def Evaluation(gold_file_path, predict_file_path):
with open(gold_file_path) as gold_file, open(predict_file_path) as predict_file:
gold_list = [int(line.strip().split('\t')[0]) for line in gold_file]
predicted_list = [int(line.strip().split("\t")[0]) for line in predict_file]
predict_labels = [config.id2category[int(predict)] for predict in predicted_list]
gold_labels = [config.id2category[int(gold)] for gold in gold_list]
binary_alphabet = Alphabet()
for i in range(20):
binary_alphabet.add(DICT_INDEX_TO_LABEL[i])
cm = ConfusionMatrix(binary_alphabet)
cm.add_list(predict_labels, gold_labels)
confusion_matrix(gold_list, predicted_list)
cm.print_summary()
macro_p, macro_r, macro_f1 = cm.get_average_prf()
overall_accuracy = cm.get_accuracy()
return overall_accuracy, macro_p, macro_r, macro_f1
