Batch insert python script. It is using the python driver provided by Datastax

batch-insert.py

#!/usr/bin/env python
from cassandra.cluster import Cluster
from cassandra.query import *
from cassandra import *
import hashlib
import sys

KEYSPACE = 'test'
TABLE = 'user'
BATCH_SIZE = 1000

cluster = Cluster()
session = cluster.connect(KEYSPACE)

def getHash(val):
    return hashlib.sha256(str(val)).hexdigest()

def batchInsert(start, num):
    insert_q = session.prepare("insert into test.user (user_id, fname, lname, number) values (?, ?, ?, ?)")

    for i in range(start, num):
        batch = BatchStatement()
        for j in range(1, BATCH_SIZE + 1):
            hashval = getHash(j)
            batch.add(insert_q, (i, hashval, hashval, i + j))
        try:
            session.execute(batch)
        except WriteTimeout as e:
            print "write timeout occurred."

if __name__ == "__main__":
    start = int(sys.argv[1])
    num = int(sys.argv[2])
    batchInsert(start, num)

Setup

See: Installation

install dependencies

sudo yum install gcc python-devel
sudo yum install libev libev-devel

To install cassandra driver you can use pip

pip install cassandra-driver