void test_sparse_als_zero_order_only(TestFixture_T *pFix, gconstpointer pg) {
int n_features = pFix->X->n;
int k = 0;
ffm_param param = {.n_iter = 1,
.warm_start = true,
.ignore_w = true,
.init_sigma = 0.1,
.SOLVER = SOLVER_ALS,
.TASK = TASK_REGRESSION};
ffm_coef *coef = alloc_fm_coef(n_features, k, true);
param.init_lambda_w = 0;
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
// g_assert_cmpfloat(4466.666666, ==, coef->w_0);
g_assert_cmpfloat(fabs(4466.666666 - coef->w_0), <, 1e-6);
free_ffm_coef(coef);
}
void test_sparse_als_first_order_only(TestFixture_T *pFix, gconstpointer pg) {
int n_features = pFix->X->n;
int k = 0;
ffm_param param = {.n_iter = 1,
.warm_start = true,
.ignore_w_0 = true,
.init_sigma = 0.1,
.SOLVER = SOLVER_ALS,
.TASK = TASK_REGRESSION};
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
coef->w_0 = 0;
param.init_lambda_w = 0;
ffm_vector_set(coef->w, 0, 10);
ffm_vector_set(coef->w, 1, 20);
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
// hand calculated results 1660.57142857 -11.87755102
g_assert_cmpfloat(fabs(1660.57142857 - ffm_vector_get(coef->w, 0)), <, 1e-8);
g_assert_cmpfloat(fabs(-11.87755102 - ffm_vector_get(coef->w, 1)), <, 1e-8);
free_ffm_coef(coef);
}
void test_sparse_als_second_order_only(TestFixture_T *pFix, gconstpointer pg) {
int n_features = pFix->X->n;
int k = 1;
ffm_param param = {.n_iter = 1,
.warm_start = true,
.ignore_w_0 = true,
.ignore_w = true,
.init_sigma = 0.1,
.SOLVER = SOLVER_ALS,
.TASK = TASK_REGRESSION};
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
coef->w_0 = 0;
param.init_lambda_w = 0;
param.init_lambda_V = 0;
ffm_matrix_set(coef->V, 0, 0, 300);
ffm_matrix_set(coef->V, 0, 1, 400);
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
// hand calculated results 0.79866412 400.
g_assert_cmpfloat(fabs(0.79866412 - ffm_matrix_get(coef->V, 0, 0)), <, 1e-8);
g_assert_cmpfloat(fabs(400 - ffm_matrix_get(coef->V, 0, 1)), <, 1e-8);
free_ffm_coef(coef);
}
void test_sparse_als_all_interactions(TestFixture_T *pFix, gconstpointer pg) {
int n_features = pFix->X->n;
int k = 1;
ffm_param param = {.n_iter = 1,
.warm_start = true,
.ignore_w_0 = false,
.ignore_w = false,
.init_sigma = 0.1,
.SOLVER = SOLVER_ALS,
.TASK = TASK_REGRESSION};
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
coef->w_0 = 0;
ffm_vector_set(coef->w, 0, 10);
ffm_vector_set(coef->w, 1, 20);
ffm_matrix_set(coef->V, 0, 0, 300);
ffm_matrix_set(coef->V, 0, 1, 400);
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
// hand calculated results checked with libfm
g_assert_cmpfloat(fabs(-1755643.33333 - coef->w_0), <, 1e-5);
g_assert_cmpfloat(fabs(-191459.71428571 - ffm_vector_get(coef->w, 0)), <,
1e-6);
g_assert_cmpfloat(fabs(30791.91836735 - ffm_vector_get(coef->w, 1)), <, 1e-6);
g_assert_cmpfloat(fabs(253.89744249 - ffm_matrix_get(coef->V, 0, 0)), <,
1e-6);
g_assert_cmpfloat(fabs(400 - ffm_matrix_get(coef->V, 0, 1)), <, 1e-6);
param.n_iter = 99;
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
g_assert_cmpfloat(fabs(210911.940403 - coef->w_0), <, 1e-7);
g_assert_cmpfloat(fabs(-322970.68313639 - ffm_vector_get(coef->w, 0)), <,
1e-6);
g_assert_cmpfloat(fabs(51927.60978978 - ffm_vector_get(coef->w, 1)), <, 1e-6);
g_assert_cmpfloat(fabs(94.76612018 - ffm_matrix_get(coef->V, 0, 0)), <, 1e-6);
g_assert_cmpfloat(fabs(400 - ffm_matrix_get(coef->V, 0, 1)), <, 1e-6);
free_ffm_coef(coef);
}
void test_sparse_als_first_order_interactions(TestFixture_T *pFix,
gconstpointer pg) {
ffm_vector *y_pred = ffm_vector_calloc(5);
int n_features = pFix->X->n;
int k = 0;
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter = 500,
.init_sigma = 0.1,
.SOLVER = SOLVER_ALS,
.TASK = TASK_REGRESSION};
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
sparse_predict(coef, pFix->X, y_pred);
/* reference values from sklearn LinearRegression
y_pred: [ 321.05084746 346.6779661 -40.15254237 321.05084746
790.37288136]
coef: [ 69.6779661 152.16949153]
mse: 3134.91525424 */
g_assert_cmpfloat(fabs(321.05084746 - ffm_vector_get(y_pred, 0)), <, 1e-6);
g_assert_cmpfloat(fabs(346.6779661 - ffm_vector_get(y_pred, 1)), <, 1e-6);
g_assert_cmpfloat(fabs(-40.15254237 - ffm_vector_get(y_pred, 2)), <, 1e-6);
g_assert_cmpfloat(fabs(321.05084746 - ffm_vector_get(y_pred, 3)), <, 1e-6);
g_assert_cmpfloat(fabs(790.37288136 - ffm_vector_get(y_pred, 4)), <, 1e-6);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
}
void test_sparse_als_second_interactions(TestFixture_T *pFix,
gconstpointer pg) {
ffm_vector *y_pred = ffm_vector_calloc(5);
int n_features = pFix->X->n;
int k = 2;
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter = 1000, .init_sigma = 0.1, .SOLVER = SOLVER_ALS};
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
sparse_predict(coef, pFix->X, y_pred);
/* reference values from sklearn LinearRegression
y_pred: [ 298. 266. 29. 298. 848.]
