本文整理汇总了Java中org.apache.mahout.math.Vector.like方法的典型用法代码示例。如果您正苦于以下问题：Java Vector.like方法的具体用法？Java Vector.like怎么用？Java Vector.like使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.apache.mahout.math.Vector的用法示例。
在下文中一共展示了Vector.like方法的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: observe
import org.apache.mahout.math.Vector; //导入方法依赖的package包/类
@Override
public void observe(Vector x, double weight) {
double temp = weight + sumWeight;
Vector q;
if (mean == null) {
mean = x.like();
q = x.clone();
} else {
q = x.minus(mean);
}
Vector r = q.times(weight).divide(temp);
if (s == null) {
s = q.times(sumWeight).times(r);
} else {
s = s.plus(q.times(sumWeight).times(r));
}
mean = mean.plus(r);
sumWeight = temp;
variance = s.divide(sumWeight - 1); // # if sample is the population, omit -1
}
示例2: sampleFromPrior
import org.apache.mahout.math.Vector; //导入方法依赖的package包/类
@Override
public Model<VectorWritable>[] sampleFromPrior(int howMany) {
Model<VectorWritable>[] result = new GaussianCluster[howMany];
for (int i = 0; i < howMany; i++) {
Vector prototype = getModelPrototype().get();
Vector mean = prototype.like();
for (int j = 0; j < prototype.size(); j++) {
mean.set(j, UncommonDistributions.rNorm(0, 1));
}
Vector sd = prototype.like();
for (int j = 0; j < prototype.size(); j++) {
sd.set(j, UncommonDistributions.rNorm(1, 1));
}
result[i] = new GaussianCluster(mean, sd, i);
}
return result;
}
示例3: rDirichlet
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;
}
示例4: infer
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;
}