BrandCultivation/utils/reports_process.py

from models.rank.data.config import ImportanceFeaturesMap, DeliveryConfig
import os
import pandas as pd


def filter_data(data, filter_dict):
    """从shap结果中过滤特征相关性数据"""
    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 feats_relation_process(shap_result, product_content):
    """生成特征相关性分析报告"""
    # 筛选商户相关性排序结果
    report = filter_data(shap_result, product_content).copy()
    cust_feats_sum = report.groupby("cust_feat")["relation"].sum()
    # 筛选出正相关性的cust_feat
    valid_cust_feats = cust_feats_sum[cust_feats_sum > 0].index.to_list()
    report = report[report["cust_feat"].isin(valid_cust_feats)]
    report = report.reset_index(drop=True)
    report = report.rename(
        columns = {
            "product_feat": "卷烟特征",
            "cust_feat": "商户特征",
            "relation": "相关性"
        }
    )
    return report

def build_recommend_report(recommend_data, recommend_cust_infos):
    """根据推荐数据生成推荐商户报告（不含投放量）"""
    recommend_data = pd.DataFrame(recommend_data)

    cust_ids = recommend_cust_infos.set_index("cust_code")
    recommend_data = recommend_data.join(cust_ids, on="cust_code", how="inner")
    recommend_data = recommend_data[["cust_code", "cust_name", "recommend_score"]]
    recommend_data = recommend_data.reset_index(drop=True)
    recommend_data.index = recommend_data.index + 1
    recommend_data = recommend_data.reset_index()
    recommend_data = recommend_data.rename(
        columns={
            "index": "推荐序号",
            "cust_code": "商户编号",
            "cust_name": "商户名称",
            "recommend_score": "推荐系数",
        }
    )
    return recommend_data

def eval_report_process_pre(eval_order_data, recommend_data):
    # 获取订单数据并处理
    eval_order_data = eval_order_data[["cust_code", "cust_name", "product_code", "product_name", "sale_qty", "sale_amt"]]
    
    # 确保cust_code是字符串类型
    eval_order_data["cust_code"] = eval_order_data["cust_code"].astype(str)
    
    eval_order_data = eval_order_data.groupby(["cust_code", "cust_name", "product_code", "product_name"])[["sale_qty", "sale_amt"]].mean().reset_index()
    eval_order_data["sale_qty"] = eval_order_data["sale_qty"].round(0).astype(int)
    eval_order_data = eval_order_data.sort_values("sale_qty", ascending=False)
    
    # recommend_data = recommend_data.drop(columns=["sale_qty"])
    # 确保recommend_data中的cust_code也是字符串类型
    recommend_data["商户编号"] = recommend_data["商户编号"].astype(str)
    cust_ids = recommend_data.set_index("商户编号")
    
    # 执行合并操作
    merge_data = eval_order_data.join(cust_ids, on="cust_code", how="left")
    merge_data = merge_data[["cust_code", "cust_name", "product_code", "product_name", "sale_qty", "推荐序号", "推荐系数"]]
    merge_data = merge_data.rename(
        columns={
            "cust_code": "商户编号", 
            "cust_name": "商户名称", 
            "product_code": "卷烟编码", 
            "product_name": "卷烟名称", 
            "sale_qty": "月均销量"
        }
    )
    return merge_data

def eval_report_process(delivery_data, recommend_data):
    report = recommend_data.merge(delivery_data, left_on="商户编号", right_on="customer_code", how="left")
    report = report.drop(columns=["customer_code", "goods_code"])
    report = report.rename(columns={
        "retail_index_week": DeliveryConfig.FEATURES_MAP["retail_index_week"],
        "turnover_rate_collpoint": DeliveryConfig.FEATURES_MAP["turnover_rate_collpoint"],
        "turnover_rate_terminal": DeliveryConfig.FEATURES_MAP["turnover_rate_terminal"],
        "sale_qty": DeliveryConfig.FEATURES_MAP["sale_qty"],
    })
    return report

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')