一、MF介绍

(1)实验的主要任务:使用MF模型在数据集合上的评分预测(movielens,随机80%训练数据,20%测试数据,随机构造 Koren的经典模型)

(2)参考论文:MATRIX  FACTORIZATION TECHNIQUES FOR RECOMMENDER SYSTEMS

简单模型:难点在于构造qipu,通过来预测评分rui。在构造qipu时,对于每个useritem构造为包含k个特征因子的vector

目标函数为:

3)部署环境:python37 + pytorch1.3

4)数据集:Movielensmall数据集,数据集按照8:2的比例进行划分,随机挑选80%的数据当做训练集,剩余的20%当做测试集。(数据下载网址:https://grouplens.org/datasets/movielens/

5)代码结构:

进行数据预处理以及数据划分的代码在load_data.py文件中,划分之后得到rating_train.csvrating_test.csv两个文件(数据集的划分是在抽样之后的数据集ratings_sample.csv上进行划分的)。(data文件夹下的ratings.csv为原始数据集,其中会得到一些中间文件:ratingsNoHead.csv文件为去掉数据集的表头得到的文件;ratings_sample.csv文件为从原始数据中选取1%的数据作为实验数据。)

mf.py文件是读取训练集以及测试集,并使用pytorch框架编写MF训练模型,最后使用rmse作为评价指标,使用测试集对模型进行测试。模型训练过程中采用batch对数据集进行分批训练,最终以曲线的形式展现出来。最终测试集的曲线图如下图所示:

6)评价标准:采用rmse作为评价指标,使用测试集对模型进行测试。(实验只使用了数据集中的一部分数据,同样也使用了完整的数据集进行了测试,测试误差为0.46。由于数据集较大,这里只上传使用的部分数据集。)训练集与测试集的rmse结果为:

二、代码 

 1.代码结构:

 2.load_data.py代码:

# coding: utf-8
"""
该文件主要是对数据进行预处理,将评分数据按照8:2分为训练数据与测试数据
"""
import pandas as pd
import csv
import random
import os

# 删除文件中的表头
origin_f = open('data/ratings.csv','rt',encoding='utf-8',errors="ignore")
new_f = open('data/ratingsNoHead.csv','wt+',encoding='utf-8',errors="ignore",newline="")
reader = csv.reader(origin_f)
writer = csv.writer(new_f)
i=0
for i,row in enumerate(reader):
    if i>0:
        writer.writerow(row)
origin_f.close()
new_f.close()

#从原始数据集中选取1%作为实验数据
df = pd.read_csv('data/ratingsNoHead.csv', encoding='utf-8')
df=df.sample(frac=1.0)  #全部打乱
cut_idx=int(round(0.01*df.shape[0]))
df_sample=df.iloc[:cut_idx]
#将数据存储到csv文件中
df_sample=pd.DataFrame(df_sample)
print("sample shape:",df_sample.shape)
df_sample.to_csv('data/ratings_sample_tmp.csv',index=False)
#去掉第一行
origin_f = open('data/ratings_sample_tmp.csv','rt',encoding='utf-8',errors="ignore")
new_f = open('data/ratings_sample.csv','wt+',encoding='utf-8',errors="ignore",newline="")     #必须加上newline=""否则会多出空白行
reader = csv.reader(origin_f)
writer = csv.writer(new_f)
for i,row in enumerate(reader):
    if i>0:
        writer.writerow(row)
origin_f.close()
new_f.close()
os.remove('data/ratings_sample_tmp.csv')

#将数据按照8:2的比例进行划分得到训练数据集与测试数据集
df = pd.read_csv('data/ratings_sample.csv', encoding='utf-8')
# df.drop_duplicates(keep='first', inplace=True)  # 去重,只保留第一次出现的样本
# print(df)
df = df.sample(frac=1.0)  # 全部打乱
cut_idx = int(round(0.2 * df.shape[0]))
df_test, df_train = df.iloc[:cut_idx], df.iloc[cut_idx:]
# 打印数据集中的数据记录数
print("df shape:",df.shape,"test shape:",df_test.shape,"train shape:",df_train.shape)
# print(df_train)
# 将数据记录存储到csv文件中
# 存储训练数据集
df_train=pd.DataFrame(df_train)
df_train.to_csv('data/ratings_train_tmp.csv',index=False)
# 由于一些不知道为什么的原因,使用pandas读取得到的数据多了一行,在存储时也会将这一行存储起来,所以应该删除这一行(如果有时间在查一查看能不能解决这个问题)
origin_f = open('data/ratings_train_tmp.csv','rt',encoding='utf-8',errors="ignore")
new_f = open('data/ratings_train.csv','wt+',encoding='utf-8',errors="ignore",newline="")     #必须加上newline=""否则会多出空白行
reader = csv.reader(origin_f)
writer = csv.writer(new_f)
for i,row in enumerate(reader):
    if i>0:
        writer.writerow(row)
origin_f.close()
new_f.close()
os.remove('data/ratings_train_tmp.csv')
# 存储测试数据集
df_test=pd.DataFrame(df_test)
df_test.to_csv('data/ratings_test_tmp.csv',index=False)
origin_f = open('data/ratings_test_tmp.csv','rt',encoding='utf-8',errors="ignore")
new_f = open('data/ratings_test.csv','wt+',encoding='utf-8',errors="ignore",newline="")
reader = csv.reader(origin_f)
writer = csv.writer(new_f)
for i,row in enumerate(reader):
    if i>0:
        writer.writerow(row)
origin_f.close()
new_f.close()
os.remove('data/ratings_test_tmp.csv')

