def create_data_rep_training(file_name, fist_time_stamp, last_time_stamp):
gcd_res = readCompleteMatFile(file_name)
data_for_eval = ExtractDataVer4(gcd_res['all_relevant_channels'],
gcd_res['marker_positions'],
gcd_res['target'], fist_time_stamp,
last_time_stamp)
data_for_eval = (downsample_data(data_for_eval[0],
data_for_eval[0].shape[1],
1), data_for_eval[1])
train_mode_per_block = gcd_res['train_mode'].reshape(-1, 30)[:, 0]
all_data_per_char_as_matrix = np.zeros(
(train_mode_per_block.shape[0], 30, data_for_eval[0].shape[1],
data_for_eval[0].shape[2]))
all_data_per_char = dict()
target_per_char_as_matrix = np.zeros((train_mode_per_block.shape[0], 30),
dtype=np.int)
for i, stimuli_i in enumerate(range(1, 31)):
all_data_per_char[i] = data_for_eval[0][gcd_res['stimulus'] ==
stimuli_i]
all_data_per_char_as_matrix[:, i, :, :] = data_for_eval[0][
gcd_res['stimulus'] == stimuli_i]
target_per_char = dict()
for i, stimuli_i in enumerate(range(1, 31)):
target_per_char[i] = data_for_eval[1][gcd_res['stimulus'] == stimuli_i]
target_per_char_as_matrix[:, i] = data_for_eval[1][gcd_res['stimulus']
== stimuli_i]
return all_data_per_char, target_per_char, train_mode_per_block, all_data_per_char_as_matrix, target_per_char_as_matrix
def create_data_rep_training(file_name, fist_time_stamp, last_time_stamp, downsampe_params=1):
"""
The function divide the data into epochs and shaping it such that it is
easy to do operation per stimuli category on it.
:param file_name:
:param fist_time_stamp:
:param last_time_stamp:
:return:
"""
gcd_res = readCompleteMatFile(file_name)
data_for_eval = ExtractDataVer4(gcd_res['all_relevant_channels'], gcd_res['marker_positions'],
gcd_res['target'], fist_time_stamp, last_time_stamp)
data_for_eval = (downsample_data(data_for_eval[0], data_for_eval[0].shape[1], downsampe_params), data_for_eval[1])
train_mode_per_block = gcd_res['train_mode'].reshape(-1, 30)[:, 0]
all_data_per_char_as_matrix = np.zeros(
(train_mode_per_block.shape[0], 30, data_for_eval[0].shape[1], data_for_eval[0].shape[2]))
all_data_per_char = dict()
target_per_char_as_matrix = np.zeros((train_mode_per_block.shape[0], 30), dtype=np.int)
for i, stimuli_i in enumerate(range(1, 31)):
all_data_per_char[i] = data_for_eval[0][gcd_res['stimulus'] == stimuli_i]
all_data_per_char_as_matrix[:, i, :, :] = data_for_eval[0][gcd_res['stimulus'] == stimuli_i]
target_per_char = dict()
for i, stimuli_i in enumerate(range(1, 31)):
target_per_char[i] = data_for_eval[1][gcd_res['stimulus'] == stimuli_i]
target_per_char_as_matrix[:, i] = data_for_eval[1][gcd_res['stimulus'] == stimuli_i]
return all_data_per_char, target_per_char, train_mode_per_block, all_data_per_char_as_matrix, target_per_char_as_matrix
def create_data_for_compare_by_repetition(file_name):
gcd_res = readCompleteMatFile(file_name)
sub_gcd_res = dict(
train_trial=gcd_res['train_trial'][gcd_res['train_mode'] != 1],
train_block=gcd_res['train_block'][gcd_res['train_mode'] != 1],
stimulus=gcd_res['stimulus'][gcd_res['train_mode'] != 1])
return sub_gcd_res
def create_train_data(file_name, down_samples_param):
all_positive_train = []
all_negative_train = []
others = ["RSVP_Color116msVPgcd.mat"]
for other_file_name in others:
file_name = r'C:\Users\ORI\Documents\Thesis\dataset_all\{0}'.format(
other_file_name)
gcd_res = readCompleteMatFile(file_name)
last_time_stamp = 800
fist_time_stamp = -200
data_for_eval = ExtractDataVer4(gcd_res['all_relevant_channels'],
gcd_res['marker_positions'],
