贝叶斯个性化排序 bpr

一些要注意的点

1.虽然训练集和测试集都只保留4、5分的数据，但是最后做推荐时不需要去掉小于4分的数据，只需要按照从高到低的顺序推荐即可。

2.损失函数中的和都指的是预测分数而不是训练集里的实际评分，因为这是单类问题，只有喜欢与不喜欢两种状态。

import math
import numpy as np
import pandas as pd
from random import *
import sys
import random
from sklearn.metrics.pairwise import pairwise_distances
from sklearn.metrics import precision_score, recall_score, f1_scoreimport sysimport sys# log_print = open('Bayesian.py运行结果.log', 'w')
# sys.stdout = log_print
# sys.stderr = log_printdef getSigma(a):return 1/(1+math.exp(-a));d = 20
au = av = bu = bv = 0.01;
gama = 0.01;
T = 500k = 50col = ['user','movie','rating','timestamp']
Origin_data = pd.read_csv('./ml-100k/u1.base',sep='\t',names=col,encoding='latin-1')
test_data = pd.read_csv('./ml-100k/u1.test',sep='\t',names=col,encoding='latin-1')
Origin_data.drop(['timestamp'],axis=1,inplace=True)
Origin_data  = Origin_data[(Origin_data['rating']==4)|(Origin_data['rating']==5)]test_data.drop(['timestamp'],axis=1,inplace=True)
test_data  = test_data[(test_data['rating']==4)|(test_data['rating']==5)]ori_user = Origin_data['user'].drop_duplicates()
ori_user = ori_user.tolist()ori_movie = Origin_data['movie'].drop_duplicates()
ori_movie = ori_movie.tolist();test_user = test_data['user'].drop_duplicates()
test_user = test_user.tolist()like_user = {}
dislike_user = {}for i in range(len(Origin_data)):u = Origin_data.iloc[i]['user']m = Origin_data.iloc[i]['movie']r = Origin_data.iloc[i]['rating']if u not in like_user:like_user[u] = []if u not in dislike_user:dislike_user[u] = []if(r >= 4):like_user[u].append(m)for i in ori_user:dislike_user[i] = list(set(ori_movie)-set(like_user[i]))test_like_user = {}for i in range(len(test_data)):u = test_data.iloc[i]['user']m = test_data.iloc[i]['movie']r = test_data.iloc[i]['rating']if u not in test_like_user:test_like_user[u] = []if r >= 4:test_like_user[u].append(m)n = len(ori_user)
m = len(ori_movie)aver = len(Origin_data)/n/mU = {}
V = {}
bias = {}for i in ori_user:tem = np.random.random(d);tem = (tem-0.5)*0.01U[i] = tem;for i in ori_movie:tem = np.random.random(d);tem = (tem - 0.5) * 0.01V[i] = tem;for i in ori_movie:user = Origin_data.loc[Origin_data['movie']==i]['user'].drop_duplicates()sum = len(user)/n - averbias[i] = sumlenth = len(Origin_data)for t in range(T):for t2 in range(lenth):ran = randint(0,lenth - 1)u = Origin_data.iloc[ran]['user']i = Origin_data.iloc[ran]['movie']l = len(dislike_user[u])ran1 = randint(0,l-1)j = dislike_user[u][ran1]rui = np.sum(U[u]*V[i])+bias[i]ruj = np.sum(U[u]*V[j])+bias[j]ruij = rui-ruj;#print(ruij)sig = getSigma((-ruij))# print(U[u]*V[m].T)# print(rui)# print(np.sum(U[u]*V[m]))delUu = -sig*(V[i]-V[j])+au*U[u]delVi = -sig*U[u]+av*V[i];delVj = -sig*(-U[u])+av*V[j]delbi = -sig + bv*bias[i];delbj = -sig*(-1)+bv*bias[j];U[u] = U[u] - gama * delUuV[i] = V[i] - gama * delViV[j] = V[j] - gama * delVjbias[i] = bias[i] - gama * delbibias[j] = bias[j] - gama * delbjrecomand = {}
p = 0
r = 0
for u in test_user:rec = []ratingHash = {}testSet = set(test_like_user[u])lenth = len(testSet)hav = set(like_user[u])num = 1for m in ori_movie:if m not in hav:ratingHash[m] = np.sum(U[u]*V[m])+bias[m]ratingHash = sorted(ratingHash.items(),key=lambda x:x[1],reverse=True)for i,val in ratingHash:if (num == 6):break;if i in testSet:p += 1/5r += 1/lenthnum+=1p/=len(test_user)
r/=len(test_user)print(p)
print(r)# log_print.close();

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！