推荐系统实践之新闻推荐baseline理解

%matplotlib inline
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
plt.rc('font', family='SimHei', size=13)
import os,gc,re,warnings,sys
warnings.filterwarnings("ignore")

# path = './data/' # 自定义的路径
path='./data_raw/'
trn_click = pd.read_csv(path+'train_click_log.csv')
#trn_click = pd.read_csv(path+'train_click_log.csv', names=['user_id','item_id','click_time','click_environment','click_deviceGroup','click_os','click_country','click_region','click_referrer_type'])
item_df = pd.read_csv(path+'articles.csv')
item_df = item_df.rename(columns={'article_id': 'click_article_id'})  #重命名，方便后续match
item_emb_df = pd.read_csv(path+'articles_emb.csv')
#####test
tst_click = pd.read_csv(path+'testA_click_log.csv')

trn_click.head()

item_df.head()

item_emb_df.head()

'运行
运行

trn_click['rank'] = trn_click.groupby(['user_id'])['click_timestamp'].rank(ascending=False).astype(int)
tst_click['rank'] = tst_click.groupby(['user_id'])['click_timestamp'].rank(ascending=False).astype(int)

trn_click['click_cnts'] = trn_click.groupby(['user_id'])['click_timestamp'].transform('count')
tst_click['click_cnts'] = tst_click.groupby(['user_id'])['click_timestamp'].transform('count')

trn_click.groupby(['user_id'])['click_timestamp'].transform('count')
• 1

0          11
1          11
2          11
3          40
4          40
           ..
1112618     4
1112619     2
1112620     2
1112621    14
1112622    14
Name: click_timestamp, Length: 1112623, dtype: int64

trn_click.groupby(['user_id'])['click_timestamp'].agg('count')

user_id
0          2
1          2
2          2
3          2
4          2
          ..
199995     7
199996    13
199997     2
199998    40
199999    11
Name: click_timestamp, Length: 200000, dtype: int64

trn_click = trn_click.merge(item_df, how='left', on=['click_article_id'])
trn_click.head()

trn_click.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1112623 entries, 0 to 1112622
Data columns (total 17 columns):
user_id                1112623 non-null int64
click_article_id       1112623 non-null int64
click_timestamp        1112623 non-null int64
click_environment      1112623 non-null int64
click_deviceGroup      1112623 non-null int64
click_os               1112623 non-null int64
click_country          1112623 non-null int64
click_region           1112623 non-null int64
click_referrer_type    1112623 non-null int64
rank                   1112623 non-null int32
click_cnts             1112623 non-null int64
category_id_x          1112623 non-null int64
created_at_ts_x        1112623 non-null int64
words_count_x          1112623 non-null int64
category_id_y          1112623 non-null int64
created_at_ts_y        1112623 non-null int64
words_count_y          1112623 non-null int64
dtypes: int32(1), int64(16)
memory usage: 148.6 MB

trn_click.describe([0.01,0.25,0.5,0.75,0.99])

#训练集中的用户数量为20w
trn_click["user_id"].nunique()

200000
• 1

trn_click.groupby('user_id')['click_article_id'].count().min()
# 训练集里面每个用户至少点击了两篇文章

2

trn_click.groupby('user_id')['click_article_id'].count()

user_id
0          2
1          2
2          2
3          2
4          2
          ..
199995     7
199996    13
199997     2
199998    40
199999    11
Name: click_article_id, Length: 200000, dtype: int64

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
import collections
from collections import defaultdict
warnings.filterwarnings('ignore')

data_path = './data_raw/'
save_path = './tmp_results/' 
• 1
• 2
'运行
运行

# 节约内存的一个标配函数
def reduce_mem(df):
    starttime = time.time()
    numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']
    start_mem = df.memory_usage().sum() / 1024**2
    for col in df.columns:
        col_type = df[col].dtypes
        if col_type in numerics:
            c_min = df[col].min()
            c_max = df[col].max()
            if pd.isnull(c_min) or pd.isnull(c_max):
                continue
            if str(col_type)[:3] == 'int':
                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
                    df[col] = df[col].astype(np.int8)
                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:
                    df[col] = df[col].astype(np.int16)
                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:
                    df[col] = df[col].astype(np.int32)
                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:
                    df[col] = df[col].astype(np.int64)
            else:
                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
                    df[col] = df[col].astype(np.float16)
                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:
                    df[col] = df[col].astype(np.float32)
                else:
                    df[col] = df[col].astype(np.float64)
    end_mem = df.memory_usage().sum() / 1024**2
    print('-- Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction),time spend:{:2.2f} min'.format(end_mem,
                                                                                                           100*(start_mem-end_mem)/start_mem,
                                                                                                           (time.time()-starttime)/60))
    return df

# debug模式：从训练集中划出一部分数据来调试代码
def get_all_click_sample(data_path, sample_nums=5000):
    """
        训练集中采样一部分数据调试
        data_path: 原数据的存储路径
        sample_nums: 采样数目（这里由于机器的内存限制，可以采样用户做）
    """
    all_click = pd.read_csv(data_path + 'train_click_log.csv')
    all_user_ids = all_click.user_id.unique()
    sample_user_ids = np.random.choice(all_user_ids, size=sample_nums, replace=False) 
    all_click = all_click[all_click['user_id'].isin(sample_user_ids)]
    
    all_click = all_click.drop_duplicates((['user_id', 'click_article_id', 'click_timestamp']))
    return all_click

# 读取点击数据，这里分成线上和线下，如果是为了获取线上提交结果应该讲测试集中的点击数据合并到总的数据中
# 如果是为了线下验证模型的有效性或者特征的有效性，可以只使用训练集
def get_all_click_df(data_path='./data_raw/', offline=True):
    if offline:
        all_click = pd.read_csv(data_path + 'train_click_log.csv')
    else:
        trn_click = pd.read_csv(data_path + 'train_click_log.csv')
        tst_click = pd.read_csv(data_path + 'testA_click_log.csv')
        all_click = trn_click.append(tst_click)
    
    all_click = all_click.drop_duplicates((['user_id', 'click_article_id', 'click_timestamp']))
    return all_click
'运行
运行

# 全量训练集因为已经分成两部分数据集，可以是读取合并成一大部分数据集
all_click_df = get_all_click_df(offline=False)

# 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
'运行
运行

# 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
'运行
运行

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_5
'运行
运行

i2i_sim = itemcf_sim(all_click_df)

# 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] # 注意，此时获取得到的是一个元组列表，需要将里面的user_id提取出来
    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
'运行
运行

# 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'))

• 1
'运行
运行

# 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)

• 1
'运行
运行

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)

100%|████████████████████████████████████████████████████████████████████████| 250000/250000 [2:06:25<00:00, 32.96it/s]

# 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'])

100%|███████████████████████████████████████████████████████████████████████| 250000/250000 [00:11<00:00, 22018.74it/s]

# 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)
'运行
运行

• 1
'运行
运行

# 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')