evaluation.py

submission_inception_resnet = pd.DataFrame({'Id':test_files, 'task_1':test_predictions_task1,'task_2':test_predictions_task2})
pd.DataFrame.to_csv(submission_inception_resnet, 'submission.csv', index=False)

preds_path = sys.argv[1]
    
thresh = 0.5

# get ground truth labels for test dataset
truth = pd.read_csv('ground_truth.csv')
y_true = truth.as_matrix(columns=["task_1", "task_2"])

# get model predictions for test dataset
y_pred = pd.read_csv('submission.csv')
y_pred = y_pred.as_matrix(columns=["task_1", "task_2"])

# plot ROC curves and print scores
plot_roc_auc(y_true, y_pred)
# plot confusion matrix
classes = ['benign', 'malignant']
plot_confusion_matrix(y_true[:,0], y_pred[:,0], thresh, classes)