BrandCultivation/utils/result_process.py

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

dao = MySqlDao()
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, filter_dict, save_dir):
    """拆分卷烟商户特征相关性子表"""
    data = filter_data(data, filter_dict).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')
        
def generate_report(data, filter_dict, save_dir):
    """根据总表筛选结果"""
    # 1. 筛选商户相关性排序结果
    data = filter_data(data, filter_dict).copy()
    data.to_csv(os.path.join(save_dir, "feats_interaction.csv"), index=False, encoding='utf-8-sig')
    group_sums = data.groupby("cust_feat")["relation"].sum()
    # 筛选出总和非负的cust_feat
    valid_cust_feats = group_sums[group_sums > 0].index.tolist()
    cust_relation = data[data["cust_feat"].isin(valid_cust_feats)]
    cust_relation = cust_relation.reset_index(drop=True)
    
    # 2. 品规信息
    cust_relation[:20].to_csv(os.path.join(save_dir, "cust_relation.csv"), index=False, encoding='utf-8-sig')
    with open(os.path.join(save_dir, "product_info.csv"), "w", encoding='utf-8-sig') as f:
        for key, value in filter_dict.items():
            if key != 'product_code':
                f.write(f"{ImportanceFeaturesMap.PRODUCT_FEATRUES_MAP[key]}, {value}\n")
    
        
def get_cust_list_from_history_order(city_uuid, product_code):
    order_data = dao.get_order_by_product(city_uuid, product_code)
    return order_data
        
if __name__ == "__main__":
    order_data = get_cust_list_from_history_order("00000000000000000000000011445301", "350139")
    order_data.to_csv("./data/history.csv", index=False)