gcd_res['target'], fist_time_stamp,
last_time_stamp)
# total_time = last_time_stamp - fist_time_stamp
# number_of_original_samples = total_time / 5
# new_number_of_time_stamps = number_of_original_samples / down_samples_param
#
#
# # print data_for_eval
# temp_data_for_eval = np.zeros((data_for_eval[0].shape[0], new_number_of_time_stamps, data_for_eval[0].shape[2]))
#
# for new_i, i in enumerate(range(0, 200, new_number_of_time_stamps)):
# temp_data_for_eval[:, new_i, :] = np.mean(data_for_eval[0][:, range(i, (i + new_number_of_time_stamps)), :], axis=1)
print data_for_eval[0].shape
temp_data_for_eval = downsample_data(data_for_eval[0],
data_for_eval[0].shape[1],
down_samples_param)
positive_train_data_gcd = temp_data_for_eval[np.all(
[gcd_res['train_mode'] == 1, gcd_res['target'] == 1], axis=0)]
negative_train_data_gcd = temp_data_for_eval[np.all(
[gcd_res['train_mode'] == 1, gcd_res['target'] == 0], axis=0)]
all_positive_train.append(positive_train_data_gcd)
all_negative_train.append(negative_train_data_gcd)
positive_train_data_gcd = np.vstack(all_positive_train)
negative_train_data_gcd = np.vstack(all_negative_train)
all_data = np.vstack([positive_train_data_gcd, negative_train_data_gcd])
all_tags = np.vstack([
np.ones((positive_train_data_gcd.shape[0], 1)),
np.zeros((negative_train_data_gcd.shape[0], 1))
])
categorical_tags = to_categorical(all_tags)
shuffeled_samples, suffule_tags = shuffle(all_data,
categorical_tags,
random_state=0)
# shuffeled_samples, suffule_tags = (all_data, categorical_tags)
return shuffeled_samples, suffule_tags
def create_evaluation_data(file_name, down_samples_param):
gcd_res = readCompleteMatFile(file_name)
data_for_eval = ExtractDataVer4(gcd_res['all_relevant_channels'],
gcd_res['marker_positions'],
gcd_res['target'], -200, 800)
# print data_for_eval
temp_data_for_eval = downsample_data(data_for_eval[0],
data_for_eval[0].shape[1],
down_samples_param)
test_data_gcd, test_target_gcd = temp_data_for_eval[
gcd_res['train_mode'] != 1], data_for_eval[1][
gcd_res['train_mode'] != 1]
return test_data_gcd, test_target_gcd
def get_indexes_by_stimuli(stimulus_range, stimulus, train_trial, train_block):
stimuli_histogram = {}
for i in stimulus_range:
stimuli_histogram[i] = dict(stimuli=i,
idx=np.where(stimulus == i)[0],
train_trial=train_trial[np.where(stimulus == i)[0]],
train_block=train_block[np.where(stimulus == i)[0]])
return stimuli_histogram
import numpy as np
if __name__ == '__main__':
res = readCompleteMatFile(r'C:\Users\ori22_000\Documents\Thesis\dataset_all\RSVP_Color116msVPgcd.mat');
print get_indexes_by_stimuli(range(1,3), res['stimulus'], res['train_trial'], res['train_block'])
# # stimuli_histogram = {}
# for i in range(1,31):
# stimuli_histogram[i] = dict(stimuli=i,
# idx=np.where(res['stimulus'] == i)[0],
# train_trial=res['train_trial'][np.where(res['stimulus'] == i)[0]],
# train_block=res['train_block'][np.where(res['stimulus'] == i)[0]])
# np.where(res['stimulus'] == i)[0]
# print np.where(res['stimulus'] == i)[0]
# print res['train_trial'][np.where(res['stimulus'] == i)[0]]
# print res['train_block'][np.where(res['stimulus'] == i)[0]]
# print np.where(res['stimulus'] == i)[0]
# print stimuli_histogram[2]['idx'][np.where(stimuli_histogram[2]['train_block'] <= 3)[0]]
"RSVP_Color116msVPgcg.mat",
"RSVP_Color116msVPgch.mat",
"RSVP_Color116msVPiay.mat",
"RSVP_Color116msVPicn.mat"];
data_base_dir = r'C:\Users\ORI\Documents\Thesis\dataset_all'
# model = LDA()
all_models = [LSTM_EEG_CNN(50.0, 20)]
