Fishtrans object (Multivariate Analysis Toolbox for MatlabŪ)

written by: Liran Carmel

Last modified: 16:34, Sun 12-Sep-2010

General Description
This object represents linear transformation using the multidimensional Fisher class-separation criterion. Here, the factors are named discriminant vectors, and their maximal number is g-1, with g being the number of classes.

Navigate to:     General Description     Class Structure     Class Construction     Class Functions

Class Structure
Each field can be accessed by the dot (.) operation, or by the GET function. The GET function can work on multiple instances simultaneously. Most fields, except for those that are Dependent, can be modified using the dot (.) operation, or by the SET function.
    Field Description Type Default Dedicated Get/Set Function  
    ratio Type of ratio optimized. Can be either 'Sb/Sw' or 'Sb/St' string 'Sb/Sw'    
    ortho_constraints orthogonality contraints. Each constraint is a column vector. double matrix []    
    name Inherited from lintrans. name of object, should be short and used as identifier. This field will never be empty. string 'unnamed'    
    description Inherited from lintrans. verbal description of the class content. string ''    
    source Inherited from lintrans. verbal description of the source of information. string ''    
    type Inherited from lintrans. type of linear transformation. string ''    
    U Inherited from lintrans. Transformation matrix. vvmatrix []    
    eigvals Inherited from lintrans. eigenvalues associated with the solution. double vector []    
    f_eigvals Inherited from lintrans. fractional importance of each eigenvalue. double vector []    
    no_samples Inherited from lintrans. number of samples in the original data. integer [] nosamples  
    preprocess Inherited from lintrans. preprocessing of the data matrix. Should be applied to any data before operating with the linear transformation. vector of preprocess structures []    
    scores Inherited from lintrans. the data projected into the new variables (factors). vsmatrix []    
  Dependent no_factors Inherited from lintrans. number of new factors. integer scalar 0 nofactors  
  Dependent no_variables Inherited from lintrans. number of original variables. integer scalar 0 novariables  

Class Construction
Empty instance (scalar)
an empty fishtrans instance, with all fields initialized to their default values.
syntax: ft = fishtrans;
Empty instance (matrix)
an array of empty fishtrans instances.
syntax: ft = fishtrans(size);
Copy constructor
one fishtrans instance is copied into another.
syntax: ft_destination = fishtrans(ft_origin);
Construction by field names
an instance is formed by directly providing field values. Any field which is not dependent is permitted.
syntax: ft = fishtrans(field_name, field_value, ...);
Computing from a vsmatrix
Computing factors from an input in the form of a sample-variable matrix.
syntax: ft = fishtrans(vsm, opt_name, opt_val, ...);

List of Functions

Display functions:

displays class content. Source: lintrans.


operating with the linear transformation Source: lintrans.

SET/GET functions:

retrieves the eigenvalues of the linear transformation. Source: lintrans.
retrieves the names of the factors. Source: lintrans.
retrieves the factors of the linear transformation. Source: lintrans.
get method
retrieves the number of factors. Source: lintrans.
retrieves the number of samples. Source: lintrans.
retrieves the number of original variables. Source: lintrans.
set method
retrieves the names of the original variables. Source: lintrans.


excludes certain factors. Source: lintrans.
inverts the signs of selected factors. Source: lintrans.


plots the loadings of the linear transformation. Source: lintrans.
plots factors versus factors for all data samples Source: lintrans.
plots a scree diagram of the transformation eigenvalues. Source: lintrans.