-
Notifications
You must be signed in to change notification settings - Fork 58
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Prediction function #9
Comments
Indeed I couldn't find one too. |
I wound up using/rewriting most of test.py into an init.py with an importable predict(url) function just to take a single unlabeled URL and provide a score. I totally violated the DRY principle since there's so much shared code, but it was a quick hack. |
sounds great! |
@mdavis332 I am trying to do the same for my scientific work. Can you share your solution with us? |
@eladwass In general, I had to redo everything myself) I just combined the test.py and utils.py files in such a way that using the neural network was reduced to calling one method 'main_logic'. I apologize in advance for the terrible style of the code, I made a lot of attempts until I got a workable code, and besides, I have only been learning python for a couple of weeks.
|
I was unable to find an exportable function that could be called from another python script to provide a prediction or score based on a single or list of URLs.
i.e., once the model is developed, how does one use it to make predictions on a naked URL with no label?
Is that something I missed within this code or is the code solely meant as an academic proof of model development?
The text was updated successfully, but these errors were encountered: