Class MathUtil

java.lang.Object
  MathUtil

public class MathUtil
extends java.lang.Object

class that round off floating point numbers to the specified number of decimal places givem

Field Summary

static long	RAND_SEED
static java.util.Random	random

Constructor Summary

MathUtil()
Default constructor.

Method Summary

static boolean	almostEqual(double val1, double val2) method sees if input doubles are "almost" equal
static boolean	almostEqual(java.util.Vector vec1, double val2) method sees if input vectors are "almost" equal
static boolean	almostEqual(java.util.Vector vec1, java.util.Vector vec2) method sees if input vectors are "almost" equal
static void	betweenClass(DataPoints d, Matrix M, double rx_a, double ry_a) this method determines the between class scatter matrix for the class independent linear discrimination algorithm
static MyPoint	computeClusterMean(java.util.Vector vec) methods computes and returns the mean of the given cluster
static MyPoint	computeMyPointMean(java.util.Vector vec) methods computes and returns the mean of the given cluster
static MyPoint	computePointMean(java.util.Vector vec) methods computes and returns the mean of the given cluster
static void	copyVector(java.util.Vector<java.lang.Double> vec1_a, java.util.Vector<java.lang.Double> vec2_a, int length_a, int index1_a, int index2_a) Copies vector given specific parameters
static double	distance(double x1, double y1, double x2, double y2) calculate the euclidean distance between the two points
static double	doubleValue(java.util.Vector<java.lang.Double> vec_a, int index_a) gets the double value of the input vector at the index passed
static double	grand(double mean, double stddev) method generates a random distribution centered about the mean with a variance that is specified by the standard deviation.
static void	initDoubleVector(java.util.Vector<java.lang.Double> vec_a, double value_a) initializes components of vector to double value passed
static double	linearKernel(java.util.Vector point1, java.util.Vector point2) this method evaluates the linear Kernel on the input vectors K(x,y) = (x .
static double	polynomialKernel(java.util.Vector points1, java.util.Vector points2) this method evaluates the second degree polynomial Kernel on the input vectors K(x,y) = (x .
static double	rbfKernel(java.util.Vector point1, java.util.Vector point2) this method evaluates the redial basis function Kernel on the input vectors with standard deviation sigma K(x,y) = exp(-gamma * ((a.a)-2*(a.b)+(b.b)))
static double	rbfKernel(java.util.Vector point1, java.util.Vector point2, double gamma_a) this method evaluates the redial basis function Kernel on the input vectors with standard deviation sigma K(x,y) = exp(-gamma * ((a.a)-2*(a.b)+(b.b)))
static double	setDecimal(double doubleNumber, int decimalPlaces) method takes in a decimal number and rounds to the given number of decimal places passed
static double	SetDecimal(double doubleNumber, int decimalPlaces) method to round off floating point numbers to the specified number of decimal places given
static double	vectorProduct(java.util.Vector vec1, java.util.Vector vec2) this method evaluates the vector dot product
static void	withinClass(DataPoints data_a, double rx_a, double ry_a) Within Class

Methods inherited from class java.lang.Object

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

Field Detail

RAND_SEED

public static final long RAND_SEED

See Also:

Constant Field Values

random

public static final java.util.Random random

Constructor Detail

MathUtil

public MathUtil()

Default constructor. Empty body

Method Detail

grand

public static double grand(double mean,
                           double stddev)

method generates a random distribution centered about the mean with a variance that is specified by the standard deviation.

Parameters:

mean - mean of the distribution

stddev - standard deviation of the distribution

Returns:

random number centered about the mean

SetDecimal

public static double SetDecimal(double doubleNumber,
                                int decimalPlaces)

method to round off floating point numbers to the specified number of decimal places given

Parameters:

doubleNumber - input number

decimalPlaces - number of decimal places to round

distance

public static double distance(double x1,
                              double y1,
                              double x2,
                              double y2)

calculate the euclidean distance between the two points

Parameters:

x1 - x-coordinate of the first point

y1 - y-coordinate of the first point

x2 - x-coordinate of the second point

y2 - y-coordinate of the second point

Returns:

distance between the points

computeClusterMean

public static MyPoint computeClusterMean(java.util.Vector vec)

methods computes and returns the mean of the given cluster

Parameters:

vec - Vector of points from the cluster

Returns:

MyPoint value of the cluster mean

computePointMean

public static MyPoint computePointMean(java.util.Vector vec)

methods computes and returns the mean of the given cluster

Parameters:

vec - Vector of points from the cluster

Returns:

