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("item-cf2");
/* Basic arguments for application */
min_allowed_intersection = get_option_int("min_allowed_intersection", min_allowed_intersection);
distance_metric = get_option_int("distance", JACCARD_WEIGHT);
if (distance_metric != JACCARD_WEIGHT)
logstream(LOG_FATAL)<<"--distance_metrix=XX should be one of:9= JACCARD_WEIGHT" << std::endl;
debug = get_option_int("debug", 0);
parse_command_line_args();
//if (distance_metric != JACKARD && distance_metric != AA && distance_metric != RA)
// logstream(LOG_FATAL)<<"Wrong distance metric. --distance_metric=XX, where XX should be either 0) JACKARD, 1) AA, 2) RA" << std::endl;
mytimer.start();
int nshards = convert_matrixmarket<EdgeDataType>(training, 0, 0, 3, TRAINING, true);
assert(M > 0 && N > 0);
//initialize data structure which saves a subset of the items (pivots) in memory
adjcontainer = new adjlist_container();
/* Run */
ItemDistanceProgram program;
CE_Graph_engine<VertexDataType, EdgeDataType> engine(training, nshards, true, m);
set_engine_flags(engine);
//open output files as the number of operating threads
out_files.resize(number_of_omp_threads());
for (uint i=0; i< out_files.size(); i++){
char buf[256];
sprintf(buf, "%s.out%d", training.c_str(), i);
out_files[i] = open_file(buf, "w");
}
//run the program
engine.run(program, niters);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
std::cout<<"Total item pairs compared: " << item_pairs_compared << " total written to file: " << written_pairs << std::endl;
for (uint i=0; i< out_files.size(); i++)
fclose(out_files[i]);
std::cout<<"Created output files with the format: " << training << ".outXX, where XX is the output thread number" << std::endl;
return 0;
}
void init_validation_rmse_engine(graphchi_engine<VertexDataType,EdgeDataType> *& pvalidation_engine, int nshards,float (*prediction_func)(const vertex_data & user, const vertex_data & movie, float rating, double & prediction, void * extra), bool _time_weighting, bool _time_nodes, int _matlab_time_offset){
metrics * m = new metrics("validation_rmse_engine");
graphchi_engine<VertexDataType, EdgeDataType> * engine = new graphchi_engine<VertexDataType, EdgeDataType>(validation, nshards, false, *m);
set_engine_flags(*engine);
pvalidation_engine = engine;
time_weighting = _time_weighting;
time_nodes = _time_nodes;
matlab_time_offset = _matlab_time_offset;
pprediction_func = prediction_func;
num_threads = number_of_omp_threads();
}
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;
}
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("item-cf");
/* Basic arguments for application */
min_allowed_intersection = get_option_int("min_allowed_intersection", min_allowed_intersection);
distance_metric = get_option_int("distance", JACCARD);
asym_cosine_alpha = get_option_float("asym_cosine_alpha", 0.5);
debug = get_option_int("debug", debug);
if (distance_metric != JACCARD && distance_metric != AA && distance_metric != RA && distance_metric != ASYM_COSINE && distance_metric != PROB)
logstream(LOG_FATAL)<<"Wrong distance metric. --distance_metric=XX, where XX should be either 0= JACCARD, 1= AA, 2= RA, 3= ASYM_COSINE, 4 = PROB" << std::endl;
parse_command_line_args();
mytimer.start();
int nshards = convert_matrixmarket<EdgeDataType>(training, 0, 0, 3, TRAINING, false);
if (nshards != 1)
logstream(LOG_FATAL)<<"This application currently supports only 1 shard" << std::endl;
K = get_option_int("K", K);
if (K <= 0)
logstream(LOG_FATAL)<<"Please specify the number of ratings to generate for each user using the --K command" << std::endl;
logstream(LOG_INFO) << "M = " << M << std::endl;
assert(M > 0 && N > 0);
//initialize data structure which saves a subset of the items (pivots) in memory
adjcontainer = new adjlist_container();
//array for marking which items are conected to the pivot items via users.
