prithvi514

 sqoop job --create test_job1 -- import --connect "jdbc:sqlserver://192.168.1.206;database=wells-fargo"  --username sa --password Hadoop123 --driver com.microsoft.sqlserver.jdbc.SQLServerDriver --query 'select * from dbo.tVulnMgmt_DeltaRiskAGGHist where $CONDITIONS'  --target-dir "/tmp/dbo-delta2" -m 1
 
 sqoop job --list
 sqoop job --exec test_job1

sqoop import --connect "jdbc:sqlserver://192.168.1.206;database=wells-fargo"  --username sa --password Hadoop123 --driver com.microsoft.sqlserver.jdbc.SQLServerDriver --query "select * from dbo.tVulnMgmt_DeltaRiskAGGHist WHERE $CONDITIONS"  --target-dir "/tmp/dbo-delta" --split-by "Date"

spark-submit --class org.apache.spark.examples.SparkPi --deploy-mode client --master yarn spark-examples_2.11-2.1.1.2.6.1.0-129.jar

hive.optimize.reducededuplication.min.reducer=4

prithvi514

__author__ = 'Amal G Jose'

import time
import logging
from boto.emr.connection import EmrConnection
from boto.emr.bootstrap_action import BootstrapAction
from boto.emr.step import InstallHiveStep
from boto.emr.step import InstallPigStep
from boto.regioninfo import RegionInfo