import sagemaker
import logging
import boto3
from sagemaker.processing import ScriptProcessor, ProcessingInput, ProcessingOutput, FrameworkProcessor
from sagemaker import get_execution_role

role = get_execution_role()
bucket = 'dev-cucumbers'
sagemaker_session = sagemaker.session.Session(default_bucket = bucket)

script_processor = ScriptProcessor(
    image_uri='683313688378.dkr.ecr.us-east-1.amazonaws.com/sagemaker-scikit-learn:0.20.0-cpu-py3',
    sagemaker_session=sagemaker_session,
    role=role,
    instance_count=1,
    instance_type= 'ml.c5.4xlarge',    # 'ml.t3.medium',  #'ml.c5.4xlarge',  'ml.c5.18xlarge',
    command=['python3'],
    base_job_name="ProcessingJob"
)

destination = '/opt/ml/processing/input'

script1='/home/ec2-user/SageMaker/ml-collab/eimpara/Maze/ML_pipelines/regression_run_v2.py'
#script1='/home/ec2-user/SageMaker/ml-collab/eimpara/Maze/ML_pipelines/table.py'

logging.info(f"Running: {script1}")
script_processor.run(
        code=script1,
#         arguments = ["--run-id", str(run_id),
#                     '--folder', FOLDER],
        inputs=[
            ProcessingInput(
                source='s3://dev-cucumbers/eimpara/requirements-maze.txt',
                destination = '/opt/ml/processing/input/dependencies'
            )
        ],
        outputs=[
            ProcessingOutput(
                source='/opt/ml/processing/output',  
                destination=destination,
                output_name="Master_output",
            ),
        ]
    )