Code covered by the BSD License
-
...
Handle arguments to function
-
[idx,netsim,i,unconverged,dps...
-
ind2cluster(labels)
-
matrix_transform(M,ngiven,nma...
transform to full matrix
-
silhouette2(X, clust, distanc...
SILHOUETTE Silhouette plot for clustered data.
-
simatrix_make(data,type,nrow)
data: a matrix with each column representing a variable.
-
similarity_euclid(data,vararg...
-
similarity_pearson(data)
pearson coefficients between every two columns
-
similarity_pearsonC(data, C)
pearson coefficients between every column and the center
-
solution_evaluation(data,M,la...
-
solution_positive(refseq_exon...
load GeneFindingProblem.mat;
-
valid_errorate(labels, truela...
computing error rates for every clusters if true labels are given
-
valid_external(index1,c2)
-
valid_sumpearson(data,labels,...
within-, between-cluster and total sum of squares
-
valid_sumsqures(data,labels,k...
data: a matrix with each column representing a variable.
-
Main_adaptAP_demo.m
-
data_load.m
-
solution_findK.m
-
View all files
from
Adaptive Affinity Propagation clustering
by Kaijun Wang
advantage of speed & performance appears under large number of clusters & large dataset
|
| data_load.m |
p = [];
if simatrix == 1
Ms = load(sw);
if id == 12 || id == 13
M = Ms.s; % given similarity matrix
p = Ms.p;
name = Ms.x;
elseif id == 14
M = Ms.s;
p = [];
refseq_exon = Ms.refseq_exon;
refseq_intron = Ms.refseq_intron;
[M,dim] = matrix_transform(M,nsubset,nrow);
refseq_exon = refseq_exon(1:nsubset-1);
refseq_intron = refseq_intron(1:nsubset-1);
nrow = nsubset;
else
M = Ms;
end
Ms = [];
data = [];
else
data = load(sw);
[nrow, dim] = size(data);
M = [];
end
% taking true class labels from a data file
truelabels = ones(nrow,1);
if id < 11 || (id > 20 && id < 30) % when 1st column is class labels
truelabels = data(:,1);
data = data(:,2:dim);
dim = dim-1;
end
|
|
Contact us at files@mathworks.com