manboubird

// transcribed from an Apache Spark 1.0 spark-shell session
// using data from http://chriswhong.com/open-data/foil_nyc_taxi/
// and the QTree algorithm for approximate quantiles over large datasets
// each of the distanceRange and minutesRange calculations below takes about 15 minutes on my four-core SSD-based Macbook Pro

import com.twitter.algebird._
import com.twitter.algebird.Operators._
implicit val qtSemigroupD = new QTreeSemigroup[Double](6)

val in = sc.textFile("trip_data") // a directory containing all the trip_data*.csv files downloaded from the above link

manboubird

#!/usr/bin/ruby

class IPGenerator
  public
  def initialize(session_count, session_length)
    @session_count = session_count
    @session_length = session_length

    @sessions = {}
  end