org.openimaj.ml.clustering.rforest

Class RandomDecisionTree

java.lang.Object

org.openimaj.ml.clustering.rforest.RandomDecisionTree

public class RandomDecisionTree
extends Object

A tree of RandomDecision nodes used for constructing a string of bits which represent a cluster point for a single data point

Author:

Sina Samangooei (ss@ecs.soton.ac.uk)

Constructor Summary

Constructors

Constructor and Description
RandomDecisionTree() A convenience function allowing the RandomDecisionTree to be written and read.
RandomDecisionTree(int nDecisions, int featureLength, int[] minVal, int[] maxVal) Construct a new RandomDecisionTree setting the number of decisions and the values needed to choose a random index and min/max values for each feature vector index.
RandomDecisionTree(int nDecisions, int featureLength, int[] minVal, int[] maxVal, Random r) Construct a new RandomDecisionTree setting the number of decisions and the values needed to choose a random index and min/max values for each feature vector index.

Method Summary

Modifier and Type	Method and Description
boolean	equals(Object o)
boolean[]	getLetter(int[] feature) The function which finds the path down this random tree for a given feature.
RandomDecisionTree	readASCII(Scanner br) Read/Write RandomDecisionTree (including decision nodes)
RandomDecisionTree	readBinary(DataInput dis) Read/Write RandomDecisionTree (including decision nodes)
String	toString()
void	write(DataOutput o) Read/Write RandomDecisionTree (including decision nodes)
void	writeASCII(PrintWriter writer) Read/Write RandomDecisionTree (including decision nodes)

Methods inherited from class java.lang.Object

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

Constructor Detail

RandomDecisionTree

public RandomDecisionTree(int nDecisions,
                          int featureLength,
                          int[] minVal,
                          int[] maxVal)

Construct a new RandomDecisionTree setting the number of decisions and the values needed to choose a random index and min/max values for each feature vector index.

Parameters:

nDecisions -

featureLength -

minVal -

maxVal -

RandomDecisionTree

public RandomDecisionTree(int nDecisions,
                          int featureLength,
                          int[] minVal,
                          int[] maxVal,
                          Random r)

Construct a new RandomDecisionTree setting the number of decisions and the values needed to choose a random index and min/max values for each feature vector index.

Parameters:

nDecisions -

featureLength -

minVal -

maxVal -

r -

RandomDecisionTree

public RandomDecisionTree()

A convenience function allowing the RandomDecisionTree to be written and read.

Method Detail

getLetter

public boolean[] getLetter(int[] feature)

The function which finds the path down this random tree for a given feature. Tests each required feature vector index against the threshold and assigns booleans.

Parameters:

feature -

Returns:

return the letter as a string of bytes

write

public void write(DataOutput o)
           throws IOException

Read/Write RandomDecisionTree (including decision nodes)

Parameters:

o -

Throws:

IOException

writeASCII

public void writeASCII(PrintWriter writer)

Read/Write RandomDecisionTree (including decision nodes)

Parameters:

writer -

readBinary

public RandomDecisionTree readBinary(DataInput dis)
                              throws IOException

Read/Write RandomDecisionTree (including decision nodes)

Parameters:

dis -

Returns:

this

Throws:

IOException

readASCII

public RandomDecisionTree readASCII(Scanner br)
                             throws IOException

Read/Write RandomDecisionTree (including decision nodes)

Parameters:

br -

Returns:

this

Throws:

IOException

toString

public String toString()

Overrides:

toString in class Object

equals

public boolean equals(Object o)

Overrides:

equals in class Object