Module: Numo::Libsvm
- Defined in:
- ext/numo/libsvm/libsvmext.c,
lib/numo/libsvm/version.rb,
ext/numo/libsvm/libsvmext.c
Overview
Numo::Libsvm is a binding library for LIBSVM that handles dataset with Numo::NArray.
Defined Under Namespace
Modules: KernelType, SvmType
Constant Summary collapse
- VERSION =
The version of Numo::Libsvm you are using.
'0.4.0'
- LIBSVM_VERSION =
The version of LIBSVM used in backgroud library.
INT2NUM(LIBSVM_VERSION)
Class Method Summary collapse
-
.cv(x, y, param, n_folds) ⇒ Numo::DFloat
Perform cross validation under given parameters.
-
.decision_function(x, param, model) ⇒ Numo::DFloat
Calculate decision values for given samples.
-
.load_svm_model(filename) ⇒ Array
Load the SVM parameters and model from a text file with LIBSVM format.
-
.predict(x, param, model) ⇒ Numo::DFloat
Predict class labels or values for given samples.
-
.predict_proba(x, param, model) ⇒ Numo::DFloat
Predict class probability for given samples.
-
.save_svm_model(filename, param, model) ⇒ Boolean
Save the SVM parameters and model as a text file with LIBSVM format.
-
.train(x, y, param) ⇒ Hash
Train the SVM model according to the given training data.
Class Method Details
.cv(x, y, param, n_folds) ⇒ Numo::DFloat
Perform cross validation under given parameters. The given samples are separated to n_fols folds. The predicted labels or values in the validation process are returned.
159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 |
# File 'ext/numo/libsvm/libsvmext.c', line 159
static
VALUE cross_validation(VALUE self, VALUE x_val, VALUE y_val, VALUE param_hash, VALUE nr_folds)
{
const int n_folds = NUM2INT(nr_folds);
size_t t_shape[1];
VALUE t_val;
double* t_pt;
narray_t* x_nary;
narray_t* y_nary;
char* err_msg;
VALUE random_seed;
VALUE verbose;
struct svm_problem* problem;
struct svm_parameter* param;
if (CLASS_OF(x_val) != numo_cDFloat) {
x_val = rb_funcall(numo_cDFloat, rb_intern("cast"), 1, x_val);
}
if (CLASS_OF(y_val) != numo_cDFloat) {
y_val = rb_funcall(numo_cDFloat, rb_intern("cast"), 1, y_val);
}
if (!RTEST(nary_check_contiguous(x_val))) {
x_val = nary_dup(x_val);
}
if (!RTEST(nary_check_contiguous(y_val))) {
y_val = nary_dup(y_val);
}
GetNArray(x_val, x_nary);
GetNArray(y_val, y_nary);
if (NA_NDIM(x_nary) != 2) {
rb_raise(rb_eArgError, "Expect samples to be 2-D array.");
return Qnil;
}
if (NA_NDIM(y_nary) != 1) {
rb_raise(rb_eArgError, "Expect label or target values to be 1-D arrray.");
return Qnil;
}
if (NA_SHAPE(x_nary)[0] != NA_SHAPE(y_nary)[0]) {
rb_raise(rb_eArgError, "Expect to have the same number of samples for samples and labels.");
return Qnil;
}
random_seed = rb_hash_aref(param_hash, ID2SYM(rb_intern("random_seed")));
if (!NIL_P(random_seed)) {
srand(NUM2UINT(random_seed));
}
param = rb_hash_to_svm_parameter(param_hash);
problem = dataset_to_svm_problem(x_val, y_val);
err_msg = svm_check_parameter(problem, param);
if (err_msg) {
xfree_svm_problem(problem);
xfree_svm_parameter(param);
rb_raise(rb_eArgError, "Invalid LIBSVM parameter is given: %s", err_msg);
return Qnil;
}
t_shape[0] = problem->l;
t_val = rb_narray_new(numo_cDFloat, 1, t_shape);
t_pt = (double*)na_get_pointer_for_write(t_val);
verbose = rb_hash_aref(param_hash, ID2SYM(rb_intern("verbose")));
if (verbose != Qtrue) {
svm_set_print_string_function(print_null);
}
svm_cross_validation(problem, param, n_folds, t_pt);
xfree_svm_problem(problem);
xfree_svm_parameter(param);
return t_val;
}
|
.decision_function(x, param, model) ⇒ Numo::DFloat
Calculate decision values for given samples.
