def score_training_set():
# Generate a data frame that points to the challenge files
tr_files, te_files = phyc.get_files()
score = Challenge2018Score()
for i in range(0, np.size(tr_files, 0)):
gc.collect()
sys.stdout.write('Evaluating training subject: %d/%d' %
(i + 1, np.size(tr_files, 0)))
sys.stdout.flush()
record_name = tr_files.header.values[i][:-4]
predictions = R.classify_record(record_name)
arousals = phyc.import_arousals(tr_files.arousal.values[i])
arousals = np.ravel(arousals)
score.score_record(arousals, predictions, record_name)
auroc = score.record_auroc(record_name)
auprc = score.record_auprc(record_name)
print(' AUROC:%f AUPRC:%f' % (auroc, auprc))
print()
auroc_g = score.gross_auroc()
auprc_g = score.gross_auprc()
print('Training AUROC Performance (gross): %f' % auroc_g)
print('Training AUPRC Performance (gross): %f' % auprc_g)
print()
def evaluate_test_set():
# Generate a data frame that points to the challenge files
tr_files, te_files = phyc.get_files()
for i in range(0, np.size(te_files, 0)):
gc.collect()
print('Evaluating test subject: %d/%d' % (i + 1, np.size(te_files, 0)))
record_name = te_files.header.values[i][:-4]
output_file = os.path.basename(record_name) + '.vec'
predictions = R.classify_record(record_name)
np.savetxt(output_file, predictions, fmt='%.3f')