copie du travail de Maxime

Semestre1/IML/TP/TP3/George.m

-X = load("george.dat");
-
-figure, plot(X(:,1), X(:,2), 'o', 'markersize', 8, 'markerfacecolor', 'r')
-hold on
-title('George','fontsize', 14)
-
-ltlX = mydownsampling(X, 10);
-M = distance(ltlX);
-
-%%
-
-method='complete'; 
-level_max = aggclust(M, method);
-
-figure
-dendro(level_max);
-title('Clustering avec distance max', 'fontsize', 24)
-
-K=2; % nombre de clusters voulus
-% recuperation des indices des points de chaque cluster
-N = size(ltlX, 1);
-clusters=level_max(N-K+1).cluster;
-
-% trace des clusters obtenus
-plotclusters(clusters, X, K);
-title('Clustering avec distance max', 'fontsize', 24)
\ No newline at end of file

Semestre1/IML/TP/TP3/kmoyennes.m

-function [C,clusters,JWiter] = kmoyennes(X,K,Co)
-    C = Co;
-    MaxIter = 15;
-    JWiter = zeros(MaxIter,1);
-    iter = 1;
-    
-    while (iter <= MaxIter)
-        [clusters, Jw] = affectation(X,C,K);
-        JWiter(iter) = Jw;
-        C = nouveaux_centres(X,clusters);
-    end
-    
-end

Semestre1/IML/TP/TP3/matlab/Kmoyennes.m

+function [C, clusters, JwIter] = Kmoyennes(X, K, C0) % JwIter est le cout
+
+    Jw_old=0;
+    Jw_new=10;
+    JwIter=[];
+    i=1;
+    epsilon=0.01;
+    imax=500;
+    
+    while ((abs(Jw_new-Jw_old)>epsilon) && (i<imax))
+        Jw_old=Jw_new;
+        
+        [clusters, Jw_new] = affectation(X, C0, K);
+        [C0] = nouveaux_centres(X, clusters, K);
+        
+        JwIter=[JwIter; Jw_new];        
+        i=i+1;
+    end
+    C=C0;
+end
\ No newline at end of file

Semestre1/IML/TP/TP3/matlab/affectation.m

+function [clusters, Jw] = affectation(X, C, K)
+    N=size(X,1);
+    Jw=0;
+
+    %K=size(C,1); % Damien
+        
+    for i=1:N
+        for k=1:K
+             distance(k)=norm(X(i,:)-C(k,:),2)^2;
+        end
+        [val, indice]=min(distance);
+        clusters(i)=indice; 
+        % i est le numero du point en question et indice est l'indice du cluster 
+        % le plus proche de ce point
+        Jw=Jw+val;
+    end
+end
\ No newline at end of file

Semestre1/IML/TP/TP3/matlab/affectationmoi.m

+function [clusters, Jw] = affectation(X, C, K)
+n = length(X);
+Jw=0;
+clusters = zeros(n, 1);
+tailleC=size(C)
+for i=1:n
+    distance = zeros(K, 1);
+    for k=1:K
+        distance(k) = norm(X(i,:)-C(k,:),2)^2;
+    end;
+[val indice]=min(distance);
+clusters(i)=indice;
+Jw=Jw+val;
+end
\ No newline at end of file

Semestre1/IML/TP/TP3/aggclust.m → Semestre1/IML/TP/TP3/matlab/aggclust.m

@@ -15,7 +15,7 @@ function level = aggclust(distance, method)
 %		of level i 
 %
 %	Type "aggclust" to see a demo of a hierarchical clustering
-%	cluster(single-linkage) of 50 random patterns of dimensionality 2.
+%	(single-linkage) of 50 random patterns of dimensionality 2.
 %
 %	See also DENDRO, LINKCLU.
 

Semestre1/IML/TP/TP3/matlab/alban/Kmoyennes.m

+function [C, clusters, JwIter] = Kmoyennes(X, K, C0)
+
+[clusters, J] = affectation(X, C0, K);
+C = nouveauxCentres(X, clusters);
+JwIter = (J);
+
+difJ = 1;
+
+while difJ > 0
+    
+    size(C)
+    
+    [clusters, J] = affectation(X, C, K);
+    
+    C = nouveauxCentres(X, clusters);
+    
+    difJ = JwIter(length(JwIter)) - J;
+    
+    JwIter = [JwIter J];
+    
+end
\ No newline at end of file

