Examples of weka.classifiers.Evaluation

weka.classifiers.Evaluation
Class for evaluating machine learning models.
-------------------------------------------------------------------
General options when evaluating a learning scheme from the command-line:
-t filename
Name of the file with the training data. (required)
-T filename
Name of the file with the test data. If missing a cross-validation is performed.
-c index
Index of the class attribute (1, 2, ...; default: last).
-x number
The number of folds for the cross-validation (default: 10).
-no-cv
No cross validation. If no test file is provided, no evaluation is done.
-split-percentage percentage
Sets the percentage for the train/test set split, e.g., 66.
-preserve-order
Preserves the order in the percentage split instead of randomizing the data first with the seed value ('-s').
-s seed
Random number seed for the cross-validation and percentage split (default: 1).
-m filename
The name of a file containing a cost matrix.
-l filename
Loads classifier from the given file. In case the filename ends with ".xml", a PMML file is loaded or, if that fails, options are loaded from XML.
-d filename
Saves classifier built from the training data into the given file. In case the filename ends with ".xml" the options are saved XML, not the model.
-v
Outputs no statistics for the training data.
-o
Outputs statistics only, not the classifier.
-i
Outputs information-retrieval statistics per class.
-k
Outputs information-theoretic statistics.
-classifications "weka.classifiers.evaluation.output.prediction.AbstractOutput + options"
Uses the specified class for generating the classification output. E.g.: weka.classifiers.evaluation.output.prediction.PlainText or : weka.classifiers.evaluation.output.prediction.CSV -p range
Outputs predictions for test instances (or the train instances if no test instances provided and -no-cv is used), along with the attributes in the specified range (and nothing else). Use '-p 0' if no attributes are desired.
Deprecated: use "-classifications ..." instead.
-distribution
Outputs the distribution instead of only the prediction in conjunction with the '-p' option (only nominal classes).
Deprecated: use "-classifications ..." instead.
-r
Outputs cumulative margin distribution (and nothing else).
-g
Only for classifiers that implement "Graphable." Outputs the graph representation of the classifier (and nothing else).
-xml filename | xml-string
Retrieves the options from the XML-data instead of the command line.
-threshold-file file
The file to save the threshold data to. The format is determined by the extensions, e.g., '.arff' for ARFF format or '.csv' for CSV.
-threshold-label label
The class label to determine the threshold data for (default is the first label)
-------------------------------------------------------------------
Example usage as the main of a classifier (called FunkyClassifier):
```
 public static void main(String [] args) { runClassifier(new FunkyClassifier(), args); } 
```
------------------------------------------------------------------
Example usage from within an application:
```
 Instances trainInstances = ... instances got from somewhere Instances testInstances = ... instances got from somewhere Classifier scheme = ... scheme got from somewhere Evaluation evaluation = new Evaluation(trainInstances); evaluation.evaluateModel(scheme, testInstances); System.out.println(evaluation.toSummaryString()); 
```
@author Eibe Frank (eibe@cs.waikato.ac.nz) @author Len Trigg (trigg@cs.waikato.ac.nz) @version $Revision: 7228 $

   * @throws Exception if subset can't be evaluated
   */
  protected double estimatePerformance(BitSet feature_set, int num_atts)
  throws Exception {


    m_evaluation = new Evaluation(m_theInstances);
    int i;
    int [] fs = new int [num_atts];


    double [] instA = new double [num_atts];
    int classI = m_theInstances.classIndex();

View Full Code Here

    delTransform.setInputFormat(trainCopy);
    trainCopy = Filter.useFilter(trainCopy, delTransform);


    // max of 5 repititions ofcross validation
    for (i = 0; i < 5; i++) {
      m_Evaluation = new Evaluation(trainCopy);
      m_Evaluation.crossValidateModel(m_BaseClassifier, trainCopy, m_folds, Rnd);
      repError[i] = m_Evaluation.errorRate();


      // check on the standard deviation
      if (!repeat(repError, i + 1)) {

View Full Code Here

      throw new Exception("On-demand cost file doesn't exist: " + costFile);
    }
    CostMatrix costMatrix = new CostMatrix(new BufferedReader(
    new FileReader(costFile)));
    
    Evaluation eval = new Evaluation(train, costMatrix);    
    m_Classifier = Classifier.makeCopy(m_Template);
    
    trainTimeStart = System.currentTimeMillis();
    if(canMeasureCPUTime)
      CPUStartTime = thMonitor.getThreadUserTime(thID);
    m_Classifier.buildClassifier(train);
    if(canMeasureCPUTime)
      trainCPUTimeElapsed = thMonitor.getThreadUserTime(thID) - CPUStartTime;
    trainTimeElapsed = System.currentTimeMillis() - trainTimeStart;
    testTimeStart = System.currentTimeMillis();
    if(canMeasureCPUTime)
      CPUStartTime = thMonitor.getThreadUserTime(thID);
    eval.evaluateModel(m_Classifier, test);
    if(canMeasureCPUTime)
      testCPUTimeElapsed = thMonitor.getThreadUserTime(thID) - CPUStartTime;
    testTimeElapsed = System.currentTimeMillis() - testTimeStart;
    thMonitor = null;
    
