def import_eeglab_sets(filepaths, target_path):
# try load metadata-db
metadb_file = os.path.join(target_path, 'metadata_db.pklz')
if os.path.exists(metadb_file) and os.path.isfile(metadb_file):
metadb = load(metadb_file)
log.info('metadb loaded from {}'.format(metadb_file))
else:
metadb = {} # empty DB
log.info('no metadb found at {}. using empty db'.format(metadb_file))
for filepath in filepaths:
# load extra data
filename = os.path.basename(filepath)
data, metadata = load_eeglab_data(filepath)
# save data
savepath = generate_filepath_from_metadata(metadata)
save(os.path.join(target_path, savepath), (data, metadata),
mkdirs=True)
# save metadata
metadb[savepath] = metadata
save(metadb_file, metadb, mkdirs=True)
log.debug('imported as {}'.format(savepath))
def extract_output(experiment_root):
train, model = load_results(experiment_root);
# get the datasets with their names from the monitor
for key, dataset in train.algorithm.monitoring_dataset.items():
# process each dataset
with log_timing(log, 'processing dataset \'{}\''.format(key)):
y_real, y_pred, output = process_dataset(model, dataset)
save(os.path.join(experiment_root, 'cache', key+'_output.pklz'), (y_real, y_pred, output));
def extract_output(experiment_root):
train, model = load_results(experiment_root)
# get the datasets with their names from the monitor
for key, dataset in train.algorithm.monitoring_dataset.items():
# process each dataset
with log_timing(log, 'processing dataset \'{}\''.format(key)):
y_real, y_pred, output = process_dataset(model, dataset)
save(os.path.join(experiment_root, 'cache', key + '_output.pklz'),
(y_real, y_pred, output))
def split_trial(path, trial_len):
log.info('processing {}'.format(path))
datafile = glob.glob(os.path.join(path, '*.txt'))[0]
metafile = glob.glob(os.path.join(path, '*_Trials_Onsets.xlsx'))[0]
log.debug('data file: {}'.format(datafile))
log.debug('meta file: {}'.format(metafile))
onsets = load_xlsx_meta_file(metafile)
data = load_data_file(datafile)
log.debug(onsets)
onsets.append([len(data), 'end'])
# artificial last marker
trials = {}
for i in xrange(len(onsets) - 1):
onset, label = onsets[i]
next_onset = onsets[i + 1][0]
# rounding to integers
onset = int(math.floor(float(onset)))
next_onset = int(math.floor(float(next_onset)))
next_onset = min(onset + trial_len, next_onset)
log.debug('[{}..{}) -> {}'.format(onset, next_onset, label))
trial_data = np.vstack(data[onset:next_onset])
log.debug('{} samples extracted'.format(trial_data.shape))
trials[label] = trial_data
filename = os.path.join(path, 'trials.pklz')
with log_timing(log, 'saving to {}'.format(filename)):
save(filename, trials)
return trials
def split_trial(path, trial_len):
log.info('processing {}'.format(path));
datafile = glob.glob(os.path.join(path,'*.txt'))[0];
metafile = glob.glob(os.path.join(path,'*_Trials_Onsets.xlsx'))[0];
log.debug('data file: {}'.format(datafile));
log.debug('meta file: {}'.format(metafile));
onsets = load_xlsx_meta_file(metafile);
data = load_data_file(datafile);
log.debug(onsets);
onsets.append([len(data), 'end']); # artificial last marker
trials = {};
for i in xrange(len(onsets) - 1):
onset, label = onsets[i];
next_onset = onsets[i+1][0];
# rounding to integers
onset = int(math.floor(float(onset)));
next_onset = int(math.floor(float(next_onset)));
next_onset = min(onset+trial_len, next_onset);
log.debug('[{}..{}) -> {}'.format(onset, next_onset, label));
trial_data = np.vstack(data[onset:next_onset]);
log.debug('{} samples extracted'.format(trial_data.shape));
trials[label] = trial_data;
filename = os.path.join(path, 'trials.pklz');
with log_timing(log, 'saving to {}'.format(filename)):
save(filename, trials);
return trials;
def import_eeglab_sets(filepaths, target_path):
# try load metadata-db
metadb_file = os.path.join(target_path, 'metadata_db.pklz')
if os.path.exists(metadb_file) and os.path.isfile(metadb_file):
