音视频点播推荐

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

# 示例数据
movies = {
    'The Matrix': 'action science fiction',
    'Inception': 'action science fiction thriller',
    'Interstellar': 'adventure drama science fiction',
    'The Dark Knight': 'action crime drama thriller'
}

# 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())

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

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[1:3]  # 获取最相似的两个电影
    movie_indices = [i[0] for i in sim_scores]
    return list(movies.keys())[movie_indices]

# 示例调用
print(get_recommendations('The Matrix'))