BrandCultivation/gbdt_lr.py

import argparse
import os
from models.rank import DataProcess, Trainer, GbdtLrModel
import time
import pandas as pd

# train_data_path = "./moldes/rank/data/gbdt_data.csv"
# model_path = "./models/rank/weights"

def train(args):
    model_dir = os.path.join(args.model_path, args.city_uuid)
    if not os.path.exists(model_dir):
        os.makedirs(model_dir)
    
    # 准备数据集  
    print("正在整合训练数据...")
    processor = DataProcess(args.city_uuid, args.train_data_dir)
    processor.data_process()
    print("训练数据整合完成！")
    
    # 进行训练
    print("开始训练原始模型")
    trainer(args, os.path.join(args.train_data_dir, "original_train_data.csv"), model_dir, "ori_model.pkl")
    
    print("开始训练pos模型")
    trainer(args, os.path.join(args.train_data_dir, "pos_train_data.csv"), model_dir, "pos_model.pkl")
    
    print("开始训练shopping模型")
    trainer(args, os.path.join(args.train_data_dir, "shopping_train_data.csv"), model_dir, "shopping_model.pkl")

def trainer(args, train_data_path, model_dir, model_name):
    trainer = Trainer(train_data_path)
    
    start_time = time.time()
    trainer.train()
    end_time = time.time()
    
    training_time_hours = (end_time - start_time) / 3600
    print(f"训练时间: {training_time_hours:.4f} 小时")
    
    eval_metrics = trainer.evaluate()
    
    # 输出评估结果
    print("GBDT-LR Evaluation Metrics:")
    for metric, value in eval_metrics.items():
        print(f"{metric}: {value:.4f}")
        
    # 保存模型
    trainer.save_model(os.path.join(model_dir, model_name))

def recommend_by_product(args):
    model_dir = os.path.join(args.model_path, args.city_uuid)
    if not os.path.exists(model_dir):
        print("暂无该城市的模型，请先进行模型训练")
        return
    
    # 加载模型
    model = GbdtLrModel(os.path.join(model_dir, args.model_name))
    recommend_list = model.sort(args.city_uuid, args.product_id)
    for item in recommend_list[:min(args.last_n, len(recommend_list))]:
        print(item)

def get_features_importance(args):
    model_dir = os.path.join(args.model_path, args.city_uuid)
    if not os.path.exists(model_dir):
        print("暂无该城市的模型，请先进行模型训练")
        return
    
    # 加载模型
    model = GbdtLrModel(os.path.join(model_dir, args.model_name))
    cust_features_importance, product_features_importance = model.generate_feats_importance()
    
    # 将字典列表转换为 DataFrame
    cust_df = pd.DataFrame([
        {"Features": list(item.keys())[0], "Importance": list(item.values())[0]}
        for item in cust_features_importance
    ])
    
    product_df = pd.DataFrame([
        {"Features": list(item.keys())[0], "Importance": list(item.values())[0]}
        for item in product_features_importance
    ])
    
    cust_file_path = os.path.join(model_dir, "cust_features_importance.csv")
    product_file_path = os.path.join(model_dir, "product_features_importance.csv")
    cust_df.to_csv(cust_file_path, index=False, encoding='utf-8')
    product_df.to_csv(product_file_path, index=False, encoding='utf-8')
        
def run():
    parser = argparse.ArgumentParser()
    
    parser.add_argument("--run_train", action='store_true')
    parser.add_argument("--recommend", action='store_true')
    parser.add_argument("--importance", action='store_true')
    
    parser.add_argument("--train_data_dir", type=str, default="./data")
    parser.add_argument("--model_path", type=str, default="./models/rank/weights")
    parser.add_argument("--model_name", type=str, default='model.pkl')
    parser.add_argument("--last_n", type=int, default=200)
    
    parser.add_argument("--city_uuid", type=str, default='00000000000000000000000011445301')
    parser.add_argument("--product_id", type=str, default='110102')
    
    
    args = parser.parse_args()
    
    if args.run_train:
        train(args)
        
    if args.recommend:
        recommend_by_product(args)
        
    if args.importance:
        get_features_importance(args)
        
if __name__ == "__main__":
    run()