Dongdong Zhang

你可以从 [CPSC2018](http://2018.icbeb.org/Challenge.html)、[Physionet 2020 Challenge](https://physionet.org/content/challenge-2020/1.0.1/) 或者[这里](https://www.dropbox.com/s/unicm8ulxt24vh8/CPSC.zip?dl=0)下载数据集。Dropbox 上的文件是原始数据，只是组织上更规整一些。

> Hello, I have downloaded the CPSC2018 dataset. But I found that the dataset and the code `preprocess.py` do not match. > > For example, in the CPSC2018 dataset, here...

@UESTCkevin Sorry for the late reply. It's strange that `\` appears in the file name. Could you please check whether you've made any modification [here](https://github.com/onlyzdd/ecg-diagnosis/blob/dfa9033d5ae7be135db63ff567e66fdb2b86d76d/shap_values.py#L48)? Try remove `\` or replace...

@renatodeleone Sorry to a late reply. It seems `pandas` is treating the `dx` column as `int`. To solve this problem, you can change it to `dxs = [dx_dict.get(code, '') for...

@shenqiajun 你好，对于极少数存在较大噪音的ECG记录（约20条），目前的代码还无法提取到心率。当前论文中还未考虑心率、HOS等信息，计划后期加入。

@UESTCkevin 抱歉，README中Shap包版本存在问题，应该是0.35.1才对，之前看成了shortuuid的版本了，稍后更新。

Sorry for the late reply. The problem is unexpected introduced in the last commit. I've reverted it, and it should work now.

@way-sal Sorry for the late reply. Do you mean how to get train_ids or test_ids? After running `preprocess.py`, you'll get the `labels.csv`. Each row in `labels.csv` contains a patient's id...

Sorry for the late reply. The _--use-unstructure_ argument which use the _unstructure_dict.json_ file is deprecated. To modify the inputs, please modify the arguments for the _forward_ function in _lstm.py_ and...