3.模型文件mf.py代码:

import pandas as pd
import torch as pt
import numpy as np
import torch.utils.data as Data
import matplotlib.pyplot as plt

BATCH_SIZE=100

# 读取测试以及训练数据
cols=['user','item','rating','timestamp']
train=pd.read_csv('data/ratings_train.csv',encoding='utf-8',names=cols)
test=pd.read_csv('data/ratings_test.csv',encoding='utf-8',names=cols)

# 去掉时间戳
train=train.drop(['timestamp'],axis=1)
test=test.drop(['timestamp'],axis=1)
print("train shape:",train.shape)
print("test shape:",test.shape)

#userNo的最大值
userNo=max(train['user'].max(),test['user'].max())+1
print("userNo:",userNo)
#movieNo的最大值
itemNo=max(train['item'].max(),test['item'].max())+1
print("itemNo:",itemNo)

rating_train=pt.zeros((itemNo,userNo))
rating_test=pt.zeros((itemNo,userNo))
for index,row in train.iterrows():
    #train数据集进行遍历
    rating_train[int(row['item'])][int(row['user'])]=row['rating']
print(rating_train[0:3][1:10])
for index,row in test.iterrows():
    rating_test[int(row['item'])][int(row['user'])] = row['rating']

def normalizeRating(rating_train):
    m,n=rating_train.shape
    # 每部电影的平均得分
    rating_mean=pt.zeros((m,1))
    #所有电影的评分
    all_mean=0
    for i in range(m):
        #每部电影的评分
        idx=(rating_train[i,:]!=0)
        rating_mean[i]=pt.mean(rating_train[i,idx])
    tmp=rating_mean.numpy()
    tmp=np.nan_to_num(tmp)        #对值为NaN进行处理,改成数值0
    rating_mean=pt.tensor(tmp)
    no_zero_rating=np.nonzero(tmp)                #numpyy提取非0元素的位置
    # print("no_zero_rating:",no_zero_rating)
    no_zero_num=np.shape(no_zero_rating)[1]   #非零元素的个数
    print("no_zero_num:",no_zero_num)
    all_mean=pt.sum(rating_mean)/no_zero_num
    return rating_mean,all_mean

rating_mean,all_mean=normalizeRating(rating_train)
print("all mean:",all_mean)

#训练集分批处理
loader = Data.DataLoader(
    dataset=rating_train,      # torch TensorDataset format
    batch_size=BATCH_SIZE,      # 最新批数据
    shuffle=False           # 是否随机打乱数据
)

loader2 = Data.DataLoader(
    dataset=rating_test,      # torch TensorDataset format
    batch_size=BATCH_SIZE,      # 最新批数据
    shuffle=False           # 是否随机打乱数据
)

class MF(pt.nn.Module):
    def __init__(self,userNo,itemNo,num_feature=20):
        super(MF, self).__init__()
        self.num_feature=num_feature     #num of laten features
        self.userNo=userNo               #user num
        self.itemNo=itemNo               #item num
        self.bi=pt.nn.Parameter(pt.rand(self.itemNo,1))    #parameter
        self.bu=pt.nn.Parameter(pt.rand(self.userNo,1))    #parameter
        self.U=pt.nn.Parameter(pt.rand(self.num_feature,self.userNo))    #parameter
        self.V=pt.nn.Parameter(pt.rand(self.itemNo,self.num_feature))    #parameter

    def mf_layer(self,train_set=None):
        # predicts=all_mean+self.bi+self.bu.t()+pt.mm(self.V,self.U)
        predicts =self.bi + self.bu.t() + pt.mm(self.V, self.U)
        return predicts

    def forward(self, train_set):
        output=self.mf_layer(train_set)
        return output


num_feature=2    #k
mf=MF(userNo,itemNo,num_feature)
mf
print("parameters len:",len(list(mf.parameters())))
param_name=[]
params=[]
for name,param in mf.named_parameters():
    param_name.append(name)
    print(name)
    params.append(param)
# param_name的参数依次为bi,bu,U,V

lr=0.3
_lambda=0.001
loss_list=[]
optimizer=pt.optim.SGD(mf.parameters(),lr)
# 对数据集进行训练
for epoch in range(1000):
    optimizer.zero_grad()
    output=mf(train)
    loss_func=pt.nn.MSELoss()
    # loss=loss_func(output,rating_train)+_lambda*(pt.sum(pt.pow(params[2],2))+pt.sum(pt.pow(params[3],2)))
    loss = loss_func(output, rating_train)
    loss.backward()
    optimizer.step()
    loss_list.append(loss)

print("train loss:",loss)

#评价指标rmse
def rmse(pred_rate,real_rate):
    #使用均方根误差作为评价指标
    loss_func=pt.nn.MSELoss()
    mse_loss=loss_func(pred_rate,real_rate)
    rmse_loss=pt.sqrt(mse_loss)
    return rmse_loss

# 测试网络
#测试时测试的是原来评分矩阵为0的元素,通过模型将为0的元素预测一个评分,所以需要找寻评分矩阵中原来元素为0的位置。
prediction=output[np.where(rating_train==0)]
#评分矩阵中元素为0的位置对应测试集中的评分
rating_test=rating_test[np.where(rating_train==0)]
rmse_loss=rmse(prediction,rating_test)
print("test loss:",rmse_loss)

plt.clf()
plt.plot(range(epoch+1),loss_list,label='Training data')
plt.title("The MovieLens Dataset Learning Curve")
plt.xlabel('Number of Epochs')
plt.ylabel('RMSE')
plt.legend()
plt.grid()
plt.show()

如果有疑问,欢迎留言。

posted on 2020-01-05 15:31  wyhluckydog  阅读(3310)  评论(0编辑  收藏  举报