Add bootstarp for maven and update the configurations for EMR

rudra/deployments/emr_scripts/maven_emr.py

@@ -26,7 +26,7 @@ def run_job(self, input_dict):
             bucket=self.bucket_name,
             log_file=log_file_name)
 
-        logger.info("Logs are gonna store at {}".format(log_uri))
+        logger.info("Logs will be stored at {}".format(log_uri))
 
         emr_config_obj = EMRConfig(name=name,
                                    s3_bootstrap_uri=bootstrap_uri,
@@ -37,6 +37,8 @@ def run_job(self, input_dict):
                                    hyper_params=self.hyper_params)
 
         configs = emr_config_obj.get_config()
+        configs["Applications"] = []
+        logger.info("Configurations for Maven EMR are: {}".format(configs))
         status = self.aws_emr.run_flow(configs)
         logger.info("EMR job is running {}".format(status))
         status_code = status.get('ResponseMetadata', {}).get('HTTPStatusCode')

scripts/bootstrap_maven.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+# Copyright 2017 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License").
+# You may not use this file except in compliance with the License.
+# A copy of the License is located at
+#
+# http://aws.amazon.com/apache2.0/
+#
+# or in the "license" file accompanying this file. This file is distributed
+# on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
+# express or implied. See the License for the specific language governing
+# permissions and limitations under the License.
+
+set -e -x
+
+# enable debugging & set strict error trap
+sudo yum install -y zip gcc-c++ git python36-pip python36-requests httpd httpd-devel python36-devel wget git 
+sudo pip install --upgrade pip
+sudo python3.6 -m pip install pandas
+sudo python3.6 -m pip install Cython==0.29.1
+sudo python3.6 -m pip install hpfrec==0.2.2.9
+sudo python3.6 -m pip install git+https://github.com/fabric8-analytics/fabric8-analytics-rudra
+
+# Now set the PYTHONPATH
+export PYTHONPATH='/home/hadoop'