int main(int argc, const char ** argv) {
print_copyright();
//* CE_Graph initialization will read the command line arguments and the configuration file. */
CE_Graph_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("biassgd-inmemory-factors");
biassgd_lambda = get_option_float("biassgd_lambda", 1e-3);
biassgd_gamma = get_option_float("biassgd_gamma", 1e-3);
biassgd_step_dec = get_option_float("biassgd_step_dec", 0.9);
parse_command_line_args();
parse_implicit_command_line();
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket<EdgeDataType>(training, 0, 0, 3, TRAINING, false);
init_feature_vectors<std::vector<vertex_data> >(M+N, latent_factors_inmem, !load_factors_from_file);
if (validation != ""){
int vshards = convert_matrixmarket<EdgeDataType>(validation, 0, 0, 3, VALIDATION, false);
init_validation_rmse_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards, &bias_sgd_predict);
}
/* load initial state from disk (optional) */
if (load_factors_from_file){
load_matrix_market_matrix(training + "_U.mm", 0, D);
load_matrix_market_matrix(training + "_V.mm", M, D);
vec user_bias = load_matrix_market_vector(training +"_U_bias.mm", false, true);
assert(user_bias.size() == M);
vec item_bias = load_matrix_market_vector(training +"_V_bias.mm", false, true);
assert(item_bias.size() == N);
for (uint i=0; i<M+N; i++){
latent_factors_inmem[i].bias = ((i<M)?user_bias[i] : item_bias[i-M]);
}
vec gm = load_matrix_market_vector(training + "_global_mean.mm", false, true);
globalMean = gm[0];
}
/* Run */
BIASSGDVerticesInMemProgram program;
CE_Graph_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, niters);
/* Output latent factor matrices in matrix-market format */
output_biassgd_result(training);
test_predictions(&bias_sgd_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
int main(int argc, const char ** argv) {
print_copyright();
/* GraphChi initialization will read the command line
arguments and the configuration file. */
graphchi_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("als-inmemory-factors");
lambda = get_option_float("lambda", 0.065);
parse_command_line_args();
parse_implicit_command_line();
if (unittest == 1){
if (training == "") training = "test_wals";
niters = 100;
}
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket4<edge_data>(training);
init_feature_vectors<std::vector<vertex_data> >(M+N, latent_factors_inmem, !load_factors_from_file);
if (validation != ""){
int vshards = convert_matrixmarket4<EdgeDataType>(validation, false, M==N, VALIDATION, 0);
init_validation_rmse_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards, &wals_predict, true, false, 0);
}
if (load_factors_from_file){
load_matrix_market_matrix(training + "_U.mm", 0, D);
load_matrix_market_matrix(training + "_V.mm", M, D);
}
/* Run */
WALSVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, niters);
/* Output latent factor matrices in matrix-market format */
output_als_result(training);
test_predictions(&wals_predict);
if (unittest == 1){
if (dtraining_rmse > 0.03)
logstream(LOG_FATAL)<<"Unit test 1 failed. Training RMSE is: " << training_rmse << std::endl;
if (dvalidation_rmse > 0.61)
logstream(LOG_FATAL)<<"Unit test 1 failed. Validation RMSE is: " << validation_rmse << std::endl;
}
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
int main(int argc, const char ** argv) {
print_copyright();
/* GraphChi initialization will read the command line
arguments and the configuration file. */
graphchi_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("als-inmemory-factors");
lambda = get_option_float("lambda", 0.065);
user_sparsity = get_option_float("user_sparsity", 0.9);
movie_sparsity = get_option_float("movie_sparsity", 0.9);
algorithm = get_option_int("algorithm", SPARSE_USR_FACTOR);
parse_command_line_args();
parse_implicit_command_line();
if (user_sparsity < 0.5 || user_sparsity >= 1)
logstream(LOG_FATAL)<<"Sparsity level should be [0.5,1). Please run again using --user_sparsity=XX in this range" << std::endl;
if (movie_sparsity < 0.5 || movie_sparsity >= 1)
