BrandCultivation/models/rank/data/preprocess.py

from dao.dao import load_cust_data_from_mysql, load_product_data_from_mysql, load_order_data_from_mysql
from models.rank.data.config import CustConfig, ProductConfig, OrderConfig
import os
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from sklearn.utils import shuffle
import numpy as np

class DataProcess():
    def __init__(self, city_uuid):
        self._save_res_path = "./models/rank/data/gbdt_data.csv"
        print("正在加载cust_info...")
        self._cust_data = load_cust_data_from_mysql(city_uuid)
        print("正在加载product_info...")
        self._product_data = load_product_data_from_mysql(city_uuid)
        print("正在加载order_info...")
        self._order_data = load_order_data_from_mysql(city_uuid)
        
    def data_process(self):
        """数据预处理"""
        if os.path.exists(self._save_res_path):
            os.remove(self._save_res_path)
        
        # 1. 获取指定的特征组合
        self._cust_data = self._cust_data[CustConfig.FEATURE_COLUMNS]
        self._product_data = self._product_data[ProductConfig.FEATURE_COLUMNS]
        self._order_data = self._order_data[OrderConfig.FEATURE_COLUMNS]
        
        # 2. 数据清洗
        self._clean_cust_data()
        self._clean_product_data()
        self._clean_order_data()
        
        # # 3. 将零售户信息表与卷烟信息表进行笛卡尔积连接
        # self._descartes()
        
        # # 4. 根据order表中的信息给数据打标签
        # self._labeled_data()
        
        # 3. 根据特征权重给order表中的记录打分
        self._calculate_score()
        
        # 4. 根据中位数打标签
        self.labeled_data()
        
        # 5. 选取训练样本
        self._generate_train_data()
        
    
    def _clean_cust_data(self):
        """用户信息表数据清洗"""
        # 根据配置规则清洗数据
        for feature, rules, in CustConfig.CLEANING_RULES.items():
            if rules["type"] == "num":
                # 先将数值型字符串转换为数值
                self._cust_data[feature] = pd.to_numeric(self._cust_data[feature], errors="coerce")
                
            if rules["method"] == "fillna":
                if rules["opt"] == "fill":
                    self._cust_data[feature] = self._cust_data[feature].fillna(rules["value"])
                elif rules["opt"] == "replace":
                    self._cust_data[feature] = self._cust_data[feature].fillna(self._cust_data[rules["value"]])
                elif rules["opt"] == "mean":
                    self._cust_data[feature] = self._cust_data[feature].fillna(self._cust_data[feature].mean())
                self._cust_data[feature] = self._cust_data[feature].infer_objects(copy=False)
    
    def _clean_product_data(self):
        """卷烟信息表数据清洗"""
        for feature, rules, in ProductConfig.CLEANING_RULES.items():
            if rules["type"] == "num":
                self._product_data[feature] = pd.to_numeric(self._product_data[feature], errors="coerce")
            
            if rules["method"] == "fillna":
                if rules["opt"] == "fill":
                    self._product_data[feature] = self._product_data[feature].fillna(rules["value"])
                elif rules["opt"] == "mean":
                    self._product_data[feature] = self._product_data[feature].fillna(self._product_data[feature].mean())
                self._product_data[feature] = self._product_data[feature].infer_objects(copy=False)
                    
    def _clean_order_data(self):
        pass
    
    def _calculate_score(self):
        """计算order记录的fens"""
        self._order_score = self._order_data.copy()
        # 对参与算分的特征值进行归一化
        scaler = MinMaxScaler()
        self._order_score[list(OrderConfig.WEIGHTS.keys())] = scaler.fit_transform(self._order_score[list(OrderConfig.WEIGHTS.keys())])
        # 计算加权分数
        self._order_score["score"] = sum(self._order_score[feat] * weight 
                          for feat, weight in OrderConfig.WEIGHTS.items())
    
    def labeled_data(self):
        """通过计算分数打标签"""
        # 按品规分组计算中位数
        product_medians = self._order_score.groupby("PRODUCT_CODE")["score"].median().reset_index()
        product_medians.columns = ["PRODUCT_CODE", "median_score"]
        
        # 合并中位数到原始订单数据
        self._order_score = pd.merge(self._order_score, product_medians, on="PRODUCT_CODE")
        
        # 生成标签 (1: 大于等于中位数, 0: 小于中位数)
        self._order_score["label"] = np.where(
            self._order_score["score"] >= self._order_score["median_score"], 1, 0
        )
        self._order_score = self._order_score.sort_values("score", ascending=False)
        self._order_score = self._order_score[["BB_RETAIL_CUSTOMER_CODE", "PRODUCT_CODE", "label"]]
        self._order_score.rename(columns={"PRODUCT_CODE": "product_code"}, inplace=True)
    
    def _generate_train_data(self):
        cust_feats = self._cust_data.set_index("BB_RETAIL_CUSTOMER_CODE")
        product_feats = self._product_data.set_index("product_code")
        
        self._train_data = self._order_score.copy()
        
        self._train_data = self._train_data.join(cust_feats, on="BB_RETAIL_CUSTOMER_CODE", how="left")
        self._train_data = self._train_data.join(product_feats, on="product_code", how="left")
        
        self._train_data = shuffle(self._train_data, random_state=42)
        
        self._train_data.to_csv(self._save_res_path, index=False)
    
    def _descartes(self):
        """将零售户信息与卷烟信息进行笛卡尔积连接"""
        self._cust_data["descartes"] = 1
        self._product_data["descartes"] = 1
        
        self._descartes_data = pd.merge(self._cust_data, self._product_data, on="descartes").drop("descartes", axis=1)
        
    def _labeled_data_from_descartes(self):
        """根据order表信息给descartes_data数据打标签"""
        # 获取order表中的正样本组合
        order_combinations = self._order_data[["BB_RETAIL_CUSTOMER_CODE", "PRODUCT_CODE"]].drop_duplicates()
        order_set = set(zip(order_combinations["BB_RETAIL_CUSTOMER_CODE"], order_combinations["PRODUCT_CODE"]))
        
        # 在descartes_data中打标签：正样本为1，负样本为0
        self._descartes_data['label'] = self._descartes_data.apply(
            lambda row: 1 if (row['BB_RETAIL_CUSTOMER_CODE'], row['product_code']) in order_set else 0, axis=1)
    
    def _generate_train_data_from_descartes(self):
        """从descartes_data中生成训练数据"""
        positive_samples = self._descartes_data[self._descartes_data["label"] == 1]
        negative_samples = self._descartes_data[self._descartes_data["label"] == 0]
        
        positive_count = len(positive_samples)
        negative_count = min(1 * positive_count, len(negative_samples))
        print(positive_count)
        print(negative_count)
        
        # 随机抽取2倍正样本数量的负样本
        negative_samples_sampled = negative_samples.sample(n=negative_count, random_state=42)
        # 合并正负样本
        self._train_data = pd.concat([positive_samples, negative_samples_sampled], axis=0)
        self._train_data = self._train_data.sample(frac=1, random_state=42).reset_index(drop=True)
        
        # 保存训练数据
        self._train_data.to_csv(self._save_res_path, index=False)
    
if __name__ == '__main__':
    processor = DataProcess("00000000000000000000000011445301")
    processor.data_process()