Skip to content
This repository has been archived by the owner on Jul 24, 2023. It is now read-only.

How I can save/load the learned things? #9

Open
rkmax opened this issue Feb 5, 2018 · 4 comments
Open

How I can save/load the learned things? #9

rkmax opened this issue Feb 5, 2018 · 4 comments

Comments

@rkmax
Copy link

rkmax commented Feb 5, 2018

Assuming that I can have many models and each one with a lot of samples, how I can store the learned things, so I can store it in some file and later on i can read from the file?

@shixzie
Copy link
Owner

shixzie commented Feb 8, 2018

Hey! To answer your question, currently you can not save trained models. This was a project of mine to try and get involved with machine learning, but as it turned out, I just ended up with something that looks cool at first sight but then you realize it's just a fancy and maybe more performant regex. I say maybe because no benchmarks have been done. Also, the only process that can be persisted to a file (save training) is the training of the Naive Bayes algorithm used to distinguish between models. Every expression would still have to iterate through all samples to see which sample fits best the expression.

@rkmax
Copy link
Author

rkmax commented Feb 8, 2018

Thanks a lot for the clarification

@legion-zver
Copy link

@rkmax сan you try using my fork https://github.com/itrabbit/nlp.
I added the Export/Import methods.

@rkmax
Copy link
Author

rkmax commented May 20, 2018

thx @legion-zver I'll try to give a try next week

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants