12.12云端大数据实时搜索推荐

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel

# 示例数据：电影标题及其描述
movies = {
    'The Matrix': 'A computer hacker learns from mysterious rebels about the true nature of his reality...',
    'Inception': 'A thief who steals corporate secrets through the use of dream-sharing technology...',
    # ... 其他电影数据
}

# 将电影描述转换为TF-IDF特征向量
tfidf = TfidfVectorizer(stop_words='english')
tfidf_matrix = tfidf.fit_transform(movies.values())

# 计算电影之间的余弦相似度
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = list(movies.keys()).index(title)
    sim_scores = list(enumerate(cosine_sim[idx]))
    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
    sim_scores = sim_scores[1:6]  # 获取最相似的前5部电影
    movie_indices = [i[0] for i in sim_scores]
    return list(movies.keys())[movie_indices]

# 使用示例
print(get_recommendations('The Matrix'))