def test_a(self):
gcd_res = readCompleteMatFile(r'C:\Users\ORI\Documents\Thesis\dataset_all\RSVP_Color116msVPicr.mat');
all_data, columns, all_data_for_sum = create_target_table(gcd_res, gcd_res['target'])
results_table = pd.DataFrame( all_data)
results_table.rename(columns=columns, inplace=True)
# print results_table.columns
results_table.to_csv('res.csv')
# print results_table
#now get a vector of random probabilities:
temp = np.random.rand(len(gcd_res['target']),1)
all_data2, columns2, all_data_for_sum2 = create_target_table(gcd_res, temp)
# sum over the trials axe compare
gt = np.argmax(np.sum(all_data_for_sum, axis=1),axis=1)
actual = np.argmax(np.sum(all_data_for_sum2, axis=1),axis=1)
print accuracy_by_repetition(all_data_for_sum, all_data_for_sum2)
results_table2 = pd.DataFrame( all_data2)
results_table2.rename(columns=columns2, inplace=True)
# print results_table.columns
results_table2.to_csv('res2.csv')
temp2 = results_table2[all_data2[:, 1]<3, :]
pass
def test_a(self):
gcd_res = readCompleteMatFile(
r'C:\Users\ORI\Documents\Thesis\dataset_all\RSVP_Color116msVPicr.mat'
)
all_data, columns, all_data_for_sum = create_target_table(
gcd_res, gcd_res['target'])
results_table = pd.DataFrame(all_data)
results_table.rename(columns=columns, inplace=True)
# print results_table.columns
results_table.to_csv('res.csv')
# print results_table
#now get a vector of random probabilities:
temp = np.random.rand(len(gcd_res['target']), 1)
all_data2, columns2, all_data_for_sum2 = create_target_table(
gcd_res, temp)
# sum over the trials axe compare
gt = np.argmax(np.sum(all_data_for_sum, axis=1), axis=1)
actual = np.argmax(np.sum(all_data_for_sum2, axis=1), axis=1)
print accuracy_by_repetition(all_data_for_sum, all_data_for_sum2)
results_table2 = pd.DataFrame(all_data2)
results_table2.rename(columns=columns2, inplace=True)
# print results_table.columns
results_table2.to_csv('res2.csv')
temp2 = results_table2[all_data2[:, 1] < 3, :]
pass
def LoadSingleSubjectPythonNoPermute(file_name):
res = readCompleteMatFile(file_name)
all_data, all_tags = ExtractDataVer3(res["all_relevant_channels"], res["marker_positions"], res["target"], 0, 400)
trasposed_data = all_data.transpose(0, 2, 1)
trasposed_data = trasposed_data.reshape(trasposed_data.shape[0], -1)
all_target = trasposed_data[np.where(all_tags == 1)[0], :]
all_non_target = trasposed_data[np.where(all_tags != 1)[0], :]
subset_size = all_target.shape[0]
all_target = all_target
all_non_target = all_non_target
return [all_target, all_non_target, res["marker_positions"]]
def LoadSingleSubjectPythonNoPermute(file_name):
res = readCompleteMatFile(file_name)
all_data, all_tags = ExtractDataVer3(res['all_relevant_channels'],
res['marker_positions'],
res['target'], 0, 400)
trasposed_data = all_data.transpose(0, 2, 1)
trasposed_data = trasposed_data.reshape(trasposed_data.shape[0], -1)
all_target = trasposed_data[np.where(all_tags == 1)[0], :]
all_non_target = trasposed_data[np.where(all_tags != 1)[0], :]
subset_size = all_target.shape[0]
all_target = all_target
all_non_target = all_non_target
return [all_target, all_non_target, res['marker_positions']]