BrandCultivation/models/recall/itemCF/score.py

from database import MySqlDao
from models.rank.data.config import OrderConfig
import numpy as np
from sklearn.preprocessing import StandardScaler
class UserItemScore:
    def __init__(self, city_uuid):
        self._dao = MySqlDao()
        self._load_data(city_uuid)
        
    def _load_data(self, city_uuid):
        """加载订单记录表"""
        print("item-cf: 正在加载order_info...")
        self._order_data = self._dao.load_order_data(city_uuid)
        self._order_data =self._order_data[OrderConfig.FEATURE_COLUMNS]
        
        # 数据清洗
        self._order_data["sale_qty"] = self._order_data["sale_qty"].fillna(0)
        self._order_data = self._order_data.groupby(["cust_code", "product_code"], as_index=False)["sale_qty"].sum()
        self._order_data = self._order_data[self._order_data["sale_qty"] != 0]
        
        # 归一化处理
        scaler = StandardScaler()
        normalized = scaler.fit_transform(self._order_data["sale_qty"].values.reshape(-1, 1))
        self._order_data["sale_qty"] = ((1 / (1 + np.exp(-normalized))) * 100).flatten()
    
        
    def generate_product_scores(self, save_path):
        self._order_data = self._order_data.rename(columns={'sale_qty': 'score'})
        self._order_data = self._order_data.sort_values(['product_code', 'score'], ascending=[True, False])
        self._score_data = self._order_data[['product_code', 'cust_code', 'score']]
        self._score_data.to_csv(save_path, index=False, encoding="utf-8")
        
        
if __name__ == "__main__":
    save_path = "./data/itemcf/scores.csv"
    score_utils = UserItemScore("00000000000000000000000011445301") 
    score_utils.generate_product_scores(save_path)