Package adams.data.instancesanalysis.pls

Class SIMPLS

  • All Implemented Interfaces:
    Destroyable, GlobalInfoSupporter, LoggingLevelHandler, LoggingSupporter, OptionHandler, SizeOfHandler, TechnicalInformationHandler, Serializable, weka.core.CapabilitiesHandler, GenericPLSMatrixAccess
    public class SIMPLS
extends AbstractSingleClassPLS
    Implementation of SIMPLS algorithm.

    Available matrices: W, B

    For more information see:

    Tormod Naes, Tomas Isaksson, Tom Fearn, Tony Davies (2002). A User Friendly Guide to Multivariate Calibration and Classification. NIR Publications.

    S. de Jong (1993). SIMPLS: an alternative approach to partial least squares regression. Chemometrics and Intelligent Laboratory Systems. 18:251-263. 

     @book{Naes2002,
    author = {Tormod Naes and Tomas Isaksson and Tom Fearn and Tony Davies},
    publisher = {NIR Publications},
    title = {A User Friendly Guide to Multivariate Calibration and Classification},
    year = {2002},
    ISBN = {0-9528666-2-5}
 }

 @article{Jong1993,
    author = {S. de Jong},
    journal = {Chemometrics and Intelligent Laboratory Systems},
    pages = {251-263},
    title = {SIMPLS: an alternative approach to partial least squares regression},
    volume = {18},
    year = {1993}
 }
 


    -logging-level <OFF|SEVERE|WARNING|INFO|CONFIG|FINE|FINER|FINEST> (property: loggingLevel)
    The logging level for outputting errors and debugging output.
    default: WARNING
 
    -preprocessing-type <NONE|CENTER|STANDARDIZE> (property: preprocessingType)
    The type of preprocessing to perform.
    default: CENTER
 
    -replace-missing <boolean> (property: replaceMissing)
    Whether to replace missing values.
    default: false
 
    -num-components <int> (property: numComponents)
    The number of components to compute.
    default: 20
    minimum: 1
 
    -prediction-type <NONE|ALL|EXCEPT_CLASS> (property: predictionType)
    The type of prediction to perform.
    default: NONE
 
    -num-coefficients <int> (property: numCoefficients)
    The number of coefficients of W matrix to keep (rest gets zeroed); use 0
    to keep all.
    default: 0
    minimum: 0
    Author:
    FracPete (fracpete at waikato dot ac dot nz)
    See Also:
    Serialized Form

    • Field Detail

      • m_NumCoefficients

        protected int m_NumCoefficients
        the number of coefficients in W to keep (0 keep all).

      • m_W

        protected weka.core.matrix.Matrix m_W
        the W matrix

      • m_B

        protected weka.core.matrix.Matrix m_B
        the B matrix (used for prediction)

    • Constructor Detail

      • SIMPLS

        public SIMPLS()

    • Method Detail

      • setNumCoefficients

        public void setNumCoefficients​(int value)
        Sets the number of coefficients of W matrix to keep (rest gets zeroed).
        Parameters:
        value - the number of coefficients, 0 to keep all

      • getNumCoefficients

        public int getNumCoefficients()
        returns the number of coefficients of W matrix to keep (rest gets zeroed).
        Returns:
        the maximum number of attributes, 0 to keep all

      • numCoefficientsTipText

        public String numCoefficientsTipText()
        Returns the tip text for this property
        Returns:
        tip text for this property suitable for displaying in the explorer/experimenter gui

      • getMatrix

        public weka.core.matrix.Matrix getMatrix​(String name)
        Returns the matrix with the specified name.
        Specified by:
        getMatrix in interface GenericPLSMatrixAccess
        Specified by:
        getMatrix in class AbstractPLS
        Parameters:
        name - the name of the matrix
        Returns:
        the matrix, null if not available

      • slim

        protected void slim​(weka.core.matrix.Matrix in)
        Zeroes the coefficients of the W matrix beyond the specified number of coefficients.
        Parameters:
        in - the matrix to process in-place

      • doTransform

        protected weka.core.Instances doTransform​(weka.core.Instances data,
                                          Map<String,​Object> params)
                                   throws Exception
        Transforms the data, initializes if necessary.
        Specified by:
        doTransform in class AbstractPLS
        Parameters:
        data - the data to use
        params - additional parameters
        Returns:
        the transformed data
        Throws:
        Exception