ir.classifiers
Class DirectoryExamplesConstructor

java.lang.Object
  ir.classifiers.ExamplesConstructor
      ir.classifiers.DirectoryExamplesConstructor

public class DirectoryExamplesConstructor
extends ExamplesConstructor

Creates a list of examples from a directory where file names contain the category name as a substring.

Field Summary

protected java.lang.String[]	categories Array of categories (classes) in the data
protected java.lang.String	dirName Name of the directory where the example files are stored.
protected short	docType Type of document (text or HTML)
protected boolean	stem Flag set to stem words to their root forms

Constructor Summary

DirectoryExamplesConstructor(java.lang.String dirName, java.lang.String[] categories)
Construct an ExamplesConstructor for the given directory and category labels

DirectoryExamplesConstructor(java.lang.String dirName, java.lang.String[] categories, short docType, boolean stem)
Construct an ExamplesConstructor for the given directory and category labels

Method Summary

int	findClassID(java.lang.String name) Finds the class ID from the name of the document file.
java.util.List<Example>	getExamples() Get the examples from the directory, process them into HashMapVector's and label them with the correct category label
static void	main(java.lang.String[] args) Test loading a sample directory of examples

Methods inherited from class java.lang.Object

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

Field Detail

dirName

protected java.lang.String dirName

Name of the directory where the example files are stored.

docType

protected short docType

Type of document (text or HTML)

stem

protected boolean stem

Flag set to stem words to their root forms

categories

protected java.lang.String[] categories

Array of categories (classes) in the data

Constructor Detail

DirectoryExamplesConstructor

public DirectoryExamplesConstructor(java.lang.String dirName,
                                    java.lang.String[] categories,
                                    short docType,
                                    boolean stem)

Construct an ExamplesConstructor for the given directory and category labels

DirectoryExamplesConstructor

public DirectoryExamplesConstructor(java.lang.String dirName,
                                    java.lang.String[] categories)

Construct an ExamplesConstructor for the given directory and category labels

Method Detail

getExamples

public java.util.List<Example> getExamples()

Get the examples from the directory, process them into HashMapVector's and label them with the correct category label

Specified by:

getExamples in class ExamplesConstructor

findClassID

public int findClassID(java.lang.String name)

Finds the class ID from the name of the document file. Assumes file name contains the category name as a substring

main

public static void main(java.lang.String[] args)

Test loading a sample directory of examples