mark.nlp.features
Class Util

java.lang.Object
  |
  +--mark.nlp.features.Util

public class Util
extends java.lang.Object

Provides some utility routines.


Constructor Summary
Util()
           
 
Method Summary
static ObjectMap genFeatures(DataSet dataSet, int rareMax, int numCommon, java.lang.String featureOrdererName, java.lang.String featureOrdererParameter, int numFeatures)
          Given a training set and some parameters, generates a set of features.
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

Util

public Util()
Method Detail

genFeatures

public static ObjectMap genFeatures(DataSet dataSet,
                                    int rareMax,
                                    int numCommon,
                                    java.lang.String featureOrdererName,
                                    java.lang.String featureOrdererParameter,
                                    int numFeatures)
                             throws java.lang.Exception
Given a training set and some parameters, generates a set of features.

Parameters:
dataSet - the training set.
rareMax - if a feature occurs this many times or fewer, it will be eliminated.
numCommon - the most common features will be eliminated. This number defines how many.
featureOrdererName - the feature orderer.
featureOrdererParameter - the feature orderer parameter.
numFeatures - the number of features desired.
Returns:
the set of features.
java.lang.Exception