双十一视频智能分析推荐

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel

# 假设我们有一个包含视频信息和用户观看历史的DataFrame
data = pd.DataFrame({
    'video_id': [...],
    'title': [...],  # 视频标题
    'description': [...],  # 视频描述
    'user_id': [...],  # 用户ID
    'watched_videos': [...]  # 用户观看过的视频ID列表
})

# 使用TF-IDF向量化视频描述
tfidf = TfidfVectorizer(stop_words='english')
data['description'] = data['description'].fillna('')
tfidf_matrix = tfidf.fit_transform(data['description'])

# 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 = data.index[data['title'] == title].tolist()[0]
    sim_scores = list(enumerate(cosine_sim[idx]))
    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
    sim_scores = sim_scores[1:11]  # 获取最相似的10个视频
    video_indices = [i[0] for i in sim_scores]
    return data['video_id'].iloc[video_indices]

# 示例调用
recommended_videos = get_recommendations('双十一购物攻略')
print(recommended_videos)