for model_type in all_models:
all_model_results = []
for subject in all_subjects:
file_name = os.path.join(data_base_dir, subject)
gcd_res = readCompleteMatFile(file_name)
repetition_eval = EvaluateByRepetition(file_name)
# for data_extraction_method in [create_training_and_testing(gcd_res, 0, 400, 1, True),
# create_training_and_testing(gcd_res, 0, 400, 1, False),
# create_training_and_testing(gcd_res, 0, 400, 8, True),
# create_training_and_testing(gcd_res, 0, 400, 8, False),
# create_training_and_testing(gcd_res, -200, 800, 1, True),
# create_training_and_testing(gcd_res, -200, 800, 1, False),
# create_training_and_testing(gcd_res, -200, 800, 8, True),
# create_training_and_testing(gcd_res, -200, 800, 8, False)
# ]:
for data_extraction_method in [create_training_and_testing(gcd_res, -200, 800, 8, False)
]:
def foo():
return 1, 2, 3
if __name__ == "__main__":
# [all_target1, all_non_target1] = LoadSingleSubjectPythonByMode(r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat" ,1)
# [all_target2, all_non_target2] = LoadSingleSubjectPythonByMode(r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat" ,2)
# [all_target3, all_non_target3] = LoadSingleSubjectPythonByMode(r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat" ,3)
# LoadSingleSubjectPython(r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat");
temp = readCompleteMatFile(r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat")
PredictByRepetitions3(temp, 3, None);
all_relevant_channels, channels_names, marker_positions, target = readCompleteMatFile(
r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat")
# other option: take the model
# load the trial data
# load the prediction data - the prediction data is an index with tag\probablity
a, b = foo()
print ('hello');
"RSVP_Color116msVPgch.mat", "RSVP_Color116msVPiay.mat",
"RSVP_Color116msVPicn.mat"
]
all_subjects = ["RSVP_Color116msVPicr.mat", "RSVP_Color116msVPpia.mat"]
data_base_dir = r'C:\Users\ORI\Documents\Thesis\dataset_all'
# model = LDA()
all_models = [LSTM_CNN_EEG_Comb(50, 20)]
for model_type in all_models:
# all_model_results = [create_training_and_testing(gcd_res, -200, 800, 1, False)]
all_model_results = []
all_res = [
readCompleteMatFile(os.path.join(data_base_dir, subject))
for subject in all_subjects
]
training_data, train_tags, = create_train_data_from_all(
all_res, -200, 800, 1, False)
model = model_type
model.fit(training_data, train_tags)
for subject in all_subjects:
file_name = os.path.join(data_base_dir, subject)
gcd_res = readCompleteMatFile(file_name)
repetition_eval = EvaluateByRepetition(file_name)
for data_extraction_method in [
create_only_testing(gcd_res, -200, 800, 1, False)
]:
negative_train_data_gcd = temp_data_for_eval[
np.all([indexes, data_from_mat['target'] == 0], axis=0)]
all_positive_train.append(positive_train_data_gcd)
all_negative_train.append(negative_train_data_gcd)
positive_train_data_gcd = np.vstack(all_positive_train)
negative_train_data_gcd = np.vstack(all_negative_train)
all_data = np.vstack([positive_train_data_gcd, negative_train_data_gcd])
all_tags = np.vstack(
[np.ones((positive_train_data_gcd.shape[0], 1)), np.zeros((negative_train_data_gcd.shape[0], 1))])
categorical_tags = to_categorical(all_tags)
shuffeled_samples, suffule_tags = (all_data, categorical_tags)
return shuffeled_samples, suffule_tags
if __name__ == "__main__":
file_name = r'C:\Users\ORI\Documents\Thesis\dataset_all\RSVP_Color116msVPfat.mat'
# read the raw data
raw_data = readCompleteMatFile(file_name)
