12.12应用对接云推荐

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

# 假设我们有一个用户-物品评分矩阵
ratings = np.array([[4, 0, 0, 5], [0, 5, 3, 0], [1, 0, 0, 4], [0, 3, 4, 0]])

# 计算用户之间的相似度
user_similarity = cosine_similarity(ratings)

# 为用户1推荐物品（假设用户1已经评价了物品0和物品3）
user_id = 0
rated_items = [0, 3]
 unrated_items = [i for i in range(ratings.shape[1]) if i not in rated_items]

# 基于相似用户的评分来预测用户1对未评价物品的评分
predicted_ratings = []
for item in unrated_items:
 predicted_rating = 0
 similarity_sum = 0
 for other_user_id in range(ratings.shape[0]):
 if other_user_id != user_id:
 similarity = user_similarity[user_id][other_user_id]
 predicted_rating += similarity * ratings[other_user_id][item]
 similarity_sum += similarity
 if similarity_sum > 0:
 predicted_ratings.append((item, predicted_rating / similarity_sum))

# 根据预测评分排序并推荐前N个物品
N = 2
recommended_items = sorted(predicted_ratings, key=lambda x: x[1], reverse=True)[:N]
print(f"为用户{user_id}推荐的物品是：{recommended_items}")