    m_result = eval.toSummaryString();
    // The results stored are all per instance -- can be multiplied by the
    // number of instances to get absolute numbers
    int current = 0;
    result[current++] = new Double(train.numInstances());
    result[current++] = new Double(eval.numInstances());
    
    result[current++] = new Double(eval.correct());
    result[current++] = new Double(eval.incorrect());
    result[current++] = new Double(eval.unclassified());
    result[current++] = new Double(eval.pctCorrect());
    result[current++] = new Double(eval.pctIncorrect());
    result[current++] = new Double(eval.pctUnclassified());
    result[current++] = new Double(eval.totalCost());
    result[current++] = new Double(eval.avgCost());
    
    result[current++] = new Double(eval.meanAbsoluteError());
    result[current++] = new Double(eval.rootMeanSquaredError());
    result[current++] = new Double(eval.relativeAbsoluteError());
    result[current++] = new Double(eval.rootRelativeSquaredError());
    
    result[current++] = new Double(eval.SFPriorEntropy());
    result[current++] = new Double(eval.SFSchemeEntropy());
    result[current++] = new Double(eval.SFEntropyGain());
    result[current++] = new Double(eval.SFMeanPriorEntropy());
    result[current++] = new Double(eval.SFMeanSchemeEntropy());
    result[current++] = new Double(eval.SFMeanEntropyGain());
    
    // K&B stats
    result[current++] = new Double(eval.KBInformation());
    result[current++] = new Double(eval.KBMeanInformation());
    result[current++] = new Double(eval.KBRelativeInformation());
    
    // Timing stats
    result[current++] = new Double(trainTimeElapsed / 1000.0);
    result[current++] = new Double(testTimeElapsed / 1000.0);
    if(canMeasureCPUTime) {

View Full Code Here

    boolean prune = (nodeList.size() > 0);


    //alpha_0 is always zero (unpruned tree)
    alphas[0] = 0;


    Evaluation eval;


    // error of unpruned tree
    if (errors != null) {
      eval = new Evaluation(test);
      eval.evaluateModel(this, test);
      errors[0] = eval.errorRate();
    }


    int iteration = 0;
    double preAlpha = Double.MAX_VALUE;
    while (prune) {


      iteration++;


      // get node with minimum alpha
      SimpleCart nodeToPrune = nodeToPrune(nodeList);


      // do not set m_sons null, want to unprune
      nodeToPrune.m_isLeaf = true;


      // normally would not happen
      if (nodeToPrune.m_Alpha==preAlpha) {
  iteration--;
  treeErrors();
  calculateAlphas();
  nodeList = getInnerNodes();
  prune = (nodeList.size() > 0);
  continue;
      }


      // get alpha-value of node
      alphas[iteration] = nodeToPrune.m_Alpha;


      // log error
      if (errors != null) {
  eval = new Evaluation(test);
  eval.evaluateModel(this, test);
  errors[iteration] = eval.errorRate();
      }
      preAlpha = nodeToPrune.m_Alpha;


      //update errors/alphas
      treeErrors();

View Full Code Here

   * pruned) is rooted. This is needed for calculating the alpha-values.
   * 
   * @throws Exception   if something goes wrong
   */
  public void modelErrors() throws Exception{
    Evaluation eval = new Evaluation(m_train);


    if (!m_isLeaf) {
      m_isLeaf = true; //temporarily make leaf


      // calculate distribution for evaluation
      eval.evaluateModel(this, m_train);
      m_numIncorrectModel = eval.incorrect();


      m_isLeaf = false;


      for (int i = 0; i < m_Successors.length; i++)
  m_Successors[i].modelErrors();


    } else {
      eval.evaluateModel(this, m_train);
      m_numIncorrectModel = eval.incorrect();
    }       
  }

View Full Code Here

    }


    // build the classifier
    m_Classifier.buildClassifier(trainCopy);


    m_Evaluation = new Evaluation(trainCopy);
    if (!m_useTraining) {
      m_Evaluation.evaluateModel(m_Classifier, testCopy);
    } else {
      m_Evaluation.evaluateModel(m_Classifier, trainCopy);
    }

View Full Code Here

    testCopy = Filter.useFilter(testCopy, delTransform);


    // build the classifier
    m_Classifier.buildClassifier(trainCopy);


    m_Evaluation = new Evaluation(trainCopy);
    m_Evaluation.evaluateModel(m_Classifier, testCopy);


    if (m_trainingInstances.classAttribute().isNominal()) {
      errorRate = m_Evaluation.errorRate();
    } else {

