void train (const ssi_char_t *dir, const ssi_char_t *model) {
// load samples
StringList files;
FileTools::ReadFilesFromDir (files, dir, "*.wav");
SampleList samples;
samples.addUserName ("user");
for (ssi_size_t i = 0; i < files.size (); i++) {
ssi_stream_t *stream = new ssi_stream_t;
ssi_sample_t *sample = new ssi_sample_t;
const ssi_char_t *filename = files.get (i);
// parse class name
FilePath fp (files.get(i));
ssi_char_t *class_name = ssi_strcpy (fp.getName ());
for (ssi_size_t j = 0; j < strlen (class_name); j++) {
if (class_name[j] == '_') {
class_name[j] = '\0';
break;
}
}
ssi_size_t class_id = samples.addClassName (class_name);
delete[] class_name;
// read wave file
WavTools::ReadWavFile (filename, *stream);
// create sample
sample->class_id = class_id;
sample->num = 1;
sample->score = 1.0f;
sample->streams = new ssi_stream_t *[1];
sample->streams[0] = stream;
sample->time = 0;
sample->user_id = 0;
// add sample
samples.addSample (sample);
}
// extract features
SampleList samples_t;
EmoVoiceFeat *ev_feat = ssi_create (EmoVoiceFeat, "ev_feat", true);
ModelTools::TransformSampleList (samples, samples_t, *ev_feat);
// create model
IModel *bayes = ssi_create (NaiveBayes, "bayes", true);
Trainer trainer (bayes);
// evalulation
Evaluation eval;
eval.evalKFold (&trainer, samples_t, 10);
eval.print ();
// train & save
trainer.train (samples_t);
trainer.save (model);
}
bool Rank::train (ISamples &samples,
ssi_size_t stream_index) {
if (!_model) {
ssi_wrn ("a model has not been set yet");
return false;
}
release ();
_n_scores = samples.getStream (stream_index).dim;
_scores = new score[_n_scores];
Evaluation eval;
Trainer trainer (_model, stream_index);
SSI_DBG (SSI_LOG_LEVEL_DEBUG, "evaluate dimensions:");
for (ssi_size_t ndim = 0; ndim < _n_scores; ndim++) {
ISSelectDim samples_s (&samples);
samples_s.setSelection (stream_index, 1, &ndim);
if (_options.loo) {
eval.evalLOO (&trainer, samples_s);
} else if (_options.louo) {
eval.evalLOUO (&trainer, samples_s);
} else {
eval.evalKFold (&trainer, samples_s, _options.kfold);
}
_scores[ndim].index = ndim;
_scores[ndim].value = eval.get_classwise_prob ();
SSI_DBG (SSI_LOG_LEVEL_DEBUG, " #%02u -> %.2f", _scores[ndim].index, _scores[ndim].value);
}
trainer.release ();
return true;
}
bool ex_eval(void *arg) {
ssi_size_t n_classes = 2;
ssi_size_t n_samples = 20;
ssi_size_t n_streams = 1;
ssi_real_t train_distr[][3] = { 0.3f, 0.3f, 0.2f, 0.3f, 0.6f, 0.2f, 0.6f, 0.3f, 0.2f, 0.6f, 0.6f, 0.2f };
ssi_real_t test_distr[][3] = { 0.5f, 0.5f, 0.5f };
SampleList samples;
ModelTools::CreateTestSamples (samples, n_classes, n_samples, n_streams, train_distr);
ssi_char_t string[SSI_MAX_CHAR];
for (ssi_size_t n_class = 1; n_class < n_classes; n_class++) {
ssi_sprint (string, "class%02d", n_class);
samples.addClassName (string);
}
Evaluation eval;
NaiveBayes *model = ssi_create (NaiveBayes, 0, true);
Trainer trainer (model);
trainer.train (samples);
Evaluation2Latex e2latex;
e2latex.open ("eval.tex");
ssi_print_off ("devel set:\n");
eval.eval (&trainer, samples);
eval.print (ssiout);
eval.print_result_vec ();
e2latex.writeHead (eval, "caption", "label");
e2latex.writeText ("results with different evaluation strategies", true);
e2latex.writeEval ("devel", eval);
ssi_print_off("k-fold:\n");
eval.evalKFold (&trainer, samples, 3);
eval.print ();
eval.print_result_vec ();
e2latex.writeEval ("k-fold", eval);
ssi_print_off("split:\n");
eval.evalSplit (&trainer, samples, 0.5f);
eval.print ();
eval.print_result_vec ();
e2latex.writeEval ("split", eval);
ssi_print_off("loo:\n");
eval.evalLOO (&trainer, samples);
eval.print ();
eval.print_result_vec ();
e2latex.writeEval ("loo", eval);
e2latex.writeTail ();
e2latex.close ();
FILE *fp = fopen("eval.csv", "w");
eval.print(fp, Evaluation::PRINT::CSV_EX);
fclose(fp);
return true;
}
