import datetime #from datetime from multiprocessing import Pool import json import os import time import traceback import warnings from keras.models import load_model import pickle 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 DataSplit.COMMON.service.iotp.IotpAlgoService import IotpAlgoService #test_code from ZlwlAlgosCommon.service.iotp.Beans import DataField from ZlwlAlgosCommon.orm.models import * from DataSplit.V_1_0_0 import data_status as ds ##充电状态标准化程序 from DataSplit.V_1_0_0 import data_split as dt ##分段函数程序 from DataSplit.V_1_0_0 import data_drive_stat as ddt ##行驶数据按行驶段汇总统计 from DataSplit.V_1_0_0 import data_charge_stat as dct ##充电数据按充电段汇总 from DataSplit.V_1_0_0 import data_stand_stat as dst ##静置数据按静置段汇总 from DataSplit.V_1_0_0 import data_drive_stat_period as ddtp ##行驶数据按充电周期汇总统计 from DataSplit.V_1_0_0 import trans_day as trd ##解决跨天的问题 from DataSplit.V_1_0_0 import stand_status as ss def update_param(db_engine): # 从redis中获取参数，如果redis中获取不到，则去数据库中获取 df_algo_adjustable_param = pd.read_sql("select * from algo_adjustable_param", db_engine) df_algo_list = pd.read_sql("select * from algo_list", db_engine) df_algo_pack_param = pd.read_sql("select* from algo_pack_param", db_engine) return df_algo_adjustable_param, df_algo_list, df_algo_pack_param def main(): process_num=1 # 程序不能停止 while(True): try: warnings.filterwarnings("ignore") try: cleanUtils = CleanUtils() # 调用算法前的准备工作 mysql_algo_conn = None mysql_algo_engine = None mysql_iotp_conn = None mysql_iotp_engine= None kafka_consumer = None rc= None algo_list = ['socdiag','low_soc_diag','Sor_Diag','Li_Plted','Data_Split'] # 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() mysql_iotp_data = sysUtils.get_cf_param('mysql-iotp') mysqlUtils = MysqlUtils() mysql_iotp_engine, mysql_iopt_Session= mysqlUtils.get_mysql_engine(mysql_iotp_data) mysql_iotp_conn = mysql_iotp_engine.connect() #Hbase hbase_params = sysUtils.get_cf_param('hbase-datafactory')# test_code iotp_service = IotpAlgoService(hbase_params=hbase_params) #redis redis_params = sysUtils.get_cf_param('redis') reidsUtils = RedisUtils() rc = reidsUtils.get_redis_conncect(redis_params) except Exception as e: logger_main.error(f'process-{process_num}: {e}') logger_main.error(f'process-{process_num}: {traceback.format_exc()}') cleanUtils.clean(mysql_algo_conn, mysql_algo_engine, mysql_iotp_conn, mysql_iotp_engine, kafka_consumer, rc) # 开始准备调度 # for message in kafka_consumer: #KafkaConsumer.commit(self) try: logger_main.info(f'收到调度') 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 df_algo_adjustable_param, df_algo_list, df_algo_pack_param=update_param(mysql_algo_conn) df_algo_adjustable_param[df_algo_adjustable_param['pack_code']=='JX19220'] df_algo_pack_param=df_algo_pack_param[df_algo_pack_param['pack_code']=='JX19220'] df_algo_pack_param=json.loads(df_algo_pack_param.iloc[0]['param']) pack_code='JX19220' # schedule_params = json.loads(message.value) # if (schedule_params is None) or (schedule_params ==''): # logger_main.info('{} kafka数据异常，跳过本次运算'.format(str(message.value))) # 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_pack_param = {k: eval(v) if isinstance(v, str) else v for k, v in df_algo_pack_param.items()} # df_algo_param = 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'] 