317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 |
# File 'ext/numo/libsvm/libsvmext.c', line 317
static
VALUE decision_function(VALUE self, VALUE x_val, VALUE param_hash, VALUE model_hash)
{
struct svm_parameter* param;
struct svm_model* model;
struct svm_node* x_nodes;
narray_t* x_nary;
double* x_pt;
size_t y_shape[2];
VALUE y_val;
double* y_pt;
double* dec_values;
int y_cols;
int i, j;
int n_samples;
int n_features;
/* Obtain C data structures. */
if (CLASS_OF(x_val) != numo_cDFloat) {
x_val = rb_funcall(numo_cDFloat, rb_intern("cast"), 1, x_val);
}
if (!RTEST(nary_check_contiguous(x_val))) {
x_val = nary_dup(x_val);
}
GetNArray(x_val, x_nary);
if (NA_NDIM(x_nary) != 2) {
rb_raise(rb_eArgError, "Expect samples to be 2-D array.");
return Qnil;
}
param = rb_hash_to_svm_parameter(param_hash);
model = rb_hash_to_svm_model(model_hash);
model->param = *param;
/* Initialize some variables. */
n_samples = (int)NA_SHAPE(x_nary)[0];
n_features = (int)NA_SHAPE(x_nary)[1];
if (model->param.svm_type == ONE_CLASS || model->param.svm_type == EPSILON_SVR || model->param.svm_type == NU_SVR) {
y_shape[0] = n_samples;
y_shape[1] = 1;
y_val = rb_narray_new(numo_cDFloat, 1, y_shape);
} else {
y_shape[0] = n_samples;
y_shape[1] = model->nr_class * (model->nr_class - 1) / 2;
y_val = rb_narray_new(numo_cDFloat, 2, y_shape);
}
x_pt = (double*)na_get_pointer_for_read(x_val);
y_pt = (double*)na_get_pointer_for_write(y_val);
/* Predict values. */
if (model->param.svm_type == ONE_CLASS || model->param.svm_type == EPSILON_SVR || model->param.svm_type == NU_SVR) {
x_nodes = ALLOC_N(struct svm_node, n_features + 1);
x_nodes[n_features].index = -1;
x_nodes[n_features].value = 0.0;
for (i = 0; i < n_samples; i++) {
for (j = 0; j < n_features; j++) {
x_nodes[j].index = j + 1;
x_nodes[j].value = (double)x_pt[i * n_features + j];
}
svm_predict_values(model, x_nodes, &y_pt[i]);
}
xfree(x_nodes);
} else {
y_cols = (int)y_shape[1];
dec_values = ALLOC_N(double, y_cols);
x_nodes = ALLOC_N(struct svm_node, n_features + 1);
x_nodes[n_features].index = -1;
x_nodes[n_features].value = 0.0;
for (i = 0; i < n_samples; i++) {
for (j = 0; j < n_features; j++) {
x_nodes[j].index = j + 1;
x_nodes[j].value = (double)x_pt[i * n_features + j];
}
svm_predict_values(model, x_nodes, dec_values);
for (j = 0; j < y_cols; j++) {
y_pt[i * y_cols + j] = dec_values[j];
}
}
xfree(x_nodes);
xfree(dec_values);
}
xfree_svm_model(model);
xfree_svm_parameter(param);
return y_val;
}
|
.load_svm_model(filename) ⇒ Array
Load the SVM parameters and model from a text file with LIBSVM format.
496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 |
# File 'ext/numo/libsvm/libsvmext.c', line 496
static
VALUE load_svm_model(VALUE self, VALUE filename)
{
char* filename_ = StringValuePtr(filename);
struct svm_model* model = svm_load_model(filename_);
VALUE res = rb_ary_new2(2);
VALUE param_hash = Qnil;
VALUE model_hash = Qnil;
if (model == NULL) {
rb_raise(rb_eIOError, "Failed to load file '%s'", filename_);
return Qnil;
}
if (model) {
param_hash = svm_parameter_to_rb_hash(&(model->param));
model_hash = svm_model_to_rb_hash(model);
svm_free_and_destroy_model(&model);
}
rb_ary_store(res, 0, param_hash);
rb_ary_store(res, 1, model_hash);
return res;
}
|
.predict(x, param, model) ⇒ Numo::DFloat
Predict class labels or values for given samples.
