ActivityComponentSim.java

package kb.howtokb.clustering;

import java.util.Map;

import kb.howtokb.clustering.sim.ActivityWordCategorySim.SparseSims;
import kb.howtokb.utils.IDMap;

public class ActivityComponentSim implements ISimilarity<Integer> {

	private double threshold = 0.0;
	private SparseSims sims; // cache.
	private IDMap<String, Integer> ids;
	private ISimilarity<String> word2vecSim;

	public ActivityComponentSim(double threshold, IDMap<String, Integer> ids, ISimilarity<String> word2vecSim) {
		this.threshold = threshold;
		this.sims = new SparseSims((float) this.threshold);
		this.ids = ids;
		this.word2vecSim = word2vecSim;
		computeAllPairsSim();
	}

	private void computeAllPairsSim() {
		//Progress p = new Progress(1);
		Integer[] ids = this.ids.values().toArray(new Integer[0]);
		System.out.println("\n" + ids.length + " activity components. (one dot per activity neighborhood)");
		for (int i = 0; i < ids.length; i++) {
			//p.next();
			int e1 = ids[i];
			for (int j = i; j < ids.length; j++) {
				// cache before returning the result.
				int e2 = ids[j];
				sims.set(e1, e2, (float) sim(e1, e2));
			}
		}
	}

	@Override
	public double sim(Integer e1, Integer e2) {
		String word1 = ids.getKeyFromValue(e1);
		String word2 = ids.getKeyFromValue(e2);
		return word2vecSim.sim(word1, word2);
	}

	@Override
	public Map<Integer, Double> getNeighbors(Integer e) {
		System.err.println(
				"neighborhood for an integer " + "activity (noun or verb) not yet implemented.");
		return null;
	}

	@Override
	public boolean simThreshold(Integer e1, Integer e2, double minthreshold) throws Exception {
		return sim(e1, e2) >= minthreshold;
	}

	// Use this function once the object is completely constructed.
	/**
	 * Also checks for e2,e1
	 * 
	 * @param e1
	 * @param e2
	 * @return if (e1,e2) are similar, return true. otherwise returns false
	 */
	public boolean simFromCache(int e1, int e2) {
		return sims.get(e1, e2);
	}

	/**
	 * Also checks for e2,e1 <br>
	 * <b>NOTE: ensure that word1 and word2 are either both verbs or both noun.
	 * And modified according to the ISim func. provided to the constructor</b>
	 * 
	 * @param word1
	 *            go away => v_go (we only lookup "go" in word2vec)
	 * @param word2
	 *            move => v_move
	 * @return if (e1,e2) are similar, return true. otherwise returns false
	 */
	public boolean simFromCache(String word1, String word2) {
		int e1 = ids.getValueFromKey(word1);
		int e2 = ids.getValueFromKey(word2);
		return sims.get(e1, e2);
	}

}