def preprocess_glue()

in dags/xgboost-ml-pipeline/2.0/mwaa-customer-churn-dag.py [0:0]

• 32 lines of code
• 1 McCabe index (conditional complexity)

def preprocess_glue():
  """preprocess data using glue for etl"""

  # not best practice to hard code location 
  glue_script_location = 's3://{}/{}'.format(config.GLUE_JOB_SCRIPT_S3_BUCKET, config.GLUE_JOB_SCRIPT_S3_KEY)
  glue_client = boto3.client('glue')

  # instantiate the Glue ETL job
  response = glue_client.create_job(
    Name=glue_job_name,
    Description='PySpark job to extract the data and split in to training and validation data sets',
    Role=config.GLUE_ROLE_NAME,
    ExecutionProperty={
      'MaxConcurrentRuns': 2
    },
    Command={
      'Name': 'glueetl',
      'ScriptLocation': glue_script_location,
      'PythonVersion': '3'
    },
    DefaultArguments={
      '--job-language': 'python'
    },
    GlueVersion='1.0',
    WorkerType='Standard',
    NumberOfWorkers=2,
    Timeout=60
    )
  
  # execute the previously instantiated Glue ETL job
  response = glue_client.start_job_run(
    JobName=response['Name'],
    Arguments={
      '--S3_SOURCE': config.DATA_S3_SOURCE,
      '--S3_DEST': config.DATA_S3_DEST,
      '--TRAIN_KEY': 'train/',
      '--VAL_KEY': 'validation/' 
    }
  )