View Full Code Here

    int bestIndex = -1;
    double bestPerformance = Double.NaN;
    int numClassifiers = m_Classifiers.length;
    for (int i = 0; i < numClassifiers; i++) {
      Classifier currentClassifier = getClassifier(i);
      Evaluation evaluation;
      if (m_NumXValFolds > 1) {
  evaluation = new Evaluation(newData);
  for (int j = 0; j < m_NumXValFolds; j++) {


          // We want to randomize the data the same way for every 
          // learning scheme.
    train = newData.trainCV(m_NumXValFolds, j, new Random (1));
    test = newData.testCV(m_NumXValFolds, j);
    currentClassifier.buildClassifier(train);
    evaluation.setPriors(train);
    evaluation.evaluateModel(currentClassifier, test);
  }
      } else {
  currentClassifier.buildClassifier(train);
  evaluation = new Evaluation(train);
  evaluation.evaluateModel(currentClassifier, test);
      }


      double error = evaluation.errorRate();
      if (m_Debug) {
  System.err.println("Error rate: " + Utils.doubleToString(error, 6, 4)
         + " for classifier "
         + currentClassifier.getClass().getName());
      }

View Full Code Here

      throw new Exception("On-demand cost file doesn't exist: " + costFile);
    }
    CostMatrix costMatrix = new CostMatrix(new BufferedReader(
    new FileReader(costFile)));
    
    Evaluation eval = new Evaluation(train, costMatrix);    
    m_Classifier = Classifier.makeCopy(m_Template);
    
    trainTimeStart = System.currentTimeMillis();
    if(canMeasureCPUTime)
      CPUStartTime = thMonitor.getThreadUserTime(thID);
    m_Classifier.buildClassifier(train);
    if(canMeasureCPUTime)
      trainCPUTimeElapsed = thMonitor.getThreadUserTime(thID) - CPUStartTime;
    trainTimeElapsed = System.currentTimeMillis() - trainTimeStart;
    testTimeStart = System.currentTimeMillis();
    if(canMeasureCPUTime)
      CPUStartTime = thMonitor.getThreadUserTime(thID);
    eval.evaluateModel(m_Classifier, test);
    if(canMeasureCPUTime)
      testCPUTimeElapsed = thMonitor.getThreadUserTime(thID) - CPUStartTime;
    testTimeElapsed = System.currentTimeMillis() - testTimeStart;
    thMonitor = null;
    
    m_result = eval.toSummaryString();
    // The results stored are all per instance -- can be multiplied by the
    // number of instances to get absolute numbers
    int current = 0;
    result[current++] = new Double(train.numInstances());
    result[current++] = new Double(eval.numInstances());
    
    result[current++] = new Double(eval.correct());
    result[current++] = new Double(eval.incorrect());
    result[current++] = new Double(eval.unclassified());
    result[current++] = new Double(eval.pctCorrect());
    result[current++] = new Double(eval.pctIncorrect());
    result[current++] = new Double(eval.pctUnclassified());
    result[current++] = new Double(eval.totalCost());
    result[current++] = new Double(eval.avgCost());
    
    result[current++] = new Double(eval.meanAbsoluteError());
    result[current++] = new Double(eval.rootMeanSquaredError());
    result[current++] = new Double(eval.relativeAbsoluteError());
    result[current++] = new Double(eval.rootRelativeSquaredError());
    
    result[current++] = new Double(eval.SFPriorEntropy());
    result[current++] = new Double(eval.SFSchemeEntropy());
    result[current++] = new Double(eval.SFEntropyGain());
    result[current++] = new Double(eval.SFMeanPriorEntropy());
    result[current++] = new Double(eval.SFMeanSchemeEntropy());
    result[current++] = new Double(eval.SFMeanEntropyGain());
    
    // K&B stats
    result[current++] = new Double(eval.KBInformation());
    result[current++] = new Double(eval.KBMeanInformation());
    result[current++] = new Double(eval.KBRelativeInformation());
    
    // Timing stats
    result[current++] = new Double(trainTimeElapsed / 1000.0);
    result[current++] = new Double(testTimeElapsed / 1000.0);
    if(canMeasureCPUTime) {

View Full Code Here

    double[][] probs = initialProbs(numInstances);
    m_NumGenerated = 0;
    double sumOfWeights = train.sumOfWeights();
    for (int j = 0; j < getNumIterations(); j++) {
      performIteration(trainYs, trainFs, probs, trainN, sumOfWeights);
      Evaluation eval = new Evaluation(train);
      eval.evaluateModel(this, test);
      results[j] += eval.correct();
    }
  }
      }
      
      // Find the number of iterations with the lowest error

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of weka.classifiers.Evaluation

bnGUI.att_BayesAttSel

bnGUI.att_ev_SingleBayesROCAttributeEval

bnGUI.att_Ranker$EvalThread

bnGUI.gui_WekaExperiment

bnGUI.Thread_competitors

bnGUI.Thread_weka_run

com.deafgoat.ml.prognosticator.AppClassifier

CrossValWeka

de.tudarmstadt.ukp.similarity.experiments.coling2012.util.Evaluator

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.