双十二商品智能识别推荐

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel

# 假设我们有商品描述数据
products = {
    'product1': '高质量棉质T恤，适合日常穿着',
    'product2': '时尚牛仔裤，潮流设计',
    'product3': '舒适运动鞋，适合跑步',
    # ...更多商品
}

# 将商品描述转换为TF-IDF特征向量
tfidf = TfidfVectorizer(stop_words='english')
tfidf_matrix = tfidf.fit_transform(products.values())

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

def get_recommendations(title, cosine_sim=cosine_sim):
    idx = list(products.keys()).index(title)
    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]  # 获取最相似的两个商品
    product_indices = [i[0] for i in sim_scores]
    return list(products.keys())[product_indices]

# 示例调用
print(get_recommendations('product1'))