sajaddarabi/taper-ehr

Patient Code & Text Representation Learning

taper-ehr's Issues

Python Version

Hello Dr. Darabi,

What Python version are you using for this project?

Best Regards,
Harold Mo

Error in processing while using gen_text_plus_code_data.py

Hello Dr. Darabi,

I am trying to run gen_text_plus_code_data.py file for generating dictionary containing patient id's.

python gen_text_plus_code_data.py -p '<path-to-where-df-were-saved>/df_less_1.pkl' -s '<path-to-save-output>' -et -cpb './data/biobert_pubmed/bert_config.json' -sdp './data/biobert_pubmed_model' -vpb './data/biobert_pubmed/vocab.txt' -bsl 512 -diag -proc -med -cpt -sc -vp <path-to-medical-code-vocabulary>

I am using Google Colab Pro with GPU but still it is taking so much time. I have executed it for more than 15 hrs but still it is not getting completed and is still showing 0%. Can you please help us to execute this step?

Thanking you in Advance!

Best regards,
Mohit Gureja

Error on 'ADMITTIME'

Hello Dr. Darabi
I try to run gen_data_df.py on Colab and upload the MIMIC III dataset (CSV files) folder on Google Drive.
I get an error on ADMITTIME.

NumExpr defaulting to 2 threads.
removing diagnosis codes occuring less than 5 times.
num codes before filter: 88 after filtering: 1
removing cpt procedure codes occuring less than 5 times.
num codes before filter: 18 after filtering: 3
removing prescription codes occuring less than 5 times.
num codes before filter: 121 after filtering: 9
removing procedure codes occuring less than 5 times.
num codes before filter: 1995 after filtering: 1055
Traceback (most recent call last):
File "/content/TAPER-EHR/TAPER-EHR/gen_data_df.py", line 99, in
df_adm_notes['ADMITTIME_C'] = df_adm_notes.ADMITTIME.apply(lambda x: str(x).split(' ')[0])
File "/usr/local/lib/python3.6/dist-packages/pandas/core/generic.py", line 5139, in getattr
return object.getattribute(self, name)
AttributeError: 'DataFrame' object has no attribute 'ADMITTIME'

Could you please guide in this issue?
Thank you