algorithm_platform/models_processing/model_train/model_training_lightgbm.py

import lightgbm as lgb
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error,mean_absolute_error
from flask import Flask,request
import time
import traceback
import logging
from common.database_dml import get_data_from_mongo,insert_pickle_model_into_mongo
app = Flask('model_training_lightgbm——service')


def build_model(df,args):
    np.random.seed(42)
    #lightgbm预测下
    numerical_features,categorical_features,label,model_name,num_boost_round,model_params = str_to_list(args['numerical_features']),str_to_list(args['categorical_features']),args['label'],args['model_name'],int(args['num_boost_round']),eval(args['model_params'])
    features = numerical_features+categorical_features
    print("features:************",features)
    # 拆分数据为训练集和测试集
    X_train, X_test, y_train, y_test = train_test_split(df[features], df[label], test_size=0.2, random_state=42)
    # 创建LightGBM数据集
    lgb_train = lgb.Dataset(X_train, y_train,categorical_feature=categorical_features)
    lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)
    # 设置参数
    params = {
        'objective': 'regression',
        'metric': 'rmse',
        'boosting_type': 'gbdt',
        'verbose':1
    }

    params.update(model_params)
    # 训练模型
    print('Starting training...')
    gbm = lgb.train(params,
                    lgb_train,
                    num_boost_round=num_boost_round,
                    valid_sets=[lgb_train, lgb_eval],
                    )
    y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)

    # 评估
    mse = mean_squared_error(y_test, y_pred)
    rmse = np.sqrt(mse)
    mae = mean_absolute_error(y_test, y_pred)
    print(f'The test rmse is: {rmse},"The test mae is:"{mae}')
    

    return gbm


def str_to_list(arg):
    if arg == '':
        return []
    else:
        return arg.split(',')


@app.route('/model_training_lightgbm', methods=['POST'])
def model_training_lightgbm():
    # 获取程序开始时间  
    start_time = time.time()  
    result = {}
    success = 0
    print("Program starts execution!")
    try:
        args = request.values.to_dict()
        print('args',args)
        logger.info(args)
        power_df = get_data_from_mongo(args)
        model = build_model(power_df,args)
        insert_pickle_model_into_mongo(model,args)
        success = 1
    except Exception as e:
        my_exception = traceback.format_exc()
        my_exception.replace("\n","\t")
        result['msg'] = my_exception
    end_time = time.time() 
   
    result['success'] = success
    result['args'] = args
    result['start_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(start_time))
    result['end_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(end_time))
    print("Program execution ends!")
    return result


if __name__=="__main__":  
    print("Program starts execution!")
    logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
    logger = logging.getLogger("model_training_lightgbm log")
    from waitress import serve
    serve(app, host="0.0.0.0", port=10089)
    print("server start!")