logstream(LOG_FATAL)<<"Sparsity level should be [0.5,1). Please run again using --movie_sparsity=XX in this range" << std::endl;
if (algorithm != SPARSE_USR_FACTOR && algorithm != SPARSE_BOTH_FACTORS && algorithm != SPARSE_ITM_FACTOR)
logstream(LOG_FATAL)<<"Algorithm should be 1 for SPARSE_USR_FACTOR, 2 for SPARSE_ITM_FACTOR and 3 for SPARSE_BOTH_FACTORS" << std::endl;
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket<EdgeDataType>(training);
init_feature_vectors<std::vector<vertex_data> >(M+N, latent_factors_inmem, !load_factors_from_file);
if (validation != ""){
int vshards = convert_matrixmarket<EdgeDataType>(validation, 0, 0, 3, VALIDATION);
init_validation_rmse_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards, &sparse_als_predict);
}
if (load_factors_from_file){
load_matrix_market_matrix(training + "_U.mm", 0, D);
load_matrix_market_matrix(training + "_V.mm", M, D);
}
/* Run */
ALSVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, niters);
/* Output latent factor matrices in matrix-market format */
output_als_result(training);
test_predictions(&sparse_als_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
int main(int argc, const char ** argv) {
print_copyright();
//* GraphChi initialization will read the command line arguments and the configuration file. */
graphchi_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("rbm-inmemory-factors");
/* Basic arguments for RBM algorithm */
rbm_bins = get_option_int("rbm_bins", rbm_bins);
rbm_alpha = get_option_float("rbm_alpha", rbm_alpha);
rbm_beta = get_option_float("rbm_beta", rbm_beta);
rbm_mult_step_dec = get_option_float("rbm_mult_step_dec", rbm_mult_step_dec);
rbm_scaling = get_option_float("rbm_scaling", rbm_scaling);
parse_command_line_args();
parse_implicit_command_line();
mytimer.start();
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket<float>(training);
rbm_init();
if (validation != "") {
int vshards = convert_matrixmarket<EdgeDataType>(validation, 0, 0, 3, VALIDATION);
init_validation_rmse_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards, &rbm_predict);
}
/* load initial state from disk (optional) */
if (load_factors_from_file) {
load_matrix_market_matrix(training + "_U.mm", 0, 3*D);
load_matrix_market_matrix(training + "_V.mm", M, rbm_bins*(D+1));
}
print_config();
/* Run */
RBMVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, niters);
/* Output latent factor matrices in matrix-market format */
output_rbm_result(training);
test_predictions(&rbm_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
int main(int argc, const char ** argv) {
//* GraphChi initialization will read the command line arguments and the configuration file. */
graphchi_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("climf-inmemory-factors");
/* Basic arguments for application. NOTE: File will be automatically 'sharded'. */
sgd_lambda = get_option_float("sgd_lambda", 1e-3);
sgd_gamma = get_option_float("sgd_gamma", 1e-4);
sgd_step_dec = get_option_float("sgd_step_dec", 1.0);
binary_relevance_thresh = get_option_float("binary_relevance_thresh", 0);
halt_on_mrr_decrease = get_option_int("halt_on_mrr_decrease", 0);
num_ratings = get_option_int("num_ratings", 10000); //number of top predictions over which we compute actual MRR
verbose = get_option_int("verbose", 0);
debug = get_option_int("debug", 0);
parse_command_line_args();
parse_implicit_command_line();
/* Preprocess data if needed, or discover preprocess files */
bool allow_square = false;
int nshards = convert_matrixmarket<EdgeDataType>(training, 0, 0, 3, TRAINING, allow_square);
init_feature_vectors<std::vector<vertex_data> >(M+N, latent_factors_inmem, !load_factors_from_file, 0.01);
if (validation != ""){
int vshards = convert_matrixmarket<EdgeDataType>(validation, 0, 0, 3, VALIDATION);
init_mrr_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards);
}
if (load_factors_from_file)
{
load_matrix_market_matrix(training + "_U.mm", 0, D);
load_matrix_market_matrix(training + "_V.mm", M, D);
}
print_config();
/* Run */
SGDVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, niters);
