icebreaker-science / network

Exploring the network of concepts and methods in the chemistry using text mining techniques
2 stars 0 forks source link

Feature/get merge by abbreviations #8

Closed michael-kamel closed 3 years ago

michael-kamel commented 3 years ago

This adds getting the merge candidates based on the alias data in the DB.

One refinement would be to clean up the wiki data first since most generated results are completely out of context or wrong.

michael-kamel commented 3 years ago

I think that I have understood the structure of the code, looks very nice!

But it's hard to tell if it really works correctly. I will need a little more time. However, if you are certain, you can also just run it.

Have you tried it on a small sample locally?

I tried it on a sample of 11 nodes that should cover all cases, however it is indeed really difficult to tell