BrandCultivation/utils/result_process.py

import os
import pandas as pd
from database import MySqlDao
from models.rank.data.config import ImportanceFeaturesMap, ProductConfig

def filter_data(data, filter_dict):
    
    product_content = []
    for key, value in filter_dict.items():
        if key != 'product_code':
            product_content.append(f"{ImportanceFeaturesMap.PRODUCT_FEATRUES_MAP[key]}({value})")
    
    data = data[data['product_feat'].isin(product_content)]
    return data

def split_relation_subtable(data, product_data, save_dir):
    """拆分卷烟商户特征相关性子表"""
    data = filter_data(data, product_data).copy()
    data.to_csv(os.path.join(save_dir, "feats_interaction.csv"), index=False, encoding='utf-8-sig')
    data['group_key'] = data["product_feat"].str.extract(r'^([^(]+)')
    grouped = data.groupby('group_key')
    sub_tables = {
        name: group.drop(columns=['group_key']).sort_values('relation', ascending=False)
        for name, group in grouped
    }
    
    for name, sub_data in sub_tables.items():
        sub_data.to_csv(os.path.join(save_dir, f"{name}.csv"), index=False, encoding='utf-8-sig')
        
if __name__ == "__main__":
    dao = MySqlDao()
    
    save_dir = "./data"
    data = pd.read_csv("./data/feats_interaction.csv")
    product_data = dao.get_product_by_id("00000000000000000000000011445301", "430201")[ProductConfig.FEATURE_COLUMNS]
    filter_dict = product_data.to_dict("records")[0]
    split_relation_subtable(data, filter_dict, save_dir)