def calculate_metrics(Y, P, dataset='davis'):
# aupr = get_aupr(Y, P)
cindex = get_cindex(Y, P) # DeepDTA
cindex2 = get_ci(Y, P) # GraphDTA
rm2 = get_rm2(Y, P) # DeepDTA
mse = get_mse(Y, P)
pearson = get_pearson(Y, P)
spearman = get_spearman(Y, P)
rmse = get_rmse(Y, P)
print('metrics for ', dataset)
# print('aupr:', aupr)
print('cindex:', cindex)
print('cindex2', cindex2)
print('rm2:', rm2)
print('mse:', mse)
print('pearson', pearson)
result_file_name = 'results/result_' + model_st + '_' + dataset + '.txt'
result_str = ''
result_str += dataset + '\r\n'
result_str += 'rmse:' + str(rmse) + ' ' + ' mse:' + str(
mse) + ' ' + ' pearson:' + str(pearson) + ' ' + 'spearman:' + str(
spearman) + ' ' + 'ci:' + str(cindex) + ' ' + 'rm2:' + str(rm2)
print(result_str)
open(result_file_name, 'w').writelines(result_str)
def get_scores_full(labels, predictions, validation_test, total_training_loss,
total_validation_test_loss, epoch, comp_tar_pair_dataset,
fold_epoch_results):
deep_dta_rm2 = get_rm2(np.asarray(labels), np.asarray(predictions))
# deep_dta_aupr = get_aupr(np.asarray(labels), np.asarray(
# predictions))
deep_dta_cindex = get_cindex(np.asarray(labels), np.asarray(predictions))
deep_dta_mse = mse(np.asarray(labels), np.asarray(predictions))
rmse_score = rmse(np.asarray(labels), np.asarray(predictions))
pearson_score = pearson(np.asarray(labels), np.asarray(predictions))
spearman_score = spearman(np.asarray(labels), np.asarray(predictions))
ci_score = ci(np.asarray(labels), np.asarray(predictions))
f1_score = f1(np.asarray(labels), np.asarray(predictions))
ave_auc_score = average_AUC(np.asarray(labels), np.asarray(predictions))
fold_epoch_results.append([
deep_dta_rm2, deep_dta_cindex, deep_dta_mse, pearson_score,
spearman_score, ci_score, f1_score, ave_auc_score
])
print("Epoch:{}\tTraining Loss:{}\t{} Loss:{}".format(
epoch, total_training_loss, validation_test,
total_validation_test_loss))
print("{} DeepDTA RM2:\t{}".format(validation_test, deep_dta_rm2))
print("{} DeepDTA MSE\t{}".format(validation_test, deep_dta_mse))
print("{} RMSE\t{}".format(validation_test, rmse_score))
print("{} DeepDTA c-index\t{}".format(validation_test, deep_dta_cindex))
print("{} Pearson:\t{}".format(validation_test, pearson_score))
print("{} Spearman:\t{}".format(validation_test, spearman_score))
print("{} Ci:\t{}".format(validation_test, ci_score))
print("{} F1-Score:\t{}".format(validation_test, f1_score))
print("{} Average_AUC:\t{}".format(validation_test, ave_auc_score))
def test(self, dataset):
N = len(dataset)
T, S = [], []
for data in dataset:
(correct_labels, predicted_scores) = self.model(data, train=False)
# print(correct_labels, predicted_scores)
T.append(correct_labels)
S.append(predicted_scores)
MSE = mean_squared_error(T, S)
cindex = get_cindex(T, S)
rm2 = get_rm2(T, S)
AUPR = get_aupr(T, S)
return MSE, cindex, rm2, AUPR, T, S