11.11视频智能分类推荐

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

# 假设我们有以下视频数据和它们的描述
videos = {
    'video1': 'A thrilling action movie with lots of explosions.',
    'video2': 'A romantic comedy about two people finding love.',
    'video3': 'An educational documentary on space exploration.'
}

# 将视频描述转换为TF-IDF特征向量
tfidf = TfidfVectorizer(stop_words='english')
tfidf_matrix = tfidf.fit_transform(videos.values())

# 计算视频之间的相似度
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = list(videos.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]  # 获取最相似的两个视频
    video_indices = [i[0] for i in sim_scores]
    return list(videos.keys())[video_indices]

# 使用示例
print(get_recommendations('video1'))