relevant_items = new bool[N];
//store node degrees in an array to be used for AA distance metric
if (distance_metric == AA || distance_metric == RA || distance_metric == PROB)
latent_factors_inmem.resize(M);
if (distance_metric == PROB)
prob_sim_normalization_constant = (double)L / (double)(M*N-L);
/* Run */
ItemDistanceProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, 1, true, m);
set_engine_flags(engine);
engine.set_maxwindow(M+N+1);
//open output files as the number of operating threads
out_files.resize(number_of_omp_threads());
for (uint i=0; i< out_files.size(); i++){
char buf[256];
sprintf(buf, "%s.out%d", training.c_str(), i);
out_files[i] = open_file(buf, "w");
}
//run the program
engine.run(program, niters);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
std::cout<<"Total item pairs compared: " << item_pairs_compared << " total written to file: " << sum(written_pairs) << " pairs with zero distance: " << zero_dist << std::endl;
if (not_enough)
logstream(LOG_WARNING)<<"Items that did not have enough similar items: " << not_enough << std::endl;
for (uint i=0; i< out_files.size(); i++)
fclose(out_files[i]);
delete[] relevant_items;
/* write the matrix market info header to be used later */
FILE * pmm = fopen((training + "-topk:info").c_str(), "w");
if (pmm == NULL)
logstream(LOG_FATAL)<<"Failed to open " << training << ":info to file" << std::endl;
fprintf(pmm, "%%%%MatrixMarket matrix coordinate real general\n");
fprintf(pmm, "%u %u %u\n", N, N, (unsigned int)sum(written_pairs));
fclose(pmm);
/* sort output files */
logstream(LOG_INFO)<<"Going to sort and merge output files " << std::endl;
std::string dname= dirname(strdup(argv[0]));
system(("bash " + dname + "/topk.sh " + std::string(basename(strdup(training.c_str())))).c_str());
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("itemsim2rating2");
/* Basic arguments for application */
min_allowed_intersection = get_option_int("min_allowed_intersection", min_allowed_intersection);
debug = get_option_int("debug", 0);
parse_command_line_args();
std::string similarity = get_option_string("similarity", "");
if (similarity == "")
logstream(LOG_FATAL)<<"Missing similarity input file. Please specify one using the --similarity=filename command line flag" << std::endl;
undirected = get_option_int("undirected", 0);
mytimer.start();
int nshards = convert_matrixmarket_and_item_similarity<edge_data>(training, similarity, 3, °rees);
assert(M > 0 && N > 0);
prob_sim_normalization_constant = (double)L / (double)(M*N-L);
//initialize data structure which saves a subset of the items (pivots) in memory
adjcontainer = new adjlist_container();
//array for marking which items are conected to the pivot items via users.
relevant_items = new bool[N];
/* Run */
ItemDistanceProgram program;
graphchi_engine<VertexDataType, edge_data> engine(training, nshards, true, m);
set_engine_flags(engine);
//open output files as the number of operating threads
out_files.resize(number_of_omp_threads());
for (uint i=0; i< out_files.size(); i++){
char buf[256];
sprintf(buf, "%s-rec.out%d", training.c_str(), i);
out_files[i] = open_file(buf, "w");
}
K = get_option_int("K");
assert(K > 0);
//run the program
engine.run(program, niters);
for (uint i=0; i< out_files.size(); i++)
fclose(out_files[i]);
delete[] relevant_items;
/* Report execution metrics */
if (!quiet)
metrics_report(m);
std::cout<<"Total item pairs compared: " << item_pairs_compared << " total written to file: " << sum(written_pairs) << std::endl;
logstream(LOG_INFO)<<"Going to sort and merge output files " << std::endl;
std::string dname= dirname(strdup(argv[0]));
system(("bash " + dname + "/topk.sh " + std::string(basename(strdup((training+"-rec").c_str())))).c_str());
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("item-cf");
/* Basic arguments for application */
min_allowed_intersection = get_option_int("min_allowed_intersection", min_allowed_intersection);
distance_metric = get_option_int("distance", JACCARD);
asym_cosine_alpha = get_option_float("asym_cosine_alpha", 0.5);
if (distance_metric != JACCARD && distance_metric != AA && distance_metric != RA && distance_metric != ASYM_COSINE)
logstream(LOG_FATAL)<<"Wrong distance metric. --distance_metric=XX, where XX should be either 0) JACCARD, 1) AA, 2) RA, 3) ASYM_COSINE" << std::endl;
parse_command_line_args();
mytimer.start();
int nshards = convert_matrixmarket<EdgeDataType>(training/*, orderByDegreePreprocessor*/);
if (nshards != 1)
logstream(LOG_FATAL)<<"This application currently supports only 1 shard" << std::endl;
K = get_option_int("K", K);
if (K <= 0)
logstream(LOG_FATAL)<<"Please specify the number of ratings to generate for each user using the --K command" << std::endl;
assert(M > 0 && N > 0);
//initialize data structure which saves a subset of the items (pivots) in memory
adjcontainer = new adjlist_container();
//array for marking which items are conected to the pivot items via users.
relevant_items = new bool[N];
//store node degrees in an array to be used for AA distance metric
if (distance_metric == AA || distance_metric == RA)
latent_factors_inmem.resize(M);
/* Run */
ItemDistanceProgram program;
graphchi_engine<VertexDataType, EdgeDataType> engine(training, nshards, true, m);
set_engine_flags(engine);
engine.set_maxwindow(M+N+1);
//open output files as the number of operating threads
out_files.resize(number_of_omp_threads());
for (uint i=0; i< out_files.size(); i++){
char buf[256];
sprintf(buf, "%s.out%d", training.c_str(), i);
out_files[i] = open_file(buf, "w");
}
//run the program
engine.run(program, niters);
/* Report execution metrics */
if (!quiet)
metrics_report(m);
std::cout<<"Total item pairs compared: " << item_pairs_compared << " total written to file: " << sum(written_pairs) << " pairs with zero distance: " << zero_dist << std::endl;
if (not_enough)
logstream(LOG_WARNING)<<"Items that did not have enough similar items: " << not_enough << std::endl;
for (uint i=0; i< out_files.size(); i++){
fflush(out_files[i]);
fclose(out_files[i]);
}
std::cout<<"Created " << number_of_omp_threads() << " output files with the format: " << training << ".outXX, where XX is the output thread number" << std::endl;
delete[] relevant_items;
return 0;
}
