/** The gather function computes XtX and Xy */
gather_type gather(icontext_type& context, const vertex_type& vertex,
edge_type& edge) const {
if(edge.data().role == edge_data::TRAIN) {
const vertex_type other_vertex = get_other_vertex(edge, vertex);
return gather_type(other_vertex.data().factor, edge.data().obs);
} else return gather_type();
} // end of gather function
/**
* \brief The scatter function just signal adjacent pages
*/
void scatter(icontext_type& context, const vertex_type& vertex,
edge_type& edge) const {
const vertex_type other = get_other_vertex(edge, vertex);
distance_type newd = vertex.data().dist + edge.data().dist;
if (other.data().dist > newd) {
const min_distance_type msg(newd);
context.signal(other, msg);
}
} // end of scatter
factor_type gather(icontext_type& context, const vertex_type& vertex,
edge_type& edge) const {
vertex_type other_vertex = get_other_vertex(edge, vertex);
// VIOLATING THE ABSTRACTION!
vertex_data& vdata = graph_type::vertex_type(vertex).data();
// VIOLATING THE ABSTRACTION!
vertex_data& other_vdata = other_vertex.data();
factor_type& doc_topic_count =
is_doc(vertex) ? vdata.factor : other_vdata.factor;
factor_type& word_topic_count =
is_word(vertex) ? vdata.factor : other_vdata.factor;
ASSERT_EQ(doc_topic_count.size(), NTOPICS);
ASSERT_EQ(word_topic_count.size(), NTOPICS);
// run the actual gibbs sampling
factor_type& belief = edge.data().belief;
const uint32_t count = edge.data().count;
// Resample the topics
double sum = 0, old_sum = 0;
for(size_t t = 0; t < NTOPICS; ++t) {
old_sum += belief[t];
doc_topic_count[t] -= belief[t];
word_topic_count[t] -= belief[t];
GLOBAL_TOPIC_COUNT[t] -= belief[t];
const double n_dt =
std::max(count_type(doc_topic_count[t]), count_type(0));
ASSERT_GE(n_dt, 0);
const double n_wt =
std::max(count_type(word_topic_count[t]), count_type(0));
ASSERT_GE(n_wt, 0);
const double n_t =
std::max(count_type(GLOBAL_TOPIC_COUNT[t]), count_type(0));
ASSERT_GE(n_t, 0);
belief[t] = (ALPHA + n_dt) * (BETA + n_wt) / (BETA * NWORDS + n_t);
sum += belief[t];
} // End of loop over each token
ASSERT_GT(sum, 0);
if(old_sum == 0) {
size_t asg = graphlab::random::multinomial(belief);
for(size_t i = 0; i < NTOPICS; ++i) belief[i] = 0;
belief[asg] = count;
return belief;
}
for(size_t t = 0; t < NTOPICS; ++t) {
belief[t] = count * (belief[t]/sum);
doc_topic_count[t] += belief[t];
word_topic_count[t] += belief[t];
GLOBAL_TOPIC_COUNT[t] += belief[t];
}
return belief;
} // end of gather
/*
* \brief Returns the sparse vector containing all the items rated by the user vertex.
*/
rated_type map_get_topk(graph_type::edge_type edge, graph_type::vertex_type other)
{
// return the list of items rated by the user
const rated_type& similar_items = other.data().rated_items;
// To hold the similarity score
rated_type similarity_score;
// Get the id of the current item
id_type current_id = get_other_vertex(edge, other).id();
// Go through all the items rated by the other user, except for current item
for(rated_type::const_iterator cit = similar_items.begin(); cit != similar_items.end(); cit++)
if(cit->first != current_id)
{
// Get the score and add only if score is valid
// Score is invalid if common users are less than MIN_ALLOWED_INTERSECTION
double score = adj_cosine_similarity(item_vector[cit->first], item_vector[current_id]);
if(score != INVALID_SIMILARITY)
similarity_score[cit->first] = score;
}
return similarity_score;
}
void scatter(icontext_type& context, const vertex_type& vertex,
edge_type& edge) const {
const vertex_type other_vertex = get_other_vertex(edge, vertex);
context.signal(other_vertex);
} // end of scatter function