metadb = load(metadb_file)
log.info('metadb loaded from {}'.format(metadb_file))
else:
metadb = {} # empty DB
log.info('no metadb found at {}. using empty db'.format(metadb_file))
for filepath in filepaths:
# load extra data
filename = os.path.basename(filepath)
data, metadata = load_eeglab_data(filepath)
# save data
savepath = generate_filepath_from_metadata(metadata)
save(os.path.join(target_path, savepath), (data, metadata), mkdirs=True)
# save metadata
metadb[savepath] = metadata
save(metadb_file, metadb, mkdirs=True)
log.debug('imported as {}'.format(savepath))
def save(filepath, data):
return fs_util.save(filepath, data)
#, case_sensitive=False, limit=None, offset=0)
for filename in files:
x, y = loadfile(filename,
auto_sample_rate=config.audio.autpsamplerate,
samplerate=config.audio.samplerate,
barsamples=config.audio.barsamples,
maxbars=config.audio.maxbars)
data.append(x)
labels.append(y)
data = np.vstack(data)
# transform list to a big numpy array by stacking
labels = np.vstack(labels)
logging.info('loaded {0} values from {1} files in total'.format(
data.shape, len(files)))
# print labels;
return (data, labels)
if __name__ == '__main__':
#pass
# logging.basicConfig(format='%(asctime)s - %(levelname)s - %(message)s', level=logging.DEBUG);
# global config;
config = Config(file('deepbeat.cfg'))
logging.basicConfig(format=config.logger.pattern, level=logging.DEBUG)
dataset = loadall(config.audio.path)
#split = splitdata(dataset, ptest=config.audio.ptest, pvalid=config.audio.pvalid);
#save(config.audio.datasetpath, split);
save(config.audio.datasetpath, dataset)
# load();
def import_dataset(source_path, target_path):
# config = load_config(default_config='../train_sda.cfg');
# DATA_ROOT = source_path
# DATA_ROOT = config.eeg.get('dataset_root', './')
SAMPLE_RATE = 400 # in Hz
TRIAL_LENGTH = 32 # in sec
TRIAL_LENGTH += 4 # add 4s after end of presentation
TRIAL_SAMPLE_LENGTH = SAMPLE_RATE * TRIAL_LENGTH
log.info('using dataset at {}'.format(source_path))
'''
Note from Dan:
All subjects should have channels 15, 16, 17 and 18 removed [...]
If you want to make them truly identical, you could remove channel 19 from
the subjects with more channels, although this should be 'good' data.
'''
bad_channels = {}
bad_channels[1] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[2] = [7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[3] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[4] = [7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[5] = [7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[6] = [7, 8, 9, 12, 15, 16, 17, 18]
bad_channels[7] = [5, 6, 12, 15, 16, 17, 18, 20]
bad_channels[8] = [7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[9] = [5, 6, 12, 15, 16, 17, 18, 20]
bad_channels[10] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[11] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[12] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[13] = [5, 6, 12, 15, 16, 17, 18, 20]
label_converter = LabelConverter()
metadb_file = os.path.join(target_path, 'metadata_db.pklz')
metadb = {} # empty DB
with log_timing(log, 'generating datasets'):
for subject_id in xrange(1, 14):
search_path = os.path.join(source_path,
'Sub{0:03d}*'.format(subject_id))
sourcefile_path = glob.glob(search_path)
if sourcefile_path is None or len(sourcefile_path) == 0:
log.warn('nothing found at {}'.format(search_path))
continue
else:
sourcefile_path = sourcefile_path[0]
trials = split_session(sourcefile_path, TRIAL_SAMPLE_LENGTH)
for stimulus, trial_data in trials.iteritems():
stimulus_id = label_converter.get_stimulus_id(stimulus)
log.debug(
'processing {} with {} samples and stimulus_id {}'.format(
stimulus, trial_data.shape, stimulus_id))
channels = trial_data.transpose()
trial_data = []
channel_ids = []
for i, channel in enumerate(channels):
channel_id = i + 1
# filter bad channels
if channel_id in bad_channels[subject_id]:
