Python常用学习包（六）——Surprise

最新推荐文章于 2024-09-25 16:15:23 发布

又见智能商业

最新推荐文章于 2024-09-25 16:15:23 发布

阅读量3.1k

点赞数

分类专栏： python 文章标签： python

python 专栏收录该内容

19 篇文章 4 订阅

订阅专栏

笔者是一个痴迷于挖掘数据中的价值的学习人，希望在平日的工作学习中，挖掘数据的价值，找寻数据的秘密，笔者认为，数据的价值不仅仅只体现在企业中，个人也可以体会到数据的魅力，用技术力量探索行为密码，让大数据助跑每一个人，欢迎直筒们关注我的公众号，大家一起讨论数据中的那些有趣的事情。

我的公众号为：livandata

在推荐系统的建模过程中，我们将用到python库 Surprise(Simple Python RecommendatIon System Engine)，是scikit系列中的一个(很多同学用过scikit-learn和scikit-image等库)。Surprise的User Guide有详细的解释和说明

简单易用，同时支持多种推荐算法：

算法类名	说明
random_pred.NormalPredictor	Algorithm predicting a random rating based on the distribution of the training set, which is assumed to be normal.
baseline_only.BaselineOnly	Algorithm predicting the baseline estimate for given user and item.
knns.KNNBasic	A basic collaborative filtering algorithm.
knns.KNNWithMeans	A basic collaborative filtering algorithm, taking into account the mean ratings of each user.
knns.KNNBaseline	A basic collaborative filtering algorithm taking into account a baseline rating.
matrix_factorization.SVD	The famous SVD algorithm, as popularized by Simon Funk during the Netflix Prize.
matrix_factorization.SVDpp	The SVD++ algorithm, an extension of SVD taking into account implicit ratings.
matrix_factorization.NMF	A collaborative filtering algorithm based on Non-negative Matrix Factorization.
slope_one.SlopeOne	A simple yet accurate collaborative filtering algorithm.
co_clustering.CoClustering	A collaborative filtering algorithm based on co-clustering.

其中基于近邻的方法(协同过滤)可以设定不同的度量准则。

相似度度量标准	度量标准说明
cosine	Compute the cosine similarity between all pairs of users (or items).
msd	Compute the Mean Squared Difference similarity between all pairs of users (or items).
pearson	Compute the Pearson correlation coefficient between all pairs of users (or items).
pearson_baseline	Compute the (shrunk) Pearson correlation coefficient between all pairs of users (or items) using baselines for centering instead of means.

支持不同的评估准则

评估准则	准则说明
rmse	Compute RMSE (Root Mean Squared Error).
mae	Compute MAE (Mean Absolute Error).
fcp	Compute FCP (Fraction of Concordant Pairs).

使用示例

基本使用方法如下：

# 可以使用上面提到的各种推荐系统算法
from surprise import SVD
from surprise import Dataset
from surprise import evaluate, print_perf
 
# 默认载入movielens数据集，会提示是否下载这个数据集，这是非常经典的公开推荐系统数据集——MovieLens数据集之一
data = Dataset.load_builtin('ml-100k')
# k折交叉验证(k=3)
data.split(n_folds=3)
# 试一把SVD矩阵分解
algo = SVD()
# 在数据集上测试一下效果
perf = evaluate(algo, data, measures=['RMSE', 'MAE'])
#输出结果
print_perf(perf)

载入自己的数据集方法

# 指定文件所在路径
file_path = os.path.expanduser('~/.surprise_data/ml-100k/ml-100k/u.data')
# 告诉文本阅读器，文本的格式是怎么样的
reader = Reader(line_format='user item rating timestamp', sep='\t')
# 加载数据
data = Dataset.load_from_file(file_path, reader=reader)
# 手动切分成5折(方便交叉验证)
data.split(n_folds=5)

算法调参(让推荐系统有更好的效果)

这里实现的算法用到的算法无外乎也是SGD等，因此也有一些超参数会影响最后的结果，我们同样可以用sklearn中常用到的网格搜索交叉验证(GridSearchCV)来选择最优的参数。简单的例子如下所示：

