BrandCultivation/models/rank/gbdt_lr.py

#!/usr/bin/env python3
# -*- coding:utf-8 -*-
import numpy as np
from models.rank.data import DataLoader
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import OneHotEncoder
import joblib
import time

class Trainer:
    def __init__(self, path):
        self._load_data(path)
        
        # 初始化GBDT和LR模型参数
        self._gbdt_params = {
            'n_estimators': 100,
            'learning_rate': 0.01,
            'max_depth': 6,
            'subsample': 0.8,
            'random_state': 42,
        }
        self._lr_params = {
            "max_iter": 1000,
            'C': 1.0, 
            'penalty': 'elasticnet', 
            'l1_ratio': 0.8,  # 添加 l1_ratio 参数，可以根据需要调整
            'solver': 'saga',
            'random_state': 42,
            'class_weight': 'balanced'
        }
        
        # 初始化模型
        self._gbdt_model = GradientBoostingClassifier(**self._gbdt_params)
        self._lr_model = LogisticRegression(**self._lr_params)
        
        self._onehot_encoder = OneHotEncoder(sparse_output=True, handle_unknown='ignore')
        
    def _load_data(self, path):
        dataloader = DataLoader(path)
        self._train_dataset, self._test_dataset = dataloader.split_dataset()
        
    def train(self):
        """模型训练"""
        print("开始训练GBDT模型...")
        # 训练GBDT模型
        self._gbdt_model.fit(self._train_dataset["data"], self._train_dataset["label"])
        
        # 获取GBDT的每棵树的分数（决策值）
        gbdt_train_preds = self._gbdt_model.apply(self._train_dataset["data"])[:, :, 0]  # 仅取每棵树的叶节点输出
        
        gbdt_feats_encoded = self._onehot_encoder.fit_transform(gbdt_train_preds)
        
        print("开始训练LR模型...")
        # 使用决策树输出作为LR的输入特征
        self._lr_model.fit(gbdt_feats_encoded, self._train_dataset["label"])
        
    def predict(self, X):
        # 获取GBDT模型的预测分数
        gbdt_preds = self._gbdt_model.apply(X)[:, :, 0]
        
        gbdt_feats_encoded = self._onehot_encoder.transform(gbdt_preds)
        
        # 使用训练好的LR模型输出概率
        return self._lr_model.predict(gbdt_feats_encoded)
    
    def predict_proba(self, X):
        # 获取GBDT模型的预测分数
        gbdt_preds = self._gbdt_model.apply(X)[:, :, 0]
        
        gbdt_feats_encoded = self._onehot_encoder.transform(gbdt_preds)
        
        # 使用训练好的LR模型输出概率
        return self._lr_model.predict_proba(gbdt_feats_encoded)
        
    def evaluate(self):
        # 对测试集进行预测
        y_pred = self.predict(self._test_dataset["data"])
        y_pred_proba = self.predict_proba(self._test_dataset["data"])[:, 1]  # 获取正类的概率
        
        # 计算各类评估指标
        accuracy = accuracy_score(self._test_dataset["label"], y_pred)
        precision = precision_score(self._test_dataset["label"], y_pred)
        recall = recall_score(self._test_dataset["label"], y_pred)
        f1 = f1_score(self._test_dataset["label"], y_pred)
        roc_auc = roc_auc_score(self._test_dataset["label"], y_pred_proba)    
        
        return {
            'accuracy': accuracy,
            'precision': precision,
            'recall': recall,
            'f1_score': f1,
            'roc_auc': roc_auc
        }
        
    def save_model(self, model_path):
        """将模型保存到本地"""
        models = {"gbdt_model": self._gbdt_model, "lr_model": self._lr_model, "onehot_encoder": self._onehot_encoder}
        joblib.dump(models, model_path)
    
     
if __name__ == "__main__":
    gbdt_data_path = "./data/train_data.csv"
    trainer = Trainer(gbdt_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
    model_path = "./models/rank/weights/model.pkl"
    trainer.save_model(model_path)