MyPoint value of the mean

computeMyPointMean

public static MyPoint computeMyPointMean(java.util.Vector vec)

methods computes and returns the mean of the given cluster

Parameters:

vec - point from the cluster

Returns:

MyPoint value of the mean

setDecimal

public static double setDecimal(double doubleNumber,
                                int decimalPlaces)

method takes in a decimal number and rounds to the given number of decimal places passed

Parameters:

doubleNumber - input number

decimalPlaces - number of significant decimal places

Returns:

double value of decimal with correct signifcant figures

linearKernel

public static double linearKernel(java.util.Vector point1,
                                  java.util.Vector point2)

this method evaluates the linear Kernel on the input vectors K(x,y) = (x . y)

Parameters:

point1 - First vector of points

point2 - Second vector of points

Returns:

double value of Kernel evaluation

rbfKernel

public static double rbfKernel(java.util.Vector point1,
                               java.util.Vector point2)

this method evaluates the redial basis function Kernel on the input vectors with standard deviation sigma K(x,y) = exp(-gamma * ((a.a)-2*(a.b)+(b.b)))

Parameters:

point1 - First vector of points

point2 - Second vector of points

Returns:

double value of Kernel evaluation

rbfKernel

public static double rbfKernel(java.util.Vector point1,
                               java.util.Vector point2,
                               double gamma_a)

this method evaluates the redial basis function Kernel on the input vectors with standard deviation sigma K(x,y) = exp(-gamma * ((a.a)-2*(a.b)+(b.b)))

Parameters:

point1 - First vector of points

point2 - Second vector of points

gamma_a - Double value of gamma

Returns:

double value of Kernel evaluation

polynomialKernel

public static double polynomialKernel(java.util.Vector points1,
                                      java.util.Vector points2)

this method evaluates the second degree polynomial Kernel on the input vectors K(x,y) = (x . y + 1)^p

Parameters:

points1 - First vector of points

points2 - Second vector of points

Returns:

Double value of Kernel evaluation

vectorProduct

public static double vectorProduct(java.util.Vector vec1,
                                   java.util.Vector vec2)

this method evaluates the vector dot product

Parameters:

vec1 - First vector of points

vec2 - Second vector of points

Returns:

dot product

almostEqual

public static boolean almostEqual(java.util.Vector vec1,
                                  java.util.Vector vec2)

method sees if input vectors are "almost" equal

Parameters:

vec1 - First vector of points

vec2 - Second vector of points

Returns:

True if all input vector components are "almost" equal

almostEqual

public static boolean almostEqual(java.util.Vector vec1,
                                  double val2)

method sees if input vectors are "almost" equal

Parameters:

vec1 - First vector of points

val2 - Value to compare to

Returns:

True if all input vector components are "almost" equal

almostEqual

public static boolean almostEqual(double val1,
                                  double val2)

method sees if input doubles are "almost" equal

Parameters:

val1 - First double value

val2 - Second double value

Returns:

True if doubles are "almost" equal

initDoubleVector

public static void initDoubleVector(java.util.Vector<java.lang.Double> vec_a,
                                    double value_a)

initializes components of vector to double value passed

Parameters:

vec_a - point from the cluster

value_a - value to set to vector

doubleValue

public static double doubleValue(java.util.Vector<java.lang.Double> vec_a,
                                 int index_a)

gets the double value of the input vector at the index passed

Parameters:

vec_a - point from the cluster

index_a -

Returns:

double value of vector at indexed value

copyVector

public static void copyVector(java.util.Vector<java.lang.Double> vec1_a,
                              java.util.Vector<java.lang.Double> vec2_a,
                              int length_a,
                              int index1_a,
                              int index2_a)

Copies vector given specific parameters

Parameters:

vec1_a - vector to be overwritten/copyied to

vec2_a - vector to be copied from

length_a - number of elements to be copyied

index1_a - index to start copying to first vector

index2_a - index to start copying from second vector

withinClass

public static void withinClass(DataPoints data_a,
                               double rx_a,
                               double ry_a)

Within Class

Parameters:

data_a - input data points

rx_a - double input of x

ry_a - double input of y

betweenClass

public static void betweenClass(DataPoints d,
                                Matrix M,
                                double rx_a,
                                double ry_a)

this method determines the between class scatter matrix for the class independent linear discrimination algorithm

Parameters:

d - input data points

M - between class scatter matrix

rx_a - double input of x

ry_a - double input of y