how to plot the graph for the following result

I am getting the following result in the command window.

iter = 1

1. global fitness is 1.9669

iter = 2

2. global fitness is 1.9669

iter = 3

3. global fitness is 1.9669

iter = 4

4. global fitness is 1.2878

I want to plot the graph in a manner iter should be on x axis and global fitness on y axis.

I tried with the command plot((global_fitness,:),'-*b') but unable to get the result.

Could anyone please help to fix the issue

Answer 1

[KSSV]

figure
hold on
for i = 1:100
    global_fitness = rand ;
    plot(i,global_fitness,'*r')
end

Or, save all the values of a loop and plot at the end.

y = zeros([],1) ;
for i = 1:100
    global_fitness = rand ;
    y(i) = global_fitness ;
   
end

plot(1:100,y,'*r')

[jaah navi]

ok.I can get the graph.But I want to connect all the points.

I tried with the command

figure

hold on

for i = 1:4

global_fitness = rand ;

plot(i,global_fitness,'*-r')

end

But still the points are not getting connected.

Could you please help me on this.

[Torsten]

Collect your data inside the loop and plot outside the loop (KSSV's second option).

[jaah navi]

I tried but unabe to get the result with respect to the following code:

for iter = 1:iterations

y(iter) = global_fitness

end

plot(1:iterations,y(iter),'*-r').

Could you please help me on this.

[Torsten]

Did KSSV write anything like "y(iter)" in the plot command ? I can only see "y" ...

[KSSV]

for iter = 1:iterations
 y(iter) = global_fitness    
end
plot(1:iterations,y,'*-r').

[jaah navi]

as i am unable to get the result i tried with the above command.

so far i can able to plot only the last value of the global fitness with respect to last iteration.

what i actually need is i want to plot the graph for each global_fitness correponds to that particular iteration.

As mentioned before i am getting the following result in the command window

iter = 1

1. global fitness is 1.9669

iter = 2

2. global fitness is 1.9669

iter = 3

3. global fitness is 1.9669

iter = 4

4. global fitness is 1.2878

I want to plot iteration in xaxis and global fitness in yaxis by connecting all the points.Could you help me to fix it.

[KSSV]

copy the whole code here.

[jaah navi]

clear;
close all;
centroids = 2;          % == clusters here (aka centroids)
dimensions = 2;         % how many dimensions in each centroid x and y axis
particles = 2;         % how many particles in the swarm, aka how many solutions
iterations = 50;        % iterations of the optimization alg.
simtime=0.801;           % simulation delay btw each iteration
dataset_subset = 2;     % for the IRIS dataset, dataset_subset and dimensions are dependent on one another 
write_video = false;    % enable to grab the output picture and save a video
hybrid_pso = true;     % enable/disable hybrid_pso
manual_init = false;    % enable/disable manual initialization (only for dimensions={2,3})

% VIDEO GRUB STUFF...
if write_video
    writerObj = VideoWriter('PSO.avi');
    writerObj.Quality=100;
%     writerObj.FrameRate=30;
    open(writerObj);
end

% LOAD DEFAULT CLUSTER (IRIS DATASET); USE WITH CARE!
% load fisheriris.mat
load fisheriris.mat
meas = meas(:,1+dataset_subset:dimensions+dataset_subset); %RESIZE THE DATASET WITH CURRENT DIMENSIONS; USE WITH CARE!
dataset_size = size (meas);

% GLOBAL PARAMETERS 
w  = 0.72; %INERTIA
c1 = 1.49; %COGNITIVE
c2 = 1.49; %SOCIAL

% PLOT STUFF... HANDLERS AND COLORS
pc = []; txt = [];
cluster_colors_vector = rand(particles, 3);

% PLOT DATASET
fh=figure(1);
hold on;
if dimensions == 3
    plot3(meas(:,1),meas(:,2),meas(:,3),'k*');
    view(3);
elseif dimensions == 2
    plot(meas(:,1),meas(:,2),'k*');
end

% PLOT STUFF .. SETTING UP AXIS IN THE FIGURE
axis equal;
axis(reshape([min(meas)-2; max(meas)+2],1,[]));
hold off;

% SETTING UP PSO DATA STRUCTURES
swarm_vel = rand(centroids,dimensions,particles)*0.1;
swarm_pos = rand(centroids,dimensions,particles);
swarm_best = zeros(centroids,dimensions);
c = zeros(dataset_size(1),particles);
ranges = max(meas)-min(meas); %%scale
swarm_pos = swarm_pos .* repmat(ranges,centroids,1,particles) + repmat(min(meas),centroids,1,particles)% with respect to dataset
swarm_fitness(1:particles)=Inf;

% MANUAL INITIALIZATION (only for dimension 2 and 3)
if manual_init
    if dimensions == 3
        % MANUAL INIT ONLY FOR THE FIRST PARTICLE
             swarm_pos(:,:,1) = [6 3 4; 5 3 1]; 
    elseif dimensions == 2
        % KEYBOARD INIT ONLY FOR THE FIRST PARTICLE
             swarm_pos(:,:,1) = ginput(2)
    end
end

for iteration=1:iterations
      
    %CALCULATE EUCLIDEAN DISTANCES TO ALL CENTROIDS
    distances=zeros(dataset_size(1),centroids,particles);
    for particle=1:particles
        for centroid=1:centroids
            distance=zeros(dataset_size(1),1);
            for data_vector=1:dataset_size(1)
                %meas(data_vector,:)
                distance(data_vector,1)=norm(swarm_pos(centroid,:,particle)-meas(data_vector,:));
            end
            distances(:,centroid,particle)=distance;
        end
    end
    