coeff: [ 9. 2. 40.]
mse: 4.53374139449e-27 */
g_assert_cmpfloat(fabs(298 - ffm_vector_get(y_pred, 0)), <, 1e-4);
g_assert_cmpfloat(fabs(266 - ffm_vector_get(y_pred, 1)), <, 1e-4);
g_assert_cmpfloat(fabs(29 - ffm_vector_get(y_pred, 2)), <, 1e-3);
g_assert_cmpfloat(fabs(298 - ffm_vector_get(y_pred, 3)), <, 1e-4);
g_assert_cmpfloat(fabs(848.0 - ffm_vector_get(y_pred, 4)), <, 1e-4);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
}
void test_sparse_mcmc_second_interactions(TestFixture_T *pFix,
gconstpointer pg) {
int n_features = pFix->X->n;
int n_samples = pFix->X->m;
int k = 2;
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_vector *y_pred = ffm_vector_calloc(n_samples);
ffm_param param = {.n_iter = 100,
.init_sigma = 0.1,
.SOLVER = SOLVER_MCMC,
.TASK = TASK_REGRESSION,
.rng_seed = 1234};
sparse_fit(coef, pFix->X, pFix->X, pFix->y, y_pred, param);
g_assert_cmpfloat(ffm_r2_score(pFix->y, y_pred), >, .98);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
}
void test_sparse_mcmc_second_interactions_classification(TestFixture_T *pFix,
gconstpointer pg) {
int n_features = pFix->X->n;
int n_samples = pFix->X->m;
int k = 2;
ffm_vector_make_labels(pFix->y);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_vector *y_pred = ffm_vector_calloc(n_samples);
ffm_param param = {.n_iter = 10,
.init_sigma = 0.1,
.SOLVER = SOLVER_MCMC,
.TASK = TASK_CLASSIFICATION};
sparse_fit(coef, pFix->X, pFix->X, pFix->y, y_pred, param);
g_assert_cmpfloat(ffm_vector_accuracy(pFix->y, y_pred), >=, .98);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
}
void test_train_test_of_different_size(TestFixture_T *pFix, gconstpointer pg) {
int n_features = pFix->X->n;
int k = 2;
int n_samples_short = 3;
int m = n_samples_short;
int n = n_features;
cs *X = cs_spalloc(m, n, m * n, 1, 1); /* create triplet identity matrix */
cs_entry(X, 0, 0, 6);
cs_entry(X, 0, 1, 1);
cs_entry(X, 1, 0, 2);
cs_entry(X, 1, 1, 3);
cs_entry(X, 2, 0, 3);
cs *X_csc = cs_compress(X); /* A = compressed-column form of T */
cs *X_t = cs_transpose(X_csc, 1);
cs_spfree(X);
ffm_vector *y = ffm_vector_calloc(n_samples_short);
// y [ 298 266 29 298 848 ]
y->data[0] = 298;
y->data[1] = 266;
y->data[2] = 29;
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_vector *y_pred = ffm_vector_calloc(n_samples_short);
ffm_param param = {.n_iter = 20, .init_sigma = 0.01};
// test: train > test
param.SOLVER = SOLVER_ALS;
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
sparse_predict(coef, X_csc, y_pred);
param.TASK = TASK_CLASSIFICATION;
sparse_fit(coef, pFix->X, NULL, pFix->y, NULL, param);
sparse_predict(coef, X_csc, y_pred);
param.SOLVER = SOLVER_MCMC;
param.TASK = TASK_CLASSIFICATION;
sparse_fit(coef, pFix->X, X_csc, pFix->y, y_pred, param);
param.TASK = TASK_REGRESSION;
sparse_fit(coef, pFix->X, X_csc, pFix->y, y_pred, param);
// test: train < test
param.SOLVER = SOLVER_MCMC;
param.TASK = TASK_CLASSIFICATION;
sparse_fit(coef, X_csc, pFix->X, y_pred, pFix->y, param);
param.TASK = TASK_REGRESSION;
sparse_fit(coef, X_csc, pFix->X, y_pred, pFix->y, param);
param.SOLVER = SOLVER_ALS;
sparse_fit(coef, X_csc, NULL, y_pred, NULL, param);
sparse_predict(coef, pFix->X, pFix->y);
param.TASK = TASK_CLASSIFICATION;
sparse_fit(coef, X_csc, NULL, y_pred, NULL, param);
sparse_predict(coef, pFix->X, pFix->y);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
cs_spfree(X_t);
cs_spfree(X_csc);
}
void test_sparse_als_generated_data(void) {
int n_features = 10;
int n_samples = 100;
int k = 2;
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 = 50, .init_sigma = 0.01, .SOLVER = SOLVER_ALS};
param.init_lambda_w = 23.5;
param.init_lambda_V = 23.5;
sparse_fit(coef, data->X, NULL, data->y, NULL, param);
sparse_predict(coef, data->X, y_pred);
g_assert_cmpfloat(ffm_r2_score(data->y, y_pred), >, 0.85);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data, NULL);
}
void test_hyerparameter_sampling(void) {
ffm_rng *rng = ffm_rng_seed(12345);
int n_features = 20;
int n_samples = 150;
int k = 1; // don't just change k, the rank is hard coded in the test
