Examples with Instances weka.core.Instances used on opensource projects

Example 31 with Instances

use of weka.core.Instances in project iobserve-analysis by research-iobserve.

the class UserGroupExtraction method extractUserGroups.

/**
 * Function to extract user groups.
 */
public void extractUserGroups() {
    final ClusteringPrePostProcessing clusteringProcessing = new ClusteringPrePostProcessing();
    final XMeansClustering xMeansClustering = new XMeansClustering();
    ClusteringResults xMeansClusteringResults;
    /**
     * 1. Extraction of distinct system operations. Creates a list of the distinct operation
     * signatures occurring within the entryCallSequenceModel. It is required to transform each
     * user session to counts of its called operations. The counts are used to determine the
     * similarity between the user sessions
     */
    final List<String> listOfDistinctOperationSignatures = clusteringProcessing.getListOfDistinctOperationSignatures(this.entryCallSequenceModel.getUserSessions());
    /**
     * 2. Transformation to the call count model. Transforms the call sequences of the user
     * sessions to a list of counts of calls that state the number of calls of each distinct
     * operation signature for each user session
     */
    final List<UserSessionAsCountsOfCalls> callCountModel = clusteringProcessing.getCallCountModel(this.entryCallSequenceModel.getUserSessions(), listOfDistinctOperationSignatures);
    /**
     * 3. Clustering of user sessions. Clustering of the user sessions whose behavior is
     * represented as counts of their called operation signatures to obtain user groups
     */
    final Instances instances = xMeansClustering.createInstances(callCountModel, listOfDistinctOperationSignatures);
    /*
         * The clustering is performed 5 times and the best result is taken. The quality of a
         * clustering result is determined by the value of the sum of squared error (SSE) of the
         * clustering. The lower the SSE is the better the clustering result.
         */
    for (int i = 0; i < 5; i++) {
        xMeansClusteringResults = xMeansClustering.clusterSessionsWithXMeans(instances, this.numberOfUserGroupsFromInputUsageModel, this.varianceOfUserGroups, i);
        if (this.clusteringResults == null) {
            this.clusteringResults = xMeansClusteringResults;
        } else if (xMeansClusteringResults.getClusteringMetrics().getSumOfSquaredErrors() < this.clusteringResults.getClusteringMetrics().getSumOfSquaredErrors()) {
            this.clusteringResults = xMeansClusteringResults;
        }
    }
    /**
     * 4. Obtaining the user groups' call sequence models. Creates for each cluster resp. user
     * group its own entry call sequence model that exclusively contains its assigned user
     * sessions
     */
    final List<EntryCallSequenceModel> entryCallSequenceModelsOfXMeansClustering = clusteringProcessing.getForEachUserGroupAnEntryCallSequenceModel(this.clusteringResults, this.entryCallSequenceModel);
    /**
     * 5. Obtaining the user groups' workload intensity. Calculates and sets for each user group
     * its specific workload intensity parameters
     */
    clusteringProcessing.setTheWorkloadIntensityForTheEntryCallSequenceModels(entryCallSequenceModelsOfXMeansClustering, this.isClosedWorkload);
    /**
     * Sets the resulting entryCallSequenceModels that can be retrieved via the getter method
     */
    this.entryCallSequenceModelsOfUserGroups = entryCallSequenceModelsOfXMeansClustering;
}