Hi,

Just wondering where we could find the "umls_install.sh" script?

Thanks!

Would it be possible to use Trove to perform sentiment analysis on clinical notes? I have access to all the MIMIC-IV discharge notes but am struggling to find a good tool to use for sentiment analysis. It seems like most models are not designed for such use.

A lot of the imports in the scripts under the "applications" subfolder fail - for example:
from trove.utils import score_umls_ontologies
from trove.labelers.norm import lowercase, strip_affixes

This makes it impossible to reproduce the experiments in the paper

Could you please share these functions (or the previous version of the repo) to make the code runnable?
Thanks a lot in advance!

Describe the bug

I can't install the UMLS as directed by the tutorial notebooks. The UMLS object can't be initialized.

Steps to reproduce the bug

I downloaded the relevant zip file from the provided link (https://download.nlm.nih.gov/umls/kss/2020AB/umls-2020AB-metathesaurus.zip) and placed the file in the same directory as the 1_Installing_the_UMLS.ipynb notebook in the tutorials folder. Then I ran the notebook as given in the github.

Sample code to reproduce the bug

Expected results

A clear and concise description of the expected results.

Actual results

Specify the actual results or traceback.

The libraries and python version are all on the pdf attached

Environment info

• datasets version:
• Platform:
  1_Installing_the_UMLS_with_decode_error.pdf

• Python version:

The libraries and python version are all on the pdf attached

• PyArrow version:

The libraries and python version are all on the pdf attached

Hi, thank you for the interesting piece of work!

When I tried to preprocess my data, I encountered this error: ImportError: cannot import name 'SentenceSegmenter' from 'spacy.pipeline' when running parse.py. I checked for spacy documentation and it doesn't have the SentenceSegmenter feature. May I get your advice on how to solve this issue?

Thank you so much!