mahout推荐发动机使用hadoop（二） 计算协同矩阵

mahout推荐引擎使用hadoop（二） 计算协同矩阵

?

?????? 第二步，计算协同矩阵，主要在RowSimilarityJob 这个类中完成

?

??

public static class SimilarityReducer      extends Reducer<IntWritable,VectorWritable,IntWritable,VectorWritable> {    @Override    protected void reduce(IntWritable row, Iterable<VectorWritable> partialDots, Context ctx)        throws IOException, InterruptedException {      Iterator<VectorWritable> partialDotsIterator = partialDots.iterator();      //取一个vecotr作为该item的行向量      Vector dots = partialDotsIterator.next().get();      while (partialDotsIterator.hasNext()) {        Vector toAdd = partialDotsIterator.next().get();        Iterator<Vector.Element> nonZeroElements = toAdd.iterateNonZero();        while (nonZeroElements.hasNext()) {          Vector.Element nonZeroElement = nonZeroElements.next();          //nonZeroElement.index()为itemid，将另一个vecotr中itemid的value加进去          dots.setQuick(nonZeroElement.index(), dots.getQuick(nonZeroElement.index()) + nonZeroElement.get());        }      }      //最后得到的dots是协同矩阵中行号为row的一行，行中元素是item对其他的item的相似度      Vector similarities = dots.like();      double normA = norms.getQuick(row.get());      Iterator<Vector.Element> dotsWith = dots.iterateNonZero();      while (dotsWith.hasNext()) {        Vector.Element b = dotsWith.next();        double similarityValue = similarity.similarity(b.get(), normA, norms.getQuick(b.index()), numberOfColumns);        if (similarityValue >= treshold) {          similarities.set(b.index(), similarityValue);        }      }      if (excludeSelfSimilarity) {        similarities.setQuick(row.get(), 0);      }      ctx.write(row, new VectorWritable(similarities));    }  }

?

?

?

?

?

?