Method run

src/modules/lda/lda.cpp:177–294

* @brief This function learns the topics of words in a document and is the * main step of a Gibbs sampling iteration. The word topic counts and * corpus topic counts are passed to this function in the first call and * then transfered to the rest calls through args.mSysInfo->user_fctx for * efficiency. * @param args[0] The unique words in the documents * @param args[1] The counts of each

 *                  the document
 **/
AnyType lda_gibbs_sample::run(AnyType & args)
{
    ArrayHandle<int32_t> words = args[0].getAs<ArrayHandle<int32_t> >();
    ArrayHandle<int32_t> counts = args[1].getAs<ArrayHandle<int32_t> >();
    MutableArrayHandle<int32_t> doc_topic = args[2].getAs<MutableArrayHandle<int32_t> >();
    double alpha = args[4].getAs<double>();
    double beta = args[5].getAs<double>();
    int32_t voc_size = args[6].getAs<int32_t>();
    int32_t topic_num = args[7].getAs<int32_t>();
    int32_t iter_num = args[8].getAs<int32_t>();
    size_t model64_size = static_cast<size_t>(voc_size * (topic_num + 1) + 1) * sizeof(int32_t) / sizeof(int64_t);

    if(alpha <= 0)
        throw std::invalid_argument("invalid argument - alpha");
    if(beta <= 0)
        throw std::invalid_argument("invalid argument - beta");
    if(voc_size <= 0)
        throw std::invalid_argument(
            "invalid argument - voc_size");
    if(topic_num <= 0)
        throw std::invalid_argument(
            "invalid argument - topic_num");
    if(iter_num <= 0)
        throw std::invalid_argument(
            "invalid argument - iter_num");

    if(words.size() != counts.size())
        throw std::invalid_argument(
            "dimensions mismatch: words.size() != counts.size()");
    if(__min(words) < 0 || __max(words) >= voc_size)
        throw std::invalid_argument(
            "invalid values in words");
    if(__min(counts) <= 0)
        throw std::invalid_argument(
            "invalid values in counts");

    int32_t word_count = __sum(counts);
    if(doc_topic.size() != (size_t)(word_count + topic_num))
        throw std::invalid_argument(
            "invalid dimension - doc_topic.size() != word_count + topic_num");
    if(__min(doc_topic, 0, topic_num) < 0)
        throw std::invalid_argument("invalid values in topic_count");
    if(
        __min(doc_topic, topic_num, word_count) < 0 ||
        __max(doc_topic, topic_num, word_count) >= topic_num)
        throw std::invalid_argument( "invalid values in topic_assignment");

    if (!args.getUserFuncContext()) {
        ArrayHandle<int64_t> model64 = args[3].getAs<ArrayHandle<int64_t> >();
        if (model64.size() != model64_size) {
            std::stringstream ss;
            ss << "invalid dimension: model64.size() = " << model64.size();
            throw std::invalid_argument(ss.str());
        }
        if (__min(model64) < 0) {
            throw std::invalid_argument("invalid topic counts in model");
        }