Java Vector.get方法代码示例

import org.apache.mahout.math.Vector; //导入方法依赖的package包/类
/** Returns one sample from a multinomial. */
public static int rMultinom(Vector probabilities) {
  // our probability argument are not normalized.
  double total = probabilities.zSum();
  double nextDouble = RANDOM.nextDouble();
  double p = nextDouble * total;
  for (int i = 0; i < probabilities.size(); i++) {
    double pi = probabilities.get(i);
    if (p < pi) {
      return i;
    } else {
      p -= pi;
    }
  }
  // can't happen except for round-off error so we don't care what we return here
  return 0;
}
 

import org.apache.mahout.math.Vector; //导入方法依赖的package包/类
/**
 * Computes {@code p(topic x|term a, document i)} distributions given input document {@code i}.
 * {@code pTGT[x][a]} is the (un-normalized) {@code p(x|a,i)}, or if docTopics is {@code null},
 * {@code p(a|x)} (also un-normalized).
 *
 * @param document doc-term vector encoding {@code w(term a|document i)}.
 * @param docTopics {@code docTopics[x]} is the overall weight of topic {@code x} in given
 *          document. If {@code null}, a topic weight of {@code 1.0} is used for all topics.
 * @param termTopicDist storage for output {@code p(x|a,i)} distributions.
 */
private void pTopicGivenTerm(Vector document, Vector docTopics, Matrix termTopicDist) {
  // for each topic x
  for (int x = 0; x < numTopics; x++) {
    // get p(topic x | document i), or 1.0 if docTopics is null
    double topicWeight = docTopics == null ? 1.0 : docTopics.get(x);
    // get w(term a | topic x)
    Vector topicTermRow = topicTermCounts.viewRow(x);
    // get \sum_a w(term a | topic x)
    double topicSum = topicSums.get(x);
    // get p(topic x | term a) distribution to update
    Vector termTopicRow = termTopicDist.viewRow(x);

    // for each term a in document i with non-zero weight
    Iterator<Vector.Element> it = document.iterateNonZero();
    while (it.hasNext()) {
      Vector.Element e = it.next();
      int termIndex = e.index();

      // calc un-normalized p(topic x | term a, document i)
      double termTopicLikelihood = (topicTermRow.get(termIndex) + eta) * (topicWeight + alpha) / (topicSum + eta * numTerms);
      termTopicRow.set(termIndex, termTopicLikelihood);
    }
  }
}
 

import org.apache.mahout.math.Vector; //导入方法依赖的package包/类
/**
 * @param x
 *          a Vector
 * @return the zSum(((x[i]-c[i])/r[i])^2) over all i
 */
private double sumXminusCdivRsquared(Vector x) {
  double result = 0;
  for (Iterator<Element> it = getRadius().iterateNonZero(); it.hasNext();) {
    Element radiusElem = it.next();
    int index = radiusElem.index();
    double quotient = (x.get(index) - getCenter().get(index))
        / radiusElem.get();
    result += quotient * quotient;
  }
  return result;
}
 

import org.apache.mahout.math.Vector; //导入方法依赖的package包/类
/**
 * Sample from a Dirichlet distribution, returning a vector of probabilities using a stick-breaking
 * algorithm
 * 
 * @param totalCounts
 *          an unnormalized count Vector
 * @param alpha0
 *          a double
 * @return a Vector of probabilities
 */
public static Vector rDirichlet(Vector totalCounts, double alpha0) {
  Vector pi = totalCounts.like();
  double total = totalCounts.zSum();
  double remainder = 1.0;
  for (int k = 0; k < pi.size(); k++) {
    double countK = totalCounts.get(k);
    total -= countK;
    double betaK = rBeta(1.0 + countK, Math.max(0.0, alpha0 + total));
    double piK = betaK * remainder;
    pi.set(k, piK);
    remainder -= piK;
  }
  return pi;
}
 

import org.apache.mahout.math.Vector; //导入方法依赖的package包/类
public Vector infer(Vector original, Vector docTopics) {
  Vector pTerm = original.like();
  Iterator<Vector.Element> it = original.iterateNonZero();
  while (it.hasNext()) {
    Vector.Element e = it.next();
    int term = e.index();
    // p(a) = sum_x (p(a|x) * p(x|i))
    double pA = 0;
    for (int x = 0; x < numTopics; x++) {
      pA += (topicTermCounts.viewRow(x).get(term) / topicSums.get(x)) * docTopics.get(x);
    }
    pTerm.set(term, pA);
  }
  return pTerm;
}