log.debug('skipping bad channel {}'.format(channel_id))
continue
# convert to float32
channel = np.asfarray(channel, dtype='float32')
trial_data.append(channel)
channel_ids.append(channel_id)
trial_data = np.vstack(
trial_data).transpose() # fromat: (samples, channels)
log.debug('extracted {} from channels: {}'.format(
trial_data.shape, channel_ids))
label = label_converter.get_label(
stimulus_id, 'rhythm') # raw label, unsorted
label = label_converter.shuffle_classes[
label] # sorted label id
metadata = {
'subject':
subject_id,
'label':
label,
'meta_label':
label_converter.get_label(stimulus_id, 'rhythm_meta'),
'stimulus':
stimulus,
'stimulus_id':
stimulus_id,
'rhythm_type':
label_converter.get_label(stimulus_id, 'rhythm'),
'tempo':
label_converter.get_label(stimulus_id, 'tempo'),
'audio_file':
label_converter.get_label(stimulus_id, 'audio_file'),
'trial_no':
1,
'trial_type':
'perception',
'condition':
'n/a',
'channels':
channel_ids,
}
# save data
savepath = generate_filepath_from_metadata(metadata)
save(os.path.join(target_path, savepath),
(trial_data, metadata),
mkdirs=True)
# save metadata
metadb[savepath] = metadata
log.debug('imported {}={} as {}'.format(
label, metadata['meta_label'], savepath))
save(metadb_file, metadb, mkdirs=True)
log.info('import finished')
def preprocess(config):
# config = load_config(default_config='../train_sda.cfg');
DATA_ROOT = config.eeg.get('dataset_root', './');
SAMPLE_RATE = 400; # in Hz
TRIAL_LENGTH = 32; # in sec
TRIAL_LENGTH += 4; # add 4s after end of presentation
TRIAL_SAMPLE_LENGTH = SAMPLE_RATE * TRIAL_LENGTH;
log.info('using dataset at {}'.format(DATA_ROOT));
'''
Note from Dan:
All subjects should have channels 15, 16, 17 and 18 removed [...]
If you want to make them truly identical, you could remove channel 19 from
the subjects with more channels, although this should be 'good' data.
'''
bad_channels = {};
bad_channels[1] = [5, 6, 15, 16, 17, 18, 20, 21];
bad_channels[2] = [ 7, 8, 15, 16, 17, 18, 20, 21];
bad_channels[3] = [5, 6, 15, 16, 17, 18, 20, 21];
bad_channels[4] = [ 7, 8, 15, 16, 17, 18, 20, 21];
bad_channels[5] = [ 7, 8, 15, 16, 17, 18, 20, 21];
bad_channels[6] = [ 7, 8, 9, 12, 15, 16, 17, 18 ];
bad_channels[7] = [5, 6, 12, 15, 16, 17, 18, 20 ];
bad_channels[8] = [ 7, 8, 15, 16, 17, 18, 20, 21];
bad_channels[9] = [5, 6, 12, 15, 16, 17, 18, 20 ];
bad_channels[10] = [5, 6, 15, 16, 17, 18, 20, 21];
bad_channels[11] = [5, 6, 15, 16, 17, 18, 20, 21];
bad_channels[12] = [5, 6, 15, 16, 17, 18, 20, 21];
bad_channels[13] = [5, 6, 12, 15, 16, 17, 18, 20 ];
with log_timing(log, 'generating datasets'):
for subject_id in xrange(1,14):
search_path = os.path.join(DATA_ROOT, 'Sub{0:03d}*'.format(subject_id));
path = glob.glob(search_path);
if path is None or len(path) == 0:
log.warn('nothing found at {}'.format(search_path));
continue;
else:
path = path[0];
trials_filename = os.path.join(path, 'trials.pklz');
trials = None;
if not os.path.isfile(trials_filename):
log.debug('{} not found. running split_trial()'.format(trials_filename));
trials = split_trial(path, TRIAL_SAMPLE_LENGTH);
else:
with log_timing(log, 'loading data from {}'.format(trials_filename)):
trials = load(trials_filename);
assert trials;
dataset_filename = os.path.join(path, 'dataset_13goodchannels_plus4s.pklz');
dataset = generate_cases(subject_id, trials, bad_channels[subject_id]); # = data, labels
with log_timing(log, 'saving dataset to {}'.format(dataset_filename)):
save(dataset_filename, dataset);
def preprocess(config):
# config = load_config(default_config='../train_sda.cfg');
DATA_ROOT = config.eeg.get('dataset_root', './')
SAMPLE_RATE = 400
# in Hz
TRIAL_LENGTH = 32
# in sec
TRIAL_LENGTH += 4
# add 4s after end of presentation
TRIAL_SAMPLE_LENGTH = SAMPLE_RATE * TRIAL_LENGTH
log.info('using dataset at {}'.format(DATA_ROOT))
'''
Note from Dan:
All subjects should have channels 15, 16, 17 and 18 removed [...]
