void test_sparse_map_gibbs_first_order_interactions(void) {
int n_features = 10;
int n_samples = 100;
int k = 0;
TestFixture_T *data = makeTestFixture(124, n_samples, n_features, k);
ffm_vector *y_pred = ffm_vector_calloc(n_samples);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter = 200, .init_sigma = 0.1, .SOLVER = SOLVER_MCMC};
sparse_fit(coef, data->X, data->X, data->y, y_pred, param);
g_assert_cmpfloat(ffm_r2_score(data->y, y_pred), >, .99);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data, NULL);
}
void test_train_test_data(void) {
// test if training and test data a propertly handeled
// no check of prediction quality
int n_features = 10;
int n_samples_train = 100;
int n_samples_test = 30;
int k = 3;
TestFixture_T *data_train =
makeTestFixture(124, n_samples_train, n_features, k);
TestFixture_T *data_test =
makeTestFixture(124, n_samples_test, n_features, k);
ffm_vector *y_pred = ffm_vector_calloc(n_samples_test);
// gibts
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter = 200, .init_sigma = 0.1, .SOLVER = SOLVER_MCMC};
sparse_fit(coef, data_train->X, data_test->X, data_train->y, y_pred, param);
free_ffm_coef(coef);
// als
coef = alloc_fm_coef(n_features, k, false);
ffm_param param_als = {
.n_iter = 200, .init_sigma = 0.1, .SOLVER = SOLVER_ALS};
sparse_fit(coef, data_train->X, data_test->X, data_train->y, y_pred,
param_als);
sparse_predict(coef, data_test->X, y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data_train, NULL);
TestFixtureDestructor(data_test, NULL);
}
void test_sparse_map_gibbs_second_interactions(void) {
int n_features = 10;
int n_samples = 1000;
int k = 2;
double init_sigma = 0.1;
TestFixture_T *data = makeTestFixture(124, n_samples, n_features, k);
ffm_vector *y_pred = ffm_vector_calloc(n_samples);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {
.n_iter = 5, .init_sigma = init_sigma, .SOLVER = SOLVER_MCMC};
sparse_fit(coef, data->X, data->X, data->y, y_pred, param);
double score_5_samples = ffm_r2_score(data->y, y_pred);
free_ffm_coef(coef);
ffm_vector_set_all(y_pred, 0);
coef = alloc_fm_coef(n_features, 0, false);
ffm_param param_50 = {
.n_iter = 50, .init_sigma = init_sigma, .SOLVER = SOLVER_MCMC};
sparse_fit(coef, data->X, data->X, data->y, y_pred, param_50);
double score_50_samples_first_order = ffm_r2_score(data->y, y_pred);
free_ffm_coef(coef);
ffm_vector_set_all(y_pred, 0);
coef = alloc_fm_coef(n_features, k + 5, false);
sparse_fit(coef, data->X, data->X, data->y, y_pred, param_50);
double score_50_samples = ffm_r2_score(data->y, y_pred);
g_assert_cmpfloat(score_50_samples, >, score_50_samples_first_order);
g_assert_cmpfloat(score_50_samples, >, score_5_samples);
g_assert_cmpfloat(score_50_samples, >, .72);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data, NULL);
}
void test_sparse_als_classification(void) {
int n_features = 10;
int n_samples = 100;
int k = 2;
double init_sigma = 0.01;
TestFixture_T *data = makeTestFixture(124, n_samples, n_features, k);
// map to classification problem
ffm_vector_make_labels(data->y);
ffm_vector *y_pred = ffm_vector_calloc(n_samples);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter = 50,
.init_sigma = init_sigma,
.SOLVER = SOLVER_ALS,
.TASK = TASK_CLASSIFICATION};
param.init_lambda_w = 5.5;
param.init_lambda_V = 5.5;
sparse_fit(coef, data->X, NULL, data->y, NULL, param);
sparse_predict(coef, data->X, y_pred);
ffm_vector_normal_cdf(y_pred);
g_assert_cmpfloat(ffm_vector_accuracy(data->y, y_pred), >=, .8);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data, NULL);
}
void test_sparse_als_classification_path(void) {
int n_features = 10;
int n_samples = 200;
int k = 4;
double init_sigma = 0.1;
TestFixture_T *data = makeTestFixture(124, n_samples, n_features, k);
// map to classification problem
ffm_vector_make_labels(data->y);
ffm_vector *y_pred = ffm_vector_calloc(n_samples);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter = 0,
.init_sigma = init_sigma,
.SOLVER = SOLVER_ALS,
.TASK = TASK_CLASSIFICATION};
param.init_lambda_w = 5.5;
param.init_lambda_V = 5.5;
double acc = 0;
// objective does not decline strigtly monotonic because of latend target
// but should still decrease on average (at least till convergence)
for (int i = 1; i < 9; i = i * 2) {
param.n_iter = i;
sparse_fit(coef, data->X, NULL, data->y, NULL, param);
sparse_predict(coef, data->X, y_pred);
ffm_vector_normal_cdf(y_pred);
double tmp_acc = ffm_vector_accuracy(data->y, y_pred);
// training error should (almost) always decrease
// printf("iter %d, last acc %f\n", i, acc);
g_assert_cmpfloat(tmp_acc, >=, acc);
acc = tmp_acc;
}
ffm_vector_free(y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data, NULL);
}
void test_sparse_mcmc_classification(void) {
int n_features = 10;
int n_samples = 100;
int k = 2;
double init_sigma = 0.1;
TestFixture_T *data = makeTestFixture(124, n_samples, n_features, k);
// map to classification problem
ffm_vector_make_labels(data->y);
ffm_vector *y_pred = ffm_vector_calloc(n_samples);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter = 50,
.init_sigma = init_sigma,
.SOLVER = SOLVER_MCMC,
.TASK = TASK_CLASSIFICATION};
param.init_lambda_w = 5.5;
param.init_lambda_V = 5.5;
sparse_fit(coef, data->X, data->X, data->y, y_pred, param);
sparse_predict(coef, data->X, y_pred);
g_assert_cmpfloat(ffm_vector_accuracy(data->y, y_pred), >=, .84);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data, NULL);
}
void test_numerical_stability(void) {
int n_features = 10;
int n_samples = 10000;
int k = 2;
TestFixture_T *data = makeTestFixture(15, n_samples, n_features, k);
ffm_vector *y_pred = ffm_vector_calloc(n_samples);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter = 7, .init_sigma = 0.01, .SOLVER = SOLVER_ALS};
param.init_lambda_w = 400;
param.init_lambda_V = 400;
sparse_fit(coef, data->X, data->X, data->y, y_pred, param);
sparse_predict(coef, data->X, y_pred);
double score_als = ffm_r2_score(data->y, y_pred);
g_assert_cmpfloat(score_als, >, .98);
free_ffm_coef(coef);
ffm_vector_set_all(y_pred, 0);
coef = alloc_fm_coef(n_features, k, false);
ffm_param param_mcmc = {
.n_iter = 50, .init_sigma = 0.01, .SOLVER = SOLVER_MCMC};
sparse_fit(coef, data->X, data->X, data->y, y_pred, param_mcmc);
double score_gibbs = ffm_r2_score(data->y, y_pred);
g_assert_cmpfloat(score_gibbs, >, .99);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data, NULL);
}
void test_map_update_target(void) {
double pred[] = {0.5, 0.2, -0.2, -0.5, -0.1, 0.8};
double true_[] = {1, 1, -1, -1, 1, -1};
double z[] = {0.509160434, 0.6750731798, -0.6750731798,
-0.509160434, 0.8626174715, -1.3674022692};
ffm_vector y_pred = {.data = pred, .size = 6};
ffm_vector y_true = {.data = true_, .size = 6};
ffm_vector *z_target = ffm_vector_alloc(6);
map_update_target(&y_pred, z_target, &y_true);
for (int i = 0; i < 6; i++)
g_assert_cmpfloat(fabs(z_target->data[i] - z[i]), <=, 1e-9);
ffm_vector_free(z_target);
}
void test_als_warm_start(TestFixture_T *pFix, gconstpointer pg) {
int n_features = pFix->X->n;
int n_samples = pFix->X->m;
int k = 4;
ffm_vector *y_10_iter = ffm_vector_calloc(n_samples);
ffm_vector *y_15_iter = ffm_vector_calloc(n_samples);
ffm_vector *y_5_plus_5_iter = ffm_vector_calloc(n_samples);
ffm_param param = {.warm_start = false,
.init_sigma = 0.1,
.SOLVER = SOLVER_ALS,
.TASK = TASK_REGRESSION,
.rng_seed = 123};
param.n_iter = 10;
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
sparse_predict(coef, pFix->X, y_10_iter);
param.n_iter = 15;
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
sparse_predict(coef, pFix->X, y_15_iter);
param.n_iter = 5;
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
param.warm_start = true;
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
sparse_predict(coef, pFix->X, y_5_plus_5_iter);
// check that the results are equal
double mse = ffm_vector_mean_squared_error(y_10_iter, y_5_plus_5_iter);
double mse_diff = ffm_vector_mean_squared_error(y_15_iter, y_5_plus_5_iter);
g_assert_cmpfloat(mse, <=, 1e-8);
g_assert_cmpfloat(mse, <, mse_diff);
free_ffm_coef(coef);
ffm_vector_free_all(y_10_iter, y_5_plus_5_iter);
}
void test_mcmc_warm_start(TestFixture_T *pFix, gconstpointer pg) {
int n_features = pFix->X->n;
int n_samples = pFix->X->m;
int k = 4;
ffm_vector *y_10_iter = ffm_vector_calloc(n_samples);
ffm_vector *y_15_iter = ffm_vector_calloc(n_samples);
ffm_vector *y_5_plus_5_iter = ffm_vector_calloc(n_samples);
ffm_param param = {.warm_start = false,
.init_sigma = 0.1,
.SOLVER = SOLVER_MCMC,
.TASK = TASK_REGRESSION,
.rng_seed = 125};
param.n_iter = 100;
// printf("n_iter %d\n", param.n_iter);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
sparse_fit(coef, pFix->X, pFix->X, pFix->y, y_10_iter, param);
param.n_iter = 150;
sparse_fit(coef, pFix->X, pFix->X, pFix->y, y_15_iter, param);
param.n_iter = 50;
sparse_fit(coef, pFix->X, pFix->X, pFix->y, y_5_plus_5_iter, param);
param.warm_start = true;
param.iter_count = param.n_iter;
param.n_iter += 50; // add more iterations
sparse_fit(coef, pFix->X, pFix->X, pFix->y, y_5_plus_5_iter, param);
// check that the results are equal
// double mse10 = ffm_vector_mean_squared_error(pFix->y, y_5_plus_5_iter);
double mse10_55 = ffm_vector_mean_squared_error(y_10_iter, y_5_plus_5_iter);
double mse15_55 = ffm_vector_mean_squared_error(y_15_iter, y_5_plus_5_iter);
g_assert_cmpfloat(mse10_55, <, mse15_55);
free_ffm_coef(coef);
ffm_vector_free_all(y_10_iter, y_5_plus_5_iter);
}
int main(int argc, char **argv) {
/*
feenableexcept(FE_INVALID |
FE_DIVBYZERO |
FE_OVERFLOW |
FE_UNDERFLOW);
*/
g_test_init(&argc, &argv, NULL);
TestFixture_T Fixture;
g_test_add("/als/update second-order error", TestFixture_T, &Fixture,
TestFixtureContructorLong, test_update_second_order_error,
TestFixtureDestructor);
g_test_add("/als/eval second-order term", TestFixture_T, &Fixture,
TestFixtureContructorLong, test_eval_second_order_term,
TestFixtureDestructor);
g_test_add("/als/update v_ij", TestFixture_T, &Fixture,
TestFixtureContructorLong, test_sparse_update_v_ij,
TestFixtureDestructor);
g_test_add("/general/predict", TestFixture_T, &Fixture,
TestFixtureContructorLong, test_sparse_predict,
TestFixtureDestructor);
g_test_add("/general/row_predict", TestFixture_T, &Fixture,
