Examples of weka.filters.unsupervised.attribute.ReplaceMissingValues

Package weka.filters.unsupervised.attribute

Examples of weka.filters.unsupervised.attribute.ReplaceMissingValues

weka.filters.unsupervised.attribute.ReplaceMissingValues
Replaces all missing values for nominal and numeric attributes in a dataset with the modes and means from the training data.
Valid options are:
```
 -unset-class-temporarily Unsets the class index temporarily before the filter is applied to the data. (default: no)
```
@author Eibe Frank (eibe@cs.waikato.ac.nz) @version $Revision: 5547 $

    // remove instances with missing class
    Instances filteredData = new Instances(data);
    filteredData.deleteWithMissingClass();
    
    //replace missing values
    m_replaceMissing = new ReplaceMissingValues();
    m_replaceMissing.setInputFormat(filteredData);  
    filteredData = Filter.useFilter(filteredData, m_replaceMissing);
    
    //possibly convert nominal attributes globally
    if (m_convertNominal) {

View Full Code Here

    m_trainCopy = null;
    
    m_attributeFilter = null;
    m_nominalToBinaryFilter = null;
    
    m_replaceMissingFilter = new ReplaceMissingValues();
    m_replaceMissingFilter.setInputFormat(m_trainInstances);
    m_trainInstances = Filter.useFilter(m_trainInstances, m_replaceMissingFilter);
    
    // vector to hold indices of attributes to delete (class attribute, 
    // attributes that are all missing, or attributes with one distinct value)

View Full Code Here

   */
  public void buildClusterer(Instances data) throws Exception {
    // can clusterer handle the data ?
    getCapabilities().testWithFail(data);


    m_replaceMissing = new ReplaceMissingValues();
    Instances instances = new Instances(data);
    instances.setClassIndex(-1);
    m_replaceMissing.setInputFormat(instances);
    data = weka.filters.Filter.useFilter(instances, m_replaceMissing);
    instances = null;

View Full Code Here

   */  
  public void buildClusterer(Instances data) throws Exception {
    // can clusterer handle the data?
    getCapabilities().testWithFail(data);


    m_replaceMissing = new ReplaceMissingValues();
    m_replaceMissing.setInputFormat(data);
    data = weka.filters.Filter.useFilter(data, m_replaceMissing);


    m_theInstances = new Instances(data, 0);
    if (m_wrappedClusterer == null) {

View Full Code Here

    // can clusterer handle the data?
    getCapabilities().testWithFail(data);


    m_Iterations = 0;


    m_ReplaceMissingFilter = new ReplaceMissingValues();
    Instances instances = new Instances(data);
    instances.setClassIndex(-1);
    if (!m_dontReplaceMissing) {
      m_ReplaceMissingFilter.setInputFormat(instances);
      instances = Filter.useFilter(instances, m_ReplaceMissingFilter);

View Full Code Here

    // can clusterer handle the data?
    getCapabilities().testWithFail(data);


    //long start = System.currentTimeMillis();


    m_ReplaceMissingFilter = new ReplaceMissingValues();
    m_ReplaceMissingFilter.setInputFormat(data);
    m_instances = Filter.useFilter(data, m_ReplaceMissingFilter);


    initMinMax(m_instances);

View Full Code Here


    // make a copy of the training data so that we can get the class
    // column to append to the transformed data (if necessary)
    m_trainCopy = new Instances(m_trainInstances);
    
    m_replaceMissingFilter = new ReplaceMissingValues();
    m_replaceMissingFilter.setInputFormat(m_trainInstances);
    m_trainInstances = Filter.useFilter(m_trainInstances, 
                                        m_replaceMissingFilter);


    if (m_normalize) {

View Full Code Here

    m_NumSplits = 0;
    m_NumSplitsDone = 0;
    m_NumSplitsStillDone = 0;


    // replace missing values
    m_ReplaceMissingFilter = new ReplaceMissingValues();
    m_ReplaceMissingFilter.setInputFormat(data);
    m_Instances = Filter.useFilter(data, m_ReplaceMissingFilter);
    
    // initialize random function
    Random random0 = new Random(m_Seed);

View Full Code Here

        resultVector = new FastVector();
        long time_1 = System.currentTimeMillis();


        numberOfGeneratedClusters = 0;


        replaceMissingValues_Filter = new ReplaceMissingValues();
        replaceMissingValues_Filter.setInputFormat(instances);
        Instances filteredInstances = Filter.useFilter(instances, replaceMissingValues_Filter);


        database = databaseForName(getDatabase_Type(), filteredInstances);
        for (int i = 0; i < database.getInstances().numInstances(); i++) {

View Full Code Here

    throws Exception {
    
    // can clusterer handle the data?
    getCapabilities().testWithFail(data);


    m_replaceMissing = new ReplaceMissingValues();
    Instances instances = new Instances(data);
    instances.setClassIndex(-1);
    m_replaceMissing.setInputFormat(instances);
    data = weka.filters.Filter.useFilter(instances, m_replaceMissing);
    instances = null;

View Full Code Here

0 1 2 3 4 5 6 7

TOP

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

weka.attributeSelection.LatentSemanticAnalysis

weka.attributeSelection.PrincipalComponents

weka.classifiers.bayes.BayesNet

weka.classifiers.functions.GaussianProcesses

weka.classifiers.functions.LeastMedSq

weka.classifiers.functions.LibLINEAR

weka.classifiers.functions.LibSVM

weka.classifiers.functions.LinearRegression

weka.classifiers.functions.Logistic

weka.classifiers.functions.SGD

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.