overlap.m

可视化matlab程序

%% Data visualization contest: Code overlap 
% The aim here is to try and visualize the degree of overlap between
% all pairs of entries.

load contest_data
n = length([d.id]);
t=[d.timestamp];
nlines=length(allLineList);
% cleanup author names
cleannames = regexprep(lower({d.author}), '_|\.|&| ', '')';
% author labels
lbls = strcat(cleannames,textwrap({sprintf(':%.5d',[d.id])}, 6));
% % contest phases
% [v,ind]=sort(find([d.twilight]));
% twilight=v(ind([1;end]));
% [v,ind]=sort(find([d.daylight]));
% daylight=v(ind([1;end]));

% unique authors
cn=unique(cleannames);
% number of unique authors
nc=length(cn);
% index of each authors entries
nl=zeros(n,1);
for ii=1:nc
    nl(strmatch(cn{ii},cleannames,'exact'))=ii;
end

%% Quantify code overlap
% The overlap coefficient between a pair of entries is the number of shared
% lines divided by the minimum of the two entry lengths. This yields a
% symmetric measure that ranges from 0 to 1. The pairwise overlap matrix is
% trivial to compute but time-consuming, so I've included a low precision
% pairwise overlap matrix.

if ~exist('pwoverlap.mat', 'file')
    % pw overlap coef. is symmetric and diag is 1, so save tril
    ov = zeros(n*(n-1)/2, 1, 'single');
    ctr=0;
    for ii=1:n-1
        d1 = d(ii).lines;
        nd1=length(d1);
        for jj=ii+1:n
            ctr=ctr+1;
            d2 = d(jj).lines;
            ov(ctr) = length(intersect(d1,d2)) / min(d1, length(d2));
        end
    end
    ov(isnan(ov))=0;
    save ('pwoverlap.mat','ov')
else
    load pwoverlap.mat
    % included file is a low res version saved as a 2 byte char
    if isequal(class(ov),'char')
        % scale back to float
        ov = single(ov/100);
    end
end
ovmat=squareform(ov);

%% A Pairwise overlap heatmap
% A heatmap of the pairwise overlap coefficients arranged by timestamps
% reveals the extent to which the entries were similar. There is minimal
% overlap during the darkness and twilight phases. During daylight the
% overlap is usually restricted to a single day. The entries of 1000
% character challenge [5/14 to 5/15] are quite distinct from the rest.

figure
imagesc(squareform(ov));
% set axis ticks for 12 noon of each day
dv = datevec(t(1));
ds = cell(8,1); 
dind = zeros(8,1); 
day0 = dv(3)-1;
for ii=1:8; 
    dv(3) = day0+ii; 
    dind(ii) = find(t<=datenum(dv), 1, 'last' ); 
    ds{ii} = datestr(dv,'mm/dd');
end
axis xy
set(gca,'tickdir','out','xtick',dind, 'xticklabel', ds, 'ytick',dind, 'yticklabel', ds, 'fontweight', 'bold')
xlabel('submission time');
ylabel('submission time');
title('Code overlap', 'fontsize', 12, 'fontweight', 'bold')

%% Visualize a single authors' results
% Display the overlap between entries for a single author.
authname ='yicao';
idx = find(nl==strmatch(authname, cn));
nidx=length(idx);
col_ord = repmat(idx,1,nidx)+repmat((idx-1)',nidx,1)*n;
x=ovmat(col_ord);
figure
imagesc(x);
title(sprintf ('Code overlap for %s',authname), 'fontsize',12, 'fontweight', 'bold')
ds=datestr(t(idx(get(gca,'xtick'))),'mm/dd');
axis xy
set(gca, 'tickdir', 'out', 'xticklabel',ds, 'yticklabel', ds, 'fontweight','bold')
xlabel('submission time')
ylabel('submission time')

%% Network analysis
% Use the bioinformatics toolbox to graph the highly overlapping
% entries. 
% Visualizing large networks is one area where I find Matlab lacking and need to resort to third-party tools.
% Perhaps we can see better network visualiztion tools in the future?

% value at which edges are considered significant 
ov_cutoff=0.7;

if ~isempty(ver('bioinfo'))   
    xcm=x.*(x>ov_cutoff);
    bg=biograph(xcm,lbls(idx),'LayoutType','radial','showarrows','off');
    view(bg)
else
    error('Requires the Bioinformatics Toolbox')
end