def make(fo):
print('making artifacts, cnn bad epoch, xml files per block')
cnn_model_name = 'cnn_5X5_2048_1'
for i in range(1, 49):
p = e.Participant(i, fid2ort=fo)
p.add_all_sessions()
for s in p.sessions:
for b in s.blocks:
if not os.path.isfile(path.eeg100hz + windower.make_name(b) +
'.npy'):
continue
if b.start_marker_missing or b.end_marker_missing:
d = load_100hz_numpy_block(windower.make_name(b))
w = windower.Windower(b, nsamples=d.shape[1], sf=100)
w = windower.Windower(b, sf=100)
if not os.path.isfile(path.artifact_data_all_pp + w.name +
'_pred.npy'):
print(path.artifact_data_all_pp + w.name + '_pred.npy',
'no prediction file present')
continue
a = xml_cnn.xml_cnn(w)
a.make_bad_epoch()
a.bad_epochs2xml()
a.write_bad_epoch_xml()
print(w.name)
def block2eegdata(self,b): '''Load the 100hz eeg data that corresponds to the block object and returns a windowed version of it, identical to the method used in make_artifact_matrix_v2.py.''' self.clean_up() self.d = load_100hz_numpy_block(windower.make_name(b)) if b.start_marker_missing or b.end_marker_missing: # the eeg data in d has a sf 100, windower expects an sf 1000, the sf parameter adjust the start and end times of snippets, therefore the nsamples needs to be multiplied by 10. w = windower.Windower(b,nsamples= self.d.shape[1] * 10, sf = 100,window_overlap_percentage = .99) else: w = windower.Windower(b,sf = 100,window_overlap_percentage = .99) self.d = remove_channels(self.d) self.d = windower.window_data(self.d,w.windows['sf100'],flatten=True,normalize= True)
def make_matrix(fo, add_pp_info = False,normalize_data = True,save_directory =None,make_data= True):
print('making artifact training np matrices per block, with default 1 sec and 99 perc overlap')
if save_directory == None: save_directory = path.artifact_training_data
print('save directory:',save_directory)
if make_data: fout = open('nrows_per_block_v2','w')
nrows = 0
for i in range(1,49):
p = e.Participant(i,fid2ort = fo)
p.add_all_sessions()
for s in p.sessions:
for b in s.blocks:
if os.path.isfile(path.artifact_training_data+ windower.make_name(b) +'.npy'):
# check whether windowed data is already present
continue
if not os.path.isfile(path.eeg100hz + windower.make_name(b) +'.npy'):
# check whether downsampled data is present to load
continue
print(windower.make_name(b))
d = load_100hz_numpy_block(windower.make_name(b))
if b.start_marker_missing or b.end_marker_missing:
w = windower.Windower(b,nsamples= d.shape[1], sf = 100,window_overlap_percentage = .99)
else:
w = windower.Windower(b,sf = 100,window_overlap_percentage = .99)
if w.fn_annotation == 0:
print('skipping:',w.name,'NO ANNOTATION')
continue # if there is no annotation file skip
print('processing:',w.name,w.fn_annotation)
w.make_info_matrix(add_pp_info = add_pp_info)
if make_data:
d = remove_channels(d)
d = windower.window_data(d,w.windows['sf100'],flatten=True,normalize= normalize_data)
# d = unit_norm(d)
# d = normalize_numpy_matrix(d)
rows = d.shape[0]
nrows += rows
fout.write(w.name + '\t' + str(rows) + '\n')
print (d.shape, w.info_matrix.shape[0])
assert d.shape[0] == w.info_matrix.shape[0]
np.save(save_directory+ w.name + '_data',d)
np.save(save_directory+ w.name + '_info',w.info_matrix)
if make_data:
fout.write('all_blocks\t'+str(nrows)+'\n')
fout.close()
def make(fo):
print('making event info xml files per block')
nartifacts = 0
nclean = 0
fout = open('artifact_info.txt', 'w')
for i in range(1, 49):
p = e.Participant(i, fid2ort=fo)
p.add_all_sessions()
for s in p.sessions:
for b in s.blocks:
if not os.path.isfile(path.eeg100hz + windower.make_name(b) +
'.npy'):
continue
if b.start_marker_missing or b.end_marker_missing:
