News Recommendation of Tianchi Competition

Competition address: recommendation system-news recommendation

1 Introduction

Environment: I use Google colab and Tianchi Lab can also be used for free.

There are 5 data sets, namely:

• train_click_log.csv: Training set user click log

• testA_click_log.csv: Test set user click log

• articles.csv: News article information data table

• articles_emb.csv: news article embedding vector representation

• sample_submit.csv: Submit sample file

I downloaded it and uploaded it to my Google Cloud Disk.

News article information data table:

Training set user click log:

Test set user click log:

News article embedding vector representation:

Submit sample file:

2.baseline：

1. Obtain Google Cloud Disk permissions

from google.colab import drive
drive.mount('/content/drive')

%cd /content/drive/My Drive
!ls

2. Import the library

# import packages
import time, math, os
from tqdm import tqdm
import gc
import pickle
import random
from datetime import datetime
from operator import itemgetter
import numpy as np
import pandas as pd
import warnings
from collections import defaultdict
import collections
warnings.filterwarnings('ignore')

3. Data address

data_path = '比赛/入门推荐系统新闻推荐/datasets/' # 数据路径
save_path = '比赛/入门推荐系统新闻推荐/'  # 保存路径

4. Get User-Article-Click Time Dictionary

# 根据点击时间获取用户的点击文章序列   {user1: [(item1, time1), (item2, time2)..]...}
def get_user_item_time(click_df):
    
    click_df = click_df.sort_values('click_timestamp')
    
    def make_item_time_pair(df):
        return list(zip(df['click_article_id'], df['click_timestamp']))
    
    user_item_time_df = click_df.groupby('user_id')['click_article_id', 'click_timestamp'].apply(lambda x: make_item_time_pair(x))\
                                                            .reset_index().rename(columns={
    
    0: 'item_time_list'})
    user_item_time_dict = dict(zip(user_item_time_df['user_id'], user_item_time_df['item_time_list']))
    
    return user_item_time_dict

5. Get the topk articles with the most clicks

# 获取近期点击最多的文章
def get_item_topk_click(click_df, k):
    topk_click = click_df['click_article_id'].value_counts().index[:k]
    return topk_click

6. Item similarity calculation of itemcf

def itemcf_sim(df):
    """
        文章与文章之间的相似性矩阵计算
        :param df: 数据表
        :item_created_time_dict:  文章创建时间的字典
        return : 文章与文章的相似性矩阵
        思路: 基于物品的协同过滤(详细请参考上一期推荐系统基础的组队学习)， 在多路召回部分会加上关联规则的召回策略
    """
    
    user_item_time_dict = get_user_item_time(df)
    
    # 计算物品相似度
    i2i_sim = {
    
    }
    item_cnt = defaultdict(int)
    for user, item_time_list in tqdm(user_item_time_dict.items()):
        # 在基于商品的协同过滤优化的时候可以考虑时间因素
        for i, i_click_time in item_time_list:
            item_cnt[i] += 1
            i2i_sim.setdefault(i, {
    
    })
            for j, j_click_time in item_time_list:
                if(i == j):
                    continue
                i2i_sim[i].setdefault(j, 0)
                
                i2i_sim[i][j] += 1 / math.log(len(item_time_list) + 1)
                
    i2i_sim_ = i2i_sim.copy()
    for i, related_items in i2i_sim.items():
        for j, wij in related_items.items():
            i2i_sim_[i][j] = wij / math.sqrt(item_cnt[i] * item_cnt[j])
    
    # 将得到的相似性矩阵保存到本地
    pickle.dump(i2i_sim_, open(save_path + 'itemcf_i2i_sim.pkl', 'wb'))
    
    return i2i_sim_

i2i_sim = itemcf_sim(all_click_df)

7.itemcf article recommendation

# 基于商品的召回i2i
def item_based_recommend(user_id, user_item_time_dict, i2i_sim, sim_item_topk, recall_item_num, item_topk_click):
    """
        基于文章协同过滤的召回
        :param user_id: 用户id
        :param user_item_time_dict: 字典, 根据点击时间获取用户的点击文章序列   {user1: [(item1, time1), (item2, time2)..]...}
        :param i2i_sim: 字典，文章相似性矩阵
        :param sim_item_topk: 整数， 选择与当前文章最相似的前k篇文章
        :param recall_item_num: 整数， 最后的召回文章数量
        :param item_topk_click: 列表，点击次数最多的文章列表，用户召回补全        
        return: 召回的文章列表 {item1:score1, item2: score2...}
        注意: 基于物品的协同过滤(详细请参考上一期推荐系统基础的组队学习)， 在多路召回部分会加上关联规则的召回策略
    """
    
