基于用户的协同过滤 Base User CF (使用jaccard_score 距离评价标准)

import  pandas as pd
import  numpy as np

users = ['user1','user2','user3','user4','user5',]
items = ['item A','item B','item C','item D','item E',]


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)

print(df)

from sklearn.metrics import  jaccard_similarity_score,jaccard_score

# sim = jaccard_similarity_score(df['item A'],df['item B'])
sim = jaccard_score(df['item A'],df['item B'])
print(sim)


from  sklearn.metrics.pairwise import  pairwise_distances

user_similar = 1 - pairwise_distances(df.values,metric='jaccard')
# print(user_similar)

user_similar = pd.DataFrame(user_similar,columns=users,index=users)
print(user_similar)


items_similar = 1 - pairwise_distances(df.T.values,metric='jaccard')

items_similar = pd.DataFrame(items_similar,columns=items,index=items)
print(items_similar)


topN_users = {}
# print(user_similar.index)
for i in user_similar.index:
    _df = user_similar.loc[i].drop([i])
    print(_df)
    _df_sorted = _df.sort_values(ascending=False)
    top2 = list(_df_sorted.index[:2])
    topN_users[i] = top2

print('Top 2 相似用户:')
print(topN_users)


rs_results = {}

# for user, sim_users in  topN_users.items():
#     rs_result = set()
#     for sim_user in sim_users:
#         #构建初始推荐结果
#         print('sim_users ',sim_users)
#         print('sim_users items :', df.ix[sim_user])
#         print('df loc :',df.ix[sim_user].replace(0,np.nan).dropna().index)
#         rs_result = rs_result.union(set(df.ix[sim_user].replace(0,np.nan).dropna().index))
#         #过滤掉已经购买过的物品
#     rs_result -= set(df.ix[user].replace(0,np.nan).dropna().index)
#     rs_results[user] = rs_result
# print('最终推荐结果:')
# print(rs_results)

for user, sim_users in  topN_users.items():
    rs_result = set()
    for sim_user in sim_users:
        #构建初始推荐结果
        print('sim_users ',sim_users)
        print('sim_users items :', df.loc[sim_user])
        print('df loc :',df.loc[sim_user].replace(0,np.nan).dropna().index)
        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:')
print(rs_results)

最终推荐结果:
{'user1': {'item E'}, 'user2': {'item B', 'item C'}, 'user3': {'item D', 'item B', 'item E'}, 'user4': {'item A', 'item C'}, 'user5': {'item D'}}