harmonydata / harmony

The Harmony Python library: a research tool for psychologists to harmonise data and questionnaire items. Open source.
https://harmonydata.ac.uk
MIT License
7 stars 12 forks source link

Harmony should remove digits if every question starts with a digit #23

Open woodthom2 opened 6 months ago

woodthom2 commented 6 months ago

Description

If I upload a CSV file like this, Harmony puts digits at the start of each question

1 I feel nervous
2 I feel afraid

Environment

Web Harmony

How to Reproduce

Make file harmony.csv with content

1 I feel nervous
2 I feel afraid

Upload to web UI

You will see digits at the start of all questions

image

Expected Behavior

Digits should be removed

woodthom2 commented 6 months ago

Also need unit test for this

shahid-0 commented 6 months ago

I will work on that issue.

rman1223 commented 6 months ago

This problem is almost close to prompt engineering. I don't know your model lable status in more detail. But, prompt engineering is very important to active the model's feature more and need to go over this step. Thus, I think that it seems to be a good to solve through prompting. Thank you!