协同过滤案例以及代码运行遇到的问题

报错：AttributeError: ‘DataFrame’ object has no attribute ‘dtype’
错误原因：scikit-learn从0.20.1不再自动修改numpy语法。所以需要养成更加规范的书写习惯解决

pairwise_distances(df, metric="jaccard")`修改为pairwise_distances(df.values, metric="jaccard")`

from sklearn.metrics import jaccard_similarity_score
修改为：from sklearn.metrics import jaccard_score

pandas:ix 、loc 、 iloc区别、.at、.iat和.get_value

.ix()运行可能会报错，需要修改为loc，上面的链接为几个函数的区别

案例1：基于用户的协议过滤

import pandas as pd
import numpy as np
from pprint import pprint

users = ["User1", "User2", "User3", "User4", "User5"]
items = ["Item A", "Item B", "Item C", "Item D", "Item E"]
# 用户购买记录数据集
datasets = [
    [1, 0, 1, 1, 0],
    [1, 0, 0, 1, 1],
    [1, 0, 1, 0, 0],
    [0, 1, 0, 1, 1],
    [1, 1, 1, 0, 1],
]

df = pd.DataFrame(datasets,
                  columns=items,
                  index=users)
"""     Item A  Item B  Item C  Item D  Item E
User1       1       0       1       1       0
User2       1       0       0       1       1
User3       1       0       1       0       0
User4       0       1       0       1       1
User5       1       1       1       0       1
"""

# 计算所有的数据两两的杰卡德相似系数
from sklearn.metrics.pairwise import pairwise_distances

# 计算用户间相似度
user_similar = 1 - pairwise_distances(df.values, metric="jaccard")
user_similar = pd.DataFrame(user_similar, columns=users, index=users)
print("用户之间的两两相似度：")
print(user_similar)

topN_users = {}
# 遍历每一行数据
for i in user_similar.index:
    # 取出每一列数据，并删除自身，然后排序数据
    _df = user_similar.loc[i].drop([i])  # 拿到每一行的数据并且剔除自己那一行（自己和自己相似度一定是一摸一样）
    _df_sorted = _df.sort_values(ascending=False)  # 降序排列
    top2 = list(_df_sorted.index[:2])  # 切片转化list
    topN_users[i] = top2

print("Top2相似用户：")
pprint(topN_users)

rs_results = {}
# 构建推荐结果
for user, sim_users in topN_users.items():
    rs_result = set()  # 存储推荐结果 set()集合能去重
    for sim_user in sim_users:
        # 构建初始的推荐结果
        rs_result = rs_result.union(set(df.loc[sim_user].replace(0, np.nan).dropna().index))
    # 过滤掉已经购买过的物品
    rs_result -= set(df.loc[user].replace(0, np.nan).dropna().index)
    rs_results[user] = rs_result
print("最终推荐结果：")
pprint(rs_results)

案例2：基于协同过滤的电影推荐

import pandas as pd
import numpy as np


def load_data(data_path):
   
    print("开始加载数据集...")
    if os.path.exists(cache_path):  # 判断是否存在缓存文件
        print("加载缓存中...")
        ratings_matrix = pd.read_pickle(cache_path)
        print("从缓存加载数据集完毕")
    else:
        print("加载新数据中...")
        # 设置要加载的数据字段的类型
        dtype = {"userId": np.int32, "movieId": np.int32, "rating": np.float32}
        # 加载数据，我们只用前三列数据，分别是用户ID，电影ID，已经用户对电影的对应评分
        ratings = pd.read_csv(data_path, dtype=dtype, usecols=range(3))
        # 透视表，将电影ID转换为列名称，转换成为一个User-Movie的评分矩阵
        ratings_matrix = ratings.pivot_table(index=["userId"], columns=["movieId"], values="rating")
        # 存入缓存文件
        ratings_matrix.to_pickle(cache_path)
        print("数据集加载完毕")
    return ratings_matrix


def compute_pearson_similarity(ratings_matrix, based="user"):
   
    user_similarity_cache_path = os.path.join(CACHE_DIR, "user_similarity.cache")
    item_similarity_cache_path = os.path.join(CACHE_DIR, "item_similarity.cache")
    if based == "user":
        if os.path.exists(user_similarity_cache_path):
            print("正从缓存加载用户相似度矩阵")
            similarity = pd.read_pickle(user_similarity_cache_path)
        else:
            print("开始计算用户相似度矩阵")
            similarity = ratings_matrix.T.corr()
            similarity.to_pickle(user_similarity_cache_path)

    elif based == "item":
        if os.path.exists(item_similarity_cache_path):
            print("正从缓存加载物品相似度矩阵")
            similarity = pd.read_pickle(item_similarity_cache_path)
        else:
            print("开始计算物品相似度矩阵")
            similarity = ratings_matrix.corr()
            similarity.to_pickle(item_similarity_cache_path)
    else:
        raise Exception("Unhandled 'based' Value: %s"%based)
    print("相似度矩阵计算/加载完毕")
    return similarity

if __name__ == '__main__':

    ratings_matrix = load_data(DATA_PATH)

    user_similar = compute_pearson_similarity(ratings_matrix, based="user")
    print(user_similar)
    item_similar = compute_pearson_similarity(ratings_matrix, based="item")
    print(item_similar)