myentry.m

%% Data Visualization Contest: Some of My Plots

load contest_data

% First load all the fields into corresponding variables.

score=[d.score];
timestamp=[d.timestamp];
passed=[d.passed];
title=[d.title];
author=[d.author];
result=[d.result];
cpu_time=[d.cpu_time];
id=[d.id];
parent=[d.parent];
darkness=[d.darkness];
twilight=[d.twilight];
daylight=[d.daylight];
nodeCount=[d.nodeCount];
mlintMsgCount=[d.mlintMsgCount];
maxComplexity=[d.maxComplexity];
%lines=[d.lines];
charCount=[d.charCount];

%% Strategy Evolution Waterfall !!
% The following 3D plot visualizes the strategy.
% In this plot, the score, result and CPU time are plotted along X-, Y- and
% Z-axis respectively.
%
% We can see a heavy parabolic cluster at the front of the graph. This shows
% that one of the final strategy to decrease the score was to settle at some result,
% then decreasing the cpu time (by tweaking other entries ;)-). As we know,
% this happened during the end phase of the contest.
% If things were ideally general, one would expect a diagonal cluster, i.e.
% connecting the two ends of the parabola.
figure('Position',[50 100 756 588])
plot3(score,result,cpu_time,'.');grid on;xlabel('Score'),ylabel('Result'),zlabel('CPU time (s)'),view([-57,28]);


%% Submission Distribution
% Let's see how many submissions were there per day. First day is tough, so
% there is minimal number of entry, daylight raises interest, hence maximal
% entry, twilight as well as end phase of contest show similar amount of
% entries. However, number of twilight entries could be resuting from
% different authors posting little number of entries, while during end
% phase, same authors submitted large number of entries. So, the ratio of
% number of entries to the number of authors could  be very interesting.
md=datevec(timestamp);

entry=[];
for i=9:16
    entry(end+1)=numel(find(md(:,3)==i)>0);
end
contestdate=9:16;
figure('Position',[50 100 800 800])
subplot(221),plot(contestdate,entry,'*-'),axis([9 16 min(entry)-10 max(entry)+10]),ylabel('Total number of entries'),xlabel('Day of May-2007');
subplot(222),plot(contestdate,cumsum(entry),'*-'),axis([9 16 0 sum(entry)+50]),ylabel('Cumulative number of entries'),xlabel('Day of May-2007');
subplot(223),pie(entry,{'May 9','May 10','May 11','May 12','May 13','May 14','May 15','May 16'});
subplot(224),pie(entry);

%% Code Complexity
% Judging the complexity of code development is pretty interesting. The
% following plot shows the variance of the cyclomatic complexity for all
% the entries submitted per day. As expected, codes of different complexity
% were submitted during the darkness and twilight, hence the variances are
% high for those phases. On the other hand, during daylight onwards till 
% the end phase, code development concentrated on some particular good entries 
% from the previous phases. Hence, the complexity settle down to a steady state.
%
% A comment: if at later stage, somehow the contest testsuite can be
% modified so that again entries of different complexities need to be
% developed, things would be very interesting.
%
ce=cumsum(entry);
index=[[1,ce(1:end-1)+1]; ce]';

var_cmplx=zeros(1,8); %for eight days
for i=1:8
    var_cmplx(i)=var(maxComplexity(index(i,1):index(i,2)));
end
figure(3)
plot(contestdate,var_cmplx,'*-'),ylabel('Variance of cyclomatic complexity'),xlabel('Day of May-2007'),title('Code complexity');