d = load_100hz_numpy_block(windower.make_name(b))
w = windower.Windower(b, nsamples=d.shape[1], sf=100)
w = windower.Windower(b, sf=100)
if not os.path.isfile(path.artifact_data_all_pp + w.name +
'_pred.npy'):
print(path.artifact_data_all_pp + w.name + '_pred.npy',
'no prediction file present')
continue
if b.exp_type == 'k': nepoch = 20
if b.exp_type == 'o': nepoch = 60
if b.exp_type == 'ifadv': nepoch = 80
ii_xml = xml_cnn.xml_cnn(w,
select_nartifact=nepoch,
select_nclean=nepoch,
cnn_model_name='cnn_5X5_2048_1')
ii_xml.make_index_info()
ii_xml.make_selection()
ii_xml.write()
nartifacts += ii_xml.nartifact_indices
nclean += ii_xml.nclean_indices
print(w.name + '\t' + ii_xml.nclean + '\t' + ii_xml.nartifact +
'\n')
fout.write(w.name + '\t' + ii_xml.nclean + '\t' +
ii_xml.nartifact + '\n')
fout.write('all_blocks\t' + str(nclean) + '\t' + str(nartifacts) + '\n')
fout.close()
def __init__(self,
b,
length=4,
corrector='martijn',
filename='',
load_xml=True):
'''Interface to easily annotate eeg signal
prediction filename for np array with classification for each segment
length duration in seconds of an epoch in the interface
coder Name of the coder (if automatic it should be computer)
filename specify xml file that is loaded for bad_epochs, default is to generate filename based on block info
'''
self.show_label = False
self.show_correctness = False
self.show_perc = False
self.key_dict = {
'1': 'clean',
'2': 'artifact',
'c': 'channel',
'u': 'signal_unclear',
'd': 'ac-balance_unclear',
'3': 'back'
}
self.redraw = False
self.b = b
self.w = windower.Windower(b, sf=100)
self.set_info()
if filename == '' or type(filename) != str:
self.filename = path.artifact_data_all_pp + self.w.name + '_artifacts-sf100.xml'
else:
self.filename = filename
self.length = int(float(length) * 100)
self.before, self.after = int(self.length / 2), int(self.length / 2)
self.e_index = 0
self.event_dict = {}
self.corrector = corrector
self.bad_epochs = []
self.boundaries = []
self.load_from_xml(self.filename)
self.load_data()
self.last_save = time.time()
self.make_epoch()
print(self.bad_epochs)
self.plot_epoch('all')
self.reset_visible()
self.handle_plot(True)
self.redraw = False
self.run()
def __init__(
self,
b=None,
cnn_ch_model_name='rep-26_perc-20_fold-1_part-70_kernel-6_model7',
save_dir=None,
bad_channels=[],
filename='',
load_predictions=True,
use_adjusted_prediction=False,
minimal_clean_duration=2000,
minimal_artifact_duration=1000):
'''Writes artifact info generated with manual_artifact_coder to xml files
b block object
cnn_model.. name of the cnn model that generated the predictions
save_dir directory to save data
bad_chan... a list of bad_channel objects, can be empty
filename xml filename, for loading or writing
'''
self.b = b
self.cnn_ch_model_name = cnn_ch_model_name
self.ch_names = utils.load_selection_ch_names()
self.use_adjusted_prediction = use_adjusted_prediction
self.minimal_artifact_duration = minimal_artifact_duration
self.minimal_clean_duration = minimal_clean_duration
if save_dir == None: self.save_dir = path.artifact_ch_cnn_xml
elif not os.path.isdir(save_dir):
print('Could not locate:', save_dir, 'using default:',
path.artifact_ch_cnn_xml)
self.save_dir = path.artifact_ch_cnn_xml
else:
self.save_dir = save_dir
if self.b != None:
self.w = windower.Windower(b, sf=100)
self.name = windower.make_name(self.b)
self.filename = make_filename(self.w, self.cnn_ch_model_name)
if load_predictions: self.load_predictions()
else: self.loaded = False
if self.loaded: self.set_indices()
else:
self.bad_channels = bad_channels
self.filename = filename
self.nclean_indices = 'NA'
self.nartifact_indices = 'NA'
# self.make_index_info()
self.cnn_result = etree.Element('artifacts')