// (ffm_vector_get(coef->lambda_V, 0);)
int n_replication = 40;
int n_draws = 1000;
ffm_vector *alpha_rep = ffm_vector_calloc(n_replication);
ffm_vector *lambda_w_rep = ffm_vector_calloc(n_replication);
ffm_vector *lambda_V_rep = ffm_vector_calloc(n_replication);
ffm_vector *mu_w_rep = ffm_vector_calloc(n_replication);
ffm_vector *mu_V_rep = ffm_vector_calloc(n_replication);
ffm_vector *err = ffm_vector_alloc(n_samples);
for (int j = 0; j < n_replication; j++) {
TestFixture_T *data = makeTestFixture(124, n_samples, n_features, k);
ffm_coef *coef = data->coef;
sparse_predict(coef, data->X, err);
ffm_vector_scale(err, -1);
ffm_vector_add(err, data->y);
// make sure that distribution is converged bevore selecting
// reference / init values
for (int l = 0; l < 50; l++) sample_hyper_parameter(coef, err, rng);
double alpha_init = coef->alpha;
double lambda_w_init = coef->lambda_w;
double lambda_V_init = ffm_vector_get(coef->lambda_V, 0);
double mu_w_init = coef->mu_w;
double mu_V_init = ffm_vector_get(coef->mu_V, 0);
double alpha_count = 0;
double lambda_w_count = 0, lambda_V_count = 0;
double mu_w_count = 0, mu_V_count = 0;
for (int l = 0; l < n_draws; l++) {
sample_hyper_parameter(coef, err, rng);
if (alpha_init > coef->alpha) alpha_count++;
if (lambda_w_init > coef->lambda_w) lambda_w_count++;
if (lambda_V_init > ffm_vector_get(coef->lambda_V, 0)) lambda_V_count++;
if (mu_w_init > coef->mu_w) mu_w_count++;
if (mu_V_init > ffm_vector_get(coef->mu_V, 0)) mu_V_count++;
}
ffm_vector_set(alpha_rep, j, alpha_count / (n_draws + 1));
ffm_vector_set(lambda_w_rep, j, lambda_w_count / (n_draws + 1));
ffm_vector_set(lambda_V_rep, j, lambda_V_count / (n_draws + 1));
ffm_vector_set(mu_w_rep, j, mu_w_count / (n_draws + 1));
ffm_vector_set(mu_V_rep, j, mu_V_count / (n_draws + 1));
TestFixtureDestructor(data, NULL);
}
double chi_alpha = 0;
for (int i = 0; i < n_replication; i++)
chi_alpha +=
ffm_pow_2(gsl_cdf_ugaussian_Qinv(ffm_vector_get(alpha_rep, i)));
g_assert_cmpfloat(gsl_ran_chisq_pdf(chi_alpha, n_replication), <, .05);
double chi_lambda_w = 0;
for (int i = 0; i < n_replication; i++)
chi_lambda_w +=
ffm_pow_2(gsl_cdf_ugaussian_Qinv(ffm_vector_get(lambda_w_rep, i)));
g_assert_cmpfloat(gsl_ran_chisq_pdf(chi_lambda_w, n_replication), <, .05);
double chi_lambda_V = 0;
for (int i = 0; i < n_replication; i++)
chi_lambda_V +=
ffm_pow_2(gsl_cdf_ugaussian_Qinv(ffm_vector_get(lambda_V_rep, i)));
g_assert_cmpfloat(gsl_ran_chisq_pdf(chi_lambda_V, n_replication), <, .05);
double chi_mu_w = 0;
for (int i = 0; i < n_replication; i++)
chi_mu_w += ffm_pow_2(gsl_cdf_ugaussian_Qinv(ffm_vector_get(mu_w_rep, i)));
g_assert_cmpfloat(gsl_ran_chisq_pdf(chi_mu_w, n_replication), <, .05);
double chi_mu_V = 0;
for (int i = 0; i < n_replication; i++)
chi_mu_V += ffm_pow_2(gsl_cdf_ugaussian_Qinv(ffm_vector_get(mu_V_rep, i)));
g_assert_cmpfloat(gsl_ran_chisq_pdf(chi_mu_V, n_replication), <, .05);
ffm_vector_free_all(alpha_rep, lambda_w_rep, lambda_V_rep, mu_w_rep, mu_V_rep,
err);
ffm_rng_free(rng);
}
void test_gradient_check_reg(TestFixture_T* pFix, gconstpointer pg){
cs *X_crs = pFix->X_t;
ffm_vector *y = pFix->y;
int test_sample_row = 0;
double y_true = ffm_vector_get(y, test_sample_row);
int n_features = pFix->coef->w->size;
double eps = 0.0001;
ffm_param param = {.n_iter=1, .stepsize=.001,
.init_sigma=.1, .k=2, .init_lambda_w=0.5, .init_lambda_V=1.5,
.warm_start=1,
.SOLVER=SOLVER_SGD, .TASK=TASK_REGRESSION, .rng_seed=44};
ffm_coef *coef_t0 = alloc_fm_coef(n_features, param.k, false);
init_ffm_coef(coef_t0, param);
ffm_coef *coef_t1 = alloc_fm_coef(n_features, param.k, false);
init_ffm_coef(coef_t1, param);
ffm_fit_sgd(coef_t1, X_crs, y, ¶m);
ffm_coef * grad = extract_gradient(coef_t0, coef_t1, param.stepsize);
// check w gradient updates
for (int i=0; i<n_features; i++)
{
// keep copy
double tmp = ffm_vector_get(coef_t0->w, i);
// x + eps
ffm_vector_set(coef_t0->w, i, tmp + eps);
double y_pred = ffm_predict_sample(coef_t0, X_crs, test_sample_row);
double sq_loss = 0.5 * pow(y_true - y_pred, 2);