    %ASSIGN MEASURES with CLUSTERS    
    for particle=1:particles
        [value, index] = min(distances(:,:,particle),[],2);
        c(:,particle) = index;
    end

    % PLOT STUFF... CLEAR HANDLERS
    delete(pc); delete(txt);
    pc = []; txt = [];
    
    % PLOT STUFF...
    hold on;
    for particle=1:particles
        for centroid=1:centroids
            if any(c(:,particle) == centroid)
                if dimensions == 3
                    pc = [pc plot3(swarm_pos(centroid,1,particle),swarm_pos(centroid,2,particle),swarm_pos(centroid,3,particle),'*','color',cluster_colors_vector(particle,:))];
                elseif dimensions == 2
                    pc = [pc plot(swarm_pos(centroid,1,particle),swarm_pos(centroid,2,particle),'*','color',cluster_colors_vector(particle,:))];
                end
            end
        end
    end
    set(pc,{'MarkerSize'},{12})
    hold off;
 
    %CALCULATE GLOBAL FITNESS and LOCAL FITNESS:=swarm_fitness
    average_fitness = zeros(particles,1)
    for particle=1:particles
        for centroid = 1 : centroids
            if any(c(:,particle) == centroid)
                local_fitness=mean(distances(c(:,particle)==centroid,centroid,particle));
                average_fitness(particle,1) = average_fitness(particle,1) + local_fitness;
            end
        end
        average_fitness(particle,1) = average_fitness(particle,1) / centroids;
        if (average_fitness(particle,1) < swarm_fitness(particle))
            swarm_fitness(particle) = average_fitness(particle,1);
            swarm_best(:,:,particle) = swarm_pos(:,:,particle);     %LOCAL BEST FITNESS
        end
    end    
    [global_fitness, index] = min(swarm_fitness);       %GLOBAL BEST FITNESS
    swarm_overall_pose = swarm_pos(:,:,index);          %GLOBAL BEST POSITION
    ------------------------------------------------------------------------------------------------------
    % SOME INFO ON THE COMMAND WINDOW
    fprintf('%3d. global fitness is %5.4f\n',iteration,global_fitness);            
     pause(simtime);
     ---------------------------------------------------------------------------------------------   
    % VIDEO GRUB STUFF...
    if write_video
        frame = getframe(fh);
        writeVideo(writerObj,frame);
    end
       
    % SAMPLE r1 AND r2 FROM UNIFORM DISTRIBUTION [0..1]
    r1 = rand;
    r2 = rand;
    
    % UPDATE CLUSTER CENTROIDS
    for particle=1:particles        
        inertia = w * swarm_vel(:,:,particle);
        cognitive = c1 * r1 * (swarm_best(:,:,particle)-swarm_pos(:,:,particle));
        social = c2 * r2 * (swarm_overall_pose-swarm_pos(:,:,particle));
        vel = inertia+cognitive+social;
                
        swarm_pos(:,:,particle) = swarm_pos(:,:,particle) + vel ;   % UPDATE PARTICLE POSE
        swarm_vel(:,:,particle) = vel;                              % UPDATE PARTICLE VEL
    end
    
end


% PLOT THE ASSOCIATIONS WITH RESPECT TO THE CLUSTER 
hold on;
particle=index; %select the best particle (with best fitness) 
cluster_colors = ['m','g','y','b','r','c','g'];
for centroid=1:centroids
    if any(c(:,particle) == centroid)
        if dimensions == 3
            plot3(meas(c(:,particle)==centroid,1),meas(c(:,particle)==centroid,2),meas(c(:,particle)==centroid,3),'-','color',cluster_colors(centroid));
        elseif dimensions == 2
            plot(meas(c(:,particle)==centroid,1),meas(c(:,particle)==centroid,2),'o','color',cluster_colors(centroid));
        end
    end
end
hold off;

% VIDEO GRUB STUFF...
if write_video
    frame = getframe(fh);
    writeVideo(writerObj,frame);
    close(writerObj);
end

% SAY GOODBYE
fprintf('\nEnd, global fitness is %5.4f\n',global_fitness);

With respect to the code i want to plot the graph for convergence by having iteration on the xaxis and global fitness on y axis with respect to the command line

fprintf('%3d. global fitness is %5.4f\n',iteration,global_fitness); on the code.

[jaah navi]

As you have told to copy the entire code I have copied it.Could you please help me on this.

[KSSV]

I forgot....I have seen the code last night itself....but as it was huge..I was kind of disappointed ;). By the way what you are trying to do with this big code..? I am just curious and want to know more......get the attched code to plot what you want.

[jaah navi]

thanks a lot.It works.

[KSSV]

i have asked some question as well....did you see that?

[jaah navi]

With resepect to the codingi need to find on which iteration the fitness function is getting converged.And to get the centroid location with respect to the data sets.