void Evaluation::evalSplit (Trainer *trainer, ISamples &samples, ssi_real_t split) {
if (split <= 0 || split >= 1) {
ssi_err ("split must be a value between 0 and 1");
}
_trainer = trainer;
destroy_conf_mat ();
init_conf_mat (samples);
ssi_size_t *indices = new ssi_size_t[samples.getSize ()];
ssi_size_t *indices_count_lab = new ssi_size_t[samples.getClassSize ()];
ssi_size_t indices_count_all;
indices_count_all = 0;
for (ssi_size_t j = 0; j < samples.getClassSize (); j++) {
indices_count_lab[j] = 0;
}
ssi_size_t label;
ssi_size_t label_size;
for (ssi_size_t j = 0; j < samples.getSize (); j++) {
label = samples.get (j)->class_id;
label_size = samples.getSize (label);
if (++indices_count_lab[label] <= ssi_cast (ssi_size_t, label_size * split + 0.5f)) {
indices[indices_count_all++] = j;
}
}
SampleList strain;
SampleList stest;
// split off samples
ModelTools::SelectSampleList (samples, strain, stest, indices_count_all, indices);
_n_total = stest.getSize ();
_result_vec = new ssi_size_t[2*_n_total];
_result_vec_ptr = _result_vec;
// train with remaining samples
_trainer->release ();
if (_preproc_mode) {
_trainer->setPreprocMode (_preproc_mode, _n_streams_refs, _stream_refs);
} else if (_fselmethod) {
_trainer->setSelection (strain, _fselmethod, _pre_fselmethod, _n_pre_feature);
}
_trainer->train (strain);
// test with remaining samples
eval_h (stest);
delete[] indices;
delete[] indices_count_lab;
}
void Evaluation::evalKFold (Trainer *trainer, ISamples &samples, ssi_size_t k) {
// init confussion matrix
_trainer = trainer;
destroy_conf_mat ();
init_conf_mat (samples);
_n_total = samples.getSize ();
_result_vec = new ssi_size_t[2*_n_total];
_result_vec_ptr = _result_vec;
ssi_size_t *indices = new ssi_size_t[samples.getSize ()];
ssi_size_t *indices_count_lab = new ssi_size_t[samples.getClassSize ()];
ssi_size_t indices_count_all;
for (ssi_size_t i = 0; i < k; ++i) {
indices_count_all = 0;
for (ssi_size_t j = 0; j < samples.getClassSize (); j++) {
indices_count_lab[j] = 0;
}
ssi_size_t label;
for (ssi_size_t j = 0; j < samples.getSize (); j++) {
label = samples.get (j)->class_id;
if (++indices_count_lab[label] % k == i) {
indices[indices_count_all++] = j;
}
}
SampleList strain;
SampleList stest;
// split off i'th fold
ModelTools::SelectSampleList (samples, stest, strain, indices_count_all, indices);
// train with i'th fold
_trainer->release ();
if (_fselmethod) {
_trainer->setSelection (strain, _fselmethod, _pre_fselmethod, _n_pre_feature);
}
if (_preproc_mode) {
_trainer->setPreprocMode (_preproc_mode, _n_streams_refs, _stream_refs);
}
_trainer->train (strain);
// test with remaining samples
eval_h (stest);
}
delete[] indices;
delete[] indices_count_lab;
}
bool Fisher::build (ISamples &samples, ssi_size_t stream_index) {
if (samples.getSize () == 0) {
ssi_wrn ("empty sample list");
return false;
}
if (isBuild ()) {
ssi_wrn ("already trained");
return false;
}
ae_state state;
ae_int_t info;
ae_matrix data;
ae_matrix_init (&data, 0, 0, DT_REAL, &state, ae_true);
// convert the samples to a matrix where the last column holds the class number to which the sample belongs
AlgLibTools::Samples2MatrixWithClass(samples, 0, &data);
_basis = new ae_matrix;
ae_matrix_init (_basis, 0, 0, DT_REAL, &state, ae_true);
fisherldan(&data,data.rows,data.cols-1 , samples.getClassSize(),&info,_basis,&state);
ae_matrix_clear (&data);
_is_build = true;
return true;
}
void Evaluation::init_conf_mat (ISamples &samples) {
_n_classes = samples.getClassSize ();
// store class names
_class_names = new ssi_char_t *[_n_classes];
for (ssi_size_t i = 0; i < _n_classes; i++) {
_class_names[i] = ssi_strcpy (samples.getClassName (i));
}
// allocate confussion matrix
_conf_mat_ptr = new ssi_size_t *[_n_classes];
