推荐模型BPR数据构建（含构建正负样本对）

参考链接：
https://www.cnblogs.com/leimu/p/13949945.html

1.读数据

import numpy as np 
import pandas as pd 
import scipy.sparse as sp
import torch.utils.data as data
import torch
import torch.nn as nn
import os
import time
dataset = 'ml-1m'
main_path = './Data/'
train_rating = main_path + '{}.train.rating'.format(dataset)
test_rating = main_path + '{}.test.rating'.format(dataset)
test_negative = main_path + '{}.test.negative'.format(dataset)
model_path = './models/'
BPR_model_path = model_path + 'BPR.pth'# 1、训练集
train_data = pd.read_csv(train_rating, sep='\t', header=None, names=['user', 'item'], usecols=[0, 1], dtype={0: np.int32, 1: np.int32})user_num = train_data['user'].max() + 1
item_num = train_data['item'].max() + 1
train_data = train_data.values.tolist()
# 2、训练样本转换为稀疏矩阵
train_mat = sp.dok_matrix((user_num, item_num), dtype=np.float32)
fo

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！