协同过滤算法，python实现

在网易公开课上看了吴恩达的课。自己用python实现了一遍

import numpy as np

R=2
alpha=0.01
beta=0.5

def norm_dataset(data_set,bool_set):
    nu=len(data_set);nm=len(data_set[0]);miu=[]
    for j in range(nm):
        sum_score=0.0;com_num=0.0
        for i in range(nu):
            if bool_set[i][j]:
                sum_score=sum_score+data_set[i][j]
                com_num=com_num+1.0
        miu.append(sum_score/com_num)
        for i in range(nu):
            if bool_set[i][j]:
                data_set[i][j]=data_set[i][j]*1.0-sum_score*1.0/com_num
            else:
                data_set[i][j]=-1.0
    return miu

def calc_loss(x,theta,data_set,bool_set):
    nu=len(data_set);nm=len(data_set[0]);total_loss=0.0
    for i in range(nu):
        for j in range(nm):
            if bool_set[i][j]:
                xTtheta=0.0;x_loss=0.0;theta_loss=0.0
                for k in range(R):
                    xTtheta=xTtheta+x[i,k]*theta[k,j]
                    x_loss=x_loss+x[i,k]*x[i,k]
                    theta_loss=theta_loss+theta[k,j]*theta[k,j]
                total_loss=total_loss+0.5*(xTtheta-data_set[i][j])*(xTtheta-data_set[i][j])+beta*x_loss+beta*theta_loss
    return total_loss

def eval(x,theta,data_set,bool_set):
    nu=len(data_set);nm=len(data_set[0]);total_loss=0.0
    for i in range(nu):
        for j in range(nm):
            if bool_set[i][j]:
                xTtheta=0.0;x_loss=0.0;theta_loss=0.0
                for k in range(R):
                    xTtheta=xTtheta+x[i,k]*theta[k,j]
                total_loss=total_loss+0.5*(xTtheta-data_set[i][j])*(xTtheta-data_set[i][j])
    return total_loss

def new_x_and_theta(x,theta,data_set,bool_set):
    nu=len(data_set);nm=len(data_set[0]);total_loss=0.0;xTtheta_minus_y=0.0
    x_partial=np.zeros((nu,R));theta_partial=np.zeros((R,nm))
    for i in range(nu):
        for j in range(nm):
            xTtheta=0.0;
            if bool_set[i][j]:
                for k in range(R):
                    xTtheta=xTtheta+x[i,k]*theta[k,j]
                for k in range(R):
                    x_partial[i,k]=x_partial[i,k]+((xTtheta-data_set[i][j])*theta[k,j]+beta*x[i,k])
                for k in range(R):
                    theta_partial[k,j]=theta_partial[k,j]+((xTtheta-data_set[i][j])*x[i,k]+beta*theta[k,j])
    for i in range(nu):
        for k in range(R):
            x[i,k]=x[i,k]-alpha*x_partial[i,k]
    for j in range(nm):
        for k in range(R):
            theta[k,j]=theta[k,j]-alpha*theta_partial[k,j]

if __name__ == '__main__':
    data_set=[[5,5,0,0],[5,-1,-1,0],[-1,4,0,-1],[0,0,5,4],[0,0,5,-1],[-1,-1,-1,-1]]
    bool_set=[[],[],[],[],[],[]]
    nu=len(data_set);nm=len(data_set[0])
    for i in range(nu):
        for j in range(nm):
            if data_set[i][j]!=-1:
                bool_set[i].append(True)
            else:
                bool_set[i].append(False)
    x=np.random.random(size=(nu,R));theta=np.random.random(size=(R,nm))
    miu=norm_dataset(data_set,bool_set)
    print(data_set)
    print(miu)
    min_loss=10000000
    final_x=np.random.random(size=(nu,R));final_theta=np.random.random(size=(R,nm))
    for e in range(1000):
        loss=calc_loss(x,theta,data_set,bool_set)
        if(loss<min_loss):
            # print(min_loss)
            min_loss=loss
            final_x=x.copy()
            final_theta=theta.copy()
        new_x_and_theta(x,theta,data_set,bool_set)
    print(final_x)
    print(final_theta)
    print(eval(final_x,final_theta,data_set,bool_set))
    result=np.zeros((nu,nm))
    for i in range(nu):
        for j in range(nm):
            for k in range(R):
                result[i,j]=result[i,j]+final_x[i,k]*final_theta[k,j]
            result[i,j]=result[i][j]+miu[j]
    for i in range(nu):
        for j in range(nm):
            if bool_set[i][j]:
                data_set[i][j]=data_set[i][j]+miu[j]
    print(result)
    print(data_set)