/**
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.mahout.clustering.lda;
import com.google.common.base.Preconditions;
import org.apache.mahout.math.Matrix;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.stats.Sampler;
import java.util.Random;
/**
* Takes in a {@link Matrix} of topic distributions (such as generated by {@link LDADriver},
* {@link org.apache.mahout.clustering.lda.cvb.CVB0Driver} or
* {@link org.apache.mahout.clustering.lda.cvb.InMemoryCollapsedVariationalBayes0}, and constructs
* a set of samplers over this distribution, which may be sampled from by providing a distribution
* over topics, and a number of samples desired
*/
public class LDASampler {
private final Random random;
private final Sampler[] samplers;
public LDASampler(Matrix model, Random random) {
this.random = random;
samplers = new Sampler[model.numRows()];
for(int i = 0; i < samplers.length; i++) {
samplers[i] = new Sampler(random, model.viewRow(i));
}
}
/**
*
* @param topicDistribution vector of p(topicId) for all topicId < model.numTopics()
* @param numSamples the number of times to sample (with replacement) from the model
* @return array of length numSamples, with each entry being a sample from the model. There
* may be repeats
*/
public int[] sample(Vector topicDistribution, int numSamples) {
Preconditions.checkNotNull(topicDistribution);
Preconditions.checkArgument(numSamples > 0, "numSamples must be positive");
Preconditions.checkArgument(topicDistribution.size() == samplers.length,
"topicDistribution must have same cardinality as the sampling model");
int[] samples = new int[numSamples];
Sampler topicSampler = new Sampler(random, topicDistribution);
for(int i = 0; i < numSamples; i++) {
samples[i] = samplers[topicSampler.sample()].sample();
}
return samples;
}
}