# 定义好需要优选的参数网格
param_grid = {'n_epochs': [5, 10], 'lr_all': [0.002, 0.005],
              'reg_all': [0.4, 0.6]}
# 使用网格搜索交叉验证
grid_search = GridSearch(SVD, param_grid, measures=['RMSE', 'FCP'])
# 在数据集上找到最好的参数
data = Dataset.load_builtin('ml-100k')
data.split(n_folds=3)
grid_search.evaluate(data)
# 输出调优的参数组 
# 输出最好的RMSE结果
print(grid_search.best_score['RMSE'])
# >>> 0.96117566386
 
# 输出对应最好的RMSE结果的参数
print(grid_search.best_params['RMSE'])
# >>> {'reg_all': 0.4, 'lr_all': 0.005, 'n_epochs': 10}
 
# 最好的FCP得分
print(grid_search.best_score['FCP'])
# >>> 0.702279736531
 
# 对应最高FCP得分的参数
print(grid_search.best_params['FCP'])
# >>> {'reg_all': 0.6, 'lr_all': 0.005, 'n_epochs': 10}

在自己的数据集上训练模型

首先载入数据

import os
from surprise import Reader, Dataset
# 指定文件路径
file_path = os.path.expanduser('./popular_music_suprise_format.txt')
# 指定文件格式
reader = Reader(line_format='user item rating timestamp', sep=',')
# 从文件读取数据
music_data = Dataset.load_from_file(file_path, reader=reader)
# 分成5折
music_data.split(n_folds=5)

使用不同的推荐系统算法进行建模比较

### 使用NormalPredictor
from surprise import NormalPredictor, evaluate
algo = NormalPredictor()
perf = evaluate(algo, music_data, measures=['RMSE', 'MAE'])
 
### 使用BaselineOnly
from surprise import BaselineOnly, evaluate
algo = BaselineOnly()
perf = evaluate(algo, music_data, measures=['RMSE', 'MAE'])
 
### 使用基础版协同过滤
from surprise import KNNBasic, evaluate
algo = KNNBasic()
perf = evaluate(algo, music_data, measures=['RMSE', 'MAE'])
 
### 使用均值协同过滤
from surprise import KNNWithMeans, evaluate
algo = KNNWithMeans()
perf = evaluate(algo, music_data, measures=['RMSE', 'MAE'])
 
### 使用协同过滤baseline
from surprise import KNNBaseline, evaluate
algo = KNNBaseline()
perf = evaluate(algo, music_data, measures=['RMSE', 'MAE'])
 
### 使用SVD
from surprise import SVD, evaluate
algo = SVD()
perf = evaluate(algo, music_data, measures=['RMSE', 'MAE'])
 
### 使用SVD++
from surprise import SVDpp, evaluate
algo = SVDpp()
perf = evaluate(algo, music_data, measures=['RMSE', 'MAE'])
 
### 使用NMF
from surprise import NMF
algo = NMF()
perf = evaluate(algo, music_data, measures=['RMSE', 'MAE'])
print_perf(perf)

建模和存储模型

1.用协同过滤构建模型并进行预测

1.1 movielens的例子

# 可以使用上面提到的各种推荐系统算法
from surprise import SVD
from surprise import Dataset
from surprise import evaluate, print_perf
 
# 默认载入movielens数据集
data = Dataset.load_builtin('ml-100k')
# k折交叉验证(k=3)
data.split(n_folds=3)
# 试一把SVD矩阵分解
algo = SVD()
# 在数据集上测试一下效果
perf = evaluate(algo, data, measures=['RMSE', 'MAE'])
#输出结果
print_perf(perf)
 
"""
以下的程序段告诉大家如何在协同过滤算法建模以后，根据一个item取回相似度最高的item，主要是用到algo.get_neighbors()这个函数
"""
 
from __future__ import (absolute_import, division, print_function,
                        unicode_literals)
import os
import io
 
from surprise import KNNBaseline
from surprise import Dataset
 
 
def read_item_names():
    """
    获取电影名到电影id 和 电影id到电影名的映射
    """
 
    file_name = (os.path.expanduser('~') +
                 '/.surprise_data/ml-100k/ml-100k/u.item')
    rid_to_name = {}
    name_to_rid = {}
    with io.open(file_name, 'r', encoding='ISO-8859-1') as f:
        for line in f:
            line = line.split('|')
            rid_to_name[line[0]] = line[1]
            name_to_rid[line[1]] = line[0]
 
    return rid_to_name, name_to_rid
 
 
# 首先，用算法计算相互间的相似度
data = Dataset.load_builtin('ml-100k')
trainset = data.build_full_trainset()
sim_options = {'name': 'pearson_baseline', 'user_based': False}
algo = KNNBaseline(sim_options=sim_options)
algo.train(trainset)
 