Semestre1/IML/TP/TP3/matlab/alban/TP3.m

+clear all;
+close all;
+clc;
+
+%% 1) aggclust gégnère un dendogramme en fonction d'une matrice de distance 
+% et  de la fonction de distance utilisée
+
+%% 2) Le script génère 2 dendogrammes en utilisant les distances max et min
+% La distance max donne le résultat de la vérité vraie alors que la
+% distance min en est très loin
+
+%% 3)
+
+load('ds2.dat'); % Load ds2
+load('george.dat'); % Load ds2
+
+X = mydownsampling(george, 50);
+
+M = distance(X);
+
+K = 6; % Nombre de clusters
+
+method='complete'; 
+level_max = aggclust(M, method);
+
+% Affichage du dendogramme 
+figure
+dendro(level_max);
+title('Clustering avec distance max', 'fontsize', 24)
+
+% recuperation des indices des points de chaque cluster
+N = size(X, 1);
+clusters=level_max(N-K+1).cluster;
+
+% trace des clusters obtenus
+plotclusters(clusters, X, K);
+title('Clustering avec distance max', 'fontsize', 24)
+
+%% 2) 4)
+close all; clc; clear all;
+X = gendata(50);
+
+K = 2;
+
+% C0 = rand(K, size(X, 2));
+% 
+% [C, clusters, JwIter] = Kmoyennes(X, K, C0);
+% 
+% % trace des clusters obtenus
+% plotclusters(clusters, X, K);
+% title('Clustering avec distance max', 'fontsize', 24)
+
+data = load('../data/ds2.dat');
+georgy = load('../data/george.dat');
+
+% 2.2)
+K=6;
+C02 = rand(K, size(georgy, 2));
+[C2, clusters2, JwIter2] = Kmoyennes(georgy, K, C02);
+plotclusters(clusters2, georgy, K);
+title('Clustering avec distance max de Georges')
+K=2;
+C03 = rand(K, size(data, 2));
+[C3, clusters3, JwIter3] = Kmoyennes(data, K, C03);
+plotclusters(clusters3, data, K);
+title('Clustering avec distance max de ds2')
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

Semestre1/IML/TP/TP3/matlab/alban/affectation.m

+function [clusters, Jw] = affectation(X, C, K)
+n = length(X);
+Jw = 0;
+clusters = zeros(n, 1);
+size(C)
+for i=1:n
+    distance = zeros(K, 1);
+    for k=1:K
+        distance(k) = norm(X(i, :) - C(k, :))^2;
+    end
+    [val, indice] = min(distance);
+    clusters(i) = indice;
+    Jw = Jw + val;
+end
\ No newline at end of file

Semestre1/IML/TP/TP3/matlab/alban/aggclust.m

+function level = aggclust(distance, method)
+% AGGCLUST Hierarchical (agglomerative) clustering
+%	Usage: level = aggclust(distance, method)
+%
+%	distance: 2D distance matrix of data points, with diagonal elements
+%		of "INF"
+%	method: "single" for single-linkage
+%		"complete" for complete-linkage
+%	level: data structure for a hierarchical clustering result
+%	level(i).distance: distance matrix at level i
+%	level(i).height: the minimum distance measure to form level i 
+%	level(i).merged: the two clusters (of level i-1) being merged to form
+%		level i 
+%	level(i).cluster{j}: a vector denotes the data points in j-th cluster
+%		of level i 
+%
+%	Type "aggclust" to see a demo of a hierarchical clustering
+%	(single-linkage) of 50 random patterns of dimensionality 2.
+%
+%	See also DENDRO, LINKCLU.
+
+% Roger Jang, 981027
+
+if nargin == 0, selfdemo; return; end
+if nargin < 2, method = 'complete'; end
+
+data_n = size(distance, 1);
+level(1).distance = distance;
+level(1).height = 0;
+level(1).merged = [];
+for i = 1:data_n,
+	level(1).cluster{i} = [i];
+end
+
+for i = 2:data_n,
+	level(i) = merge(level(i-1), method);
+end
+
+% ====== Merge clusters
+function level_out = merge(level, method)
+% MERGE Merge a level of n clusters into n-1 clusters
+
+cluster_n = length(level.cluster);
+[min_i, min_j, min_value] = minxy(level.distance);
+% Reorder to have min_i < min_j
+if min_i > min_j,
+	temp = min_i;
+	min_i = min_j; 
+	min_j = temp;
+end
+
+level_out = level;
+
+% Update height
+level_out.height = min_value;
+
+% Update merged cluster
+level_out.merged = [min_i min_j];
+
+% Update cluster
+level_out.cluster{min_i} = [level_out.cluster{min_i} level_out.cluster{min_j}];
+level_out.cluster(min_j) = [];	% delete cluster{min_j}
+%keyboard
+% New distance matrix
+distance2 = level.distance;
+% "min" for single-linkage; "max" for complete-linkage
+if strcmp(method, 'single'),
+	distance2(:, min_i) = min(distance2(:, min_i), distance2(:, min_j)); 
+	distance2(min_i, :) = min(distance2(min_i, :), distance2(min_j, :)); 
+elseif strcmp(method, 'complete'),
+	distance2(:, min_i) = max(distance2(:, min_i), distance2(:, min_j)); 
+	distance2(min_i, :) = max(distance2(min_i, :), distance2(min_j, :)); 
+else
+	error('Unsupported method in AGGCLUST!');
+end
+
+distance2(min_j, :) = [];
+distance2(:, min_j) = [];
+distance2(min_i, min_i) = inf;
+
+level_out.distance = distance2;
+
+% ====== Find the minimum value in a matrix
+function [i, j, min_value] = minxy(A)
+[value_row, index_row] = min(A);
+[min_value, j] = min(value_row);
+i = index_row(j);
+
+% ====== Self demo ======
+function selfdemo
+data_n = 50;
+dimension = 2;
+points = rand(data_n, dimension);
+for i = 1:data_n,
+	for j = 1:data_n,
+		distance(i, j) = norm(points(i,:)-points(j,:));
+	end
+end
+
+% Diagonal elements should always be inf.
+for i = 1:data_n, distance(i, i) = inf; end
+
+level = aggclust(distance);
+
+% Plot heights w.r.t. levels
+figure;
+plot([level.height], 'r:o');
+xlabel('Level');
+ylabel('Height');
+title('Height vs. level');
+
+% Plot the dendrogram
+figure;
+dendro(level);
+
+% View the formation of clusters
+figure;
+linkclu(points, distance, level);