smile.feature

Class SignalNoiseRatio

java.lang.Object

smile.feature.SignalNoiseRatio

All Implemented Interfaces:

FeatureRanking

public class SignalNoiseRatio
extends java.lang.Object
implements FeatureRanking

The signal-to-noise (S2N) metric ratio is a univariate feature ranking metric, which can be used as a feature selection criterion for binary classification problems. S2N is defined as |μ₁ - μ₂| / (σ₁ + σ₂), where μ₁ and μ₂ are the mean value of the variable in classes 1 and 2, respectively, and σ₁ and σ₂ are the standard deviations of the variable in classes 1 and 2, respectively. Clearly, features with larger S2N ratios are better for classification.

References

1. M. Shipp, et al. Diffuse large B-cell lymphoma outcome prediction by gene-expression profiling and supervised machine learning. Nature Medicine, 2002.

Field Summary

Fields

Modifier and Type	Field and Description
static SignalNoiseRatio	instance

Constructor Summary

Constructors

Constructor and Description
SignalNoiseRatio()

Method Summary

Modifier and Type	Method and Description
static double[]	of(double[][] x, int[] y) Univariate feature ranking.
double[]	rank(double[][] x, int[] y) Univariate feature ranking.

Methods inherited from class java.lang.Object

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

Field Detail

instance

public static final SignalNoiseRatio instance

Constructor Detail

SignalNoiseRatio

public SignalNoiseRatio()

Method Detail

rank

public double[] rank(double[][] x,
                     int[] y)

Description copied from interface: FeatureRanking

Univariate feature ranking. Note that this method actually does NOT rank the features. It just returns the metric values of each feature. The use can then rank and select features.

Specified by:

rank in interface FeatureRanking

Parameters:

x - a n-by-p matrix of n instances with p features.

y - class labels.

Returns:

the metric values of each feature, in the ascending order of unique labels.

of

public static double[] of(double[][] x,
                          int[] y)

Univariate feature ranking. Note that this method actually does NOT rank the features. It just returns the metric values of each feature. The use can then rank and select features.

Parameters:

x - a n-by-p matrix of n instances with p features.

y - class labels.

Returns:

the signal noise ratio for each feature.