smile.feature

Class Bag<T>

java.lang.Object

smile.feature.Bag<T>

All Implemented Interfaces:

FeatureGenerator<T[]>

public class Bag<T>
extends java.lang.Object
implements FeatureGenerator<T[]>

The bag-of-words feature of text used in natural language processing and information retrieval. In this model, a text (such as a sentence or a document) is represented as an unordered collection of words, disregarding grammar and even word order. This is a generic implementations. Thus, it can be used for sequences of any (discrete) data types with limited number of values.

Constructor Summary

Constructors

Constructor and Description
Bag(T[] features) Constructor.
Bag(T[] features, boolean binary) Constructor.

Method Summary

Modifier and Type	Method and Description
Attribute[]	attributes() Returns the variable attributes of generated features.
double[]	feature(T[] x) Returns the bag-of-words features of a document.

Methods inherited from class java.lang.Object

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

Constructor Detail

Bag

public Bag(T[] features)

Constructor.

Parameters:

features - the list of feature objects.

Bag

public Bag(T[] features,
           boolean binary)

Constructor.

Parameters:

features - the list of feature objects. The feature objects should be unique in the list. Note that the Bag class doesn't learn the features, but just use them as attributes.

binary - true to check if feature object appear in a collection instead of their frequencies.

Method Detail

attributes

public Attribute[] attributes()

Description copied from interface: FeatureGenerator

Returns the variable attributes of generated features. Note that these are NOT the original variable attributes of objects.

Specified by:

attributes in interface FeatureGenerator<T[]>

Returns:

the variable attributes of generated features

feature

public double[] feature(T[] x)

Returns the bag-of-words features of a document. The features are real-valued in convenience of most learning algorithms although they take only integer or binary values.

Specified by:

feature in interface FeatureGenerator<T[]>

Parameters:

x - an object of interest.

Returns:

a feature vector.