问Spark 1.4Mllib LDA topicDistributions()返回错误数量的文档

EN

enter code here

//parse tf vectors from corpus

JavaRDD<Vector> parsedData = data.map(
    new Function<String, Vector>() {
        public Vector call(String s) {
            s = s.substring(1, s.length()-1);
            String[] sarray = s.trim().split(",");
            double[] values = new double[sarray.length];
            for (int i = 0; i < sarray.length; i++)
            {
                values[i] = Double.parseDouble(sarray[i]);
            }
            return Vectors.dense(values);
          }

);

System.out.println(parsedData.count()) //prints 12,054

// Index documents with unique IDs

JavaPairRDD<Long, Vector> corpus =  JavaPairRDD.fromJavaRDD(parsedData.zipWithIndex().map(
     new Function<Tuple2<Vector, Long>, Tuple2<Long, Vector>>() {
       public Tuple2<Long, Vector> call(Tuple2<Vector, Long> doc_id) {
         return doc_id.swap();
       }
     }
));

System.out.println(corpus.count()) //prints 12,054

LDA lda = new LDA()
LDAModel ldaModel = lda.setK(k.intValue()).run(corpus);

RDD<scala.Tuple2<Object,Vector>> topic_dist_over_docs = ((DistributedLDAModel) ldaModel).topicDistributions();
System.out.println(topic_dist_over_docs.count()) //prints 11,655 ???

JavaPairRDD<Long,Vector> topic_dist_over_docs2 = ((DistributedLDAModel) ldaModel).javaTopicDistributions();
System.out.println(topic_dist_over_docs2.count()) //also prints 11,655 ???