云回收衣服小程序推荐商品

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衣物信息和用户偏好的数据集
data = {
    'item_id': [1, 2, 3],
    'description': ['棉质T恤', '羊毛衫', '牛仔夹克']
}
df_items = pd.DataFrame(data)

# 用户偏好描述
user_preferences = '棉质'

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

# 计算用户偏好与商品描述的相似度
user_tfidf = tfidf.transform([user_preferences])
cosine_sim = linear_kernel(user_tfidf, tfidf_matrix).flatten()

# 获取相似度最高的商品
related_items_indices = cosine_sim.argsort()[:-2:-1]
for idx in related_items_indices:
    print(df_items['item_id'][idx], df_items['description'][idx])