11.11视频直播推荐

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内容的DataFrame
data = {
    'title': ['直播1', '直播2', '直播3'],
    'description': ['这是直播1的描述', '这是直播2的描述', '这是直播3的描述']
}
df = pd.DataFrame(data)

# 使用TF-IDF向量化描述
tfidf = TfidfVectorizer(stop_words='english')
df['description'] = df['description'].fillna('')
tfidf_matrix = tfidf.fit_transform(df['description'])

# 计算余弦相似度
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = 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
   直播_indices = [i[0] for i in sim_scores]
    return df['title'].iloc[直播_indices]

# 使用示例
print(get_recommendations('直播1'))