ProbS CF matlab源代码（二分系统）(原创作品，注明出处，谢谢！)
%ProbS
clear all;
%% 数据读入与预处理
data = load('E:\network_papers\u1.base');
test = load('E:\network_papers\u1.test');
R = preprocess(data.train);
T = preprocess(test.test);
[M,N] = size(R);
[m,n] = size(T);
w = resource_allocate(R,du,di);
for u = 1:M
index_i_n(u).id = find( R(u,:) == 0 );
end
%% 对每个用户u,对其所有uncollected items预测评分
PR = zeros(M,N);
for u = 1:M
index_y = find( R(u,:) ~= 0 );
vec = R(u,index_y);
for k = 1:length(index_i_n(u).id)
PR( u, index_i_n(u).id(k) ) = w( index_i_n(u).id(k), index_y ) * vec';
end
end
value = evaluate('precision',R,PR,T,index_i_n);
hit=hitrate(PR,T,20);
save predi_matrix PR;
------------------------------------------------------------------------------------------------
%Preprocess
function R = preprocess (A)
[m,n] = size(A);
M = max( A(:,1) );
N = max( A(:,2) );
B(M,N) = 0;
for i = 1:m
B( A(i,1), A(i,2) ) = A(i,3);
end
B( B < 3 ) = 0;
B( B >= 3 ) = 1;
R = B;
-------------------------------------------------------------------------------------------------------------
%evalate
% evaluate function for multiplied rate for recommendation system
% opt：选择的评价标准,PR：经过预评分的训练集,T：测试集，index_n:所有用户没有评价的物品的索引
function value = evaluate(opt,R,PR,T,index_i_n)
[m,n] = size(T);
[M,N] = size(R);
%% 选择评价方法
switch (opt)
%% 均方根差
case {'RMSE'}
RMSE = zeros(1,m);
for u = 1:m
index_tmp = index_i_n(u).id;
index_tmp( index_tmp > n ) = [];
len = length(index_tmp);
vec = PR(u,index_tmp) - T(u,index_tmp);
RMSE(u) = sqrt( sum( vec .* vec ) / len );
if ~(mod(u,10))
fprintf('%d\n',u);
end
end
value = sum(RMSE) / length(RMSE);
fprintf('The RMSE is:\n%d',value);
%% Pearson积矩相关系数，衡量预测评分和真实评分的线性相关程度
% pcc在-1到1之间，越靠近1或者-1，线性相关性越好，0表示没有相关性
case {'pcc'}
pcc = zeros(1,m);
for u = 1:m
index_tmp = index_i_n(u).id;
index_tmp( index_tmp > n ) = [];
len = length(index_tmp);
predict = PR(u,index_tmp);
real = T(u,index_tmp);
mean_predict = sum(predict) / len;
mean_real = sum(real) / length(real);
vec1 = predict - mean_predict;
vec2 = real - mean_real;
sum1 = vec1 * vec1';
sum2 = vec2 * vec2';
if ( sum1 ~= 0 ) && ( sum2 ~= 0 )
pcc(u) = vec1 * vec2' / sqrt( sum1 * sum2 );
end
if ~(mod(u,10))
fprintf('%d\n',u);
end
end
value = sum(pcc) / m;
fprintf('The PCC is:\n%d',value);
%% 命中率hitting rate 只适用于二值标准，如“喜欢”、“不喜欢”
case {'hitrate'}
[SR,index_sr] = sort(PR,2,'descend');
rato(m,n) = 0;
for u = 1:m
sumu = sum(T(u,:));
rec = 1;
while rec <= n
tmp1 = index_sr(u,1:rec);
tmp1( tmp1 > n ) = [];
tmp2 = T(u,tmp1);
if (sumu ~= 0)
rato(u,rec) = sum(tmp2) / sumu;
end
rec = rec + 1;
end
if ~(mod(u,10))
fprintf('%d\n',u);
end
end
value = sum(rato) / m;
x = 1:length(value);
plot(x,value,'--r');
hold on;
xlabel('length of recommendation list');
ylabel('hitting rate');
%% 平均排序分
case {'rankscore'}
[SR,index_sr] = sort(PR,2,'descend');