double l_plus = sq_loss + 0.5 * l2_penalty(coef_t0);
// x - eps
ffm_vector_set(coef_t0->w, i, tmp - eps);
y_pred = ffm_predict_sample(coef_t0, X_crs, test_sample_row);
sq_loss = 0.5 * pow(y_true - y_pred, 2);
double l_minus = sq_loss + 0.5 * l2_penalty(coef_t0);
// restore
ffm_vector_set(coef_t0->w, i, tmp);
double grad_i = (l_plus - l_minus) / ( 2 * eps);
g_assert_cmpfloat(fabs(grad_i - ffm_vector_get(grad->w, i)), < , 1e-10);
}
// check V gradient updates
for (int f=0; f< param.k; f++)
for (int i=0; i<n_features; i++)
{
// keep copy
double tmp = ffm_matrix_get(coef_t0->V, f, i);
// x + eps
ffm_matrix_set(coef_t0->V, f, i, tmp + eps);
double y_pred = ffm_predict_sample(coef_t0, X_crs, test_sample_row);
double sq_loss = 0.5 * pow(y_true - y_pred, 2);
double l_plus = sq_loss + 0.5 * l2_penalty(coef_t0);
// x - eps
ffm_matrix_set(coef_t0->V, f, i, tmp - eps);
y_pred = ffm_predict_sample(coef_t0, X_crs, test_sample_row);
sq_loss = 0.5 * pow(y_true - y_pred, 2);
double l_minus = sq_loss + 0.5 * l2_penalty(coef_t0);
// restore
ffm_matrix_set(coef_t0->V, f, i, tmp);
double grad_i = (l_plus - l_minus) / ( 2 * eps);
g_assert_cmpfloat(fabs(grad_i - ffm_matrix_get(grad->V, f, i)),
< , 1e-10);
}
free_ffm_coef(coef_t0);
free_ffm_coef(coef_t1);
free_ffm_coef(grad);
}
void test_gradient_check_class(TestFixture_T* pFix, gconstpointer pg){
cs *X_crs = pFix->X_t;
ffm_vector *y = pFix->y;
int test_sample_row = 0;
double y_true = ffm_vector_get(y, test_sample_row);
int n_features = pFix->coef->w->size;
double eps = 0.0001;
ffm_param param = {.n_iter=1, .stepsize=.01,
.init_sigma=.01, .k=2, .init_lambda_w=1.5, .init_lambda_V=2.0,
.warm_start=1,
.SOLVER=SOLVER_SGD, .TASK=TASK_CLASSIFICATION, .rng_seed=44};
ffm_coef *coef_t0 = alloc_fm_coef(n_features, param.k, false);
init_ffm_coef(coef_t0, param);
ffm_coef *coef_t1 = alloc_fm_coef(n_features, param.k, false);
init_ffm_coef(coef_t1, param);
ffm_fit_sgd(coef_t1, X_crs, y, ¶m);
ffm_coef * grad = extract_gradient(coef_t0, coef_t1, param.stepsize);
// check w gradient updates
for (int i=0; i<n_features; i++)
{
// keep copy
double tmp = ffm_vector_get(coef_t0->w, i);
// x + eps
ffm_vector_set(coef_t0->w, i, tmp + eps);
double y_pred = ffm_predict_sample(coef_t0, X_crs, test_sample_row);
double log_loss = - log(ffm_sigmoid(y_true * y_pred));
double l_plus = log_loss + 0.5 * l2_penalty(coef_t0);
// x - eps
ffm_vector_set(coef_t0->w, i, tmp - eps);
y_pred = ffm_predict_sample(coef_t0, X_crs, test_sample_row);
log_loss = - log(ffm_sigmoid(y_true * y_pred));
double l_minus = log_loss + 0.5 * l2_penalty(coef_t0);
// restore
ffm_vector_set(coef_t0->w, i, tmp);
// finite central differences
double grad_i = (l_plus - l_minus) / ( 2 * eps);
//g_assert_cmpfloat(grad_i, ==, ffm_vector_get(grad->w, i));
g_assert_cmpfloat(fabs(grad_i - ffm_vector_get(grad->w, i)), < , 1e-9);
}
// check V gradient updates
for (int f=0; f< param.k; f++)
for (int i=0; i<n_features; i++)
{
// keep copy
double tmp = ffm_matrix_get(coef_t0->V, f, i);
// x + eps
ffm_matrix_set(coef_t0->V, f, i, tmp + eps);
double y_pred = ffm_predict_sample(coef_t0, X_crs, test_sample_row);
double log_loss = - log(ffm_sigmoid(y_true * y_pred));
double l_plus = log_loss + 0.5 * l2_penalty(coef_t0);
// x - eps
ffm_matrix_set(coef_t0->V, f, i, tmp - eps);
y_pred = ffm_predict_sample(coef_t0, X_crs, test_sample_row);
log_loss = - log(ffm_sigmoid(y_true * y_pred));
double l_minus = log_loss + 0.5 * l2_penalty(coef_t0);
// restore
ffm_matrix_set(coef_t0->V, f, i, tmp);
// finite central differences
double grad_i = (l_plus - l_minus) / ( 2 * eps);
g_assert_cmpfloat(fabs(grad_i - ffm_matrix_get(grad->V, f, i)),
< , 1e-10);
}
free_ffm_coef(coef_t0);
free_ffm_coef(coef_t1);
free_ffm_coef(grad);
}
void test_gradient_check_bpr(TestFixture_T* pFix, gconstpointer pg){
cs *X_crs = pFix->X_t;
ffm_matrix * pairs = ffm_matrix_calloc(1, 2);
int pos_row = 0; ffm_matrix_set(pairs, 0, 0, pos_row);
int neg_row = 1; ffm_matrix_set(pairs, 0, 1, neg_row);
int n_features = pFix->coef->w->size;
