zlwl-algos-new/DOC/main_template.py

import datetime
import gc
import re
from multiprocessing import Pool
import json
import logging
import logging.handlers
import os
import time
import traceback
import warnings

from sqlalchemy import text, delete, and_, or_, update
import pandas as pd

from ZlwlAlgosCommon.utils.ProUtils import *
from ZlwlAlgosCommon.service.iotp.IotpAlgoService import IotpAlgoService
from ZlwlAlgosCommon.service.iotp.Beans import DataField
from ZlwlAlgosCommon.orm.models import *





def invoke_algo1(logger, mysql_algo_conn, mysql_algo_Session, start_time, df_data):
    pass

def invoke_algo2(logger, mysql_algo_conn, mysql_algo_Session, start_time, df_data):
    pass                                       



def main(process_num): 
    # 程序不能停止
    while(True):
        warnings.filterwarnings("ignore")
        try:   
            # 调用算法前的准备工作
            kafka_topic_key = 'topic_task_min_10'
            kafka_groupid_key = 'group_id_task_min_10'
            algo_list = ['FaultWarning', 'other'] # 本调度所包含的算法名列表。
            
            loggers = sysUtils.get_loggers(algo_list, log_base_path, process_num) # 为每个算法分配一个logger
            logger_main.info(f"process-{process_num}: 配置中间件")
            
            # mysql
            mysql_algo_params = sysUtils.get_cf_param('mysql-algo')
            mysqlUtils = MysqlUtils()
            mysql_algo_engine, mysql_algo_Session= mysqlUtils.get_mysql_engine(mysql_algo_params)
            mysql_algo_conn = mysql_algo_engine.connect()
            
            # redis
            redis_params = sysUtils.get_cf_param('redis')
            redisUtils = RedisUtils()
            redis_conn = redisUtils.get_redis_conncect(redis_params)
            
            # hbase
            hbase_params = sysUtils.get_cf_param('hbase')
            iotp_service = IotpAlgoService(hbase_params=hbase_params)

            # kafka
            kafka_params = sysUtils.get_cf_param('kafka')
            kafkaUtils = KafkaUtils()
            kafka_consumer = kafkaUtils.get_kafka_consumer(kafka_params, kafka_topic_key, kafka_groupid_key, client_id=kafka_topic_key)
        
            logger_main.info(f"process-{process_num}: 获取算法参数及电池参数")
            
        except Exception as e:
            logger_main.error(f'process-{process_num}: {e}')
            logger_main.error(f'process-{process_num}: {traceback.format_exc()}')
        
        # 开始准备调度
        try:
            logger_main.info(f"process-{process_num}: 监听topic {kafka_params[kafka_topic_key]}等待kafka 调度")
            param_update_timer = time.time()       
            for message in kafka_consumer:
                try:
                    logger_main.info(f'process-{process_num}: 收到调度 {message.value}')
                    if not mysql_algo_conn.closed:
                        mysql_algo_conn.close()
                    mysql_algo_conn = mysql_algo_engine.connect() # 从连接池中获取一个myslq连接
                        
                    schedule_params = json.loads(message.value)                    
                    if (schedule_params is None) or (schedule_params ==''):
                        logger_main.info(f'process-{process_num}: {message.value} kafka数据异常，跳过本次运算')
                        continue
                    # kafka 调度参数解析
                    df_snlist = pd.DataFrame(schedule_params['snlist'])
                    df_algo_adjustable_param = pd.DataFrame([(d['algo_id'], d['param'],d['param_ai']) for d in schedule_params['adjustable_param']], columns=['algo_id', 'param','param_ai'])
                    df_algo_pack_param = json.loads(schedule_params['pack_param'][0]['param'])
                    df_algo_list = pd.DataFrame(schedule_params['algo_list'])
                    start_time = schedule_params['start_time']
                    end_time = schedule_params['end_time']
                    pack_code = schedule_params['pack_code']
                    cell_type = schedule_params['cell_type']  
                    sn_list=df_snlist['sn'].tolist()
                    
