Example usage for org.apache.mahout.math.neighborhood UpdatableSearcher size

Introduction

In this page you can find the example usage for org.apache.mahout.math.neighborhood UpdatableSearcher size.

Prototype

public abstract int size();

Source Link

Document

Returns the number of WeightedVectors being searched for nearest neighbors.

Usage

From source file:eu.stratosphere.library.clustering.DistributedOnePassKMeans.BallKMeans.java

License:Apache License

public BallKMeans(UpdatableSearcher searcher, int numClusters, int maxNumIterations, double trimFraction,
        boolean kMeansPlusPlusInit, boolean correctWeights, double testProbability, int numRuns) {
    Preconditions.checkArgument(searcher.size() == 0,
            "Searcher must be empty initially to populate with centroids");
    Preconditions.checkArgument(numClusters > 0, "The requested number of clusters must be positive");
    Preconditions.checkArgument(maxNumIterations > 0, "The maximum number of iterations must be positive");
    Preconditions.checkArgument(trimFraction > 0, "The trim fraction must be positive");
    Preconditions.checkArgument(testProbability >= 0 && testProbability < 1,
            "The testProbability must be in [0, 1)");
    Preconditions.checkArgument(numRuns > 0, "There has to be at least one run");

    this.centroids = searcher;
    this.numClusters = numClusters;
    this.maxNumIterations = maxNumIterations;

    this.trimFraction = trimFraction;
    this.kMeansPlusPlusInit = kMeansPlusPlusInit;
    this.correctWeights = correctWeights;

    this.testProbability = testProbability;

    this.splitTrainTest = testProbability > 0;
    this.numRuns = numRuns;

    this.random = RandomUtils.getRandom();
}

---

From source file:org.plista.kornakapi.core.training.StramingKMeansClusterer.java

License:Apache License

/**
 * retrain model//from www .j a v  a  2s . c om
 */
public void cluster() {
    long start = System.currentTimeMillis();
    List<Centroid> data = model.getData();
    UpdatableSearcher centroids = clusterer.cluster(data);
    long estimateDuration = System.currentTimeMillis() - start;
    this.model.updateCentroids(centroids);
    if (log.isInfoEnabled()) {
        log.info("Model trained in {} ms, created [{}] Clusters", estimateDuration, centroids.size());
    }
}

---

From source file:org.plista.kornakapi.core.training.StramingKMeansClusterer.java

License:Apache License

/**
 * just stream new available data-points into old coordinate system
 *///from  w w  w .j  a v a 2s  .co  m
public void stream() {
    long start = System.currentTimeMillis();
    List<Centroid> data = model.getNewData();
    UpdatableSearcher centroids = clusterer.cluster(data);
    long estimateDuration = System.currentTimeMillis() - start;
    this.model.updateCentroids(centroids);
    if (log.isInfoEnabled()) {
        log.info("Model trained in {} ms, created [{}] Clusters", estimateDuration, centroids.size());
    }
}

---