_conf_mat_data = new ssi_size_t[_n_classes * _n_classes];
for (ssi_size_t i = 0; i < _n_classes; ++i) {
_conf_mat_ptr[i] = _conf_mat_data + i*_n_classes;
}
// set all elements in the confussion matrix to zero
for (ssi_size_t i = 0; i < _n_classes; ++i) {
for (ssi_size_t j = 0; j < _n_classes; ++j) {
_conf_mat_ptr[i][j] = 0;
}
}
_n_unclassified = 0;
_n_classified = 0;
}
void Evaluation::eval (IFusion &fusion, ssi_size_t n_models, IModel **models, ISamples &samples) {
// init confussion matrix
_trainer = 0;
destroy_conf_mat ();
init_conf_mat (samples);
ssi_size_t n_classes = samples.getClassSize ();
ssi_real_t *probs = new ssi_real_t[n_classes];
_n_total = samples.getSize ();
_result_vec = new ssi_size_t[2*_n_total];
_result_vec_ptr = _result_vec;
samples.reset ();
const ssi_sample_t *sample = 0;
while (sample = samples.next ()) {
ssi_size_t real_index = sample->class_id;
*_result_vec_ptr++ = real_index;
if (fusion.forward (n_models, models, sample->num, sample->streams, n_classes, probs)) {
ssi_size_t max_ind = 0;
ssi_real_t max_val = probs[0];
for (ssi_size_t i = 1; i < n_classes; i++) {
if (probs[i] > max_val) {
max_val = probs[i];
max_ind = i;
}
}
*_result_vec_ptr++ = max_ind;
_conf_mat_ptr[real_index][max_ind]++;
_n_classified++;
} else if (!_allow_unclassified) {
ssi_size_t max_ind = _default_class_id;
*_result_vec_ptr++ = max_ind;
_conf_mat_ptr[real_index][max_ind]++;
_n_classified++;
} else {
*_result_vec_ptr++ = SSI_ISAMPLES_GARBAGE_CLASS_ID;
_n_unclassified++;
}
}
delete[] probs;
}
bool MyModel::train (ISamples &samples,
ssi_size_t stream_index) {
if (samples.getSize () == 0) {
ssi_wrn ("empty sample list");
return false;
}
if (isTrained ()) {
ssi_wrn ("already trained");
return false;
}
_n_classes = samples.getClassSize ();
_n_features = samples.getStream (stream_index).dim;
_centers = new ssi_real_t *[_n_classes];
for (ssi_size_t i = 0; i < _n_classes; i++) {
_centers[i] = new ssi_real_t[_n_features];
for (ssi_size_t j = 0; j < _n_features; j++) {
_centers[i][j] = 0;
}
}
ssi_sample_t *sample;
samples.reset ();
ssi_real_t *ptr = 0;
while (sample = samples.next ()) {
ssi_size_t id = sample->class_id;
ptr = ssi_pcast (ssi_real_t, sample->streams[stream_index]->ptr);
for (ssi_size_t j = 0; j < _n_features; j++) {
_centers[id][j] += ptr[j];
}
}
for (ssi_size_t i = 0; i < _n_classes; i++) {
ssi_size_t num = samples.getSize (i);
for (ssi_size_t j = 0; j < _n_features; j++) {
_centers[i][j] /= num;
}
}
return true;
}
bool MajorityVoting::train (ssi_size_t n_models,
IModel **models,
ISamples &samples) {
if (samples.getSize () == 0) {
ssi_wrn ("empty sample list");
return false;
}
if (samples.getStreamSize () != n_models) {
ssi_wrn ("#models (%u) differs from #streams (%u)", n_models, samples.getStreamSize ());
return false;
}
if (isTrained ()) {
ssi_wrn ("already trained");
return false;
}
_n_streams = samples.getStreamSize ();
_n_classes = samples.getClassSize ();
_n_models = n_models;
if (samples.hasMissingData ()) {
ISMissingData samples_h (&samples);
for (ssi_size_t n_model = 0; n_model < n_models; n_model++) {
if (!models[n_model]->isTrained ()) {
samples_h.setStream (n_model);
models[n_model]->train (samples_h, n_model);
}
}
}
else{
for (ssi_size_t n_model = 0; n_model < n_models; n_model++) {
if (!models[n_model]->isTrained ()) { models[n_model]->train (samples, n_model); }
}
}
return true;
}
bool SimpleKNN::train (ISamples &samples,
ssi_size_t stream_index) {
if (samples.getSize () == 0) {
ssi_wrn ("empty sample list");
return false;
}
if (samples.getSize () < _options.k) {
ssi_wrn ("sample list has less than '%u' entries", _options.k);
return false;
}
if (isTrained ()) {
ssi_wrn ("already trained");
return false;
}
_n_classes = samples.getClassSize ();
_n_samples = samples.getSize ();
