emr_loader_part3.py

    def load_cluster(self):
        response = self.boto_client("emr").run_job_flow(
            Name=self.cluster_name,
            LogUri=self.log_uri,
            ReleaseLabel=self.software_version,
            Instances={
                'MasterInstanceType': 'm3.xlarge',
                'SlaveInstanceType': 'm3.xlarge',
                'InstanceCount': self.instance_count,
                'KeepJobFlowAliveWhenNoSteps': True,
                'TerminationProtected': False,
                'Ec2KeyName': self.key_name
            },
            Applications=[
                {
                    'Name': 'Spark'
                }
            ],
            BootstrapActions=[
                {
                    'Name': 'Install Conda',
                    'ScriptBootstrapAction': {
                        'Path': 's3://{script_bucket_name}/bootstrap_actions.sh'.format(
                            script_bucket_name=self.script_bucket_name),
                    }
                },
            ],
            VisibleToAllUsers=True,
            JobFlowRole='EMR_EC2_DefaultRole',
            ServiceRole='EMR_DefaultRole'
        )
        logger.info(response)
        return response