jasonbaldridge

/**
  * R functions to create and manipulate Breeze matrices. This should go into
  * Breeze or a sub-project of Breeze eventually.
  */
object RFunc {
  import breeze.linalg._
  import breeze.stats.distributions._
  import breeze.stats.DescriptiveStats._

  /**

jasonbaldridge

package appliednlp.spell

/**
 * Note: This is exercise code meant to align with the steps of the exercises
 * on spelling correction for the Applied NLP class. The design would of course
 * be very different for an actualy spelling corrector.
 *
 * Part 1: https://github.com/utcompling/applied-nlp/wiki/SpellCorrect-Exercise
 * Part 2: https://github.com/utcompling/applied-nlp/wiki/SpellCorrect-Exercise-part2
 *

jasonbaldridge

package bcomposes.twitter

import twitter4j._

object StatusStreamer {
  def main(args: Array[String]) {
    val twitterStream = new TwitterStreamFactory(Util.config).getInstance
    twitterStream.addListener(Util.simpleStatusListener)
    twitterStream.sample
    Thread.sleep(2000)

jasonbaldridge

## An implementation of Gibbs sampling for topic models for the
## example in section 4 of Steyvers and Griffiths (2007):
##   http://cocosci.berkeley.edu/tom/papers/SteyversGriffiths.pdf
##
## Author: Jason Baldridge ([email protected])

# Functions to parse the input data
words.to.indices = data.frame(row.names=c("r","s","b","m","l"),1:5)
mysplit = function(x) { strsplit(x,"")[[1]] }
word.vector = function(x) { words.to.indices[mysplit(x),] }

jasonbaldridge

[{"name":"Radiohead","albums":[{"title":"The King of Limbs","songs":[{"title":"Bloom","length":"5:15"},{"title":"Morning Mr Magpie","length":"4:41"},{"title":"Little by Little","length":"4:27"},{"title":"Feral","length":"3:13"},{"title":"Lotus Flower","length":"5:01"},{"title":"Codex","length":"4:47"},{"title":"Give Up the Ghost","length":"4:50"},{"title":"Separator","length":"5:20"}],"description":"\n\tThe King of Limbs is the eighth studio album by English rock band Radiohead, produced by Nigel Godrich. It was self-released on 18 February 2011 as a download in MP3 and WAV formats, followed by physical CD and 12\" vinyl releases on 28 March, a wider digital release via AWAL, and a special \"newspaper\" edition on 9 May 2011. The physical editions were released through the band's Ticker Tape imprint on XL in the United Kingdom, TBD in the United States, and Hostess Entertainment in Japan.\n      "},{"title":"OK Computer","songs":[{"title":"Airbag","length":"4:44"},{"title":"Paranoid Android","length":"6:23"},

jasonbaldridge

<music>
  <artist name="Radiohead">
    <album title="The King of Limbs">
      <song title="Bloom" length="5:15"/>
      <song title="Morning Mr Magpie" length="4:41"/>
      <song title="Little by Little" length="4:27"/>
      <song title="Feral" length="3:13"/>
      <song title="Lotus Flower" length="5:01"/>
      <song title="Codex" length="4:47"/>
      <song title="Give Up the Ghost" length="4:50"/>

jasonbaldridge

// This is code to accompany my blog post about variations on sequence computations:
//   http://bcomposes.wordpress.com/2012/02/14/variations-for-computing-results-from-sequences-in-scala/
//
// Jason Baldridge

// A function to display the results of various ways of doing the same thing.
def display (intro: String, wlengths: List[Int], wcaps: List[Boolean]) {
  println(intro)
  println("Lengths: " + wlengths.mkString(" "))
  println("Caps: " + wcaps.mkString(" "))