-
Notifications
You must be signed in to change notification settings - Fork 42
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
Implement SPORF #374
Implement SPORF #374
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For oblique tree, could you please make sure all of the docstrings have underscores that match the lengths of the headers. For example, line 16 should be enough underscores to cover the "Parameters" word. Also, you shouldn't have colons after those words.
This is to make sure things render in Sphinx correctly. Once you make those changes, can you please check the web docs to make sure things render appropriately? For reference, please check the other docs to see what it should look like and update until your docs looks like that.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also, the travis tests failed. One of the reasons is you didn't include the oblique tree in the ProgLearn package. To do so, please add it to https://github.com/parthgvora/ProgLearn/blob/staging/proglearn/__init__.py
Please update the code until the travis tests pass. If the code does not pass a test, Travis will show you those errors if you check the Travis console.
Thanks for the help Will! We'll make the changes and get back to you. |
@parthgvora we also need all the benchmarks that show your implementation works as well as the main paper. |
This should be in the notebook - sorry for any confusion. We ran the code on 3 UCI datasets that SPORF was able to classify perfectly; our code was also able to classify them perfectly. Notably, we could classify the Hill-Valley dataset perfectly, which RF was unable to do. |
I will go through it in detail. It may take time. |
No problem - please let us know what you think :) If you have any questions please let me know |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@parthgvora @jmandavilli please black format your files to pass the travis test.
@parthgvora there were some strange indentations of docstrings, and I fixed them for you. This fix should not affect black formatting. |
@PSSF23 It looks good to me now. What do you think? |
@levinwil Jayanta said he was going to look through the benchmarks. Otherwise, to my limit of knowledge, everything looks good. |
@jdey4 Have you had a chance to look this over? |
@levinwil nope. |
@parthgvora Please remember to add all parameters to the docstrings |
Yep, sorry! We're just going through the changes you suggested. Thanks for your help! |
I just added the parameters to the docstrings as you suggested Will, so that should be good now. Sorry for the delay. |
@levinwil should the tutorials be included in the |
@PSSF23 yup! |
@levinwil then do you think the tutorial names should be more consistent? Like |
Co-Authored-By: jmandav1 <[email protected]> Co-Authored-By: parthgvora <[email protected]>
@parthgvora @jmandavilli I added your tutorials to the |
Thank you for taking care of that @PSSF23! We can change the file names once Will confirms. Thank you guys for all of the help. |
I agree with @PSSF23: the tutorial names should be consistent. As for if you want the prefix to be oblique or sporf - that is up to you. I don’t have a strong opinion either way. |
@jmandavilli @parthgvora Have you all renamed the notebooks? |
Hey, I'm really sorry I have a final in a couple of hours. I will rename the notebooks right after |
Just renamed the notebooks, sorry for the delay. I updated tutorials.rst as well. Let us know if there is anything else. Thanks again. |
…ecision_boundaries_functions.py Co-Authored-By: jmandav1 <[email protected]> Co-Authored-By: parthgvora <[email protected]>
Co-Authored-By: jmandav1 <[email protected]> Co-Authored-By: parthgvora <[email protected]>
Thanks for catching that Hao. My bad. |
All of my concerns were addressed! |
Reference issue
Closes #351, #352.
Type of change
Feature request
What does this implement/fix?
Additional information