samklr

object Positions {
  trait Investment
  trait Position {
    def investment: Investment
    def tradingPnL: Option[Double]
    def inventoryPnL: Option[Double]
    final def totalPnL = inventoryPnL → tradingPnL
  }

  import Monoid._

samklr

trait Monoid[A] {
  def identity: A
  def mplus(a1: A, a2: A): A
}

object Monoid {
  implicit val IntMonoid = new Monoid[Int] {
    def identity = 0
    def mplus(a1: Int, a2: Int) = a1 + a2
  }

samklr

import java.util.Currency

object Fx {
  type CcyPair = (Currency, Currency)
  case class FxRate(from: Currency, to: Currency, rate: BigDecimal) {
    def pair: CcyPair = from → to
    def unary_~ = FxRate(to, from, 1 / rate)
    def *(that: FxRate): FxRate = {
      require(this.to == that.from)
      FxRate(this.from, that.to, this.rate * that.rate)

samklr

trait MyList[+A] { 
  def fold[B](k: Option[(A, B)] => B): B
  def map[B](f: A => B): MyList[B]             = sys.error("Implement me in terms of fold")
  def flatMap[B](f: A => MyList[B]): MyList[B] = sys.error("Implement me in terms of fold")
  def headOption: Option[B]                    = sys.error("Implement me in terms of fold")
  def tailOption: Option[MyList[B]]            = sys.error("Implement me in terms of fold")
  def isEmpty                                  = sys.error("Implement me in terms of fold")
  def length                                   = sys.error("Implement me in terms of fold")
}

samklr

object GOption {
  def some[A](a: A): GOption[A] = new GOption[A] { 
    def cata[B](n: => B, s: A => B): B = sys.error("Implement me") 
  }
  def none[A]: GOption[A] = new GOption[A] { 
    def cata[B](n: => B, s: A => B): B = sys.error("Implement me") 
  }
}

trait GOption[+A] {

samklr

       public void sendMessage(String url, String params){
            final HttpURLConnection connection;
            try {
                URL requestUrl = new URL(url);
                connection = (HttpURLConnection) requestUrl.openConnection();
                connection.setDoOutput(true);

                connection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
                connection.setRequestProperty("Content-Length", Integer.toString(params.getBytes().length));
                connection.setRequestProperty("Content-Language", "en-US");

samklr

Optimizing Google’s Warehouse Scale Computers: The NUMA Experience -  authors from Univ. of Cal (SD) & Google!
http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/40696.pdf

MegaPipe: A New Programming Interface for Scalable Network I/O by several authors!
https://docs.google.com/viewer?a=v&pid=forums&srcid=MDUxODU4OTA1NTU1MzUxODE5MDQBMTA5MDUzNTI5Mzg2ODk0MjY5NjUBYWM5cnR1MEY4Z1FKATQBAXYy

What Every Programmer Should Know About Memory by Ulrich Drepper
http://www.akkadia.org/drepper/cpumemory.pdf

Memory Barriers: a Hardware View for Software Hackers - Paul E. McKenney (Linux Technology Center - IBM Beaverton)

samklr

/*
Goal: Use Scalding to datamine the 2010 US Census data (kindly provided by @ElonAzoulay & @hmason), to find
Where do the WEALTHY WELL EDUCATED ELITE live ?
WEALTHY == house value quarter million, household income 150k
WELL EDUCATED == sort by edu, edu = (10 * Phd + 5 * MS + 1 * BS) score
*/
import com.twitter.scalding._
import cascading.tuple.Fields
import cascading.tap.SinkMode

samklr

object FizzBuzz extends App {

  val nones = Stream.continually(None)
  val fizzes: Stream[Option[String]] = nones.take(2) ++ Some("Fizz") #:: fizzes
  val buzzes: Stream[Option[String]] = nones.take(4) ++ Some("Buzz") #:: buzzes

  for (((fizz, buzz), n) <- fizzes zip buzzes zip (1 to 100)) {
    println(fizz.map(_ + buzz.getOrElse("")).orElse(buzz).getOrElse(n))
  }

samklr

1. General Background and Overview
  a) Probabilistic Data Structures for Web Analytics and Data Mining : On Highly Scalable Blog (http://highlyscalable.wordpress.com/2012/05/01/probabilistic-structures-web-analytics-data-mining/) : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
  b) Models and Issues in Data Stream Systems : (http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.106.9846)
  c) Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani (http://www.vldb.org/conf/2002/S10P03.pdf) : One of the early papers on the subject.
  d) Methods for Finding Frequent Items in Data Streams by Graham Cormode & Marios Hadjieleftheriou (http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep=rep1&type=pdf)
  e) The space complexity of approximating the frequency moments by Noga Alon, Yossi Matias, Mario Szegedy : one of the most influential papers introducing succinctness in computing fre