Add MapReduceMetric a new base class to integrate all metrics into #1459
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
Signed-off-by: elronbandel <[email protected]>
dafnapension
force-pushed
the
new-base-metric
branch
from
c0217d9 to
9377910
Compare
| predictions, dataset: Union[Dataset, IterableDataset], data=None | ||
| ) -> EvaluationResults: | ||
| if data is not None: | ||
| dataset = data # for backward compatibility |
There was a problem hiding this comment.
What if both are not None?
There was a problem hiding this comment.
I wanted to rename data to dataset to have consistent name with load_dataset and create_dataset and DatasetRecipe but yet have backward compatibility for code using data=
…rocessing Signed-off-by: elronbandel <[email protected]>
Signed-off-by: elronbandel <[email protected]>
…rocessing Signed-off-by: elronbandel <[email protected]>
dafnapension
force-pushed
the
new-base-metric
branch
from
c0bbe7f to
6e29e41
Compare
…fidenceIntervalMixin Signed-off-by: elronbandel <[email protected]>
…new-base-metric Signed-off-by: elronbandel <[email protected]>
dafnapension
previously approved these changes
Dec 26, 2024
… accuracy calculations Signed-off-by: elronbandel <[email protected]>
| @abstractmethod | ||
| def _sample_to_scores(self, sample: List[Any]) -> Dict[str, Any]: | ||
| pass | ||
|
|
There was a problem hiding this comment.
to my understanding, score_names might include instance metrics as well as global metrics.
For instance metrics, the instance scores are already computed, and why compute them again?
…ccuracy and F1 metrics Signed-off-by: elronbandel <[email protected]>
Signed-off-by: elronbandel <[email protected]>
…configurations for consistency Signed-off-by: elronbandel <[email protected]>
elronbandel
force-pushed
the
new-base-metric
branch
from
0d28be9 to
7cd647b
Compare
…for improved type handling Signed-off-by: elronbandel <[email protected]>
…r and classes, and updating defaults for improved clarity and type safety Signed-off-by: elronbandel <[email protected]>
…nsistency Signed-off-by: elronbandel <[email protected]>
…ic classification Signed-off-by: elronbandel <[email protected]>
…y metrics Signed-off-by: elronbandel <[email protected]>
…ming consistency and improve text processing with new operators Signed-off-by: elronbandel <[email protected]>
…es, enhance data classification policies, and improve type safety with Literal types Signed-off-by: elronbandel <[email protected]>
… and standardize class names to lowercase for consistency Signed-off-by: elronbandel <[email protected]>
…g additions and remove unnecessary code Signed-off-by: elronbandel <[email protected]>
…d classes, enhancing type safety and consistency in multi-turn and single-turn configurations Signed-off-by: elronbandel <[email protected]>
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.
No description provided.