246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 |
# File 'ext/numo/libsvm/libsvmext.c', line 246
static
VALUE predict(VALUE self, VALUE x_val, VALUE param_hash, VALUE model_hash)
{
struct svm_parameter* param;
struct svm_model* model;
struct svm_node* x_nodes;
narray_t* x_nary;
double* x_pt;
size_t y_shape[1];
VALUE y_val;
double* y_pt;
int i, j;
int n_samples;
int n_features;
/* Obtain C data structures. */
if (CLASS_OF(x_val) != numo_cDFloat) {
x_val = rb_funcall(numo_cDFloat, rb_intern("cast"), 1, x_val);
}
if (!RTEST(nary_check_contiguous(x_val))) {
x_val = nary_dup(x_val);
}
GetNArray(x_val, x_nary);
if (NA_NDIM(x_nary) != 2) {
rb_raise(rb_eArgError, "Expect samples to be 2-D array.");
return Qnil;
}
param = rb_hash_to_svm_parameter(param_hash);
model = rb_hash_to_svm_model(model_hash);
model->param = *param;
/* Initialize some variables. */
n_samples = (int)NA_SHAPE(x_nary)[0];
n_features = (int)NA_SHAPE(x_nary)[1];
y_shape[0] = n_samples;
y_val = rb_narray_new(numo_cDFloat, 1, y_shape);
y_pt = (double*)na_get_pointer_for_write(y_val);
x_pt = (double*)na_get_pointer_for_read(x_val);
/* Predict values. */
x_nodes = ALLOC_N(struct svm_node, n_features + 1);
x_nodes[n_features].index = -1;
x_nodes[n_features].value = 0.0;
for (i = 0; i < n_samples; i++) {
for (j = 0; j < n_features; j++) {
x_nodes[j].index = j + 1;
x_nodes[j].value = (double)x_pt[i * n_features + j];
}
y_pt[i] = svm_predict(model, x_nodes);
}
xfree(x_nodes);
xfree_svm_model(model);
xfree_svm_parameter(param);
return y_val;
}
|
.predict_proba(x, param, model) ⇒ Numo::DFloat
Predict class probability for given samples. The model must have probability information calcualted in training procedure. The parameter ‘:probability’ set to 1 in training procedure.
420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 |
# File 'ext/numo/libsvm/libsvmext.c', line 420
static
VALUE predict_proba(VALUE self, VALUE x_val, VALUE param_hash, VALUE model_hash)
{
struct svm_parameter* param;
struct svm_model* model;
struct svm_node* x_nodes;
narray_t* x_nary;
double* x_pt;
size_t y_shape[2];
VALUE y_val = Qnil;
double* y_pt;
double* probs;
int i, j;
int n_samples;
int n_features;
GetNArray(x_val, x_nary);
if (NA_NDIM(x_nary) != 2) {
rb_raise(rb_eArgError, "Expect samples to be 2-D array.");
return Qnil;
}
param = rb_hash_to_svm_parameter(param_hash);
model = rb_hash_to_svm_model(model_hash);
model->param = *param;
if ((model->param.svm_type == C_SVC || model->param.svm_type == NU_SVC) && model->probA != NULL && model->probB != NULL) {
/* Obtain C data structures. */
if (CLASS_OF(x_val) != numo_cDFloat) {
x_val = rb_funcall(numo_cDFloat, rb_intern("cast"), 1, x_val);
}
if (!RTEST(nary_check_contiguous(x_val))) {
x_val = nary_dup(x_val);
}
/* Initialize some variables. */
n_samples = (int)NA_SHAPE(x_nary)[0];
n_features = (int)NA_SHAPE(x_nary)[1];
y_shape[0] = n_samples;
y_shape[1] = model->nr_class;
y_val = rb_narray_new(numo_cDFloat, 2, y_shape);
x_pt = (double*)na_get_pointer_for_read(x_val);
y_pt = (double*)na_get_pointer_for_write(y_val);
/* Predict values. */
probs = ALLOC_N(double, model->nr_class);
x_nodes = ALLOC_N(struct svm_node, n_features + 1);
x_nodes[n_features].index = -1;
x_nodes[n_features].value = 0.0;
for (i = 0; i < n_samples; i++) {
for (j = 0; j < n_features; j++) {
x_nodes[j].index = j + 1;
x_nodes[j].value = (double)x_pt[i * n_features + j];
}
svm_predict_probability(model, x_nodes, probs);
for (j = 0; j < model->nr_class; j++) {
y_pt[i * model->nr_class + j] = probs[j];
}
}
xfree(x_nodes);
xfree(probs);
}
xfree_svm_model(model);
xfree_svm_parameter(param);
return y_val;
}
|
.save_svm_model(filename, param, model) ⇒ Boolean
Save the SVM parameters and model as a text file with LIBSVM format. The saved file can be used with the libsvm tools. Note that the svm_save_model saves only the parameters necessary for estimation with the trained model.
