双十二内容识别购买

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

# 假设我们有一个商品数据集
data = {
    'product_id': [1, 2, 3],
    'description': ['智能手机 高清摄像头', '轻薄笔记本 长续航', '无线耳机 高保真音质']
}
df = pd.DataFrame(data)

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

# 计算商品间的相似度
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = df.index[df['description'] == 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]  # 取前两个最相似的商品
    product_indices = [i[0] for i in sim_scores]
    return df['product_id'].iloc[product_indices]

# 测试推荐系统
print(get_recommendations('智能手机 高清摄像头'))