If you want to make them truly identical, you could remove channel 19 from
the subjects with more channels, although this should be 'good' data.
'''
bad_channels = {}
bad_channels[1] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[2] = [7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[3] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[4] = [7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[5] = [7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[6] = [7, 8, 9, 12, 15, 16, 17, 18]
bad_channels[7] = [5, 6, 12, 15, 16, 17, 18, 20]
bad_channels[8] = [7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[9] = [5, 6, 12, 15, 16, 17, 18, 20]
bad_channels[10] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[11] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[12] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[13] = [5, 6, 12, 15, 16, 17, 18, 20]
with log_timing(log, 'generating datasets'):
for subject_id in xrange(1, 14):
search_path = os.path.join(DATA_ROOT,
'Sub{0:03d}*'.format(subject_id))
path = glob.glob(search_path)
if path is None or len(path) == 0:
log.warn('nothing found at {}'.format(search_path))
continue
else:
path = path[0]
trials_filename = os.path.join(path, 'trials.pklz')
trials = None
if not os.path.isfile(trials_filename):
log.debug('{} not found. running split_trial()'.format(
trials_filename))
trials = split_trial(path, TRIAL_SAMPLE_LENGTH)
else:
with log_timing(
log, 'loading data from {}'.format(trials_filename)):
trials = load(trials_filename)
assert trials
dataset_filename = os.path.join(
path, 'dataset_13goodchannels_plus4s.pklz')
dataset = generate_cases(subject_id, trials,
bad_channels[subject_id])
# = data, labels
with log_timing(log,
'saving dataset to {}'.format(dataset_filename)):
save(dataset_filename, dataset)
def run(self, classifiers=(), verbose=False, debug=False):
print 'running job #{}'.format(self.job_id)
import deepthought.util.fs_util as fs_util
fs_util.ensure_dir_exists(self.output_path)
print 'output path: ', self.output_path
# prepare result objects
results = {k: ClassificationResult(k) for (k, _) in classifiers}
# load full dataset with all sources only once!
from deepthought.datasets.hdf5 import get_dataset
self.full_hdf5, self.full_meta = get_dataset(self.hdf5name, selectors=self.base_selectors, sources=None)
self.initialize()
# main loop ###
# outer cross-validation
outer_folds = self.fold_generator.get_outer_cv_folds()
for ofi, ofold in enumerate(outer_folds):
print 'processing outer fold', ofold
# phase I : pre-train features ###
encoder_fn = self.pretrain_encoder(ofi, ofold) # FIXME: add params
# phase II : classify ###
train_selectors = self.fold_generator.get_fold_selectors(outer_fold=ofold['train'])
X_train, Y_train, meta_train = self.get_encoded_dataset(encoder_fn, train_selectors)
test_selectors = self.fold_generator.get_fold_selectors(outer_fold=ofold['valid'])
X_test, Y_test, _ = self.get_encoded_dataset(encoder_fn, test_selectors)
for (classifier_name, classifier_factory) in classifiers:
result = results[classifier_name]
model_prefix = os.path.join(self.output_path, '{}_fold_{}'.format(classifier_name, ofi))
# generate index folds
idx_folds = []
from deepthought.datasets.selection import DatasetMetaDB
for ifold in self.fold_generator.get_inner_cv_folds(ofold):
train_selectors = self.fold_generator.get_fold_selectors(outer_fold=ofold['train'],
inner_fold=ifold['train'])
metadb = DatasetMetaDB(meta_train, train_selectors.keys())
if 'valid' in ifold.keys():
valid_selectors = self.fold_generator.get_fold_selectors(outer_fold=ofold['train'],
inner_fold=ifold['valid'])
else:
valid_selectors = None
if debug:
print 'train_selectors:', train_selectors
print 'valid_selectors:', valid_selectors
# get selected trial IDs
train_idx = metadb.select(train_selectors)
if valid_selectors is not None:
valid_idx = metadb.select(valid_selectors)
else:
valid_idx = []
idx_folds.append((train_idx, valid_idx))
if debug:
print idx_folds # print the generated folds before running the classifier
# train classifier
classifier, predict_fn = classifier_factory.train(X_train, Y_train, idx_folds, self.hyper_params, model_prefix)
# test classifier
train_Y_pred = predict_fn(X_train)
test_Y_pred = predict_fn(X_test)
# append to result
result.append_train(Y_train, train_Y_pred)
result.append_test(Y_test, test_Y_pred)
# result.fold_scores.append(classifier.score(X_test, Y_test))
result.fold_scores.append(np.mean(Y_test == test_Y_pred))
if verbose:
print '{} results for fold {}'.format(classifier_name, ofold)
print classification_report(Y_test, test_Y_pred)
