MATLAB: What exactly is going on with this code? I’m having difficulty understanding it

codeconfusedhelppolynomial

Hello,
I'm struggling with understanding the code below. I was hoping to give my best interpretation of what's going on, and hope that I'm right. 
for FilesToRead = 1 : length(FileNames)
    y = load(fullfile(Directory, FileNames{FilesToRead}));
    y = {y};
    n = 400000;
    for i=1:length(y)
        x{i}=(1:length(y{i}))';
    end
    for ii=1:length(y)
        for k=1:length(y{ii})/n
            coeffs{ii}(k,:)=polyfit(x{ii}(n*(k-1)+1 : k*n),y{ii}(n*(k-1)+1 : k*n),1);
            yfit{ii}(k,:)=coeffs{ii}(k,2)+coeffs{ii}(k,1)*x{ii}(n*(k-1)+1 : k*n);
        end
    end
    for ii=1:length(y)
        dd{ii}= subsref(yfit{ii}.', substruct('()', {':'})).';
        dd2{ii}=y{ii}(1:length(dd{ii}))-dd{ii}';
    end
    for i=1:length(dd2)
        t{i}=zeros(1,length(dd2{i}));
    end
    t{1}=1:length(dd2{1});
    for i=2:length(dd2)
        t{i}= t{i-1}(end)+[1:length(dd2{i})];
    end
    clear coeffs dd i ii k prompt ws yfit
    
    yRaw=y; xRaw=x;
    x=t; y=dd2;
    clear dd2 t
    % Window for variance - 5 seconds = 100,000
    n = 100000;
    for i=1:length(y)
        for k=1:length(y{i})/n
            a(k)=var(y{i}(n*(k-1)+1:k*n));
        end
        v{i}=a;
        a=[];
    end
    t{1}=1:length(v{1});
    for i=2:length(y)
        t{i}=t{i-1}(end)+[1:length(v{i})];
    end
    
    for i=1:length(t)
        tm{i} = t{i}.*((n/20000)/60); % time in minutes
    end
end
So essentially, every 400,000 data points, a 1st degree polynomial is fitted to the 400,000 points. Then, the data is zeroed, or flattened, where the slope of the polynomial was turned to 0, and every data point had an equal number removed from from the area on the slope the data point was located.
This is done to the entire data set. Those new values are then stored, and variance data is gathered from every 100,000 data points.
Is this the general gist?

Best Answer

Removing all the unnecessary cruft, this is probably what the code reduces to. I've gone with the fact that your files are 400,000 elements long to remove the badly coded split into 400,000 elements.
I haven't tested the code so maybe got it wrong. i've kept the meaningless variable names. If I had written it, I would have used much better variable names (seriously, a as a variable name?)
%inputs:
y = load(fullfile(Directory, FileNames{FilesToRead}));  %since the file is text, it would be better to use csvread or similar instead of load
x = (1:numel(y))';
coeffs = polyfit(x, y(:), 1);
yfit = polyval(coeffs, x);  %much simpler than coding the polynomial yourself
dd2 = y - yfit;
n = 100000;
a = var(reshape(dd2, n, []));
tm = x * n / 20000 / 60;
I've not kept the t variable that is recreated again and agian as it doesn't do anything useful. If you still needed, it's the same as x.
It would be simple to add the split into 400,000 elements if it's really needed.
edit: as discussed below, I missed that dd2 gets renamed to y, replacing the original y. Seriously, who does that? What was wrong with the original dd2 (other than both being meaningless)?
Related Question