train_data, train_tag = create_train_data(raw_data, 8, raw_data['train_mode'] == 1)
test_data, test_tag = create_train_data(raw_data, 8, raw_data['train_mode'] != 1)
# now, extract epoch
print "done"
def get_indexes_by_stimuli(stimulus_range, stimulus, train_trial, train_block):
stimuli_histogram = {}
for i in stimulus_range:
stimuli_histogram[i] = dict(
stimuli=i,
idx=np.where(stimulus == i)[0],
train_trial=train_trial[np.where(stimulus == i)[0]],
train_block=train_block[np.where(stimulus == i)[0]])
return stimuli_histogram
import numpy as np
if __name__ == '__main__':
res = readCompleteMatFile(
r'C:\Users\ori22_000\Documents\Thesis\dataset_all\RSVP_Color116msVPgcd.mat'
)
print get_indexes_by_stimuli(range(1, 3), res['stimulus'],
res['train_trial'], res['train_block'])
# # stimuli_histogram = {}
# for i in range(1,31):
# stimuli_histogram[i] = dict(stimuli=i,
# idx=np.where(res['stimulus'] == i)[0],
# train_trial=res['train_trial'][np.where(res['stimulus'] == i)[0]],
# train_block=res['train_block'][np.where(res['stimulus'] == i)[0]])
# np.where(res['stimulus'] == i)[0]
# print np.where(res['stimulus'] == i)[0]
# print res['train_trial'][np.where(res['stimulus'] == i)[0]]
# print res['train_block'][np.where(res['stimulus'] == i)[0]]
# print np.where(res['stimulus'] == i)[0]
model.add(MaxPooling2D(pool_size=(1, number_of_in_channels)))
model.add(Convolution2D(nb_filter=number_of_out_channels, nb_row=6, nb_col=1, border_mode='same',init='glorot_normal'))
model.add(MaxPooling2D(pool_size=(20, 1)))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(100))
model.add(Activation('relu'))
# model.add(LSTM(input_dim=55, output_dim=20,return_sequences=False))
# # model.add(Dense(275))
# # model.add(Activation('tanh'))
model.add(Dense(2))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='sgd')
file_name = r'C:\Users\ORI\Documents\Thesis\dataset_all\RSVP_Color116msVPfat.mat'
raw_data = readCompleteMatFile(file_name)
train_data, train_tag = create_train_data(raw_data, 8, raw_data['train_mode'] == 1)
train_data_single_color_channel = np.expand_dims(stats.zscore(train_data, axis = 1), axis = 1)
test_data, test_tag = create_train_data(raw_data, 8, raw_data['train_mode'] != 1)
model.fit(train_data_single_color_channel, train_tag, nb_epoch=1, show_accuracy=True)
test_data_single_color_channel = np.expand_dims(stats.zscore(test_data, axis=1), axis=1)
print model.evaluate(test_data_single_color_channel, test_tag, show_accuracy=True)
print train_data.shape
def foo():
return 1, 2, 3
if __name__ == "__main__":
# [all_target1, all_non_target1] = LoadSingleSubjectPythonByMode(r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat" ,1)
# [all_target2, all_non_target2] = LoadSingleSubjectPythonByMode(r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat" ,2)
# [all_target3, all_non_target3] = LoadSingleSubjectPythonByMode(r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat" ,3)
# LoadSingleSubjectPython(r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat");
temp = readCompleteMatFile(
r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat"
)
PredictByRepetitions3(temp, 3, None)
all_relevant_channels, channels_names, marker_positions, target = readCompleteMatFile(
r"C:\Users\ori22_000\Documents\Thesis\dataset\VPfat_11_01_24\RSVP_Color116msVPfat.mat"
)
# other option: take the model
# load the trial data
# load the prediction data - the prediction data is an index with tag\probablity
a, b = foo()
print('hello')