11.11云端大数据实时搜索推荐

import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity

# 假设我们有一个用户-物品评分矩阵
data = {
    'user_id': [1, 1, 2, 2, 3, 3],
    'item_id': [101, 102, 101, 103, 102, 104],
    'rating': [5, 3, 4, 1, 5, 2]
}

df = pd.DataFrame(data)

# 创建用户-物品评分矩阵
user_item_matrix = df.pivot(index='user_id', columns='item_id', values='rating').fillna(0)

# 计算用户相似度
user_similarity = cosine_similarity(user_item_matrix)

# 推荐函数
def recommend_items(user_id, user_similarity, user_item_matrix, top_n=3):
    similar_users = user_similarity[user_id - 1].argsort()[::-1][1:]
    recommended_items = set()
    
    for similar_user in similar_users:
        items_rated_by_similar_user = user_item_matrix.iloc[similar_user].dropna().index
        recommended_items.update(items_rated_by_similar_user)
        
        if len(recommended_items) >= top_n:
            break
    
    return list(recommended_items)[:top_n]

# 示例推荐
recommended_items = recommend_items(user_id=1, user_similarity=user_similarity, user_item_matrix=user_item_matrix)
print("Recommended items for user 1:", recommended_items)