                    # 取数
                    logger_main.info(f"process-{process_num}: 开始取数")
                    columns = [DataField.error_level, DataField.error_code, DataField.pack_crnt, DataField.pack_volt,
        DataField.bms_sta, DataField.cell_voltage_count, DataField.cell_temp_count, DataField.cell_voltage, DataField.cell_temp, 
        DataField.pack_soc, DataField.other_temp_value, DataField.cell_balance,
        DataField.pack_soh, DataField.charge_sta]
                    df_data = iotp_service.get_data(sn_list=sn_list, columns=columns, start_time=start_time, end_time=end_time)
                    logger_main.info(f"process-{process_num}: {str(sn_list)}获取到{str(len(df_data))}条数据")
                except Exception as e:
                    logger_main.error(f'process-{process_num}: {pack_code}运行出错')
                    logger_main.error(f'process-{process_num}: {e}')
                    logger_main.error(f'process-{process_num}: {traceback.format_exc()}')
                try:
                    # 数据清洗                        
                    if len(df_data) == 0:
                        logger_main.info(f"process-{process_num}: 无数据跳过本次运算")      
                        continue
                    df_data,df_table,cellvolt_name,celltemp_name=iotp_service.data_clean(df_data,df_algo_pack_param)#进行数据清洗
                    if len(df_data) == 0:
                        logger_main.info(f"process-{process_num}: 数据清洗完成, 无有效数据，跳过本次运算")      
                        continue
                    else:
                        logger_main.info(f"process-{process_num}: {pack_code}, time_type:{df_data.loc[0, 'time']} ~ {df_data.iloc[-1]['time']}, 数据清洗完成")
                except Exception as e:
                    logger_main.error(f"process-{process_num}:{pack_code}数据清洗出错")
                    logger_main.error(f"process-{process_num}:{e}")
                    logger_main.error(f"process-{process_num}:{traceback.format_exc()}")
                    
                # 算法调用   
                try:
                    invoke_algo1(loggers, mysql_algo_conn, mysql_algo_Session, start_time, df_data)
                except Exception as e:
                    loggers['FaultWarning'].error('{}运行出错'.format(pack_code))
                    loggers['FaultWarning'].error(str(e))
                    loggers['FaultWarning'].error(traceback.format_exc())
                
                # 第二个算法调用
                try:
                    invoke_algo2(loggers, mysql_algo_conn, mysql_algo_Session, start_time, df_data)
                except Exception as e:
                    loggers['FaultWarning'].error('{}运行出错'.format(pack_code))
                    loggers['FaultWarning'].error(str(e))
                    loggers['FaultWarning'].error(traceback.format_exc())
                
                
                    

        except Exception as e:
            logger_main.error(f'process-{process_num}: {pack_code}运行出错')
            logger_main.error(f'process-{process_num}: {e}')
            logger_main.error(f'process-{process_num}: {traceback.format_exc()}')
        finally:
            iotp_service.close()  



if __name__ == '__main__':
   while(True):
        try:
            # 配置量
            cur_env = 'dev' # 设置运行环境
            app_path = "/home/wangliming/project/zlwl-algos/" # 设置app绝对路径
            log_base_path = f"{os.path.dirname(os.path.abspath(__file__))}/log" # 设置日志路径

            app_name = "task_second_1" # 应用名
            
            sysUtils = SysUtils(cur_env, app_path)
            logger_main = sysUtils.get_logger(app_name, log_base_path)
            logger_main.info(f"本次主进程号: {os.getpid()}")
            # 读取配置文件 (该部分请不要修改)
            processes = int(sysUtils.env_params.get("PROCESS_NUM_PER_NODE", '1')) # 默认为1个进程
            pool = Pool(processes = int(processes))
            logger_main.info("开始分配子进程")
            for i in range(int(processes)):
                pool.apply_async(main, (i, ))
            pool.close()
            logger_main.info("进程分配结束，堵塞主进程")
            pool.join()
        except Exception as e:
            logger_main.error(str(e))
            logger_main.error(traceback.format_exc())
        finally:
            handlers = logger_main.handlers.copy()
            for h in handlers:
                logger_main.removeHandler(h)
            pool.terminate()