%rato = zeros( 1, m );
for u = 1:m
len1 = length( index_i_n(u).id );
index_i_t = find( T(u,:) == 1 );
len2 = length( index_i_t );
index_tmp = zeros( 1, len2 );
if len2 ~= 0
for k = 1:len2
tmp = index_i_t(k);
index_tmp(k) = find( index_sr(u,:) == tmp );
end
rato(u) = sum( index_tmp / len1 ) / len2;
end
end
value = sum(rato) / length(rato);
fprintf('The average rank score is:\n%d\n',value);
%% 准确度及准确度提高比例
case {'precision'}
L = 10;
[SR,index_sr] = sort(PR,2,'descend');
list = index_sr(:,1:L);
p = zeros(1,m);
for u = 1:m
index_i_t = find( T(u,:) == 1 );
vec = intersect( index_i_t, list(u,:) );
p(u) = numel(vec) / L;
end
value = sum(p) / m;
ep = value * M * N / sum( sum(T) );
fprintf('The precision is:\n%d\n',value);
fprintf('The precision enhancement is:\n%d\n',ep);
%% recall & recall enhancement
case {'recall'}
L = 20;
[SR,index_sr] = sort(PR,2,'descend');
list = index_sr(:,1:L);
for u = 1:m
index_i_t = find( T(u,:) == 1 );
vec = ismember( index_i_t, list(u,:) );
if sum( T(u,:) ) ~= 0
recall(u) = sum(vec) / sum( T(u,:) );
end
end
value = sum(recall) / length(recall);
er = value * M / L;
fprintf('The recall is:\n%d\n',value);
fprintf('The recall enhancement is:\n%d\n',er);
%% personalization
case {'personalization'}
L = 20;
[SR,index_sr] = sort(PR,2,'descend');
list = index_sr(:,1:L);
flag = 1;
h = zeros(m,m);
for u = 1:m
for k = flag:m
tmp = intersect( list(u,:), list(k,:) );
h(u,k) = 1 - length( tmp ) / L;
h(k,u) = h(u,k);
end
flag = flag + 1;
end
value = sum( sum(h) ) / ( m^2 - m );
fprintf('The personalization is:\n%d\n',value);
case {'novelty'}
degree_i = sum( R,1 );
L = 20;
[SR,index_sr] = sort(PR,2,'descend');
list = index_sr(:,1:L);
I = zeros(1,m);
for u = 1:m
vec1 = degree_i( 1, list(u,:) );
vec2 = M ./ vec1;
mult = 1;
for k = 1:length(vec2)
mult = mult * vec2(k);
end
I(u) = log2(mult) / L;
end
value = sum(I) / m;
fprintf('The novelty is:\n%d\n',value);
end
-------------------------------------------------------------------------------------------------
%CF
%% 数据预处理
clear all;
%data = load('E:\network_papers\datasets\Jester\jeste_train');
%test = load('E:\network_papers\datasets\Jester\jester_test');
data = load('E:\network_papers\u1.base');
test = load('E:\network_papers\u1.test');
R = preprocess(data);
T = preprocess(test);
%{
R=data.train;
R(R<3)=0;
R(R>=3)=1;
T=test.test;
T(T<3)=0;
T(T>=3)=1;
du = sum(R,2);
di = sum(R,1);
ex=find(du==0);
R(ex,:)=[];
T(ex,:)=[];
du(ex,:)=[];
%}
[M,N] = size(R);
[m,n] = size(T);
for u = 1:M
index_i_n(u).id = find( R(u,:) == 0 );
end
%% 计算出每个用户与其他用户之间的相似度
sim = get_Sim_u(R);
%% 预测评分
PR = zeros(M,N);
for u = 1:M
index_n = find( R(u,:) == 0 );
for k = 1:length( index_n )
PR( u, index_n(k) ) = predict_Rate( u, index_n(k), sim, R );
end
end
value = evaluate('precision',R,PR,T,index_i_n);
hit=hitrate(PR,T,20);