emr_default.json

{
  "Name": "spark-emr-cluster",
  "LogUri": "s3://emr-logs-anupam",
  "ReleaseLabel": "emr-5.28.0",
  "Applications": [
    {
      "Name": "Spark"
    }
  ],
  "Configurations": [
    {
      "Classification": "spark-env",
      "Configurations": [
        {
          "Classification": "export",
          "Properties": {
            "PYSPARK_PYTHON": "/usr/bin/python3"
          }
        }
      ]
    }
  ],
  "Instances": {
    "InstanceGroups": [
      {
        "Name": "Master nodes",
        "Market": "ON_DEMAND",
        "InstanceRole": "MASTER",
        "InstanceType": "m4.large",
        "InstanceCount": 1
      },
      {
        "Name": "Slave nodes",
        "Market": "ON_DEMAND",
        "InstanceRole": "CORE",
        "InstanceType": "m4.large",
        "InstanceCount": 4
      }
    ],
    "KeepJobFlowAliveWhenNoSteps": false,
    "TerminationProtected": false
  },
  "VisibleToAllUsers": true,
  "JobFlowRole": "EMR_EC2_DefaultRole",
  "ServiceRole": "EMR_DefaultRole"
}