aws emr create-cluster --name "Spark_step_pip" \
    --release-label emr-6.5.0 \
    --applications Name=Spark \
    --log-uri s3://[your_S3_bucket]/logs/ \
    --instance-type m5.xlarge \
    --instance-count 3 \
    --bootstrap-actions Path=s3://[your_S3_bucket]/emr_bootstrap.sh \
    --use-default-roles --auto-terminate \
    --steps "Type=Spark,Name=SparkProgram,ActionOnFailure=CONTINUE,Args=[--deploy-mode,cluster,--master,yarn,--py-files,s3://[your_S3_bucket]/helper_function.py,s3://[your_S3_bucket]/spark_3mer.py,s3://[your_S3_bucket]/test.sam,[your_S3_bucket],sankey.json]" 

python sankey.py sankey.json