def create_train_data(gcd_res, fist_time_stamp=0, last_time_stamp=400, down_samples_param=1,
take_same_number_positive_and_negative=False):
all_positive_train = []
all_negative_train = []
data_for_eval = ExtractDataVer4(gcd_res['all_relevant_channels'], gcd_res['marker_positions'],
gcd_res['target'], fist_time_stamp, last_time_stamp)
temp_data_for_eval = downsample_data(data_for_eval[0], data_for_eval[0].shape[1], down_samples_param)
# extract the calibration_data
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)
if take_same_number_positive_and_negative:
negative_train_data_gcd = rng.permutation(np.vstack(all_negative_train))[0:positive_train_data_gcd.shape[0]]
else:
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, all_tags, random_state=0)
return shuffeled_samples, suffule_tags
def create_train_data_from_all(all_gcd_res,
fist_time_stamp=0,
last_time_stamp=400,
down_samples_param=1,
take_same_number_positive_and_negative=False):
all_positive_train = []
all_negative_train = []
all_data = None
all_tags = None
for i, single_subject_data in enumerate(all_gcd_res):
data_for_eval = ExtractDataVer4(
single_subject_data['all_relevant_channels'],
single_subject_data['marker_positions'],
single_subject_data['target'], fist_time_stamp, last_time_stamp)
temp_data_for_eval = downsample_data(data_for_eval[0],
data_for_eval[0].shape[1],
down_samples_param)
current_subject_tag = single_subject_data['target'][
single_subject_data['train_mode'] != 1]
current_subject_data = temp_data_for_eval[
single_subject_data['train_mode'] != 1]
if i == 0:
all_tags = current_subject_tag
all_data = current_subject_data
else:
all_tags = np.hstack([all_tags, current_subject_tag])
all_data = np.vstack([all_data, current_subject_data])
# shuffeled_samples, suffule_tags = shuffle(all_data, all_tags, random_state=0)
return all_data, all_tags
def create_train_data(gcd_res,
fist_time_stamp=0,
last_time_stamp=400,
down_samples_param=1,
take_same_number_positive_and_negative=False):
all_positive_train = []
all_negative_train = []
data_for_eval = ExtractDataVer4(gcd_res['all_relevant_channels'],
gcd_res['marker_positions'],
gcd_res['target'], fist_time_stamp,
last_time_stamp)
temp_data_for_eval = downsample_data(data_for_eval[0],
data_for_eval[0].shape[1],
down_samples_param)
all_tags = gcd_res['target'][gcd_res['train_mode'] == 1]
all_data = temp_data_for_eval[gcd_res['train_mode'] == 1]
categorical_tags = to_categorical(all_tags)
# shuffeled_samples, suffule_tags = shuffle(all_data, all_tags, random_state=0)
return all_data, all_tags
def create_train_data_split(gcd_res, fist_time_stamp=0, last_time_stamp=400, down_samples_param=1,
take_same_number_positive_and_negative=False):
all_positive_train = []
all_negative_train = []
data_for_eval = ExtractDataVer4(gcd_res['all_relevant_channels'], gcd_res['marker_positions'],
gcd_res['target'], fist_time_stamp, last_time_stamp)
temp_data_for_eval = downsample_data(data_for_eval[0], data_for_eval[0].shape[1], down_samples_param)
# extract the calibration_data
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)]
negative_splits = np.split(shuffle(negative_train_data_gcd), 29)
all_data_splits = []
all_tag_splits = []
for i in range(29):
suffuled_split_data, suffuled_split_tag = shuffle(np.vstack([positive_train_data_gcd, negative_splits[i]]),
np.vstack([np.ones((positive_train_data_gcd.shape[0], 1)),
np.zeros((negative_splits[i].shape[0], 1))]).astype(
np.int))
all_data_splits.append(suffuled_split_data)
all_tag_splits.append(suffuled_split_tag)
return all_data_splits, all_tag_splits
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_train_data(data_from_mat, down_samples_param, indexes):
all_positive_train = []
all_negative_train = []
last_time_stamp = 800
fist_time_stamp = -200
data_for_eval = ExtractDataVer4(data_from_mat['all_relevant_channels'], data_from_mat['marker_positions'],
data_from_mat['target'], fist_time_stamp, last_time_stamp)
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([indexes, data_from_mat['target'] == 1], axis=0)]
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
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(gcd_res, fist_time_stamp=0, last_time_stamp=400, down_samples_param=1):
# 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)
# 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