util

class Band extends AnyRef

One band of the Locality Sensitive Hash.
trait CanPack[T] extends AnyRef

Capability trait for packing and unpacking tuples (or other things) to a List of Any.
class ConfusionMatrix[L, I] extends AnyRef

A confusion matrix for comparing gold clusters to some predicted clusters.
class GrowableIndex[T] extends (T) ⇒ Int
class LinearHashFunction extends AnyRef

Simple line function: y = mx+b
class LocalitySensitiveHash extends AnyRef

A Locality Sensitive Hash that hashes the documents into buckets.
trait LowPriorityCanPackImplicits extends AnyRef

Low priority implicit for packing a single value as itself.
case class Scores(accuracy: Double, precisionAverage: Double, recallAverage: Double, fscoreAverage: Double, all: Seq[Seq[Double]]) extends Product with Serializable

object Band
object CanPack extends LowPriorityCanPackImplicits

Implicit packers for tuples.
object CleanStringTokenizer

A tokenizer that replaces all non-word characters with whitespace and then returns a StringTokenizer.
object CollectionUtil
object ConfusionMatrix

A companion object for constructing ConfusionMatrices.
object CrossValidation
object HashFunction

Helper object for hash function functions.
object Similarity
object SimpleTokenizer

A very simple tokenizer that pulls most puncuation off the characters.
object StringCleaner

Cleans up a string by ripping out punctuation, turning all digit sequences into a single numeric symbol, and getting rid of tokens that contain mixtures of alphabetic and numeric characters.