推荐引擎：基于余弦相似度书籍推荐Python实现

# -*- coding: utf-8 -*-

# @Date    : 2019-02-14
# @Author  : Peng Shiyu

from copy import deepcopy

import numpy as np
from sklearn.feature_extraction import DictVectorizer
from sklearn.metrics.pairwise import cosine_similarity

# 数据准备：{书名: 评分}
# user = {"红楼梦", "西游记", "水浒传", "三国演义"}

user1 = {"红楼梦": 4, "西游记": 3}
user2 = {"红楼梦": 5, "西游记": 6, "水浒传": 3}
user3 = {"红楼梦": 4, "西游记": 3, "三国演义": 5}
user4 = {"西游记": 4, "三国演义": 5}

data = [
    user1,
    user2,
    user3,
    user4
]

# 特征提取
dict_vectorizer = DictVectorizer(dtype=np.int32, sparse=False)
result = dict_vectorizer.fit_transform(data)
books = dict_vectorizer.get_feature_names()
print(dict_vectorizer.get_feature_names())
print(result)

# 余弦相似度矩阵
user_similarity = cosine_similarity(result)
print(user_similarity)

for user_id, user_looked in enumerate(data):
    user_suggest = user_similarity[user_id].tolist()

    # 找到与之相似度最高的两个人
    user_suggest_bak = deepcopy(user_suggest)
    user_suggest_bak.sort(reverse=True)
    max_similar = user_suggest_bak[1: 3]
    print(max_similar)
    max_index = list(map(user_suggest.index, max_similar))
    print(max_index)

    suggest = {}
    for index, user in enumerate([data[i] for i in max_index]):
        for key, value in user.items():
            if key not in user_looked:
                suggest[key] = user_suggest[index] * value

    print(suggest)
"""
['三国演义', '水浒传', '红楼梦', '西游记']
[[0 0 4 3]
 [0 3 5 6]
 [5 0 4 3]
 [5 0 0 4]]
 
[[1.         0.90837374 0.70710678 0.37481703]
 [0.90837374 1.         0.64231723 0.44799204]
 [0.70710678 0.64231723 1.         0.81719329]
 [0.37481703 0.44799204 0.81719329 1.        ]]
 
[0.9083737430941391, 0.7071067811865475]
{'水浒传': 3.0, '三国演义': 4.541868715470695}

[0.9083737430941391, 0.6423172335936725]
{'三国演义': 4.999999999999999}

[0.8171932929538644, 0.7071067811865475]
{}

[0.8171932929538644, 0.44799203576793445]
{'红楼梦': 2.2399601788396724, '水浒传': 1.3439761073038032}

"""

参考:
推荐算法和机器学习系列 - 协同过滤推荐算法和余弦相似性算法