Calculate loss support #1075
Merged
Calculate loss support #1075
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
Codecov Report
@@ Coverage Diff @@
## development #1075 +/- ##
===============================================
- Coverage 85.46% 85.44% -0.03%
===============================================
Files 130 130
Lines 10334 10330 -4
===============================================
- Hits 8832 8826 -6
- Misses 1502 1504 +2
Continue to review full report at Codecov.
|
mfeurer
reviewed
Feb 5, 2021
mfeurer
approved these changes
Feb 16, 2021
franchuterivera
added a commit
to franchuterivera/auto-sklearn
that referenced
this pull request
Mar 11, 2021
* MAINT cleanup readme and remove old service yaml file (.landscape.yaml) * MAINT bump to dev version * move from fork to spawn * FIX_1061 (automl#1063) * FIX_1061 * Fxi type of target * Moving to classes_ * classes_ should be np.ndarray * Force float before nan * Pynisher context is passed to metafeatures (automl#1076) * Pynisher context to metafeatures * Update test_smbo.py Co-authored-by: Matthias Feurer <[email protected]> * Calculate loss support (automl#1075) * Calculate loss support * Relaxed log loss test for individual models * Feedback from automl#1075 * Missing loss in comment * Revert back test as well * Fix rank for metrics for which greater value is not good (automl#1079) * Enable Mypy in evaluation (except Train Evaluator) (automl#1077) * Almost all files for evaluation * Feedback from PR * Feedback from comments * Solving rebase artifacts * Revert bytes * Automatically update the Copyright when building the html (automl#1074) * update the year automatically * Fixes for new numpy * Revert test * Prepare new release (automl#1081) * prepare new release * fix unit test * bump version number * Fix 1072 (automl#1073) * Improve selector checking * Remove copy error * Rebase changes to development * No .cache and check selector path * Missing params in signature (automl#1084) * Add size check before trying to split for GMeans (automl#732) * Add size check before trying to split * Rebase to new code Co-authored-by: chico <[email protected]> * Fxi broken links in docs and update parallel docs (automl#1088) * Fxi broken links * Feedback from comments * Update manual.rst Co-authored-by: Matthias Feurer <[email protected]> * automl#660 Enable Power Transformations Update (automl#1086) * Power Transformer * Correct typo * ADD_630 * PEP8 compliance * Fix target type Co-authored-by: MaxGreil <[email protected]> * Stale Support (automl#1090) * Stale Support * Enhanced criteria for stale * Enable weekly cron job * test Co-authored-by: Matthias Feurer <[email protected]> Co-authored-by: Matthias Feurer <[email protected]> Co-authored-by: Rohit Agarwal <[email protected]> Co-authored-by: Pepe Berba <[email protected]> Co-authored-by: MaxGreil <[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.
Enables calculate_loss which makes sure that all optimization problems are treated as minimization.
Please notice that calculate_score made it so that any call to functions like log_loss returned the result of a negative version of scikit learn log_loss. I have made it so that we return the score of scikit learn and only modify this score for calculate_loss. This implied changes in a couple of places of the testing code.