Function run_evaluation

test/testDeeppass2.py:210–223

(path)

def run_evaluation(path):
    
    test_data_with_preds = read_test_data("evaluation_results/deeppass2/preds_1.json")
    performance_bert = calculate_metrics(
        test_data_with_preds["cred"], test_data_with_preds["BERT"]
    )
    print(f"BERT performance:\n Strict accuracy: {performance_bert}")
    save_results("evaluation_results/deeppass2/BERT_performance.json", performance_bert)

    performance_LLM = calculate_metrics(
        test_data_with_preds["cred"], test_data_with_preds["LLM"]
    )
    print(f"LLM performance:\n {performance_LLM}")
    save_results("evaluation_results/deeppass2/LLM_performance.json", performance_LLM)

if __name__ =="__main__":
    run_evaluation("./Dataset/test/test_plain.json")