Page History

...

final Dataset<Row> df = SQLContext.getOrCreate(sc).read()
    .format("org.apache.cassandra.spark.bulkreader.CassandraDataSource")
    .option("cassandra_hosts", "127.0.0.1,127.0.0.2") // Provide at least one Cassandra host to which we can connect
    .option("app", "dailydev30")
    .option("cluster", "dailydev30")
    .option("keyspace", "my_keyspace")
    .option("table", "my_table")
    .option("DC", "DC1")
    .option("snapshotName", "my_sbr_snapshot_123")
    .option("createSnapshot", **true**)
    .option("defaultParallelism", sc.defaultParallelism())
    .option("numCores", numCores)
    .load();
    
// sum entire dataset on column 'c'
final long result = df.agg(sum("c")).first().getLong(0);

...