print confusion_matrix(Y_test, test_Y_pred)
print 'overall test accuracy so far:', 1 - result.test_error()
print 'all folds completed'
for (classifier_name, _) in classifiers:
result = results[classifier_name]
fs_util.save(os.path.join(self.output_path, '{}_result.pklz'.format(classifier_name)), result) # result
print
print 'SUMMARY for classifier', classifier_name
print
print 'fold scores: ', np.asarray(result.fold_scores)
print
print classification_report(result.test_Y_real, result.test_Y_pred)
print confusion_matrix(result.test_Y_real, result.test_Y_pred)
print
print 'train accuracy:', 1 - result.train_error()
print 'test accuracy :', 1 - result.test_error()
return [results[classifier[0]].test_error() for classifier in classifiers] # error for each classifier
def pretrain_encoder(self, outer_fold_index, outer_fold):
"""
generic template that works with any model structure
:param outer_fold_index:
:param outer_fold:
:return:
"""
import deepthought.util.fs_util as fs_util
from deepthought.util.function_util import get_function
fold_params_filename = os.path.join(self.output_path, 'fold_params_{}.pklz'.format(outer_fold_index))
inner_folds = self.fold_generator.get_inner_cv_folds(outer_fold)
if os.path.isfile(fold_params_filename):
# load trained network parameters from existing file
fold_param_values = fs_util.load(fold_params_filename)
print 'loaded trained fold network parameters from', fold_params_filename
#assert len(fold_param_values) == len(inner_folds)
else:
# compute trial fold models
fold_param_values = []
fold_errors = []
for ifi, ifold in enumerate(inner_folds):
log.info('processing fold {}.{}: {}'.format(outer_fold_index, ifi, ifold))
train_selectors = self.fold_generator.get_fold_selectors(
outer_fold=outer_fold['train'], inner_fold=ifold['train'], base_selectors=self.base_selectors)
if 'valid' in ifold.keys():
valid_selectors = self.fold_generator.get_fold_selectors(
outer_fold=outer_fold['train'], inner_fold=ifold['valid'], base_selectors=self.base_selectors)
else:
valid_selectors = None
self.pretrain_model.set_parameter_values(self.init_param_values) # reset weights
trained_model_param_values, best_error_valid = self.pretrain(
self.pretrain_model, self.hyper_params,
self.full_hdf5, self.full_meta,
train_selectors, valid_selectors)
fold_param_values.append(trained_model_param_values)
fold_errors.append(best_error_valid)
if 'only_1_inner_fold' in self.hyper_params and self.hyper_params['only_1_inner_fold']:
print 'Stop after 1 inner fold requested (only_1_inner_fold=True).'
break
fold_errors = np.asarray(fold_errors).squeeze()
print 'fold errors:', fold_errors
# store trained network parameters for later analysis
fs_util.save(fold_params_filename, fold_param_values)
print 'parameters saved to', fold_params_filename
# build encoder
encoder = self.encoder_pipeline_factory.set_pipeline_parameters(self.encoder_model, fold_param_values)
# transform dataset (re-using data_dict and working with indices as input)
encoder_fn = get_function(encoder, allow_input_downcast=True)
return encoder_fn
files = librosa.util.find_files(path, ext='wav', recurse=True); #, case_sensitive=False, limit=None, offset=0)
for filename in files:
x, y = loadfile(
filename,
auto_sample_rate=config.audio.autpsamplerate,
samplerate=config.audio.samplerate,
barsamples=config.audio.barsamples,
maxbars=config.audio.maxbars);
data.append(x);
labels.append(y);
data = np.vstack(data); # transform list to a big numpy array by stacking
labels = np.vstack(labels);
logging.info('loaded {0} values from {1} files in total'.format(data.shape, len(files)));
# print labels;
return (data, labels);
if __name__ == '__main__':
#pass
# logging.basicConfig(format='%(asctime)s - %(levelname)s - %(message)s', level=logging.DEBUG);
# global config;
config = Config(file('deepbeat.cfg'));
logging.basicConfig(format=config.logger.pattern, level=logging.DEBUG);
dataset = loadall(config.audio.path);
#split = splitdata(dataset, ptest=config.audio.ptest, pvalid=config.audio.pvalid);
#save(config.audio.datasetpath, split);
save(config.audio.datasetpath, dataset);
# load();
def save(filepath, data):
return fs_util.save(filepath, data);
def import_dataset(source_path, target_path):
# config = load_config(default_config='../train_sda.cfg');
# DATA_ROOT = source_path
# DATA_ROOT = config.eeg.get('dataset_root', './')
SAMPLE_RATE = 400 # in Hz
TRIAL_LENGTH = 32 # in sec
TRIAL_LENGTH += 4 # add 4s after end of presentation
TRIAL_SAMPLE_LENGTH = SAMPLE_RATE * TRIAL_LENGTH
log.info('using dataset at {}'.format(source_path))
'''
Note from Dan:
All subjects should have channels 15, 16, 17 and 18 removed [...]