534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 |
# File 'ext/numo/libsvm/libsvmext.c', line 534
static
VALUE save_svm_model(VALUE self, VALUE filename, VALUE param_hash, VALUE model_hash)
{
char* filename_ = StringValuePtr(filename);
struct svm_parameter* param = rb_hash_to_svm_parameter(param_hash);
struct svm_model* model = rb_hash_to_svm_model(model_hash);
int res;
model->param = *param;
res = svm_save_model(filename_, model);
xfree_svm_model(model);
xfree_svm_parameter(param);
if (res < 0) {
rb_raise(rb_eIOError, "Failed to save file '%s'", filename_);
return Qfalse;
}
return Qtrue;
}
|
.train(x, y, param) ⇒ Hash
Train the SVM model according to the given training data.
48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
# File 'ext/numo/libsvm/libsvmext.c', line 48
static
VALUE train(VALUE self, VALUE x_val, VALUE y_val, VALUE param_hash)
{
struct svm_problem* problem;
struct svm_parameter* param;
struct svm_model* model;
narray_t* x_nary;
narray_t* y_nary;
char* err_msg;
VALUE random_seed;
VALUE verbose;
VALUE model_hash;
if (CLASS_OF(x_val) != numo_cDFloat) {
x_val = rb_funcall(numo_cDFloat, rb_intern("cast"), 1, x_val);
}
if (CLASS_OF(y_val) != numo_cDFloat) {
y_val = rb_funcall(numo_cDFloat, rb_intern("cast"), 1, y_val);
}
if (!RTEST(nary_check_contiguous(x_val))) {
x_val = nary_dup(x_val);
}
if (!RTEST(nary_check_contiguous(y_val))) {
y_val = nary_dup(y_val);
}
GetNArray(x_val, x_nary);
GetNArray(y_val, y_nary);
if (NA_NDIM(x_nary) != 2) {
rb_raise(rb_eArgError, "Expect samples to be 2-D array.");
return Qnil;
}
if (NA_NDIM(y_nary) != 1) {
rb_raise(rb_eArgError, "Expect label or target values to be 1-D arrray.");
return Qnil;
}
if (NA_SHAPE(x_nary)[0] != NA_SHAPE(y_nary)[0]) {
rb_raise(rb_eArgError, "Expect to have the same number of samples for samples and labels.");
return Qnil;
}
random_seed = rb_hash_aref(param_hash, ID2SYM(rb_intern("random_seed")));
if (!NIL_P(random_seed)) {
srand(NUM2UINT(random_seed));
}
param = rb_hash_to_svm_parameter(param_hash);
problem = dataset_to_svm_problem(x_val, y_val);
err_msg = svm_check_parameter(problem, param);
if (err_msg) {
xfree_svm_problem(problem);
xfree_svm_parameter(param);
rb_raise(rb_eArgError, "Invalid LIBSVM parameter is given: %s", err_msg);
return Qnil;
}
verbose = rb_hash_aref(param_hash, ID2SYM(rb_intern("verbose")));
if (verbose != Qtrue) {
svm_set_print_string_function(print_null);
}
model = svm_train(problem, param);
model_hash = svm_model_to_rb_hash(model);
svm_free_and_destroy_model(&model);
xfree_svm_problem(problem);
xfree_svm_parameter(param);
return model_hash;
}
|