_n_features = samples.getStream (stream_index).dim;
_data = new ssi_real_t[_n_features*_n_samples];
_classes = new ssi_size_t[_n_samples];
ssi_sample_t *sample;
samples.reset ();
ssi_real_t *data_ptr = _data;
ssi_size_t *class_ptr = _classes;
ssi_stream_t *stream_ptr = 0;
ssi_size_t bytes_to_copy = _n_features * sizeof (ssi_real_t);
while (sample = samples.next ()) {
memcpy (data_ptr, sample->streams[stream_index]->ptr, bytes_to_copy);
*class_ptr++ = sample->class_id;
data_ptr += _n_features;
}
return true;
}
bool FileSamplesOut::open (ISamples &data,
const ssi_char_t *path,
File::TYPE type,
File::VERSION version) {
ssi_msg (SSI_LOG_LEVEL_DETAIL, "open files '%s'", path);
_version = version;
if (_version < File::V2) {
ssi_wrn ("version < V2 not supported");
return false;
}
if (_file_info || _file_data) {
ssi_wrn ("samples already open");
return false;
}
_n_users = data.getUserSize ();
_users = new ssi_char_t *[_n_users];
_n_per_user = new ssi_size_t[_n_users];
for (ssi_size_t i = 0; i < _n_users; i++) {
_users[i] = ssi_strcpy (data.getUserName (i));
_n_per_user[i] = 0;
}
_n_classes = data.getClassSize ();
_classes = new ssi_char_t *[_n_classes];
_n_per_class = new ssi_size_t[_n_classes];
for (ssi_size_t i = 0; i < _n_classes; i++) {
_classes[i] = ssi_strcpy (data.getClassName (i));
_n_per_class[i] = 0;
}
_n_streams = data.getStreamSize ();
_streams = new ssi_stream_t[_n_streams];
for (ssi_size_t i = 0; i < _n_streams; i++) {
ssi_stream_t s = data.getStream (i);
ssi_stream_init (_streams[i], 0, s.dim, s.byte, s.type, s.sr, 0);
}
_has_missing_data = false;
if (path == 0 || path[0] == '\0') {
_console = true;
}
if (_console) {
_file_data = File::CreateAndOpen (type, File::WRITE, "");
if (!_file_data) {
ssi_wrn ("could not open console");
return false;
}
} else {
FilePath fp (path);
ssi_char_t *path_info = 0;
if (strcmp (fp.getExtension (), SSI_FILE_TYPE_SAMPLES) != 0) {
path_info = ssi_strcat (path, SSI_FILE_TYPE_SAMPLES);
} else {
path_info = ssi_strcpy (path);
}
_path = ssi_strcpy (path_info);
_file_info = File::CreateAndOpen (File::ASCII, File::WRITE, path_info);
if (!_file_info) {
ssi_wrn ("could not open info file '%s'", path_info);
return false;
}
ssi_sprint (_string, "<?xml version=\"1.0\" ?>\n<samples ssi-v=\"%d\">", version);
_file_info->writeLine (_string);
ssi_char_t *path_data = ssi_strcat (path_info, "~");
_file_data = File::CreateAndOpen (type, File::WRITE, path_data);
if (!_file_data) {
ssi_wrn ("could not open data file '%s'", path_data);
return false;
}
if (_version == File::V3) {
_file_streams = new FileStreamOut[_n_streams];
ssi_char_t string[SSI_MAX_CHAR];
for (ssi_size_t i = 0; i < _n_streams; i++) {
ssi_sprint (string, "%s.#%u", path_info, i);
_file_streams[i].open (_streams[i], string, type);
}
}
delete[] path_info;
delete[] path_data;
}
return true;
};
bool FeatureFusion::train (ssi_size_t n_models,
IModel **models,
ISamples &samples) {
if (samples.getSize () == 0) {
ssi_wrn ("empty sample list");
return false;
}
if (isTrained ()) {
ssi_wrn ("already trained");
return false;
}
_n_streams = samples.getStreamSize ();
_n_classes = samples.getClassSize ();
_n_models = n_models;
//initialize weights
ssi_real_t **weights = new ssi_real_t*[n_models];
for (ssi_size_t n_model = 0; n_model < n_models; n_model++) {
weights[n_model] = new ssi_real_t[_n_classes+1];
}
if (samples.hasMissingData ()) {
_handle_md = true;
ISMissingData samples_h (&samples);
Evaluation eval;
if (ssi_log_level >= SSI_LOG_LEVEL_DEBUG) {
ssi_print("\nMissing data detected.\n");
}
//models[0] is featfuse_model, followed by singlechannel_models
ISMergeDim ffusionSamples (&samples);
ISMissingData ffusionSamples_h (&ffusionSamples);
ffusionSamples_h.setStream(0);
if (!models[0]->isTrained ()) { models[0]->train (ffusionSamples_h, 0); }