/* Output latent factor matrices in matrix-market format */
output_sgd_result(training);
test_predictions(&climf_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
int main(int argc, const char ** argv) {
print_copyright();
//* GraphChi initialization will read the command line arguments and the configuration file. */
graphchi_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("sgd-inmemory-factors");
/* Basic arguments for application. NOTE: File will be automatically 'sharded'. */
sgd_lambda = get_option_float("sgd_lambda", 1e-3);
sgd_gamma = get_option_float("sgd_gamma", 1e-3);
sgd_step_dec = get_option_float("sgd_step_dec", 0.9);
parse_command_line_args();
parse_implicit_command_line();
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket<EdgeDataType>(training, NULL, 0, 0, 3, TRAINING, false);
init_feature_vectors<std::vector<vertex_data> >(M+N, latent_factors_inmem, !load_factors_from_file);
if (validation != ""){
int vshards = convert_matrixmarket<EdgeDataType>(validation, NULL, 0, 0, 3, VALIDATION, false);
init_validation_rmse_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards, &sgd_predict);
}
/* load initial state from disk (optional) */
if (load_factors_from_file){
load_matrix_market_matrix(training + "_U.mm", 0, D);
load_matrix_market_matrix(training + "_V.mm", M, D);
}
print_config();
/* Run */
SGDVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, niters);
/* Output latent factor matrices in matrix-market format */
output_sgd_result(training);
test_predictions(&sgd_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
int main(int argc, const char ** argv) {
print_copyright();
/* GraphChi initialization will read the command line
arguments and the configuration file. */
graphchi_init(argc, argv);
metrics m("nmf-inmemory-factors");
parse_command_line_args();
parse_implicit_command_line();
niters *= 2; //each NMF iteration is composed of two sub iters
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket<float>(training, 0, 0, 3, TRAINING, false);
init_feature_vectors<std::vector<vertex_data> >(M+N, latent_factors_inmem, !load_factors_from_file);
if (validation != ""){
int vshards = convert_matrixmarket<EdgeDataType>(validation, 0, 0, 3, VALIDATION, false);
if (vshards != -1)
init_validation_rmse_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards, &nmf_predict);
}
if (load_factors_from_file){
load_matrix_market_matrix(training + "_U.mm", 0, D);
load_matrix_market_matrix(training + "_V.mm", M, D);
}
sum_of_item_latent_features = zeros(D);
sum_of_user_latent_feautres = zeros(D);
/* Run */
NMFVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, niters);
/* Output latent factor matrices in matrix-market format */
output_nmf_result(training);
test_predictions(&nmf_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
int main(int argc, const char ** argv) {
print_copyright();
//* GraphChi initialization will read the command line arguments and the configuration file. */
graphchi_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("sgd-inmemory-factors");
algorithm = get_option_string("algorithm", "global_mean");
if (algorithm == "global_mean")
algo = GLOBAL_MEAN;
else if (algorithm == "user_mean")
algo = USER_MEAN;
else if (algorithm == "item_mean")
algo = ITEM_MEAN;
else logstream(LOG_FATAL)<<"Unsupported algorithm name. Should be --algorithm=XX where XX is one of [global_mean,user_mean,item_mean] for example --algorithm=global_mean" << std::endl;
parse_command_line_args();
mytimer.start();
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket<float>(training, NULL, 0, 0, 3, TRAINING, false);
init_feature_vectors<std::vector<vertex_data> >(M+N, latent_factors_inmem, false);
rmse_vec = zeros(number_of_omp_threads());
print_config();
/* Run */
BaselineVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, 1);
if (algo == USER_MEAN || algo == ITEM_MEAN)
output_baseline_result(training);
test_predictions(&baseline_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
/**
* Called after an iteration has finished.