double eps = 0.0001;
ffm_param param = {.n_iter=1, .stepsize=.01,
.init_sigma=.01, .k=2, .init_lambda_w=0.0, .init_lambda_V=0.0,
.warm_start=1,
.SOLVER=SOLVER_SGD, .TASK=TASK_RANKING, .rng_seed=44};
ffm_coef *coef_t0 = alloc_fm_coef(n_features, param.k, false);
init_ffm_coef(coef_t0, param);
ffm_coef *coef_t1 = alloc_fm_coef(n_features, param.k, false);
init_ffm_coef(coef_t1, param);
ffm_fit_sgd_bpr(coef_t1, X_crs, pairs, param);
ffm_coef * grad = extract_gradient(coef_t0, coef_t1, param.stepsize);
double y_pos, y_neg, bpr_loss, l_plus, l_minus, grad_i, tmp;
// check w gradient updates
for (int i=0; i<n_features; i++)
{
// keep copy
tmp = ffm_vector_get(coef_t0->w, i);
// x + eps
ffm_vector_set(coef_t0->w, i, tmp + eps);
y_pos = ffm_predict_sample(coef_t0, X_crs, pos_row);
y_neg = ffm_predict_sample(coef_t0, X_crs, neg_row);
bpr_loss = - log(ffm_sigmoid(y_pos - y_neg));
l_plus = bpr_loss + 0.5 * l2_penalty(coef_t0);
// x - eps
ffm_vector_set(coef_t0->w, i, tmp - eps);
y_pos = ffm_predict_sample(coef_t0, X_crs, pos_row);
y_neg = ffm_predict_sample(coef_t0, X_crs, neg_row);
bpr_loss = - log(ffm_sigmoid(y_pos - y_neg));
l_minus = bpr_loss + 0.5 * l2_penalty(coef_t0);
// restore
ffm_vector_set(coef_t0->w, i, tmp);
// finite central differences
grad_i = (l_plus - l_minus) / ( 2 * eps);
//g_assert_cmpfloat(grad_i, ==, ffm_vector_get(grad->w, i));
g_assert_cmpfloat(fabs(grad_i - ffm_vector_get(grad->w, i)), < , 1e-9);
}
// check V gradient updates
for (int f=0; f< param.k; f++)
for (int i=0; i<n_features; i++)
{
// keep copy
tmp = ffm_matrix_get(coef_t0->V, f, i);
// x + eps
ffm_matrix_set(coef_t0->V, f, i, tmp + eps);
y_pos = ffm_predict_sample(coef_t0, X_crs, pos_row);
y_neg = ffm_predict_sample(coef_t0, X_crs, neg_row);
bpr_loss = - log(ffm_sigmoid(y_pos - y_neg));
l_plus = bpr_loss + 0.5 * l2_penalty(coef_t0);
// x - eps
ffm_matrix_set(coef_t0->V, f, i, tmp - eps);
y_pos = ffm_predict_sample(coef_t0, X_crs, pos_row);
y_neg = ffm_predict_sample(coef_t0, X_crs, neg_row);
bpr_loss = - log(ffm_sigmoid(y_pos - y_neg));
l_minus = bpr_loss + 0.5 * l2_penalty(coef_t0);
// restore
ffm_matrix_set(coef_t0->V, f, i, tmp);
// finite central differences
grad_i = (l_plus - l_minus) / ( 2 * eps);
//g_assert_cmpfloat(grad_i, ==, ffm_matrix_get(grad->V, f, i));
g_assert_cmpfloat(fabs(grad_i - ffm_matrix_get(grad->V, f, i)),
< , 1e-10);
}
free_ffm_coef(coef_t0);
free_ffm_coef(coef_t1);
free_ffm_coef(grad);
}
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( "/sgd/util/predict sample",
TestFixture_T,
&Fixture,
TestFixtureContructorWide,
test_sgd_predict_sample,
TestFixtureDestructor
);
g_test_add( "/sgd/reg/first order",
TestFixture_T,
&Fixture,
TestFixtureContructorLong,
test_first_order_sgd,
TestFixtureDestructor
);
g_test_add( "/sgd/reg/second order",
TestFixture_T,
&Fixture,
TestFixtureContructorLong,
test_second_order_sgd,
TestFixtureDestructor
);
g_test_add( "/sgd/class/full",
TestFixture_T,
&Fixture,
TestFixtureContructorLong,
test_sgd_classification,
TestFixtureDestructor
);
g_test_add( "/sgd/bpr/update second order",
TestFixture_T,
&Fixture,
TestFixtureContructorWide,
test_update_second_order_bpr,
TestFixtureDestructor
);
g_test_add( "/sgd/bpr/first order",
TestFixture_T,
&Fixture,
TestFixtureContructorLong,
test_first_order_bpr,
TestFixtureDestructor
);
g_test_add( "/sgd/bpr/second order",
TestFixture_T,
&Fixture,
TestFixtureContructorLong,
test_second_order_bpr,
TestFixtureDestructor
);
g_test_add_func("/sgd/class/generated data",
test_sgd_classification_generated_data);
g_test_add_func("/sgd/reg/generated data",
test_sgd_generated_data);
g_test_add_func("/sgd/bpr/generated data",
test_sgd_bpr_generated_data);
g_test_add_func("/sgd/util/extract_gradient",
test_extract_gradient);
g_test_add_func("/sgd/util/l2_penalty",
test_l2_penalty);
g_test_add("/sgd/reg/gradient check",
TestFixture_T,
&Fixture,
TestFixtureContructorWide,
test_gradient_check_reg,
TestFixtureDestructor
);
g_test_add("/sgd/class/gradient check",
TestFixture_T,
&Fixture,
TestFixtureContructorWide,
