cc.mallet.pipe
Class FeatureDocFreqPipe

java.lang.Object
  extended by cc.mallet.pipe.Pipe
      extended by cc.mallet.pipe.FeatureDocFreqPipe
All Implemented Interfaces:
AlphabetCarrying, java.io.Serializable

public class FeatureDocFreqPipe
extends Pipe

Pruning low-count features can be a good way to save memory and computation. However, in order to use Vectors2Vectors, you need to write out the unpruned instance list, read it back into memory, collect statistics, create new instances, and then write everything back out.

This class supports a simpler method that makes two passes over the data: one to collect statistics and create an augmented "stop list", and a second to actually create instances.

See Also:
Serialized Form

Constructor Summary
FeatureDocFreqPipe()
           
FeatureDocFreqPipe(Alphabet dataAlphabet, Alphabet targetAlphabet)
           
 
Method Summary
 void addPrunedWordsToStoplist(SimpleTokenizer tokenizer, double docFrequencyCutoff)
          Add all pruned words to the internal stoplist of a SimpleTokenizer.
 Instance pipe(Instance instance)
          Really this should be 'protected', but isn't for historical reasons.
 
Methods inherited from class cc.mallet.pipe.Pipe
alphabetsMatch, getAlphabet, getAlphabets, getDataAlphabet, getInstanceId, getTargetAlphabet, instanceFrom, instancesFrom, instancesFrom, isDataAlphabetSet, isTargetProcessing, newIteratorFrom, preceedingPipeDataAlphabetNotification, preceedingPipeTargetAlphabetNotification, precondition, readResolve, setDataAlphabet, setOrCheckDataAlphabet, setOrCheckTargetAlphabet, setTargetAlphabet, setTargetProcessing
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

FeatureDocFreqPipe

public FeatureDocFreqPipe()

FeatureDocFreqPipe

public FeatureDocFreqPipe(Alphabet dataAlphabet,
                          Alphabet targetAlphabet)
Method Detail

pipe

public Instance pipe(Instance instance)
Description copied from class: Pipe
Really this should be 'protected', but isn't for historical reasons.

Overrides:
pipe in class Pipe

addPrunedWordsToStoplist

public void addPrunedWordsToStoplist(SimpleTokenizer tokenizer,
                                     double docFrequencyCutoff)
Add all pruned words to the internal stoplist of a SimpleTokenizer.

Parameters:
docFrequencyCutoff - Remove words that occur in greater than this proportion of documents. 0.05 corresponds to IDF >= 3.