leifwickland

// Credit to aluizdinizsilva
object ClassUtils {
  def tagToClass[C](tag: WeakTypeTag[C]) = Class.forName(tag.tpe.baseClasses.head.asClass.fullName).asInstanceOf[Class[C]]
  object syntax extends ClassTagSyntax
}

leifwickland

Contrarian Tastes

Using Hadoop MapReduce, Apache Spark, or another distributed computing technology, analyze the Netflix Prize Dataset. (Click the "Download" link in the upper right corner, not the "uci.edu" URL near the bottom of the page.) The README in that file describes the format of the data.

We're looking for movies that are well-loved by users who dislike movies most users like.

Find the M movies which have been rated the highest across all users (of movies which have been rated by at least R users). (If there's a tie for the Mth spot, prefer most recent publication then alphabetical order of title.) These are the "top movies."

Of users who have rated all top M movies, find the U users which have given the lowest average rating of the M movies. (If there's a tie for the Uth spot, prefer users with the lower ID.) These are the "contrarian users."

leifwickland

sealed trait Pokemon {
  def name: String
  def elemental: String
}

// I want a macro like this.
// (The type names may need to need to be in strings.)
// (I'm not entirely sure that quasiquote macros can do this magic.)
enum[Pokemon](
  Bulbasaur -> ("フシギダネ", "Grass"),

leifwickland

sealed trait Pokemon {
  def name: String
  def elemental: String
}

object Pokemon {
  final val Values: Seq[Pokemon] = themAll[Pokemon]
  // Produces: Seq(
  //   Bulbasaur,
  //   Ivysaur,

leifwickland

import scalaz.stream.{ Process, Process1 }

object SnapshotRowsToDruidQuery {
  /**
   * Break the stream into a chunks of up to `n` elements as long as `f` returns true.
   */
  def chunkUpToNBy2[I](n: Int, f: (I, I) => Boolean): Process1[I, Vector[I]] = {
    require(n > 0, s"chunk size, `n`, must be > 0. It was $n.")
    def newChunk(startingWith: I): Process1[I, Vector[I]] = {
      go(Vector(startingWith), startingWith)

leifwickland

import java.util.concurrent.ConcurrentHashMap
import java.util.concurrent.ConcurrentMap
import scala.collection.JavaConverters._

val m: ConcurrentMap[String, String] = new ConcurrentHashMap[String, String]
m.put("1", "one")
m.put("2", "two")
val cm: scala.collection.concurrent.Map[String, String] = m.asScala
cm += ("3" -> "three")
cm.foreach(println)

leifwickland

def jumpConsistentHash(theKey: Long, bucketCount: Int): Int = {
  var b = -1L
  var j = 0L
  var key = theKey
  while (j < bucketCount && j >= 0) {
    b = j
    key = key * 2862933555777941757L + 1
    j = ((b + 1) * ((1L << 31).toDouble / ((key >> 33) + 1).toDouble)).toLong
  }
  return b.toInt

leifwickland

def f(s: String) = {
  s.split(':') match {
    case Array(k,v) => k -> v
    case a => error("bad: " + a)
  }
}

leifwickland

# If you launch sbt with -Dsbt.override.build.repos=true -Dsbt.repository.config=$FILE
# then this configuration should be roughly equivalent to the default behavior.
[repositories]
  local
  typesafe-ivy-releases: https://repo.typesafe.com/typesafe/ivy-releases/, [organization]/[module]/[revision]/[type]s/[artifact](-[classifier]).[ext], bootOnly
  maven-central
  sbt-plugins: https://repo.scala-sbt.org/scalasbt/sbt-plugin-releases/, [organization]/[module]/(scala_[scalaVersion]/)(sbt_[sbtVersion]/)[revision]/[type]s/[artifact](-[classifier]).[ext], bootOnly

leifwickland

gs -q -sPAPERSIZE=letter -dNOPAUSE -dBATCH -sDEVICE=pdfwrite -sOutputFile=output.pdf  /usr/share/ghostscript/9.10/lib/viewjpeg.ps -c \(image/path.jpg\) viewJPEG