else: d[row[2]] = d.get(row[2]) + '===' + row[4] item_review_l = list(d.items()) print(item_review_l[0][1]) ''' #分词，去除停用词，stem， #构建词典 #构建词袋 #lda 输出 trainfile = '../data/[email protected]' train_df = preprocess.readdata(trainfile, ',') train_list = preprocess.create_train_list(train_df) testset_df = pd.read_csv('../data/[email protected]', header=None) #构建两个字典，分别是用户-情感向量，物品-topic向量 #1. 构建字典user-pref矩阵 uisv_names = ['user', 'item', 'sentiment', 'vector', 'pref'] uisv_df = pd.read_csv('../data/out3/uisv3.csv', header=None, names=uisv_names) user_l = uisv_df['user'].tolist() pref_l = uisv_df['pref'].tolist() u_dict = dict(zip(user_l, pref_l)) #2 构建item-vertor矩阵
sys.path.append("..")
from utils.logger import get_logger
from preprocess import preprocess
from model import bmf
import pandas as pd
import numpy as np
logger = get_logger('e_BMF_list')
filename = 'j:/amazon/output/[email protected]'
dataname = filename.split('/')[-1]
#outpath
outpath = 'j:/amazon/result/result4/'
#0.读取数据
ratings = preprocess.readdata(filename, ',')
#1.判断是否有重复元素，如果有，去除重复元素
ratings_d = preprocess.drop_duplicate(ratings)
#2. 替换user_id 与 item_id
ratings_r, users, items = preprocess.replace_user_and_item(ratings_d)
#基本数据描述(包含数据总数目，用户数，物品数)
#用户数
m = len(users)
n = len(items)
logger.info('dataset:' + dataname + ',ratings:' + str(len(ratings_r)) +
',user:'******',item:' + str(n))
#3. 切分数据
trainset, testset = preprocess.split_data(ratings_r, 0.8)
trainset.to_csv(outpath + 'trainset' + '_' + dataname, index=None, header=None)
import sys
sys.path.append('../')
from preprocess import preprocess
import numpy as np
ratings_df = preprocess.readdata('j:/amazon/output/[email protected]',',')
ratings_r_df,users,items = preprocess.replace_user_and_item(ratings_df)
l = []
#row[0]=index,row[1]=user_id,row[2]=item_id
for row in ratings_r_df.itertuples():
t = [(row[1],row[2]),row[3]]
l.append(t)
row = l[0]
print(row)
print(row[0][0],row[0][1],row[1])
'''
@desc:训练
@param:trainMatrix,k(int,代表factors数量)
@return:u,v(m*k和n*k的矩阵)
'''
def train(l,k):
m = len(users)
n = len(items)
alpha = 0.01
lamda = 0.01
u = np.random.rand(m,k)