utilities/feature_store_helper.py [332:368]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        else:
            processor = PySparkProcessor(framework_version='3.0',
                                role=self._role,
                                instance_type=instance_type,  
                                instance_count=instance_count,
                                base_job_name=pipeline_name,
                                env={'AWS_DEFAULT_REGION': self._region,
                                     'mode': 'python'},
                                max_runtime_in_seconds=max_runtime_in_seconds)
            proc_inputs = []
            job_args = ['--feature_group_name', fg_name,
                        '--region_name', self._region,
                        '--s3_uri_prefix', s3_uri_prefix]
            proc_outputs = [ProcessingOutput(output_name='output-1',
                                             source='/opt/ml/processing/spark-events/',
                                             destination=f's3://{default_bucket}/spark-logs',
                                             s3_upload_mode='Continuous')]

        step_process = ProcessingStep(
            name='FeaturePipelineStep',
            processor=processor,
            inputs=proc_inputs,
            outputs=proc_outputs,
            job_arguments=job_args,
            code=self._pipeline_script_tmp_name 
            #,spark_event_logs_s3_uri=f's3://{default_bucket}/spark-logs'
        )

        # 2/ Create a simple pipeline containing that one step
        pipeline = Pipeline(
            name=pipeline_name,
            parameters=[],
            steps=[step_process],
        )

        # 3/ Save the new pipeline
        pipeline.upsert(role_arn=self._role)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



utilities/feature_store_helper.py [473:509]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        else:
            processor = PySparkProcessor(framework_version='3.0',
                                role=self._role,
                                instance_type=instance_type,  
                                instance_count=instance_count,
                                base_job_name=pipeline_name,
                                env={'AWS_DEFAULT_REGION': self._region,
                                     'mode': 'python'},
                                max_runtime_in_seconds=max_runtime_in_seconds)
            proc_inputs = []
            job_args = ['--feature_group_name', fg_name,
                        '--region_name', self._region,
                        '--s3_uri_prefix', s3_uri_prefix]
            proc_outputs = [ProcessingOutput(output_name='output-1',
                                             source='/opt/ml/processing/spark-events/',
                                             destination=f's3://{default_bucket}/spark-logs',
                                             s3_upload_mode='Continuous')]

        step_process = ProcessingStep(
            name='FeaturePipelineStep',
            processor=processor,
            inputs=proc_inputs,
            outputs=proc_outputs,
            job_arguments=job_args,
            code=self._pipeline_script_tmp_name 
            #,spark_event_logs_s3_uri=f's3://{default_bucket}/spark-logs'
        )

        # 2/ Create a simple pipeline containing that one step
        pipeline = Pipeline(
            name=pipeline_name,
            parameters=[],
            steps=[step_process],
        )

        # 3/ Save the new pipeline
        pipeline.upsert(role_arn=self._role)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -