modnlp.tc.dstruct

Class ParsedCorpus

java.lang.Object

java.util.AbstractCollection<E>

java.util.AbstractList<E>

java.util.Vector

modnlp.tc.dstruct.ParsedCorpus

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, java.lang.Iterable, java.util.Collection, java.util.List, java.util.RandomAccess

public class ParsedCorpus
extends java.util.Vector

Store ParsedDocuments.

See Also:

ParsedDocument, Serialized Form

Field Summary

Fields inherited from class java.util.Vector

capacityIncrement, elementCount, elementData

Fields inherited from class java.util.AbstractList

modCount

Constructor Summary

Constructors

Constructor and Description
ParsedCorpus()

Method Summary

Methods

Modifier and Type	Method and Description
boolean	addNewsItem(ParsedDocument pni) Deprecated. This method was used (and named) in the original REUTERS news classification system. Use addParsedDocument instead.
boolean	addParsedDocument(ParsedDocument pni) Add a new categorised text to this corpus
void	append(ParsedCorpus pt) Concatenate pt to this object.
double	getCategProbability(java.lang.String cat) Get the overall probability of category cat classifying a document in the corpus represented by this ParsedCorpus (i.e.
ParsedCorpus	getCategSubCorpus(java.lang.String cat) Get the sub-corpus defined by documents belonging to category cat
Probabilities	getProbabilities(java.lang.String term, java.lang.String cat) Get the joint probability of term 'term' occurring in a document and category 'cat' classifying it.
java.lang.String	toString()

Methods inherited from class java.util.Vector

add, add, addAll, addAll, addElement, capacity, clear, clone, contains, containsAll, copyInto, elementAt, elements, ensureCapacity, equals, firstElement, get, hashCode, indexOf, indexOf, insertElementAt, isEmpty, iterator, lastElement, lastIndexOf, lastIndexOf, listIterator, listIterator, remove, remove, removeAll, removeAllElements, removeElement, removeElementAt, removeRange, retainAll, set, setElementAt, setSize, size, subList, toArray, toArray, trimToSize

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

ParsedCorpus

public ParsedCorpus()

Method Detail

addNewsItem

public boolean addNewsItem(ParsedDocument pni)

Deprecated. This method was used (and named) in the original REUTERS news classification system. Use addParsedDocument instead.

Add a new categorised text to this corpus

Parameters:

pni - a ParsedDocument containing a categorised, uniquely indentified text.

Returns:

true if item succesfully added, false otherwise.

addParsedDocument

public boolean addParsedDocument(ParsedDocument pni)

Add a new categorised text to this corpus

Parameters:

pni - a ParsedDocument containing a categorised, uniquely indentified text.

Returns:

true if item succesfully added, false otherwise.

append

public void append(ParsedCorpus pt)

Concatenate pt to this object.

Parameters:

pt - a ParsedCorpus containing categorised texts to be appended to this object.

getCategSubCorpus

public ParsedCorpus getCategSubCorpus(java.lang.String cat)

Get the sub-corpus defined by documents belonging to category cat

getCategProbability

public double getCategProbability(java.lang.String cat)

Get the overall probability of category cat classifying a document in the corpus represented by this ParsedCorpus (i.e. category generality)

getProbabilities

public Probabilities getProbabilities(java.lang.String term,
                             java.lang.String cat)

Get the joint probability of term 'term' occurring in a document and category 'cat' classifying it. NB: this is very inneficient. Use only for one-off estimates. Use BVProbabilityModel for global estimates.

toString

public java.lang.String toString()

Overrides:

toString in class java.util.Vector