Using a Spacy Project Template in DSS
I'm trying to run a SpaCy template project: This textcat_multilabel_demo pipeline in particular.
Edit: I was able to run a project command from a notebook by hardcoding the path. Still the question remains if there is a better way to take advantage of SpaCy pipeline templates in dataiku and use it jumpstart an NLP project?
I'm failing to get it to run in any way.
I've successfully imported it into a project library using the git functionality, moved it under the python folder, and I've added __innit__.py files in each folder, all of which let's me import it as a package in a jupyter notebook; but I still can't seem to run anything. Nor can I use the command line tools anywhere - tried in a shell recipe but that didn't work either.
Is there a way to run such a Spacy pipline demo in dataiku and use it jumpstart an NLP project?
Operating system used: Windows
Operating system used: Windows
Answers
-
CoreyS Dataiker Alumni, Dataiku DSS Core Designer, Dataiku DSS Core Concepts, Registered Posts: 1,150 ✭✭✭✭✭✭✭✭✭Hi @talalmufti
thank you for your question! While you wait for a more complete response, I wanted to make you aware of a few resources just incase you haven't accessed them yet:- Using SpaCy (Documentation)
- How to use spaCy models in Dataiku DSS (Knowledge Base)
- Named Entity Recognition (Plugin)
I hope this helps!