Trigger EMR by Lambda using Boto3

createJob.py

from __future__ import print_function
import json
import boto3
import os
import time

client = boto3.client('emr')
s3client = boto3.client('s3')
job_id = os.urandom(16).encode('hex')
city_dict = {'TPE': 'A','NTP': 'F','TY': 'H','HCC': 'J','HC': 'O','ML': 'K','TC': 'B','NT': 'M','CH': 'N','YUL': 'P','CY': 'I','CYC': 'Q','TN': 'D','KH': 'E','PT': 'T','KL': 'C','YIL': 'G','HL': 'U','TT': 'V'}



def lambda_handler(event, context):
    output = {'success': True, 'id': job_id}
    job_name = 'Job' + job_id
    try:
        response = client.add_job_flow_steps(
            JobFlowId='j-3W014JHSFXXR8',
            Steps=[
                {
                    'Name': 'Find Factor',
                    'HadoopJarStep': {
                        'Jar': 's3n://cp2016-final-dataset/FindFac.jar',
                        'MainClass': 'FindFac.Main',
                        'Args': [
                            's3n://cp2016-final-dataset/findFac-input',
                            'cp2016-final-dataset/wip/' + job_id,
                            event['lat'],
                            event['lng']
                        ]
                    }
                },
                {
                    'Name': 'Calc Score',
                    'HadoopJarStep': {
                        'Jar': 's3n://cp2016-final-dataset/CalScore.jar',
                        'MainClass': 'CalScore.Main',
                        'Args': [
                            's3n://cp2016-final-dataset/CalScore-input',
                            'cp2016-final-dataset/wip/' + job_id + '/part-r-00000',
                            's3n://cp2016-final-dataset/outputs/' + job_id,
                            city_dict[event['area']],
                            event['price']
                        ]
                    }
                }
            ]
        )
    except:
        output['success'] = False
    return output