智能编辑双十一优惠活动

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历史优惠活动数据的DataFrame
data = pd.DataFrame({
    'activity': ['买一送一', '满减活动', '折扣券', '限时秒杀'],
    'description': ['全场商品买一送一', '满200减50', '领取50元折扣券', '晚上8点限时秒杀']
})

# 使用TF-IDF向量化文本数据
tfidf = TfidfVectorizer(stop_words='english')
data_vectorized = tfidf.fit_transform(data['description'])

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

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = data.index[data['activity'] == 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]  # 获取最相似的两个活动
    activity_indices = [i[0] for i in sim_scores]
    return data['activity'].iloc[activity_indices]

# 示例调用
print(get_recommendations('买一送一'))