*/
void after_iteration(int iteration, graphchi_context &gcontext) {
if (iteration == pmf_burn_in){
printf("Finished burn-in period. starting to aggregate samples\n");
}
if (pmf_additional_output && iiter >= pmf_burn_in){
char buf[256];
sprintf(buf, "%s-%d", training.c_str(), iiter-pmf_burn_in);
output_pmf_result(buf);
}
double res = training_rmse(iteration, gcontext);
sample_hyperpriors(res);
rmse_index = 0;
rmse_type = VALIDATION;
validation_rmse(&pmf_predict, gcontext, 3, &validation_avgprod, pmf_burn_in);
if (iteration >= pmf_burn_in){
rmse_index = 0;
rmse_type = TEST;
test_predictions(&pmf_predict, &gcontext, iiter == niters-1, &test_avgprod);
}
iiter++;
}
int main(int argc, const char ** argv) {
// print_copyright();
write_copyright();
//* GraphChi initialization will read the command line arguments and the configuration file. */
graphchi_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("sgd-inmemory-factors");
/* Basic arguments for application. NOTE: File will be automatically 'sharded'. */
sgd_lambda = get_option_float("sgd_lambda", 1e-3);
sgd_gamma = get_option_float("sgd_gamma", 1e-3);
sgd_step_dec = get_option_float("sgd_step_dec", 0.9);
int file_format = get_option_int("ff", 3);
parse_command_line_args();
parse_implicit_command_line();
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket<EdgeDataType>(training, 0, 0, file_format, TRAINING, false);
init_feature_vectors<std::vector<vertex_data> >(M+N, latent_factors_inmem, !load_factors_from_file);
if (validation != ""){
int vshards = convert_matrixmarket<EdgeDataType>(validation, 0, 0, 3, VALIDATION, false);
init_validation_rmse_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards, &sgd_predict);
}
/* load initial state from disk (optional) */
if (load_factors_from_file){
load_matrix_market_matrix(training + "_U.mm", 0, D);
load_matrix_market_matrix(training + "_V.mm", M, D);
}
print_config();
/* Run */
SGDVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
timer train_timer;
engine.run(program, niters);
// std::cout << "Trn Time for file test: " << std::setw(10) << train_timer.current_time() / niters << std::endl;
std::ofstream ofs(result.c_str(), std::ofstream::out | std::ofstream::app);
ofs << D << " " << train_timer.current_time() << " ";
/* Run TopN program */
n_top = get_option_int("n_int", 10);
/*timer test_timer1;
ofs << test_timer1.current_time() << " ";*/
//run_general_topn_program(pengine, &latent_factors_inmem, &sgd_predict);
timer index_timer;
kd_Node* mroot = init_kdtree(&latent_factors_inmem);
ofs << index_timer.current_time() << " ";
timer test_timer;
/* construct kd tree index */
// ofs << "constructing index: " << test_timer.current_time() << " ";
run_kd_topn_program(pengine, &latent_factors_inmem, mroot);
// std::coua << "Tst Time: " << std::setw(10) << test_timer.current_time() << std::endl;
ofs << test_timer.current_time() << std::endl;
ofs.close();
/* Output latent factor matrices in matrix-market format */
output_sgd_result(training);
test_predictions(&sgd_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
int main(int argc, const char ** argv) {
print_copyright();
//* GraphChi initialization will read the command line arguments and the configuration file. */
graphchi_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("svdpp-inmemory-factors");
svdpp.step_dec = get_option_float("svdpp_step_dec", 0.9);
svdpp.itmBiasStep = get_option_float("svdpp_item_bias_step", 1e-3);
svdpp.itmBiasReg = get_option_float("svdpp_item_bias_reg", 1e-3);
svdpp.usrBiasStep = get_option_float("svdpp_user_bias_step", 1e-3);
svdpp.usrBiasReg = get_option_float("svdpp_user_bias_reg", 1e-3);
svdpp.usrFctrStep = get_option_float("svdpp_user_factor_step", 1e-3);
svdpp.usrFctrReg = get_option_float("svdpp_user_factor_reg", 1e-3);
