A .mrjob.conf to run Pandas with EMR

.mrjob.conf

runners:
  emr:
    aws_access_key_id: youraccountid
    #aws_region: us-west-1   your region. us east by default
    aws_secret_access_key: yoursecretkey
    bootstrap_actions:
    # probably this is a good idea
    - s3://elasticmapreduce/bootstrap-actions/configurations/latest/memory-intensive
    # we disable this since it is run before our shell script and installs mrjob for python 2.6
    bootstrap_mrjob: False
    bootstrap_files:
    - s3n://yourbucket/emr_resources/bootstrap.sh
    bootstrap_cmds:
    - chmod 755 bootstrap.sh;./bootstrap.sh
    # specifying an ssh key pair allows us to ssh tunnel to the job tracker
    # and fetch logs via ssh
    ec2_key_pair: keyname
    ec2_key_pair_file: /home/$USER/.ssh/keyname.pem
    # use beefier instances in production
    ec2_instance_type: m1.large
    # master large because otherwise it is small and may end up being 32 bit
    # which would need 32 bit builds. 
    ec2_master_instance_type : m1.large
    # but only use one unless overridden
    num_ec2_instances: 1
    ec2_master_instance_bid_price: 0.15
    ec2_core_instance_bid_price: 0.15
    #ec2_task_instance_bid_price: 0.15
    cmdenv:
      #adjust this
      TZ: Europe/Berlin
    s3_log_uri: s3://yourbucket/tmp/logs/
    s3_scratch_uri: s3://yourbucket/tmp/
    
  local:
    # put any folder of your choice here. it should exist
    base_tmp_dir: /home/$USER/emr/output/local