obar1

# some tgz with random data
#!/bin/bash


for year in `seq 2013 2015`;
do
  for month in `seq 1 12`;
  do
    mkdir $year-$month
    echo $RANDOM  > $year-$month/ratings.tsv

obar1

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

obar1

rsync -r -v --progress -e  ssh   /cygdrive/c/_git/VirtualBox\ VMs/KYLO_v0.4.3  [email protected]:/tmp/kylo/

obar1

nohup wget -qc http://path-to-url/linux.iso &

obar1

#https://hub.docker.com/r/alexeiled/docker-oracle-xe-11g/

docker run -d -p 49160:22 -p 49162:8080 -p 49161:1521 -e ORACLE_ALLOW_REMOTE=true wnameless/oracle-xe-11g

obar1

#kill and rm all docker containers
if [[ $(docker ps -q) ]]; then                                              \ 
    docker kill $(docker ps -q) ;docker rm $(docker ps -a -q)                \  
fi

obar1

sqoop list-databases \  
--connect "jdbc:mysql://quickstart.cloudera:3306" \  
--username retail_dba \  
--password cloudera

obar1

sqoop list-tables \
--connect "jdbc:mysql://quickstart.cloudera:3306/retail_db" \
--username retail_dba \
--password cloudera

obar1

sqoop eval \
  --connect "jdbc:mysql://quickstart.cloudera:3306/retail_db" \
  --username retail_dba \
  --password cloudera \
  --query "select count(1) from order_items"

obar1

from pyspark import SparkContext, SparkConf
conf = SparkConf().setAppName("myPyspark")
sc = SparkContext(conf=conf)
dataRDD = sc.textFile("/user/ma186082/sqoop_import/departments")
for line  in dataRDD.collect():
    print(line)
dataRDD.saveAsTextFile("/user/ma186082/pyspark/departments")