lmatthieu

## Creating py4sci requirements repository - internet access required
 
cd /tmp
 
echo "
Theano==0.7.0
cytoolz==0.7.3
docopt==0.6.2
gdbn==0.1
gnumpy==0.2

lmatthieu

## No-internet access mode

yum install gcc openssl-devel zlib-devel blas-devel lapack-devel gcc-c++ bzip2-devel lzo-devel freetype-devel libpng-devel sqlite-devel

## Python 2.7.9 installation from sources

cd /tmp
wget https://www.python.org/ftp/python/2.7.9/Python-2.7.9.tgz
tar -zxvf Python-2.7.9.tgz
cd Python-2.7.9

lmatthieu

from pyspark import SparkContext, SparkConf
from pyspark.sql import HiveContext, SQLContext
import pandas as pd

# sc: Spark context
# file_name: csv file_name
# table_name: output table name
# sep: csv file separator
# infer_limit: pandas type inference nb rows
def read_csv(sc, file_name, table_name, sep=",", infer_limit=10000):

lmatthieu

from IPython import embed_kernel

import start_notebook

def main():
    p = start_notebook.main()
    localDict = { 'a':1, 'b':2 }
    embed_kernel()
    p.kill()