svdpp.itmFctrReg = get_option_float("svdpp_item_factor_reg", 1e-3);
svdpp.itmFctrStep = get_option_float("svdpp_item_factor_step", 1e-3);
svdpp.itmFctr2Reg = get_option_float("svdpp_item_factor2_reg", 1e-3);
svdpp.itmFctr2Step = get_option_float("svdpp_item_factor2_step", 1e-3);
parse_command_line_args();
parse_implicit_command_line();
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket<EdgeDataType>(training, 0, 0, 3, TRAINING, false);
if (validation != ""){
int vshards = convert_matrixmarket<EdgeDataType>(validation, 0, 0, 3, VALIDATION, false);
init_validation_rmse_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards, &svdpp_predict);
}
svdpp_init();
if (load_factors_from_file){
load_matrix_market_matrix(training + "_U.mm", 0, 2*D);
load_matrix_market_matrix(training + "_V.mm", M, D);
vec user_bias = load_matrix_market_vector(training +"_U_bias.mm", false, true);
assert(user_bias.size() == M);
vec item_bias = load_matrix_market_vector(training +"_V_bias.mm", false, true);
assert(item_bias.size() == N);
for (uint i=0; i<M+N; i++){
latent_factors_inmem[i].bias = ((i<M)?user_bias[i] : item_bias[i-M]);
}
vec gm = load_matrix_market_vector(training + "_global_mean.mm", false, true);
globalMean = gm[0];
}
/* Run */
SVDPPVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, niters);
/* Output latent factor matrices in matrix-market format */
output_svdpp_result(training);
test_predictions(&svdpp_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
int main(int argc, const char ** argv) {
print_copyright();
/* GraphChi initialization will read the command line
arguments and the configuration file. */
graphchi_init(argc, argv);
/* Metrics object for keeping track of performance counters
and other information. Currently required. */
metrics m("bsvd_coor-inmemory-factors");
/* Basic arguments for application. NOTE: File will be automatically 'sharded'. */
alpha = get_option_float("alpha", 1.0);
lambda = get_option_float("lambda", 1.0);
parse_command_line_args();
parse_implicit_command_line();
/* Preprocess data if needed, or discover preprocess files */
int nshards = convert_matrixmarket<EdgeDataType>(training, 0, 0, 3, TRAINING, false);
// initialize features vectors
std::string initType;
switch (init_features_type) {
case 1: // bounded random
// randomly initialize feature vectors so that rmin < rate < rmax
initType = "bounded-random";
init_random_bounded<std::vector<vertex_data> >(latent_factors_inmem, !load_factors_from_file);
break;
case 2: // baseline
initType = "baseline";
init_baseline<std::vector<vertex_data> >(latent_factors_inmem);
load_matrix_market_matrix(training + "-baseline_P.mm", 0, D);
load_matrix_market_matrix(training + "-baseline_Q.mm", M, D);
break;
case 3: // random
initType = "random";
init_feature_vectors<std::vector<vertex_data> >(M + N, latent_factors_inmem, !load_factors_from_file);
break;
default: // random
initType = "random";
init_feature_vectors<std::vector<vertex_data> >(M + N, latent_factors_inmem, !load_factors_from_file);
}
if (validation != "") {
int vshards = convert_matrixmarket<EdgeDataType>(validation, 0, 0, 3, VALIDATION, false);
init_validation_rmse_engine<VertexDataType, EdgeDataType>(pvalidation_engine, vshards, &bsvd_predict);
}
/* load initial state from disk (optional) */
if (load_factors_from_file) {
load_matrix_market_matrix(training + "_U.mm", 0, D);
load_matrix_market_matrix(training + "_V.mm", M, D);
}
/* Run */
ALSVerticesInMemProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, false, m);
set_engine_flags(engine);
pengine = &engine;
engine.run(program, niters);
/* Output latent factor matrices in matrix-market format */
output_als_result(training);
test_predictions(&bsvd_predict);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
return 0;
}