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() df_snpk_list = pd.read_sql("select sn, imei,pack_model,device_cell_type,scrap_status from t_device", mysql_algo_conn) df_snpk_list=df_snpk_list[df_snpk_list['scrap_status']<4] df_snpk_list=df_snpk_list.rename(columns={'pack_model':'pack_code'}) df_snpk_list=df_snpk_list[df_snpk_list['sn'].str.contains('N234P')] df_sn_list=list(df_snpk_list['sn']) sn_list_total=df_sn_list sn_list=sn_list_total start_time = "2023-03-25 00:00:00" end_time = "2023-06-25 00:00:00" columns = [ DataField.time, DataField.sn, DataField.pack_crnt, DataField.pack_volt, DataField.pack_soc, DataField.cell_voltage_count, DataField.cell_temp_count, DataField.cell_voltage, DataField.cell_temp, DataField.other_temp_value, DataField.bms_sta, DataField.charge_sta,DataField.latitude,DataField.longitude, DataField.mileage, DataField.accum_chg_wh, DataField.accum_dschg_wh, DataField.accum_chg_ah,DataField.accum_dschg_ah,DataField.vin] for i in range(0,len(sn_list_total)): sn_list=[sn_list_total[i]] # 取数 time_st = time.time() logger_main.info(f"process-{process_num}: 开始取数，{start_time} ~ {end_time}\n{str(sn_list)}") df_data = iotp_service.get_data(sn_list=sn_list, columns=columns, start_time=start_time, end_time=end_time) #df_data.to_excel('df_data_1.xlsx') logger_main.info(f'process-{process_num},获取到{len(df_data)}条数据,取数d耗时:{time.time()-time_st}') if len(df_data) == 0: logger_main.info(f"process-{process_num}: 数据清洗耗时{time.time()-time_st}, 无有效数据，跳过本次运算") continue # 将字符串转换成datetime对象 str_date = start_time date_time =datetime.datetime.strptime(str_date, '%Y-%m-%d %H:%M:%S') # 将datetime对象减去6小时 new_date_time = date_time - datetime.timedelta(hours=8) # 将datetime对象转换成字符串 start_time_8h = new_date_time.strftime('%Y-%m-%d %H:%M:%S') df_data_8h = iotp_service.get_data(sn_list=sn_list, columns=columns, start_time=start_time_8h, end_time=start_time) logger_main.info(f'process-{process_num},获取到{len(df_data_8h)}条数据,取数耗时:{time.time()-time_st}') # 数据清洗 try: time_st = time.time() logger_main.info(f'process-{process_num}数据清洗') if len(df_data_8h)==0: df_data_8h=pd.DataFrame(columns=['datatype','time','sn','pack_crnt','pack_volt','pack_soc', 'cell_voltage_count','cell_temp_count','cell_voltage','cell_temp','other_temp_value', 'bms_sta','charge_sta','latitude','longitude','mileage','accum_dschg_wh','accum_chg_wh','accum_chg_ah','accum_dschg_ah','vin']) #df_data_8h = df_data_8h.drop(['latitude','longitude','mileage','accum_chg_wh''accum_dschg_wh','accum_dschg_ah','accum_chg_ah','vin'], axis=1, errors='ignore') if len(df_data)==0: df_data=pd.DataFrame(columns=['datatype','time','sn','pack_crnt','pack_volt','pack_soc', 'cell_voltage_count','cell_temp_count','cell_voltage','cell_temp','other_temp_value', 'bms_sta','charge_sta','latitude','longitude','mileage','accum_dschg_wh','accum_chg_wh','accum_chg_ah','accum_dschg_ah','vin']) #df_data = df_data.drop(['latitude','longitude','mileage','accum_chg_wh','accum_dschg_wh','accum_dschg_ah','accum_chg_ah','vin'], axis=1, errors='ignore') df_data_gps=iotp_service.gps_datacleaning(df_data) df_data_gps_8h=iotp_service.gps_datacleaning(df_data_8h) df_data_accum=iotp_service.accum_datacleaning(df_data) df_data_accum_8h=iotp_service.accum_datacleaning(df_data_8h) df_data_vin=iotp_service.vin_datacleaning(df_data) df_data_vin_8h=iotp_service.vin_datacleaning(df_data_8h) df_data, df_table, cellvolt_name, celltemp_name = iotp_service.datacleaning(df_algo_pack_param,df_data)#进行数据清洗 df_data_8h, df_table_t, cellvolt_name_t, celltemp_name_t = iotp_service.datacleaning(df_algo_pack_param,df_data_8h)#进行数据清洗 #df_data.to_excel('df_data_2.xlsx') if len(df_data_gps_8h)==0: df_data_gps_8h=pd.DataFrame(columns=['sn','time','datatype','latitude','longitude','mileage']) if len(df_data_gps)==0: df_data_gps=pd.DataFrame(columns=['sn','time','datatype','latitude','longitude','mileage']) if len(df_data_accum_8h)==0: df_data_accum_8h=pd.DataFrame(columns=['sn','time','datatype','accum_chg_wh','accum_dschg_wh','accum_dschg_ah','accum_chg_ah']) if len(df_data_accum)==0: df_data_accum=pd.DataFrame(columns=['sn','time','datatype','accum_chg_wh','accum_dschg_wh','accum_dschg_ah','accum_chg_ah']) if len(df_data_vin_8h)==0: df_data_vin_8h=pd.DataFrame(columns=['sn','time','datatype','vin']) if len(df_data_vin)==0: df_data_vin=pd.DataFrame(columns=['sn','time','datatype','vin']) try: df_data_32h=pd.concat([df_data_8h,df_data]) df_data_32h=df_data_32h.reset_index(drop=True) #df_data_32h.to_excel('data_32h.xlsx') if len(df_data_32h)==0: logger_main.info(f"process-{process_num}: 数据清洗耗时{time.time()-time_st}, 无有效数据，跳过本次运算") continue else: df_data_gps_32h=pd.concat([df_data_gps_8h,df_data_gps]) df_data_gps_32h=df_data_gps_32h.reset_index(drop=True) if len(df_data_gps_32h)==0: df_data_gps_32h=pd.DataFrame(columns=['sn','time','datatype','latitude','longitude','mileage']) df_data_accum_32h=pd.concat([df_data_accum_8h,df_data_accum]) df_data_accum_32h=df_data_accum_32h.reset_index(drop=True) if len(df_data_accum_32h)==0: df_data_accum_32h=pd.DataFrame(columns=['sn','time','datatype','accum_chg_wh','accum_dschg_wh','accum_dschg_ah','accum_chg_ah']) df_data_vin_32h=pd.concat([df_data_vin_8h,df_data_vin]) df_data_vin_32h=df_data_vin_32h.reset_index(drop=True) if len(df_data_vin_32h)==0: df_data_vin_32h=pd.DataFrame(columns=['sn','time','datatype','vin']) ##先关联gps和accum df_merge_ga = pd.merge(df_data_gps_32h, df_data_accum_32h,on=['sn','time','datatype'],how='outer') df_merge_ga = pd.merge(df_merge_ga, df_data_vin_32h,on=['sn','time','datatype'],how='outer') df_merge_ga=df_merge_ga.sort_values(["sn","time"],ascending = [True, True]) df_merge_ga_filled = df_merge_ga.groupby("sn").fillna(method='ffill') df_merge_ga_filled= pd.concat([df_merge_ga[['sn']], df_merge_ga_filled], axis=1) df_merge_ga_filled = df_merge_ga_filled.groupby("sn").fillna(method='bfill') df_merge_ga= pd.concat([df_merge_ga[['sn']], df_merge_ga_filled], axis=1) ##识别静置的情况，关联非静置数据用前值填充 df_merge_ga['time'] = pd.to_datetime(df_merge_ga['time'], format='%Y-%m-%d %H:%M:%S') df_merge_bga = pd.merge(df_data_32h, df_merge_ga, on=['sn','time','datatype'],how='outer') #df_merge=ss.stand_status(df_merge_bga,s_order_delta=600,lon_delta=0.1) df_merge=df_merge_bga.sort_values(["sn","time"],ascending = [True, True]) df_merge_filled = df_merge.groupby("sn").fillna(method='ffill') df_merge = pd.concat([df_merge[['sn']], df_merge_filled], axis=1) df_merge_filled = df_merge.groupby("sn").fillna(method='bfill') df_merge = pd.concat([df_merge[['sn']], df_merge_filled], axis=1) df_merge=df_merge.dropna(subset=['pack_crnt','latitude','longitude','vin'],axis=0,how='all') df_merge=df_merge[df_merge['datatype']==12] #df_merge.to_excel('merged.xlsx') except