Examples of weka.filters.unsupervised.attribute.PropositionalToMultiInstance

Package weka.filters.unsupervised.attribute

Examples of weka.filters.unsupervised.attribute.PropositionalToMultiInstance

weka.filters.unsupervised.attribute.PropositionalToMultiInstance
Converts the propositional instance dataset into multi-instance dataset (with relational attribute). When normalize or standardize a multi-instance dataset, a MIToSingleInstance filter can be applied first to convert the multi-instance dataset into propositional instance dataset. After normalization or standardization, may use this PropositionalToMultiInstance filter to convert the data back to multi-instance format.

Note: the first attribute of the original propositional instance dataset must be a nominal attribute which is expected to be bagId attribute.
Valid options are:
```
 -S <num> The seed for the randomization of the order of bags. (default 1)
```
```
 -R Randomizes the order of the produced bags after the generation. (default off)
```
@author Lin Dong (ld21@cs.waikato.ac.nz) @version $Revision: 5547 $ @see MultiInstanceToPropositional

      m_Filter = null;




    Instances transformedInsts;
    Filter convertToProp = new MultiInstanceToPropositional();
    Filter convertToMI = new PropositionalToMultiInstance();


    //transform the data into single-instance format
    if (m_minimax){ 
      /* using SimpleMI class minimax transform method. 
         this method transforms the multi-instance dataset into minmax feature space (single-instance) */
      SimpleMI transMinimax = new SimpleMI();
      transMinimax.setTransformMethod(
          new SelectedTag(
            SimpleMI.TRANSFORMMETHOD_MINIMAX, SimpleMI.TAGS_TRANSFORMMETHOD));
      transformedInsts = transMinimax.transform(insts);
    }
    else { 
      convertToProp.setInputFormat(insts);
      transformedInsts=Filter.useFilter(insts, convertToProp);
    }


    if (m_Missing != null) {
      m_Missing.setInputFormat(transformedInsts);
      transformedInsts = Filter.useFilter(transformedInsts, m_Missing); 
    }


    if (m_NominalToBinary != null) { 
      m_NominalToBinary.setInputFormat(transformedInsts);
      transformedInsts = Filter.useFilter(transformedInsts, m_NominalToBinary); 
    }


    if (m_Filter != null) {
      m_Filter.setInputFormat(transformedInsts);
      transformedInsts = Filter.useFilter(transformedInsts, m_Filter); 
    }


    // convert the single-instance format to multi-instance format
    convertToMI.setInputFormat(transformedInsts);
    insts = Filter.useFilter( transformedInsts, convertToMI);


    m_classIndex = insts.classIndex();
    m_classAttribute = insts.classAttribute();

View Full Code Here

    Instances insts = new Instances(inst.dataset(), 0);
    insts.add(inst);


    //transform the data into single-instance format
    Filter convertToProp = new MultiInstanceToPropositional();
    Filter convertToMI = new PropositionalToMultiInstance();


    if (m_minimax){ // using minimax feature space
      SimpleMI transMinimax = new SimpleMI();
      transMinimax.setTransformMethod(
          new SelectedTag(
            SimpleMI.TRANSFORMMETHOD_MINIMAX, SimpleMI.TAGS_TRANSFORMMETHOD));
      insts = transMinimax.transform (insts);
    }
    else{
      convertToProp.setInputFormat(insts);
      insts=Filter.useFilter( insts, convertToProp);
    }


    // Filter instances 
    if (m_Missing!=null) 
      insts = Filter.useFilter(insts, m_Missing);
    
    if (m_NominalToBinary != null) { 
      insts = Filter.useFilter(insts, m_NominalToBinary); 
    }


    if (m_Filter!=null)
      insts = Filter.useFilter(insts, m_Filter);     


    // convert the single-instance format to multi-instance format
    convertToMI.setInputFormat(insts);
    insts=Filter.useFilter( insts, convertToMI);


    inst = insts.instance(0);  


    if (!m_fitLogisticModels) {

View Full Code Here

      m_Filter = null;




    Instances transformedInsts;
    Filter convertToProp = new MultiInstanceToPropositional();
    Filter convertToMI = new PropositionalToMultiInstance();


    //transform the data into single-instance format
    if (m_minimax){ 
      /* using SimpleMI class minimax transform method. 
         this method transforms the multi-instance dataset into minmax feature space (single-instance) */
      SimpleMI transMinimax = new SimpleMI();
      transMinimax.setTransformMethod(
          new SelectedTag(
            SimpleMI.TRANSFORMMETHOD_MINIMAX, SimpleMI.TAGS_TRANSFORMMETHOD));
      transformedInsts = transMinimax.transform(insts);
    }
    else { 
      convertToProp.setInputFormat(insts);
      transformedInsts=Filter.useFilter(insts, convertToProp);
    }


    if (m_Missing != null) {
      m_Missing.setInputFormat(transformedInsts);
      transformedInsts = Filter.useFilter(transformedInsts, m_Missing); 
    }


    if (m_NominalToBinary != null) { 
      m_NominalToBinary.setInputFormat(transformedInsts);
      transformedInsts = Filter.useFilter(transformedInsts, m_NominalToBinary); 
    }


    if (m_Filter != null) {
      m_Filter.setInputFormat(transformedInsts);
      transformedInsts = Filter.useFilter(transformedInsts, m_Filter); 
    }


    // convert the single-instance format to multi-instance format
    convertToMI.setInputFormat(transformedInsts);
    insts = Filter.useFilter( transformedInsts, convertToMI);


    m_classIndex = insts.classIndex();
    m_classAttribute = insts.classAttribute();

View Full Code Here

    Instances insts = new Instances(inst.dataset(), 0);
    insts.add(inst);


    //transform the data into single-instance format
    Filter convertToProp = new MultiInstanceToPropositional();
    Filter convertToMI = new PropositionalToMultiInstance();


    if (m_minimax){ // using minimax feature space
      SimpleMI transMinimax = new SimpleMI();
      transMinimax.setTransformMethod(
          new SelectedTag(
            SimpleMI.TRANSFORMMETHOD_MINIMAX, SimpleMI.TAGS_TRANSFORMMETHOD));
      insts = transMinimax.transform (insts);
    }
    else{
      convertToProp.setInputFormat(insts);
      insts=Filter.useFilter( insts, convertToProp);
    }


    // Filter instances 
    if (m_Missing!=null) 
      insts = Filter.useFilter(insts, m_Missing); 


    if (m_Filter!=null)
      insts = Filter.useFilter(insts, m_Filter);     


    // convert the single-instance format to multi-instance format
    convertToMI.setInputFormat(insts);
    insts=Filter.useFilter( insts, convertToMI);


    inst = insts.instance(0);  


    if (!m_fitLogisticModels) {

View Full Code Here

TOP

Related Classes of weka.filters.unsupervised.attribute.PropositionalToMultiInstance

weka.classifiers.mi.MISMO

weka.core.Attribute

weka.core.Capabilities

weka.core.RelationalLocator

weka.core.StringLocator

java.util.Random

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.