If you want to make them truly identical, you could remove channel 19 from
the subjects with more channels, although this should be 'good' data.
'''
bad_channels = {}
bad_channels[1] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[2] = [ 7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[3] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[4] = [ 7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[5] = [ 7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[6] = [ 7, 8, 9, 12, 15, 16, 17, 18 ]
bad_channels[7] = [5, 6, 12, 15, 16, 17, 18, 20 ]
bad_channels[8] = [ 7, 8, 15, 16, 17, 18, 20, 21]
bad_channels[9] = [5, 6, 12, 15, 16, 17, 18, 20 ]
bad_channels[10] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[11] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[12] = [5, 6, 15, 16, 17, 18, 20, 21]
bad_channels[13] = [5, 6, 12, 15, 16, 17, 18, 20 ]
label_converter = LabelConverter()
metadb_file = os.path.join(target_path, 'metadata_db.pklz')
metadb = {} # empty DB
with log_timing(log, 'generating datasets'):
for subject_id in xrange(1,14):
search_path = os.path.join(source_path, 'Sub{0:03d}*'.format(subject_id))
sourcefile_path = glob.glob(search_path)
if sourcefile_path is None or len(sourcefile_path) == 0:
log.warn('nothing found at {}'.format(search_path))
continue
else:
sourcefile_path = sourcefile_path[0]
trials = split_session(sourcefile_path, TRIAL_SAMPLE_LENGTH)
for stimulus, trial_data in trials.iteritems():
stimulus_id = label_converter.get_stimulus_id(stimulus)
log.debug('processing {} with {} samples and stimulus_id {}'.
format(stimulus,trial_data.shape,stimulus_id))
channels = trial_data.transpose()
trial_data = []
channel_ids = []
for i, channel in enumerate(channels):
channel_id = i+1
# filter bad channels
if channel_id in bad_channels[subject_id]:
log.debug('skipping bad channel {}'.format(channel_id))
continue
# convert to float32
channel = np.asfarray(channel, dtype='float32')
trial_data.append(channel)
channel_ids.append(channel_id)
trial_data = np.vstack(trial_data).transpose() # fromat: (samples, channels)
log.debug('extracted {} from channels: {}'.format(trial_data.shape, channel_ids))
label = label_converter.get_label(stimulus_id, 'rhythm') # raw label, unsorted
label = label_converter.shuffle_classes[label] # sorted label id
metadata = {
'subject' : subject_id,
'label' : label,
'meta_label' : label_converter.get_label(stimulus_id, 'rhythm_meta'),
'stimulus' : stimulus,
'stimulus_id' : stimulus_id,
'rhythm_type' : label_converter.get_label(stimulus_id, 'rhythm'),
'tempo' : label_converter.get_label(stimulus_id, 'tempo'),
'audio_file' : label_converter.get_label(stimulus_id, 'audio_file'),
'trial_no' : 1,
'trial_type' : 'perception',
'condition' : 'n/a',
'channels' : channel_ids,
}
# save data
savepath = generate_filepath_from_metadata(metadata)
save(os.path.join(target_path, savepath), (trial_data, metadata), mkdirs=True)
# save metadata
metadb[savepath] = metadata
log.debug('imported {}={} as {}'.format(label, metadata['meta_label'], savepath))
save(metadb_file, metadb, mkdirs=True)
log.info('import finished')