test_gradient_check_class,
TestFixtureDestructor
);
g_test_add("/sgd/bpr/gradient check",
TestFixture_T,
&Fixture,
TestFixtureContructorWide,
test_gradient_check_bpr,
TestFixtureDestructor
);
return g_test_run();
}
void ffm_predict(double *w_0, double *w, double *V, cs *X, double *y_pred, int k) {
int n_samples = X->m;
int n_features = X->n;
ffm_vector ffm_w = {.size=n_features, .data=w, .owner=0};
ffm_matrix ffm_V = {.size0=k, .size1=n_features, .data=V, .owner=0};
ffm_coef coef = {.w_0=*w_0, .w=&ffm_w, .V=&ffm_V};
ffm_vector ffm_y_pred = {.size=n_samples, .data=y_pred, .owner=0};
sparse_predict(&coef, X, &ffm_y_pred);
}
void ffm_als_fit(double *w_0, double *w, double *V, cs *X, double *y,
ffm_param *param) {
param->SOLVER = SOLVER_ALS;
int n_samples = X->m;
int n_features = X->n;
ffm_vector ffm_w = {.size=n_features, .data=w, .owner=0};
ffm_matrix ffm_V = {.size0=param->k, .size1=n_features, .data=V, .owner=0};
ffm_coef coef = {.w_0=*w_0, .w=&ffm_w, .V=&ffm_V,
.lambda_w=param->init_lambda_w
};
if (param->k > 0)
{
coef.lambda_V = ffm_vector_alloc(param->k);
coef.mu_V = ffm_vector_alloc(param->k);
ffm_vector_set_all(coef.lambda_V, param->init_lambda_V);
} else
{
coef.lambda_V = NULL;
coef.mu_V = NULL;
}
ffm_vector ffm_y = {.size=n_samples, .data=y, .owner=0};
sparse_fit(&coef, X, NULL, &ffm_y, NULL, *param);
// copy the last coef values back into the python memory
*w_0 = coef.w_0;
ffm_vector_free_all(coef.lambda_V, coef.mu_V);
}
void ffm_mcmc_fit_predict(double *w_0, double *w, double *V,
cs *X_train, cs *X_test, double *y_train, double *y_pred,
ffm_param *param) {
param->SOLVER = SOLVER_MCMC;
int k = param->k;
double * hyper_param = param->hyper_param;
int n_test_samples = X_test->m;
int n_train_samples = X_train->m;
int n_features = X_train->n;
ffm_vector ffm_w = {.size=n_features, .data=w, .owner=0};
ffm_matrix ffm_V = {.size0=param->k, .size1=n_features, .data=V, .owner=0};
ffm_coef coef = {.w_0=*w_0, .w=&ffm_w, .V=&ffm_V,
.lambda_w=param->init_lambda_w, .alpha=1, .mu_w=0
};
if (k > 0)
{
coef.lambda_V = ffm_vector_alloc(param->k);
coef.mu_V = ffm_vector_alloc(param->k);
}
else
{
coef.lambda_V = NULL;
coef.mu_V = NULL;
}
// set inital values for hyperparameter
int w_groups = 1;
assert(param->n_hyper_param == 1 + 2 * k + 2 * w_groups &&
"hyper_parameter vector has wrong size");
if (param->warm_start)
{
coef.alpha = hyper_param[0];
coef.lambda_w = hyper_param[1];
// copy V lambda's over
for (int i=0; i<k; i++) ffm_vector_set(coef.lambda_V, i,
hyper_param[i + 1 + w_groups]);
coef.mu_w = hyper_param[k + 1 + w_groups];
// copy V mu's over
for (int i=0; i<k; i++) ffm_vector_set(coef.mu_V, i,
hyper_param[i + 1 + (2 * w_groups) + k]);
}
ffm_vector ffm_y_train = {.size=n_train_samples, .data=y_train, .owner=0};
ffm_vector ffm_y_pred = {.size=n_test_samples, .data=y_pred, .owner=0};
sparse_fit(&coef, X_train, X_test, &ffm_y_train, &ffm_y_pred, *param);
// copy the last coef values back into the python memory
*w_0 = coef.w_0;
// copy current hyperparameter back
hyper_param[0] = coef.alpha;
hyper_param[1] = coef.lambda_w;
// copy V lambda's back
for (int i=0; i<k; i++) hyper_param[i + 1 + w_groups] =
ffm_vector_get(coef.lambda_V, i);
hyper_param[k + 1 + w_groups] = coef.mu_w;
// copy mu's back
for (int i=0; i<k; i++) hyper_param[i + 1 + (2 * w_groups) + k] =
ffm_vector_get(coef.mu_V, i);
if ( k > 0 )
ffm_vector_free_all(coef.lambda_V, coef.mu_V);
}
void ffm_sgd_bpr_fit(double *w_0, double *w, double *V,
cs *X, double *pairs, int n_pairs, ffm_param *param) {
int n_features = X->m;
ffm_vector ffm_w = {.size=n_features, .data=w, .owner=0};
ffm_matrix ffm_V = {.size0=param->k, .size1=n_features, .data=V, .owner=0};
ffm_coef coef = {.w_0=*w_0, .w=&ffm_w, .V=&ffm_V,
.lambda_w=param->init_lambda_w
};
if (param->k > 0)
{
coef.lambda_V = ffm_vector_alloc(param->k);
coef.mu_V = ffm_vector_alloc(param->k);
}
else
{
coef.lambda_V = NULL;
coef.mu_V = NULL;
}
ffm_matrix ffm_y = {.size0=n_pairs, .size1=2, .data=pairs, .owner=0};
ffm_fit_sgd_bpr(&coef, X, &ffm_y, *param);
