chore: Update experiment configs and bugfixes #631
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
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #631 +/- ##
==========================================
- Coverage 85.61% 85.59% -0.03%
==========================================
Files 258 258
Lines 11334 11338 +4
==========================================
+ Hits 9704 9705 +1
- Misses 1630 1633 +3 ☔ View full report in Codecov by Sentry. |
|
|
robinholzi
commented
Dec 28, 2024
| @@ -103,10 +103,14 @@ def inform_new_model( | |||
| ) -> None: | |||
| """Update the cost tracker with the new model metadata.""" | |||
| self._unincorporated_samples = 0 | |||
|
|
|||
| # reset regret | |||
| self.latency_tracker.inform_trigger() | |||
robinholzi
commented
Dec 28, 2024
| @@ -154,4 +157,36 @@ def _alibi_detect_metric_factory(config: AlibiDetectDriftMetric, embeddings_ref: | |||
| **kwargs, | |||
| ) | |||
|
|
|||
| if isinstance(config, AlibiDetectLSDDDriftMetric): | |||
| return LSDDDrift( | |||
robinholzi
commented
Dec 28, 2024
| @@ -24,9 +24,6 @@ def _batch_evaluated_callback(self, y_true: torch.Tensor, y_pred: torch.Tensor, | |||
| self.total_correct += labeled_correctly | |||
| self.samples_seen += batch_size | |||
|
|
|||
| self.total_correct += labeled_correctly | |||
robinholzi
commented
Dec 28, 2024
| AlibiDetectDriftMetric = Annotated[ | ||
| AlibiDetectMmdDriftMetric | AlibiDetectKSDriftMetric | AlibiDetectCVMDriftMetric, | ||
| AlibiDetectMmdDriftMetric |
There was a problem hiding this comment.
Added more drift detectors.
robinholzi
commented
Dec 28, 2024
| @@ -1,17 +1,16 @@ | |||
| import os | |||
There was a problem hiding this comment.
various experiments for thesis
robinholzi
commented
Dec 28, 2024
| @@ -2,12 +2,15 @@ | |||
|
|
|||
| import pandas as pd | |||
There was a problem hiding this comment.
Various thesis experiments for huffpost.
robinholzi
commented
Dec 28, 2024
| @@ -2,12 +2,16 @@ | |||
|
|
|||
| import pandas as pd | |||
There was a problem hiding this comment.
Various thesis experiments for arxiv.
robinholzi
commented
Dec 28, 2024
| transformed["category"] = pd.Categorical(transformed["category"]).codes | ||
| if not keep_true_category: | ||
| # to int-categorical | ||
| transformed["category"] = pd.Categorical(transformed["category"]).codes |
There was a problem hiding this comment.
For exploring dataset with original labels.
robinholzi
changed the title
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.
Motivation
Final changes from thesis.