%% test for princomp(Principal Component Analysis)
clear all;
clc;
close all;
%% load data set
data=xlsread('D:\XX\PCA.xlsx','xx'); % input the name of files and sheets
%  data2=data(:, 201:1951);
%% box plot forratings data
% To get a quickimpression of the ratings data, make a box plot
% figure;
% boxplot(data2,'orientation','horizontal','labels',categories);
% grid on;
%% pre-process
% stdr =std(data2);
% sr=repmat(stdr,400,1);
% sr =data2./repmat(stdr,400,1);
%% use princomp
[coeff,score,latent,tsquare]= pca(data,'NumComponents',10); 
%% extract the principal component 
% figure;
percent_explained= 100*latent/sum(latent); %cumsum(latent)./sum(latent)
pareto(percent_explained);
xlabel('PrincipalComponent');
ylabel('VarianceExplained (%)');
%% Visualizing theResults
% figure;
% biplot(coeff(:,1:2),'scores',score(:,1:2),...
% 'varlabels',categories);

%  biplot(coeff(:,1:10),'scores',score(:,1:10),'varlabels',categories);

% biplot(coeff(:,1:2),'varlabels',categories);
% hold on
% scatter(score(1:150,1),score(1:150,2),'g')
% 
% hold on; scatter(score(151:329,1),score(151:329,2),'r')
% axis([-.26 1 -.51.51]);