// copy the last coef values back into the python memory
*w_0 = coef.w_0;
if ( param->k > 0 )
ffm_vector_free_all(coef.lambda_V, coef.mu_V);
}
void ffm_sgd_fit(double *w_0, double *w, double *V,
cs *X, double *y, ffm_param *param) {
int n_samples = X->n;
int n_features = X->m;
ffm_vector ffm_w = {.size=n_features, .data=w, .owner=0};
ffm_matrix ffm_V = {.size0=param->k, .size1=n_features, .data=V, .owner=0};
ffm_coef coef = {.w_0=*w_0, .w=&ffm_w, .V=&ffm_V,
.lambda_w=param->init_lambda_w
};
if (param->k > 0)
{
coef.lambda_V = ffm_vector_alloc(param->k);
coef.mu_V = ffm_vector_alloc(param->k);
}
else
{
coef.lambda_V = NULL;
coef.mu_V = NULL;
}
ffm_vector ffm_y = {.size=n_samples, .data=y, .owner=0};
ffm_fit_sgd(&coef, X, &ffm_y, param);
// copy the last coef values back into the python memory
*w_0 = coef.w_0;
if ( param->k > 0 )
ffm_vector_free_all(coef.lambda_V, coef.mu_V);
}
void test_first_order_sgd(TestFixture_T* pFix, gconstpointer pg){
//int k = pFix->coef->V->size0;
int k = 0;
int n_features = pFix->X->n;
int n_iter = 50;
double init_sigma = .1;
double step_size = .002;
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_vector * y_pred = ffm_vector_calloc(5);
ffm_param param = {.n_iter=n_iter * 100, .init_sigma=init_sigma,
.stepsize=step_size, .SOLVER=SOLVER_SGD, .TASK=TASK_REGRESSION};
param.init_lambda_w = 0.5;
ffm_fit_sgd(coef, pFix->X_t, pFix->y, ¶m);
sparse_predict(coef, pFix->X, y_pred);
g_assert_cmpfloat(ffm_r2_score(y_pred, pFix->y), > , .85);
ffm_vector * y_pred_als = ffm_vector_calloc(5);
ffm_coef *coef_als = alloc_fm_coef(n_features, k, false);
ffm_param param_als = {.n_iter=50, .init_sigma=0.1, .SOLVER=SOLVER_ALS,
.TASK=TASK_REGRESSION};
param_als.init_lambda_w = 3.5;
sparse_fit(coef_als, pFix->X, pFix->X, pFix->y, y_pred_als, param_als);
sparse_predict(coef_als, pFix->X, y_pred_als);
// compare fit of als and sgd
g_assert_cmpfloat(ffm_r2_score(y_pred, y_pred_als), > , .98);
// compare coef of als and sgd
g_assert_cmpfloat(ffm_r2_score(coef->w, coef_als->w), > , .98);
ffm_vector_free_all(y_pred, y_pred_als);
free_ffm_coef(coef);
free_ffm_coef(coef_als);
}
void test_second_order_sgd(TestFixture_T* pFix, gconstpointer pg){
int n_features = pFix->X->n;
int k = 2; int n_iter = 10;
double init_sigma = .01;
double step_size = .0002;
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_vector * y_pred = ffm_vector_calloc(5);
ffm_param param = {.n_iter=n_iter * 100, .init_sigma=init_sigma,
.stepsize=step_size, .SOLVER=SOLVER_SGD, .TASK=TASK_REGRESSION};
param.init_lambda_w = 0.5;
param.init_lambda_V = 50.5;
ffm_fit_sgd(coef, pFix->X_t, pFix->y, ¶m);
sparse_predict(coef, pFix->X, y_pred);
g_assert_cmpfloat(ffm_r2_score(y_pred, pFix->y), > , .98);
ffm_vector * y_pred_als = ffm_vector_calloc(5);
ffm_coef *coef_als = alloc_fm_coef(n_features, k, false);
ffm_param param_als = {.n_iter=10, .init_sigma=0.01, .SOLVER=SOLVER_ALS};
param_als.init_lambda_w = 3.5;
param_als.init_lambda_V = 50.5;
sparse_fit(coef_als, pFix->X, pFix->X, pFix->y, y_pred_als, param_als);
sparse_predict(coef_als, pFix->X, y_pred_als);
// compare fit of als and sgd
g_assert_cmpfloat(ffm_r2_score(y_pred, y_pred_als), > , .98);
ffm_vector_free_all(y_pred, y_pred_als);
free_ffm_coef(coef);
free_ffm_coef(coef_als);
}
void test_sgd_classification(TestFixture_T* pFix, gconstpointer pg){
int n_features = pFix->X->n;
int k = 2;
int n_iter = 10;
double init_sigma = .01;
double step_size = .0002;
// map to classification problem
ffm_vector_make_labels(pFix->y);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_vector * y_pred = ffm_vector_calloc(5);
ffm_param param = {.n_iter=n_iter * 100, .init_sigma=init_sigma,
.stepsize=step_size, .SOLVER=SOLVER_SGD, .TASK=TASK_CLASSIFICATION};
param.init_lambda_w = 0.5;
param.init_lambda_V = 0.5;
ffm_fit_sgd(coef, pFix->X_t, pFix->y, ¶m);
sparse_predict(coef, pFix->X, y_pred);
for(int i=0; i< y_pred->size; i++)
ffm_vector_set(y_pred, i, ffm_sigmoid(ffm_vector_get(y_pred, i)));
g_assert_cmpfloat(ffm_vector_accuracy(pFix->y, y_pred), >= , .8);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
