Add node regression in benchmarking code #399
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jiaqima
reviewed
Nov 29, 2022
benchmarks/NodeRegression/utils.py
Outdated
| return sum(rocauc_list)/len(rocauc_list) | ||
|
|
||
|
|
||
| def check_binary_classification(dataset): |
There was a problem hiding this comment.
Let's do some cleaning on the redundant functions that are not needed for regression tasks. Please also change "classification" to "regression" in function names and comments.
|
Update:
|
jiaqima
reviewed
Nov 29, 2022
| def read_input(self): | ||
| """Read input.""" | ||
| data = gli.dataloading.get_gli_dataset(self.args.dataset, | ||
| "NodeClassification") |
There was a problem hiding this comment.
Do we need to change to "NodeRegression" here?
|
|
||
| def run(self, | ||
| save_folder: str = None, | ||
| task: str = "NodeClassification", |
| @@ -0,0 +1,207 @@ | |||
| """ | |||
| Train for node classification dataset. | |||
| def parse_args(): | ||
| """Parse the command line arguments.""" | ||
| parser = argparse.ArgumentParser(description="train for node\ | ||
| classification") |
jiaqima
reviewed
Nov 29, 2022
|
|
||
| ## Supported datasets | ||
|
|
||
| No `NodeRegrssion` datasets available now. |
There was a problem hiding this comment.
I'll add a regression dataset in the next couple of days.
If the regression implementation already seems to work well, could you add a test for NodeRegression training in another PR? Maybe let's first add the test, then I'll add a regression dataset, and let's merge this PR after I add the dataset.
There was a problem hiding this comment.
Of course, I will open another PR for this test.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
As titled.
Provide
mseandmaeas metrics and loss function.train.pycan run successfully oncora(pretending it is a node regression task).TODO: update
train_minibatch.pyandtrain_gbdt.py