[ML] Validate that AucRoc has the data necessary to be calculated #63302
Conversation
This file contains hidden or 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
przemekwitek
force-pushed
the
auc_roc_remove_doc_count
branch
2 times, most recently
from
08045f5 to
08a3942
Compare
|
run elasticsearch-ci/packaging-sample-windows |
przemekwitek
changed the title
przemekwitek
force-pushed
the
auc_roc_remove_doc_count
branch
from
08a3942 to
f41a7f5
Compare
|
run elasticsearch-ci/packaging-sample-windows |
przemekwitek
force-pushed
the
auc_roc_remove_doc_count
branch
from
f41a7f5 to
b3c8727
Compare
|
Pinging @elastic/ml-core (:ml) |
|
run elasticsearch-ci/2 |
benwtrent
reviewed
Oct 6, 2020
client/rest-high-level/src/test/java/org/elasticsearch/client/MachineLearningIT.java
Outdated
Show resolved
Hide resolved
...high-level/src/test/java/org/elasticsearch/client/documentation/MlClientDocumentationIT.java
Outdated
Show resolved
Hide resolved
...rc/main/java/org/elasticsearch/xpack/core/ml/dataframe/evaluation/classification/AucRoc.java
Outdated
Show resolved
Hide resolved
przemekwitek
force-pushed
the
auc_roc_remove_doc_count
branch
from
16d8a24 to
0fe60e4
Compare
|
run elasticsearch-ci/2 |
benwtrent
approved these changes
Oct 7, 2020
Remove AbstractAucRoc.Result.doc_count field
przemekwitek
force-pushed
the
auc_roc_remove_doc_count
branch
from
0fe60e4 to
175f2a7
Compare
przemekwitek
added a commit
to przemekwitek/elasticsearch
that referenced
this pull request
Oct 8, 2020
przemekwitek
added a commit
to przemekwitek/elasticsearch
that referenced
this pull request
Oct 8, 2020
przemekwitek
added a commit
that referenced
this pull request
Oct 8, 2020
przemekwitek
added a commit
that referenced
this pull request
Oct 8, 2020
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.
When
AucRocis evaluated in the context of multiclass classification evaluation, it must require that the probability of the class in question (class_name) is known for every document. Otherwise, the results will not be correct.This PR tightens the validation so that when the probability of the class in question is not known for at least one document, the evaluation request fails rather than returning erroneous results.
Consequently,
AbstractAucRoc.Result.doc_countfield is no longer needed so it is removed in this PR as well.Marking this PR
>non-issueas theAucRocmetric is not released yet.Relates #63306