}
void test_first_order_bpr(TestFixture_T* pFix, gconstpointer pg){
int n_features = pFix->X->n;
int n_samples = pFix->X->m;
int k = 0;
int n_iter = 200;
double init_sigma = .01;
double step_size = .002;
ffm_matrix *compares = ffm_vector_to_rank_comparision(pFix->y);
ffm_vector * true_order = ffm_vector_get_order(pFix->y);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
for(int i=0; i< 2; i++)
coef->w->data[i] = 0.1;
ffm_vector * y_pred = ffm_vector_calloc(n_samples);
ffm_param param = {.n_iter=n_iter * 100, .init_sigma=init_sigma,
.stepsize=step_size, .SOLVER=SOLVER_SGD, .TASK=TASK_RANKING};
param.init_lambda_w = 0.0;
ffm_fit_sgd_bpr(coef, pFix->X_t, compares, param);
sparse_predict(coef, pFix->X, y_pred);
ffm_vector * pred_order = ffm_vector_get_order(y_pred);
double kendall_tau = \
ffm_vector_kendall_tau(true_order, pred_order);
g_assert_cmpfloat(kendall_tau, == , 1);
ffm_vector_free_all(y_pred, true_order, pred_order);
free_ffm_coef(coef);
}
void test_update_second_order_bpr(TestFixture_T* pFix, gconstpointer pg){
double cache_p = 1.1;
double cache_n = 2.2;
double y_err = -1;
double step_size = 0.1;
double lambda_V = 4;
int sample_row_p = 1;
int sample_row_n = 0;
int V_col = 0;
update_second_order_bpr(pFix->X_t, pFix->coef->V, cache_n, cache_p, y_err,
step_size, lambda_V, sample_row_p, sample_row_n, V_col);
// 1 - 0.1*(-1 * (4*1.1 - 4^2 - (1*2.2 - 1^2*1)) + 4 *1) = -0.68
g_assert_cmpfloat(fabs(ffm_matrix_get(pFix->coef->V, 0, 0) - (-0.68)), < , 1e-10);
//> 2 - 0.1*(-1 * (0*1.1 - 0^2*2 - (2*2.2 - 2^2*2)) + 4 *2)
//[1] 1.56
g_assert_cmpfloat(ffm_matrix_get(pFix->coef->V, 0, 1), ==, 1.56);
}
void test_second_order_bpr(TestFixture_T* pFix, gconstpointer pg){
int n_features = pFix->X->n;
int n_samples = pFix->X->m;
int k = 2;
int n_iter = 200;
double init_sigma = .01;
double step_size = .02;
ffm_matrix *compares = ffm_vector_to_rank_comparision(pFix->y);
ffm_vector * true_order = ffm_vector_get_order(pFix->y);
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_vector * y_pred = ffm_vector_calloc(n_samples);
ffm_param param = {.n_iter=n_iter, .init_sigma=init_sigma,
.stepsize=step_size, .SOLVER=SOLVER_SGD, .TASK=TASK_RANKING};
param.init_lambda_w = 0.5;
param.init_lambda_V = 0.5;
ffm_fit_sgd_bpr(coef, pFix->X_t, compares, param);
sparse_predict(coef, pFix->X, y_pred);
ffm_vector * pred_order = ffm_vector_get_order(y_pred);
double kendall_tau = \
ffm_vector_kendall_tau(true_order, pred_order);
g_assert_cmpfloat(kendall_tau, == , 1);
ffm_vector_free_all(y_pred, true_order, pred_order);
free_ffm_coef(coef);
}
void test_sgd_generated_data(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);
int n_iter = 40;
double init_sigma = 0.1;
double step_size = .05;
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter=n_iter * 100, .init_sigma=init_sigma,
.stepsize=step_size, .SOLVER=SOLVER_SGD, .TASK=TASK_REGRESSION};
param.init_lambda_w = 0.05;
ffm_fit_sgd(coef, data->X_t, data->y, ¶m);
sparse_predict(coef, data->X, y_pred);
g_assert_cmpfloat(ffm_r2_score(y_pred, data->y), > , 0.95);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data, NULL);
}
void test_sgd_classification_generated_data(void){
int n_features = 10;
int n_samples = 100;
int k = 2;
TestFixture_T *data = makeTestFixture(124, n_samples, n_features, k);
ffm_vector_make_labels(data->y);
ffm_vector * y_pred = ffm_vector_calloc(n_samples);
int n_iter = 200;
double init_sigma = 0.1;
double step_size = .2;
ffm_coef *coef = alloc_fm_coef(n_features, k, false);
ffm_param param = {.n_iter=n_iter, .init_sigma=init_sigma,
.stepsize=step_size, .SOLVER=SOLVER_SGD, .TASK=TASK_CLASSIFICATION};
param.init_lambda_w = 0.05;
param.init_lambda_V = 0.05;
ffm_fit_sgd(coef, data->X_t, data->y, ¶m);
sparse_predict(coef, data->X, y_pred);
for(int i=0; i< y_pred->size; i++)
ffm_vector_set(y_pred, i, ffm_sigmoid(ffm_vector_get(y_pred, i)));
g_assert_cmpfloat(ffm_vector_accuracy(data->y, y_pred), >= , .81);
ffm_vector_free(y_pred);
free_ffm_coef(coef);
TestFixtureDestructor(data, NULL);
}
