双11标准直播推荐

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直播信息的DataFrame
data = {
    'live_id': [1, 2, 3],
    'title': ['直播1：科技新品发布', '直播2：时尚穿搭分享', '直播3：美食烹饪教程'],
    'description': ['介绍最新科技产品...', '分享时尚穿搭技巧...', '学习制作美味佳肴...']
}
df = pd.DataFrame(data)

# 使用TF-IDF向量化直播标题和描述
tfidf = TfidfVectorizer(stop_words='english')
df['content'] = df['title'] + ' ' + df['description']
tfidf_matrix = tfidf.fit_transform(df['content'])

# 计算相似度矩阵
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = df.index[df['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[1:3]  # 获取最相似的两个直播
    live_indices = [i[0] for i in sim_scores]
    return df['live_id'].iloc[live_indices]

# 示例调用
print(get_recommendations('直播1：科技新品发布'))