de.jungblut.reader

Class TwentyNewsgroupReader

java.lang.Object

de.jungblut.reader.TwentyNewsgroupReader

public final class TwentyNewsgroupReader
extends Object

Reads the "20news-bydate" dataset into a vector space model as well as predictions based on the category.

Author:

thomas.jungblut

Method Summary

Modifier and Type	Method and Description
static de.jungblut.math.tuple.Tuple3<List<String>,de.jungblut.math.dense.DenseDoubleVector,String[]>	readTwentyNewsgroups(File directory) Needs the "20news-bydate" directory that has test and train subdirectories given.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

readTwentyNewsgroups

public static de.jungblut.math.tuple.Tuple3<List<String>,de.jungblut.math.dense.DenseDoubleVector,String[]> readTwentyNewsgroups(File directory)

Needs the "20news-bydate" directory that has test and train subdirectories given.

Returns:

in tuple3 order: document as string, prediction, name mapping for prediction