if (ssi_log_level >= SSI_LOG_LEVEL_DEBUG) {
eval.eval (*models[0], ffusionSamples_h, 0);
eval.print();
}
//dummy weights for fused model
for (ssi_size_t n_class = 0; n_class < _n_classes; n_class++) {
weights[0][n_class] = 0.0f;
}
weights[0][_n_classes] = 0.0f;
for (ssi_size_t n_model = 1; n_model < n_models; n_model++) {
if (!models[n_model]->isTrained ()) {
samples_h.setStream (n_model - 1);
models[n_model]->train (samples_h, n_model - 1);
}
eval.eval (*models[n_model], samples_h, n_model - 1);
if (ssi_log_level >= SSI_LOG_LEVEL_DEBUG) {
eval.print();
}
for (ssi_size_t n_class = 0; n_class < _n_classes; n_class++) {
weights[n_model][n_class] = eval.get_class_prob (n_class);
}
weights[n_model][_n_classes] = eval.get_classwise_prob ();
}
//calculate fillers
_filler = new ssi_size_t[_n_streams];
for (ssi_size_t n_fill = 0; n_fill < _n_streams; n_fill++) {
_filler[n_fill] = 1;
ssi_real_t filler_weight = weights[1][_n_classes];
for (ssi_size_t n_model = 2; n_model < n_models; n_model++) {
if (filler_weight < weights[n_model][_n_classes]) {
_filler[n_fill] = n_model;
filler_weight = weights[n_model][_n_classes];
}
}
weights[_filler[n_fill]][_n_classes] = 0.0f;
}
if (ssi_log_level >= SSI_LOG_LEVEL_DEBUG) {
ssi_print("\nfiller:\n");
for (ssi_size_t n_model = 0; n_model < _n_streams; n_model++) {
ssi_print("%d ", _filler[n_model]);
}ssi_print("\n");
}
}
else{
_handle_md = false;
if (ssi_log_level >= SSI_LOG_LEVEL_DEBUG) {
ssi_print("\nNo missing data detected.\n");
}
ISMergeDim ffusionSamples (&samples);
if (!models[0]->isTrained ()) { models[0]->train (ffusionSamples, 0); }
//dummy
_filler = new ssi_size_t[_n_streams];
for (ssi_size_t n_fill = 0; n_fill < _n_streams; n_fill++) {
_filler[n_fill] = 0;
}
}
if (weights) {
for (ssi_size_t n_model = 0; n_model < _n_models; n_model++) {
delete[] weights[n_model];
}
delete[] weights;
weights = 0;
}
return true;
}
bool WeightedMajorityVoting::train (ssi_size_t n_models,
IModel **models,
ISamples &samples) {
if (samples.getSize () == 0) {
ssi_wrn ("empty sample list");
return false;
}
if (samples.getStreamSize () != n_models) {
ssi_wrn ("#models (%u) differs from #streams (%u)", n_models, samples.getStreamSize ());
return false;
}
if (isTrained ()) {
ssi_wrn ("already trained");
return false;
}
_n_streams = samples.getStreamSize ();
_n_classes = samples.getClassSize ();
_n_models = n_models;
_weights = new ssi_real_t*[n_models];
for (ssi_size_t n_model = 0; n_model < n_models; n_model++) {
_weights[n_model] = new ssi_real_t[_n_classes+1];
}
if (samples.hasMissingData ()) {
ISMissingData samples_h (&samples);
Evaluation eval;
for (ssi_size_t n_model = 0; n_model < n_models; n_model++) {
if (!models[n_model]->isTrained ()) {
samples_h.setStream (n_model);
models[n_model]->train (samples_h, n_model);
}
eval.eval (*models[n_model], samples_h, n_model);
for (ssi_size_t n_class = 0; n_class < _n_classes; n_class++) {
_weights[n_model][n_class] = eval.get_class_prob (n_class);
}
_weights[n_model][_n_classes] = eval.get_classwise_prob ();
}
}
else{
Evaluation eval;
for (ssi_size_t n_model = 0; n_model < n_models; n_model++) {
if (!models[n_model]->isTrained ()) { models[n_model]->train (samples, n_model); }
eval.eval (*models[n_model], samples, n_model);
for (ssi_size_t n_class = 0; n_class < _n_classes; n_class++) {
_weights[n_model][n_class] = eval.get_class_prob (n_class);
}
_weights[n_model][_n_classes] = eval.get_classwise_prob ();
}
}
if (ssi_log_level >= SSI_LOG_LEVEL_DEBUG) {
ssi_print("\nClassifier Weights: \n");
for (ssi_size_t n_model = 0; n_model < n_models; n_model++) {
for (ssi_size_t n_class = 0; n_class < _n_classes; n_class++) {
ssi_print ("%f ", _weights[n_model][n_class]);
}
ssi_print ("%f\n", _weights[n_model][_n_classes]);
}
}
return true;
}