where can i get/generate/download the vocab pickle file?

ZhiGroup / Med-BERT

Med-BERT, contextualized embedding model for structured EHR data

Apache License 2.0

244 stars 62 forks source link

where can i get/generate/download the vocab pickle file? #15

Closed josaphattirza closed 1 year ago

josaphattirza commented 1 year ago

I'm a researcher trying to reproduce the result of Med-BERT using dataset containing ICD-9 and ICD-10 codes. I am having trouble to generate the required vocab pickle file. Thank you for your help.

lrasmy commented 1 year ago

@josaphattirza

In this version, if you do not have a predefined vocab pickled file, you just set that option to NA when you run preprocess_pretrain_data.py, and a new .types file will be generated (this is the vocab pickled dictionary) based on your data.

josaphattirza commented 1 year ago

Thank you