hadoop-vm-root-setup.sh

#install basic development tools
apt-get update
apt-get upgrade
apt-get install build-essential ssh lzop git rsync curl
apt-get install python-dev python-setuptools
apt-get install libcurl4-openssl-dev
easy_install pip
pip install virtualenv virtualenvwrapper python-dateutil

#create a hadoop user
addgroup hadoop
adduser --ingroup hadoop hadoop
usermod -a -G hadoop nabeel

#isntall openjdk 8
apt-get install openjdk-8-*
java -version #check version

#install Hadoop
cd ~
curl -O http://apache.cs.utah.edu/hadoop/common/hadoop-2.7.3/hadoop-2.7.3.tar.gz
tar -xzvf hadoop-2.7.3.tar.gz 
mv hadoop-2.7.3 /srv/
chown -R hadoop:hadoop /srv/hadoop-2.7.3
chmod g+w -R /srv/hadoop-2.7.3
ln -s /srv/hadoop-2.7.3 /srv/hadoop
chown -R hadoop:hadoop /srv/hadoop
chmod g+w -R /srv/hadoop

mkdir -p /var/app/hadoop/data
chown hadoop:hadoop -R /var/app/hadoop