cancel
Save