Exception as e: logger_main.error(f"process-{process_num}:32小时拼接出错") logger_main.error(f"process-{process_num}:{e}") logger_main.error(f"process-{process_num}:{traceback.format_exc()}") if len(df_data) == 0: logger_main.info(f"process-{process_num}: 数据清洗耗时{time.time()-time_st}, 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']}, 数据清洗完成耗时{time.time()-time_st}") except Exception as e: logger_main.error(f"process-{process_num}:数据清洗出错") logger_main.error(f"process-{process_num}:{e}") logger_main.error(f"process-{process_num}:{traceback.format_exc()}") continue try: loggers['Data_Split'].info(f'开始执行算法{pack_code}, time:{start_time}~{end_time},\n sn_list:{sn_list}') df_merge=ds.data_status(df_merge,c_soc_dif_p=0.05,s_soc_dif_p=0,c_order_delta=1200,s_order_delta=300) ##基于各个状态码，进行分段，分段函数 cell_type='L' df_drive,df_charge,df_stand,df_data_split_rlt,df_rank_abnormal=dt.split(df_merge,celltemp_name,cellvolt_name,drive_interval_time_min=1200,charge_interval_time_min=1200,stand_interval_time_min=1200,single_num_min=3,drive_sts=3,charge_sts=[21,22],stand_sts=0,cell_type=cell_type,capacity=456) #df_drive,df_charge,df_stand,df_data_split_rlt=dt.split(df_merge,celltemp_name,cellvolt_name,drive_interval_time_min=1200,charge_interval_time_min=1200,stand_interval_time_min=1200,single_num_min=3,drive_sts=3,charge_sts=[21,22],stand_sts=0,cell_type=cell_type,capacity=456) df_data_split_rlt.to_excel(f'{sn_list[0]}_NEW.xlsx') loggers['Data_Split'].info(f'算法运行完成{pack_code}，算法耗时{time.time()-time_st}') except Exception as e: loggers['Data_Split'].error('算法运行出错') loggers['Data_Split'].error(str(e)) loggers['Data_Split'].error(traceback.format_exc()) df_drive=pd.DataFrame() df_charge=pd.DataFrame() df_stand=pd.DataFrame() df_data_split_rlt=pd.DataFrame() try: if not df_data_split_rlt.empty: time_record = time.time() df_data_split_rlt.reset_index(drop = True, inplace = True) #df_data_split_rlt.to_sql("algo_charge_info",con=mysql_algo_conn, if_exists="append",index=False) #write_mysql_time = write_mysql_time + time.time()-time_record logger_main.info(f'process-{process_num}数据分段统计入库{pack_code}完成') logger_main.info(f"process-{process_num}: 结果入库耗时：{time.time()-time_st}") except Exception as e: logger_main.error(f"process-{process_num}:数据分段结果入库出错") logger_main.error(f"process-{process_num}:{e}") logger_main.error(f"process-{process_num}:{traceback.format_exc()}") except Exception as e: logger_main.error(f"process-{process_num}:获取原始数据出错") logger_main.error(f"process-{process_num}:{e}") logger_main.error(f"process-{process_num}:{traceback.format_exc()}") continue #算法5_日数据分段 except Exception as e: logger_main.error(f'process-{process_num}: {e}') logger_main.error(f'process-{process_num}: {traceback.format_exc()}') cleanUtils.clean(mysql_algo_conn, mysql_algo_engine, mysql_iotp_conn, mysql_iotp_engine, kafka_consumer, rc) if __name__ == '__main__': while(True): try: # 配置量 cur_env = 'dev' # 设置运行环境 app_path = "/home/shouxueqi/projects/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_day_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") main() except Exception as e: print(str(e)) print(traceback.format_exc()) 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()