Ignore abstains in Scorer, change LabelModel default tie break policy #1450
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 Report
@@ Coverage Diff @@
## master #1450 +/- ##
=======================================
Coverage 97.58% 97.58%
=======================================
Files 55 55
Lines 2029 2029
Branches 334 334
=======================================
Hits 1980 1980
Misses 22 22
Partials 27 27
|
paroma
requested review from
vincentschen,
ajratner,
henryre and
bhancock8
and removed request for
ajratner and
henryre
bhancock8
requested changes
Sep 10, 2019
| @@ -472,6 +472,11 @@ def score( | |||
| >>> label_model.score(L, Y=np.array([1, 1, 1]), metrics=["f1"]) | |||
| {'f1': 0.8} | |||
| """ | |||
| if tie_break_policy == "abstain": # pragma: no cover | |||
| logging.warning( | |||
| "Metrics calculated over datapoints with non-abstain labels only" | |||
There was a problem hiding this comment.
Nit: we've been using data points (2 words)
test/analysis/test_scorer.py
Outdated
| # Test abstain=-1 for preds and gold | ||
| abstain_preds = np.array([-1, -1, 1, 1, 0]) | ||
| abstain_probs = np.array([0.5, 0.5, 0.9, 0.7, 0.4]) | ||
| results = scorer.score(golds, abstain_preds, abstain_probs) |
There was a problem hiding this comment.
No need to pass in probs here. They're optional, and you're only calculating accuracy in this scorer, which just requires golds and preds.
| @@ -209,6 +209,13 @@ def test_predict_proba(self): | |||
| np.testing.assert_array_almost_equal(probs, true_probs) | |||
|
|
|||
| def test_predict(self): | |||
| L = np.array([[-1, 1, 0], [0, -1, 1], [1, 0, -1]]) | |||
There was a problem hiding this comment.
Can we add a simple comment here that this test is confirming that with 3 LFs that counteract one another results in tie votes and therefore abstains on all points?
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.
Description of proposed changes
score()functionTest plan
predict()andscore()functions related to abstain defaultChecklist