123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172 |
- from concurrent.futures import ThreadPoolExecutor, as_completed
- from datetime import timedelta
- import pandas as pd
- from odps.src.types_c import datetime
- from client import ODPSClient
- odps_client = ODPSClient.ODPSClient()
- dt_list = ["20241108", "20241109", "20241110"]
- hh_list = ["00", "01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12", "13", "14", "15", "16", "17",
- "18", "19", "20", "21", "22", "23"]
- VOV_BASE_PATH = "/Users/zhao/Desktop/tzld/vov"
- # 定义查询函数
- def read_odps(dt: str, hh: str):
- # 读取SQL文件
- sql = ""
- with open(f"{VOV_BASE_PATH}/sql/vovh24_feature.sql", "r") as f:
- sql = f.read()
- real_sql = (
- sql.replace("${bizdate}", dt)
- .replace("${hh}", hh)
- .replace("${apptype}", "4")
- )
- print(f"Executing for dt: {dt}, hh: {hh}")
- odps_client.execute_sql_result_save_file(real_sql, f"{VOV_BASE_PATH}/csv/{dt}{hh}_feature.csv")
- # 并行执行函数
- def run_parallel():
- # 定义线程池的最大线程数
- with ThreadPoolExecutor(max_workers=24) as executor:
- # 创建任务列表
- future_to_task = {executor.submit(read_odps, dt, hh): (dt, hh)
- for dt in dt_list
- for hh in hh_list
- }
- # 监控每个任务的完成情况
- for future in as_completed(future_to_task):
- dt, hh = future_to_task[future]
- try:
- future.result() # 获取执行结果
- print(f"Completed for dt: {dt}, hh: {hh}")
- except Exception as exc:
- print(f"Error for dt: {dt}, hh: {hh} - {exc}")
- def download():
- # 执行并行任务
- run_parallel()
- for dt in dt_list:
- csv_list = []
- for hh in hh_list:
- csv_list.append(f"{VOV_BASE_PATH}/csv/{dt}{hh}_feature.csv")
- df_list = [pd.read_csv(file) for file in csv_list]
- df = pd.concat(df_list, ignore_index=True)
- df.to_csv(f"{VOV_BASE_PATH}/csv/{dt}_feature.csv", index=False)
- def _main():
- download()
- if __name__ == "__main__":
- _main()
|