Spark Demo

kindling_spark_demo.scala

// First Example:

val first_example = sc.cassandraTable("spark_demo", "first_example")

first_example.first

first_example.first.get[Int]("id")

//---
case class FirstExample(Id: Int, Value: Int )

val first_example = sc.cassandraTable[FirstExample]("spark_demo", "first_example")

first_example.first

first_example.take(2)

first_example.map( x => x.Value).groupBy( x => x ).map( g => (g._1, g._2.length) ).take(3)

// ######
// Raw Data:

case class RawFileData(Filename: String, LineNumber: Int, LineText: String )

val raw = sc.cassandraTable[RawFileData]("spark_demo", "raw_files" )

// -- read the user data "users.dat"
// File format: UserID::Gender::Age::Occupation::Zip-code

val raw_users = raw.filter( r => r.Filename == "users.dat" )

raw_users.first

case class User(Id: Int, Age: Int, Gender: String, Occupation: Int, Zip: String )
val users = raw_users.map( l => l.LineText.trim.split("::") ).map( v => User(Id = v(0).toInt, Age = v(2).toInt, Gender=v(1), Occupation=v(3).toInt, Zip=v(4)))

users.saveToCassandra("spark_demo", "users" )

These are the shell commands I used during the Kindling presentation at the Chicago Cassandra Meetup.