pyspark environment setup

# install-on-workers.sh
while read slave_url; do
    echo "Installing dependencies to ${slave_url}"
    ssh root@${slave_url} 'bash -s' < worker-install.sh
done <persistent-hdfs/conf/slaves

# worker-install.sh
yum install libgeos-devel -y
yum install python-devel -y 
yum install python-pip -y
yum install python-virtualenv -y
yum install gcc -y

virtualenv env
source env/bin/activate

pip install numpy
pip install cython
pip install shapely

echo "export SPARK_HOME=/root/spark/" >> /etc/profile
echo "export PYSPARK_PYTHON=/root/env/bin/python" >> /etc/profile