org.apache.mahout.utils.vectors.arff

Class ARFFVectorIterable

java.lang.Object

org.apache.mahout.utils.vectors.arff.ARFFVectorIterable

All Implemented Interfaces:

Iterable<Vector>

public class ARFFVectorIterable
extends Object
implements Iterable<Vector>

Read in ARFF (http://www.cs.waikato.ac.nz/~ml/weka/arff.html) and create Vectors

Attribute type handling:

• Numeric -> As is
• Nominal -> ordinal(value) i.e. @attribute lumber {'\'(-inf-0.5]\'','\'(0.5-inf)\''} will convert -inf-0.5 -> 0, and 0.5-inf -> 1
• Dates -> Convert to time as a long
• Strings -> Create a map of String -> long

NOTE: This class does not set the label bindings on every vector. If you want the label bindings, call MapBackedARFFModel.getLabelBindings(), as they are the same for every vector.

Constructor Summary

Constructors

Constructor and Description
ARFFVectorIterable(File file, ARFFModel model)
ARFFVectorIterable(File file, Charset encoding, ARFFModel model)
ARFFVectorIterable(Reader reader, ARFFModel model)
ARFFVectorIterable(String arff, ARFFModel model)

Method Summary

Methods

Modifier and Type	Method and Description
ARFFModel	getModel() Returns info about the ARFF content that was parsed.
Iterator<Vector>	iterator()

Methods inherited from class java.lang.Object

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

Constructor Detail

ARFFVectorIterable

public ARFFVectorIterable(File file,
                  ARFFModel model)
                   throws IOException

Throws:

IOException

ARFFVectorIterable

public ARFFVectorIterable(File file,
                  Charset encoding,
                  ARFFModel model)
                   throws IOException

Throws:

IOException

ARFFVectorIterable

public ARFFVectorIterable(String arff,
                  ARFFModel model)
                   throws IOException

Throws:

IOException

ARFFVectorIterable

public ARFFVectorIterable(Reader reader,
                  ARFFModel model)
                   throws IOException

Throws:

IOException

Method Detail

iterator

public Iterator<Vector> iterator()

Specified by:

iterator in interface Iterable<Vector>

getModel

public ARFFModel getModel()

Returns info about the ARFF content that was parsed.

Returns:

the model