float rbm_predict(const vertex_data & usr,
const vertex_data & mov,
const float rating,
double & prediction,
void * extra) {
return rbm_predict(rbm_user((vertex_data&)usr), rbm_movie((vertex_data&)mov), rating, prediction, NULL);
}
/**
* Vertex update function.
*/
void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
if (gcontext.iteration == 0) {
if (is_user(vertex.id()) && vertex.num_outedges() > 0) {
vertex_data& user = latent_factors_inmem[vertex.id()];
user.pvec = zeros(D*3);
for(int e=0; e < vertex.num_outedges(); e++) {
rbm_movie mov = latent_factors_inmem[vertex.edge(e)->vertex_id()];
float observation = vertex.edge(e)->get_data();
int r = (int)(observation/rbm_scaling);
assert(r < rbm_bins);
mov.bi[r]++;
}
}
return;
} else if (gcontext.iteration == 1) {
if (vertex.num_inedges() > 0) {
rbm_movie mov = latent_factors_inmem[vertex.id()];
setRand2(mov.w, D*rbm_bins, 0.001);
for(int r = 0; r < rbm_bins; ++r) {
mov.bi[r] /= (double)vertex.num_inedges();
mov.bi[r] = log(1E-9 + mov.bi[r]);
if (mov.bi[r] > 1000) {
assert(false);
Rcpp::Rcerr<<"Numerical overflow" <<std::endl;
}
}
}
return; //done with initialization
}
//go over all user nodes
if (is_user(vertex.id()) && vertex.num_outedges()) {
vertex_data & user = latent_factors_inmem[vertex.id()];
user.pvec = zeros(3*D);
rbm_user usr(user);
vec v1 = zeros(vertex.num_outedges());
//go over all ratings
for(int e=0; e < vertex.num_outedges(); e++) {
float observation = vertex.edge(e)->get_data();
rbm_movie mov = latent_factors_inmem[vertex.edge(e)->vertex_id()];
int r = (int)(observation / rbm_scaling);
assert(r < rbm_bins);
for(int k=0; k < D; k++) {
usr.h[k] += mov.w[D*r + k];
assert(!std::isnan(usr.h[k]));
}
}
for(int k=0; k < D; k++) {
usr.h[k] = sigmoid(usr.h[k]);
if (drand48() < usr.h[k])
usr.h0[k] = 1;
else usr.h0[k] = 0;
}
int i = 0;
double prediction;
for(int e=0; e < vertex.num_outedges(); e++) {
rbm_movie mov = latent_factors_inmem[vertex.edge(e)->vertex_id()];
float observation = vertex.edge(e)->get_data();
predict1(usr, mov, observation, prediction);
int vi = (int)(prediction / rbm_scaling);
v1[i] = vi;
i++;
}
i = 0;
for(int e=0; e < vertex.num_outedges(); e++) {
rbm_movie mov = latent_factors_inmem[vertex.edge(e)->vertex_id()];
int r = (int)v1[i];
for (int k=0; k< D; k++) {
usr.h1[k] += mov.w[r*D+k];
}
i++;
}
for (int k=0; k < D; k++) {
usr.h1[k] = sigmoid(usr.h1[k]);
if (drand48() < usr.h1[k])
usr.h1[k] = 1;
else usr.h1[k] = 0;
}
i = 0;
for(int e=0; e < vertex.num_outedges(); e++) {
rbm_movie mov = latent_factors_inmem[vertex.edge(e)->vertex_id()];
float observation = vertex.edge(e)->get_data();
double prediction;
rbm_predict(user, mov, observation, prediction, NULL);
double pui = prediction / rbm_scaling;
double rui = observation / rbm_scaling;
rmse_vec[omp_get_thread_num()] += (pui - rui) * (pui - rui);
//nn += 1.0;
int vi0 = (int)(rui);
int vi1 = (int)v1[i];
for (int k = 0; k < D; k++) {
mov.w[D*vi0+k] += rbm_alpha * (usr.h0[k] - rbm_beta * mov.w[vi0*D+k]);
assert(!std::isnan(mov.w[D*vi0+k]));
mov.w[D*vi1+k] -= rbm_alpha * (usr.h1[k] + rbm_beta * mov.w[vi1*D+k]);
assert(!std::isnan(mov.w[D*vi1+k]));
}
i++;
}
}
}
/**
* Vertex update function - computes the least square step
*/
void update(graphchi_vertex<VertexDataType, EdgeDataType> &vertex, graphchi_context &gcontext) {
//compute only for user nodes
if (vertex.id() >= std::min(M,(uint)end_user) || vertex.id() < (uint)start_user)
return;
vertex_data & vdata = latent_factors_inmem[vertex.id()];
int howmany = (int)(N*knn_sample_percent);
assert(howmany > 0 );
if (vertex.num_outedges() == 0){
mymutex.lock();
users_without_ratings++;
mymutex.unlock();
}
vec distances = zeros(howmany);
ivec indices = ivec::Zero(howmany);
for (int i=0; i< howmany; i++){
indices[i]= -1;
}
std::vector<bool> curratings;
curratings.resize(N);
for(int e=0; e < vertex.num_edges(); e++) {
//no need to calculate this rating since it is given in the training data reference
assert(vertex.edge(e)->vertex_id() - M >= 0 && vertex.edge(e)->vertex_id() - M < N);
curratings[vertex.edge(e)->vertex_id() - M] = true;
}
if (knn_sample_percent == 1.0){
for (uint i=M; i< M+N; i++){
if (curratings[i-M])
continue;
vertex_data & other = latent_factors_inmem[i];
double dist;
if (algo == SVDPP)
svdpp_predict(vdata, other, 0, dist);
else if (algo == BIASSGD)
biassgd_predict(vdata, other, 0, dist);
else if (algo == RBM)
rbm_predict(vdata, other, 0, dist);
else assert(false);
indices[i-M] = i-M;
distances[i-M] = dist + 1e-10;
}
}
else for (int i=0; i<howmany; i++){
int random_other = ::randi(M, M+N-1);
vertex_data & other = latent_factors_inmem[random_other];
double dist;
if (algo == SVDPP)
svdpp_predict(vdata, other, 0, dist);
else if (algo == BIASSGD)
biassgd_predict(vdata, other, 0, dist);
else if (algo == RBM)
rbm_predict(vdata, other, 0, dist);
else assert(false);
indices[i] = random_other-M;
distances[i] = dist;
}
vec out_dist(num_ratings);
ivec indices_sorted = reverse_sort_index2(distances, indices, out_dist, num_ratings);
assert(indices_sorted.size() <= num_ratings);
assert(out_dist.size() <= num_ratings);
vdata.ids = indices_sorted;
vdata.ratings = out_dist;
if (debug)
printf("Closest is: %d with distance %g\n", (int)vdata.ids[0], vdata.ratings[0]);
if (vertex.id() % 1000 == 0)
printf("Computing recommendations for user %d at time: %g\n", vertex.id()+1, mytimer.current_time());
}