def __init__(self,
b=None,
cnn_model_name='rep-3_perc-50_fold-2_part-90',
save_dir=None,
bad_epochs=[],
filename='',
load_predictions=True,
use_corrected=True):
'''Writes artifact info generated with manual_artifact_coder to xml files
w windower object
cnn_model.. name of the cnn model that generated the predictions
save_dir directory to save data
bad_epochs a list of bad_epoch objects, can be empty
filename xml filename, for loading or writing
use_cor... whether to use the xml that is based on automatic cnn annotation and manually
corrected, if no such file exists it will revert to the auto file
'''
self.b = b
self.cnn_model_name = cnn_model_name
if save_dir == None: self.save_dir = path.artifact_cnn_xml
elif not os.path.isdir(save_dir):
print('Could not locate:', save_dir, 'using default:',
path.artifact_cnn_xml)
self.save_dir = path.artifact_cnn_xml
else:
self.save_dir = save_dir
if self.b != None:
self.w = windower.Windower(b, sf=100)
self.name = windower.make_name(self.b)
self.filename = make_filename(self.w, self.cnn_model_name,
use_corrected)
if load_predictions: self.load_predictions()
else: self.loaded = False
if self.loaded: self.set_indices()
else:
self.bad_epochs = bad_epochs
self.filename = filename
self.nclean_indices = 'NA'
self.nartifact_indices = 'NA'
# self.make_index_info()
self.cnn_result = etree.Element('artifacts')
def make_matrix(fo,
add_pp_info=False,
normalize_data=True,
save_directory=None,
make_data=True,
start_pp=1,
overwrite=False):
print(
'making artifact training np matrices per block, with default 1 sec and 99 perc overlap'
)
if save_directory == None:
save_directory = path.channel_artifact_training_data
print('save directory:', save_directory)
if make_data: fout = open(path.bak + 'channel_nrows_per_block-p', 'w')
nrows = 0
for i in range(start_pp, 49):
p = e.Participant(i, fid2ort=fo)
p.add_all_sessions()
for s in p.sessions:
for b in s.blocks:
if os.path.isfile(path.channel_artifact_training_data +
windower.make_name(b) +
'_data.npy') and not overwrite:
# check whether windowed data is already present
continue
if not os.path.isfile(path.eeg100hz + windower.make_name(b) +
'.npy'):
# check whether downsampled data is present to load
continue
print(windower.make_name(b))
d = load_100hz_numpy_block(windower.make_name(b))
if b.start_marker_missing or b.end_marker_missing:
w = windower.Windower(b,
nsamples=d.shape[1] * 10,
sf=100,
window_overlap_percentage=.99)
else:
w = windower.Windower(b,
sf=100,
window_overlap_percentage=.99)
f = windower.block2channel_fn_annotation(
w.b, path.channel_artifacts_clean)
if f == 0:
print('skipping:', w.name, 'NO ANNOTATION')
continue # if there is no annotation file skip
print('processing:', w.name, w.fn_annotation)
w.make_channel_ca_info_matrix(add_pp_info=add_pp_info)
if make_data:
d = remove_channels(d)
d = windower.window_data(d,
w.windows['sf100'],
flatten=True,
normalize=normalize_data,
cut_off=300)
rows = d.shape[0]
nrows += rows
fout.write(w.name + '\t' + str(rows) + '\n')
print(d.shape, w.info_matrix.shape[0])
assert d.shape[0] == w.info_matrix.shape[0]
# d = insert_target_channel_rows(d,nchannels=26,kernel_size=6)
# IMPORTANT: this was not commented when I checked the file
# however resulting files look like it was commented during execution
# insert target channel is done later in pipeline
# not sure what happened
np.save(save_directory + w.name + '_data', d)
np.save(save_directory + w.name + '_info', w.info_matrix)
if make_data:
fout.write(path.bak + 'all_blocks\t' + str(nrows) + '\n')
fout.close()
def load_windower(f, fo):
b = filename2block(f, fo)
w = windower.Windower(b, window_overlap_percentage=.99, sf=100)
w.make_ca_info_matrix(True)
return w
