Get a Pandas DataFrame from a Cassandra query

cassandra_to_pandas.py

from cassandra.cluster import Cluster
from cassandra.auth import PlainTextAuthProvider
import pandas as pd

def pandas_factory(colnames, rows):
    return pd.DataFrame(rows, columns=colnames)

cluster = Cluster(
    contact_points=['127.0.0.1'], 
    auth_provider = PlainTextAuthProvider(username='cassandra', password='cassandra')
)
session = cluster.connect()
session.set_keyspace('giodevks')
session.row_factory = pandas_factory
session.default_fetch_size = 10000000 #needed for large queries, otherwise driver will do pagination. Default is 50000.

rows = session.execute("""select * from my_table""")
df = rows._current_rows
print df.head()

rows = session.execute("""select * from my_table""")
df = rows._current_rows

These two lines were time savers for me.