# 获取电影名到电影id 和 电影id到电影名的映射
rid_to_name, name_to_rid = read_item_names()
 
# Retieve inner id of the movie Toy Story
toy_story_raw_id = name_to_rid['Toy Story (1995)']
toy_story_inner_id = algo.trainset.to_inner_iid(toy_story_raw_id)
 
# Retrieve inner ids of the nearest neighbors of Toy Story.
toy_story_neighbors = algo.get_neighbors(toy_story_inner_id, k=10)
 
# Convert inner ids of the neighbors into names.
toy_story_neighbors = (algo.trainset.to_raw_iid(inner_id)
                       for inner_id in toy_story_neighbors)
toy_story_neighbors = (rid_to_name[rid]
                       for rid in toy_story_neighbors)
 
print()
print('The 10 nearest neighbors of Toy Story are:')
for movie in toy_story_neighbors:
    print(movie)

1.2 音乐预测的例子

from __future__ import (absolute_import, division, print_function, unicode_literals)
import os
import io
 
from surprise import KNNBaseline
from surprise import Dataset
 
import cPickle as pickle
# 重建歌单id到歌单名的映射字典
id_name_dic = pickle.load(open("popular_playlist.pkl","rb"))
print("加载歌单id到歌单名的映射字典完成...")
# 重建歌单名到歌单id的映射字典
name_id_dic = {}
for playlist_id in id_name_dic:
    name_id_dic[id_name_dic[playlist_id]] = playlist_id
print("加载歌单名到歌单id的映射字典完成...")
 
 
file_path = os.path.expanduser('./popular_music_suprise_format.txt')
# 指定文件格式
reader = Reader(line_format='user item rating timestamp', sep=',')
# 从文件读取数据
music_data = Dataset.load_from_file(file_path, reader=reader)
# 计算歌曲和歌曲之间的相似度
print("构建数据集...")
trainset = music_data.build_full_trainset()
#sim_options = {'name': 'pearson_baseline', 'user_based': False}

current_playlist => 歌单名
playlist_id => 歌单id(网易给的歌单id)
playlist_inner_id => 内部id(对所有歌单id重新从1开始编码)

print("开始训练模型...")
#sim_options = {'user_based': False}
#algo = KNNBaseline(sim_options=sim_options)
algo = KNNBaseline()
algo.train(trainset)
 
current_playlist = name_id_dic.keys()[39]
print(current_playlist)
 
# 取出近邻
playlist_id = name_id_dic[current_playlist]
print(playlist_id)
playlist_inner_id = algo.trainset.to_inner_uid(playlist_id)
print(playlist_inner_id)
 
playlist_neighbors = algo.get_neighbors(playlist_inner_id, k=10)
 
# 把歌曲id转成歌曲名字
playlist_neighbors = (algo.trainset.to_raw_uid(inner_id)
                       for inner_id in playlist_neighbors)
playlist_neighbors = (id_name_dic[playlist_id]
                       for playlist_id in playlist_neighbors)
 
print()
print("和歌单 《", current_playlist, "》 最接近的10个歌单为：\n")
for playlist in playlist_neighbors:
    print(playlist)

2.用SVD矩阵分解进行预测

### 使用SVD++
from surprise import SVDpp, evaluate
from surprise import Dataset
 
file_path = os.path.expanduser('./popular_music_suprise_format.txt')
# 指定文件格式
reader = Reader(line_format='user item rating timestamp', sep=',')
# 从文件读取数据
music_data = Dataset.load_from_file(file_path, reader=reader)
# 构建数据集和建模
algo = SVDpp()
trainset = music_data.build_full_trainset()
algo.train(trainset)