TestFixtureContructorLong, test_row_predict,
TestFixtureDestructor);
g_test_add("/general/col_predict", TestFixture_T, &Fixture,
TestFixtureContructorLong, test_col_predict,
TestFixtureDestructor);
g_test_add("/als/zero order only", TestFixture_T, &Fixture,
TestFixtureContructorSimple, test_sparse_als_zero_order_only,
TestFixtureDestructor);
g_test_add("/als/first order only", TestFixture_T, &Fixture,
TestFixtureContructorSimple, test_sparse_als_first_order_only,
TestFixtureDestructor);
g_test_add("/als/second order only", TestFixture_T, &Fixture,
TestFixtureContructorSimple, test_sparse_als_second_order_only,
TestFixtureDestructor);
g_test_add("/als/all interactions", TestFixture_T, &Fixture,
TestFixtureContructorSimple, test_sparse_als_all_interactions,
TestFixtureDestructor);
g_test_add("/als/first order", TestFixture_T, &Fixture,
TestFixtureContructorLong,
test_sparse_als_first_order_interactions, TestFixtureDestructor);
g_test_add("/als/second order", TestFixture_T, &Fixture,
TestFixtureContructorLong, test_sparse_als_second_interactions,
TestFixtureDestructor);
g_test_add("/mcmc/second order", TestFixture_T, &Fixture,
TestFixtureContructorLong, test_sparse_mcmc_second_interactions,
TestFixtureDestructor);
g_test_add("/mcmc/second order classification", TestFixture_T, &Fixture,
TestFixtureContructorLong,
test_sparse_mcmc_second_interactions_classification,
TestFixtureDestructor);
g_test_add("/general/train test different size", TestFixture_T, &Fixture,
TestFixtureContructorLong, test_train_test_of_different_size,
TestFixtureDestructor);
g_test_add_func("/als/generated data", test_sparse_als_generated_data);
g_test_add_func("/mcmc/MAP gibbs first order",
test_sparse_map_gibbs_first_order_interactions);
g_test_add_func("/mcmc/hyperparameter sampling", test_hyerparameter_sampling);
g_test_add_func("/mcmc/MAP gibbs second order",
test_sparse_map_gibbs_second_interactions);
g_test_add_func("/general/numerical stability", test_numerical_stability);
g_test_add_func("/mcmc/map update target", test_map_update_target);
g_test_add_func("/als/classification", test_sparse_als_classification);
g_test_add_func("/als/classification path",
test_sparse_als_classification_path);
g_test_add_func("/mcmc/classification", test_sparse_mcmc_classification);
g_test_add("/als/warm_start", TestFixture_T, &Fixture,
TestFixtureContructorSimple, test_als_warm_start,
TestFixtureDestructor);
g_test_add("/mcmc/warm_start", TestFixture_T, &Fixture,
TestFixtureContructorSimple, test_mcmc_warm_start,
TestFixtureDestructor);
return g_test_run();
}
int
main (int argc, char **argv)
{
feenableexcept(FE_INVALID |
FE_DIVBYZERO |
FE_OVERFLOW |
FE_UNDERFLOW);
struct arguments arguments;
/* Default values. */
arguments.silent = 0;
arguments.verbose = 0;
// file paths
arguments.test_file = NULL;
arguments.train_file = NULL;
arguments.test_predict_file= NULL;
arguments.train_pairs = NULL;
// fm default parameters
arguments.k = 8;
arguments.n_iter = 50;
arguments.init_var = 0.01;
arguments.step_size = 0.01;
arguments.l2_reg = 1;
arguments.l2_reg_w = 0;
arguments.l2_reg_V = 0;
arguments.solver = "mcmc";
arguments.task = "regression";
arguments.rng_seed = time(NULL);
int arg_count = 2;
arguments.arg_count = &arg_count;
/* Parse our arguments; every option seen by parse_opt will
be reflected in arguments. */
argp_parse (&argp, argc, argv, 0, 0, &arguments);
