BrandCultivation/models/item2vec/preprocess.py

from database.dao.mysql_dao import MySqlDao
from models.rank.data.config import ProductConfig
from models.rank.data.utils import sample_data_clear


class Item2VecDataProcess:
    def __init__(self, city_uuid):
        self._mysql_dao = MySqlDao()
        print("item2vec: 正在加载product_info...")
        self._product_data = self._mysql_dao.load_product_data(city_uuid)
        self._data_process()
        
    def _data_process(self):
        """数据预处理"""
        # 获取指定的特征
        self._product_data = self._product_data[ProductConfig.FEATURE_COLUMNS]
        # 数据清洗
        self._product_data = sample_data_clear(self._product_data, ProductConfig)
        
    def tokenize_features(self, row):
        """根据每款烟的特征生成sentence"""
        tokens = []
        
        for col in ProductConfig.FEATURE_COLUMNS:
            if col == 'product_code':
                continue
            if col in ["direct_retail_price", "tbc_total_length"]:
                tokens.append(f"{col}_{row[col].replace('-', '_')}")
            else:
                tokens.append(f"{col}_{row[col]}")
        
        return tokens
    
    def generate_sentence(self):
        sentcens = self._product_data.apply(self.tokenize_features, axis=1).tolist()
        return sentcens
        
if __name__ == "__main__":
    city_uuid = "00000000000000000000000011445301"
    processor = Item2VecDataProcess(city_uuid)
    processor.generate_sentence()