    # 获取用户历史交互的文章
    user_hist_items = user_item_time_dict[user_id]
    user_hist_items_ = {
    
    user_id for user_id, _ in user_hist_items}
    
    item_rank = {
    
    }
    for loc, (i, click_time) in enumerate(user_hist_items):
        for j, wij in sorted(i2i_sim[i].items(), key=lambda x: x[1], reverse=True)[:sim_item_topk]:
            if j in user_hist_items_:
                continue
                
            item_rank.setdefault(j, 0)
            item_rank[j] +=  wij
    
    # 不足10个，用热门商品补全
    if len(item_rank) < recall_item_num:
        for i, item in enumerate(item_topk_click):
            if item in item_rank.items(): # 填充的item应该不在原来的列表中
                continue
            item_rank[item] = - i - 100 # 随便给个负数就行
            if len(item_rank) == recall_item_num:
                break
    
    item_rank = sorted(item_rank.items(), key=lambda x: x[1], reverse=True)[:recall_item_num]
        
    return item_rank

8. Recommend articles to each user based on collaborative filtering of items

# 定义
user_recall_items_dict = collections.defaultdict(dict)

# 获取 用户 - 文章 - 点击时间的字典
user_item_time_dict = get_user_item_time(all_click_df)

# 去取文章相似度
i2i_sim = pickle.load(open(save_path + 'itemcf_i2i_sim.pkl', 'rb'))

# 相似文章的数量
sim_item_topk = 10

# 召回文章数量
recall_item_num = 10

# 用户热度补全
item_topk_click = get_item_topk_click(all_click_df, k=50)

for user in tqdm(all_click_df['user_id'].unique()):
    user_recall_items_dict[user] = item_based_recommend(user, user_item_time_dict, i2i_sim, 
                                                        sim_item_topk, recall_item_num, item_topk_click)

9. Convert the recall dictionary to df

# 将字典的形式转换成df
user_item_score_list = []

for user, items in tqdm(user_recall_items_dict.items()):
    for item, score in items:
        user_item_score_list.append([user, item, score])

recall_df = pd.DataFrame(user_item_score_list, columns=['user_id', 'click_article_id', 'pred_score'])

10. Generate submission files

# 生成提交文件
def submit(recall_df, topk=5, model_name=None):
    recall_df = recall_df.sort_values(by=['user_id', 'pred_score'])
    recall_df['rank'] = recall_df.groupby(['user_id'])['pred_score'].rank(ascending=False, method='first')
    
    # 判断是不是每个用户都有5篇文章及以上
    tmp = recall_df.groupby('user_id').apply(lambda x: x['rank'].max())
    assert tmp.min() >= topk
    
    del recall_df['pred_score']
    submit = recall_df[recall_df['rank'] <= topk].set_index(['user_id', 'rank']).unstack(-1).reset_index()
    
    submit.columns = [int(col) if isinstance(col, int) else col for col in submit.columns.droplevel(0)]
    # 按照提交格式定义列名
    submit = submit.rename(columns={
    
    '': 'user_id', 1: 'article_1', 2: 'article_2', 
                                                  3: 'article_3', 4: 'article_4', 5: 'article_5'})
    
    save_name = save_path + model_name + '_' + datetime.today().strftime('%m-%d') + '.csv'
    submit.to_csv(save_name, index=False, header=True)

# 获取测试集
tst_click = pd.read_csv(data_path + 'testA_click_log.csv')
tst_users = tst_click['user_id'].unique()

# 从所有的召回数据中将测试集中的用户选出来
tst_recall = recall_df[recall_df['user_id'].isin(tst_users)]

# 生成提交文件
submit(tst_recall, topk=5, model_name='itemcf_baseline')

The final online score is 0.1026. This baseline does not use all the training data, but only sampled some data to test the code, etc. The follow-up will continue to optimize the score! Come on!