ffm_param param = {.n_iter = arguments.n_iter,
.init_sigma = arguments.init_var,
.k = arguments.k,
.stepsize = arguments.step_size,
.rng_seed = arguments.rng_seed};
// parse solver
if (strcmp(arguments.solver,"mcmc") == 0)
param.SOLVER = SOLVER_MCMC;
else if(strcmp(arguments.solver,"als") == 0)
param.SOLVER = SOLVER_ALS;
else if(strcmp(arguments.solver,"sgd") == 0)
param.SOLVER = SOLVER_SGD;
else assert(0 && "unknown solver");
// parse task
if (strcmp(arguments.task,"regression") == 0)
param.TASK = TASK_REGRESSION;
else if(strcmp(arguments.task,"classification") == 0)
param.TASK = TASK_CLASSIFICATION;
else if(strcmp(arguments.task,"ranking") == 0)
param.TASK = TASK_RANKING;
else assert(0 && "unknown task");
printf ("TRAIN_FILE = %s\nTEST_FILE = %s\n"
"VERBOSE = %s\nSILENT = %s\n",
arguments.args[0], arguments.args[1],
arguments.verbose ? "yes" : "no",
arguments.silent ? "yes" : "no");
printf ("task=%s", arguments.task);
printf (", init-var=%f", param.init_sigma);
printf (", n-iter=%i", param.n_iter);
if (param.TASK == TASK_RANKING)
printf (", step-size=%f", param.stepsize);
printf (", solver=%s", arguments.solver);
printf (", k=%i", param.k);
// default if no l2_reg_w specified
param.init_lambda_w = arguments.l2_reg;
param.init_lambda_V = arguments.l2_reg;
if (arguments.l2_reg_w != 0.0)
param.init_lambda_w = arguments.l2_reg_w;
if (arguments.l2_reg_V != 0.0)
param.init_lambda_V = arguments.l2_reg_V;
if (strcmp(arguments.solver,"mcmc") != 0)
{
printf (", l2-reg-w=%f", param.init_lambda_w);
if (arguments.k > 0)
printf (", l2-reg-V=%f", param.init_lambda_V);
printf("\n");
}
printf("\nload data\n");
fm_data train_data = read_svm_light_file(arguments.args[0]);
fm_data test_data = read_svm_light_file(arguments.args[1]);
int n_features = train_data.X->n;
ffm_vector *y_test_predict = ffm_vector_calloc(test_data.y->size);
ffm_coef *coef = alloc_fm_coef(n_features, arguments.k, false);
printf("fit model\n");
if (param.TASK == TASK_RANKING)
{
assert(arguments.train_pairs != NULL && "Ranking requires the option '--train-pairs'");
ffm_matrix * train_pairs = ffm_matrix_from_file(arguments.train_pairs);
cs *X_t = cs_transpose (train_data.X, 1);
cs_spfree(train_data.X);
train_data.X = X_t;
ffm_fit_sgd_bpr(coef, train_data.X, train_pairs, param);
//printf("c%", arguments.train_pairs);
}
else
sparse_fit(coef, train_data.X, test_data.X, train_data.y, y_test_predict,
param);
// the predictions are calculated during the training phase for mcmc
if (param.SOLVER != SOLVER_MCMC){
sparse_predict(coef, test_data.X, y_test_predict);
if (param.TASK == TASK_CLASSIFICATION)
ffm_vector_normal_cdf(y_test_predict);
}
// save predictions
if (arguments.test_predict_file){
FILE *f = fopen(arguments.test_predict_file, "w");
for (int i=0; i< y_test_predict->size; i++)
fprintf(f, "%f\n", y_test_predict->data[i]);
fclose(f);
}
if (param.TASK == TASK_REGRESSION)
printf("\nr2 score: %f \n", ffm_r2_score(test_data.y, y_test_predict));
if (param.TASK == TASK_CLASSIFICATION)
printf("\nacc score: %f \n", ffm_vector_accuracy(test_data.y, y_test_predict));
/*
printf("calculate kendall tau\n");
if (param.TASK == TASK_RANKING)
{
ffm_vector * true_order = ffm_vector_get_order(test_data.y);
ffm_vector * pred_order = ffm_vector_get_order(y_test_predict);
double kendall_tau = \
ffm_vector_kendall_tau(true_order, pred_order);
printf("\nkendall tau: %f \n", kendall_tau);
}
*/
exit (0);
}
