matlab电影推荐算法,协同过滤-基于Matlab的电影推荐

clear;clc;

[~, ~, raw] = xlsread('D:\My Documents\MATLAB\MovieLens\data.xlsx','u_data','A2:D100001');

raw(cellfun(@(x) ~isempty(x) && isnumeric(x) && isnan(x),raw)) = {''};

%% Replace non-numeric cells with NaN

R = cellfun(@(x) ~isnumeric(x) && ~islogical(x),raw); % Find non-numeric cells

raw(R) = {NaN}; % Replace non-numeric cells

%% Create output variable

data = reshape([raw{:}],size(raw));

%% Allocate imported array to column variable names

userId = data(:,1);

itemId = data(:,2);

rating = data(:,3);

timestamp = data(:,4);

%% Clear temporary variables

clearvars data raw R;

[~, ~, raw] = xlsread('D:\My Documents\MATLAB\MovieLens\data.xlsx','u_item','A2:B1683');

raw(cellfun(@(x) ~isempty(x) && isnumeric(x) && isnan(x),raw)) = {''};

cellVectors = raw(:,2);

raw = raw(:,1);

%% Create output variable

data = reshape([raw{:}],size(raw));

%% Allocate imported array to column variable names

movieId = data(:,1);

movieTitle = cellVectors(:,1);

%% Clear temporary variables

clearvars data raw cellVectors;

format long;

s=cell(0,0);

unique_userId=unique(userId);

nums_of_unique_userId=length(unique_userId);

for user_index=1:nums_of_unique_userId;

example_userId=unique_userId(user_index);

example_userIds_itemId=itemId(userId==example_userId);

example_userIds_rating=rating(userId==example_userId);

nums_of_example_userIds_itemId=length(example_userIds_itemId);

example_userId_meanRating=mean(example_userIds_rating);

s{1,user_index}=example_userId;

s{2,user_index}=example_userIds_itemId;

s{3,user_index}=example_userIds_rating;

s{4,user_index}=nums_of_example_userIds_itemId;

s{5,user_index}=example_userId_meanRating;

end

% 计算example_userID的rating平均值example_userIds_meanRating

% user_index=1;

% example_userId=unique_userId(user_index);

% example_userIds_meanRating=0;

% example_userIds_rating=s{3,user_index};

% example_userId_meanRating=mean(example_userIds_rating);

load userSim;

% 找出用户u,n相同的item和对应的rating——sameitemId_both_un矩阵包括same itemId及u,n对应的rating

% userSim=zeros(nums_of_unique_userId,nums_of_unique_userId);

% for u=1:nums_of_unique_userId

%     for n=1:nums_of_unique_userId

% % u=100;n=200;

% nums_of_us_itemId=s{4,u};

% nums_of_ns_itemId=s{4,n};

% us_meanRating=s{5,u};

% ns_meanRating=s{5,n};

% us_itemId=s{2,u};

% ns_itemId=s{2,n};

% us_rating=s{3,u};

% ns_rating=s{3,n};

%

% nums_of_sameitemId_both_un=0;

% sameitemId_both_un=[];

% for us_itemId_index=1:nums_of_us_itemId

%     for ns_itemId_index=1:nums_of_ns_itemId

%         if us_itemId(us_itemId_index)==ns_itemId(ns_itemId_index),

%             nums_of_sameitemId_both_un=nums_of_sameitemId_both_un+1;

%             sameitemId_both_un=[sameitemId_both_un;us_itemId(us_itemId_index),us_rating(us_itemId_index),ns_rating(ns_itemId_index)];

%         end

%     end

% end

%

% %计算用户u,n之间皮尔逊相关系数(pearon correlation coefficient)——userSim(u,n)

% part1=0;

% part2=0;part3=0;

% for sameitemId_both_un_index=1:nums_of_sameitemId_both_un

%     part1=part1+(sameitemId_both_un(sameitemId_both_un_index,2)-us_meanRating)*(sameitemId_both_un(sameitemId_both_un_index,3)-ns_meanRating);

%     part2=part2+(sameitemId_both_un(sameitemId_both_un_index,2)-us_meanRating)^2;

%     part3=part3+(sameitemId_both_un(sameitemId_both_un_index,3)-ns_meanRating)^2;

% end

%

% part2=max(part2,1e-3);

% part3=max(part3,1e-3);

% userSim(u,n)=part1/(sqrt(part2)*sqrt(part3));

%     end

% end