Anni Matlab Fitted Curve - 6

%S=[44.71756,44.14105,43.75766,43.18222,42.60572,41.45342,40.49352]; % stress array
N = 8; % number of stress
%arr = [2262,2320,2321,2365,2400,2450,2451,2452,2465,2500,2501,2511,2515,2555,2556,2566,2567,2568,2615,2616,2617,2666,2667,2715,2715,2765,2820];
arr=[43,218087.4,204592.6,176191.2,186192,158414.3,158415,122424.6]
for i = 1:1 % for different stress
    %arr=M(2,:);
    arr = sort(arr);
    % int p=0;
    %x = (arr(2) - 10):(arr(N + 1) + 10);
    % int s1=int32(arr(2));
    % int s2=mod(s1,10);
    s = 122420;
    % int e1=int32(arr(N+1));
    % int e2=mod(e1,10);
    e = 348240;
    % p=(e-s)/10;
    p = 0;
    s_temp = s;
    while s_temp < e
        p = p + 1;
        s_temp = s_temp + 30000;
    end
    x_co = zeros(1, p);
    y_co = zeros(1, p);
    ct = 1;
    w = 0;
    while s <= e
        mn = s;
        mx = s + 30000;
        count = 0;
        for j = 1:N
            ele = arr(j);
            if ele >= mn && ele <= mx
                count = count + 1;
                % else
                %    break;
            end
        end
        x_co(ct) = (mn + mx) / 2;
        y_co(ct) = count;
        if count > 0
            w = w + 1;
        end
        ct = ct + 1;
        s = s + 30000;
        % if s>=e
        %    break;
        % end
    end
    x_coo = zeros(1, w);
    y_coo = zeros(1, w);
    l = 1;
    for k = 1:p
        if y_co(k) > 0
            y_coo(l) = y_co(k);
            x_coo(l) = x_co(k);
            l = l + 1;
        end
    end
    % plot(x_coo,y_coo);
    % ... (previous code)

    % Fit a normal distribution to your data
    pd = fitdist(x_coo', 'Normal');  % Note the transpose of x_coo

    % Extract the parameters of the fitted distribution
    mu = pd.mu;
    sigma = pd.sigma;

    % Generate x-values for the curve with smaller increments
    x_values = min(x_coo):10:max(x_coo);  % Use smaller increments for a smoother curve

    % Calculate the corresponding y-values for the normal distribution using the fitted parameters
    y_fit = pdf(pd, x_values);

    % Create a bar plot to connect the data points
    bar(x_coo, y_coo, 'b', 'BarWidth', 0.8);
    hold on;

    % Overlay the fitted Normal (Gaussian) curve
    plot(x_values, y_fit, 'r-', 'LineWidth', 2);
    legend('Data Points', 'Gaussian Fit (Bell Curve)');

    % ... (rest of your code)




    %%%%%%%%%%%%%%%%%%%%%%%%%%%% Filtering Data and Plotting Smooth Curve %%%%%%%%%%%%%%%%%%%%%%%%%%%%
    filterSize = 1;
    x_mov_fil = zeros(length(x_coo)-filterSize+2, 1);
    y_mov_fil = zeros(length(x_coo)-filterSize+2, 1);

    x_mov_fil(1) = x_coo(1);
    y_mov_fil(1) = y_coo(1);

    for ii=1:length(x_coo) - filterSize+1
        % x_mov_fil(ii+1) = (x_coo(ii) + x_coo(ii+1))/2;
        % y_mov_fil(ii+1) = (y_coo(ii) + y_coo(ii+1))/2;

        sx = 0;
        sy=0;
        for jj=1:filterSize
            sx = sx + x_coo(ii+jj-1);
            sy = sy + y_coo(ii+jj-1);
        end
        sx = sx / (filterSize);
        sy = sy / (filterSize);

        x_mov_fil(ii+1) = sx;
        y_mov_fil(ii+1) = sy;
    end



    % Plotting approx plot
    [xx,is] = sort(x_mov_fil(:));
    yy = y_mov_fil(is);

    xx = smoothdata(xx, "sgolay");
    yy = smoothdata(yy, "sgolay");

    yy = yy(:);
    dx = diff(xx);
    dy = diff(yy);
    y0 = yy(1:end-1);
    n = numel(xx)-1;
    coefs = [-2*dy./(dx.^3), 3*dy./(dx.^2), 0*dy, y0];
    pp = struct('form', 'pp',...
        'breaks', xx(:)',...
        'coefs', coefs,...
        'pieces', n, ...
        'order', 4,...
        'dim', 1);
    figure
    xi = linspace(min(x_mov_fil),max(x_mov_fil));
    yi = ppval(pp,xi);

    plot(xi,yi,'r');
    xlim([min(x_coo),max(x_coo)])
    grid on


    % Max curve value x and y point
    [~, maxIdx] = max(yi);
    maxiX = xi(maxIdx);
    maxiY = yi(maxIdx);
    disp("Maximum value y= "+ maxiY+ " at x="+ maxiX)

end