jwoo5 / ecg-qa Goto Github PK

(py310) zhu@UU:~/learn/fairseq-signals-master$ python ./fairseq_signals/data/ecg_text/preprocess/preprocess_ecgqa.py /home/zhu/learn/ecg-qa-master/ecgqa/mimic-iv-ecg
--dest /home/zhu/learn/ecg-qa-master/pre-process
--apply_paraphrase
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 829267/829267 [00:00<00:00, 5830287.43it/s]
train: 0%| | 0/829267 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/home/zhu/learn/fairseq-signals-master/./fairseq_signals/data/ecg_text/preprocess/preprocess_ecgqa.py", line 195, in
main(args)
File "/home/zhu/learn/fairseq-signals-master/./fairseq_signals/data/ecg_text/preprocess/preprocess_ecgqa.py", line 104, in main
sample["ecg_path"] = sample_data["ecg_path"]
KeyError: 'ecg_path'

When I run the preprocess script, I encounter an error.

Traceback (most recent call last):
File "/data/work/TimeLLM/ecg-qa/preprocess_ecgqa.py", line 198, in
main(args)
File "/data/work/TimeLLM/ecg-qa/preprocess_ecgqa.py", line 109, in main
sample["answer"] = encode_answer(sample_data["answer"], classes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/work/TimeLLM/ecg-qa/preprocess_ecgqa.py", line 150, in encode_answer
idx = [classes[a] for a in answer if a != "none"]
~~~~~~~^^^
KeyError: 'late stage of myocardial infarction'

Replacing "late stage of myocardial infarction" with "old stage of myocardial infarction" in the file "ecgqa/ptbxl/train/110000.json" "ecgqa/ptbxl/valid/20000.json""ecgqa/ptbxl/test/20000.json" resolves the error.