Release 0.14.0 #1247
Merged
Release 0.14.0 #1247
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
* Fix determinism for few preprocessing techniques * Code formatting * Fix: model deserialization when mutual_info score is used for select_percentile/rates Co-authored-by: Rohit Agarwal <[email protected]>
…ocessing and feature type split (#977) * making data preprocessing step configurable with two options no preprocessing and feature type split * Fix: execution fails when data_preprocessor is no_preprocesing * Incorporating review comments * Fixing test cases; updating metalearning with updated hyperparameters * Fixing examples * Updating portfolios with new config * Incorporated review comments and fix test case * Test fixes * Test fixes * Fix metalearning config * Remove unused imports * Fix test cases * Fix test cases and examples * Adding more checks for include and exclude params * Fix flake error * Fix flake error * Handling target_type in datatset_properties * Fixes * Fixes * Fix error * Fix test cases * Adding datatype annotations * Fix test cases * Fix build * Fix test case' * Update stale.yaml * Fix annotation type * Update portfolios with new config Co-authored-by: Rohit Agarwal <[email protected]>
The function `def get_runhistory_models_performance(automl):` didn't use the parameter `automl` and instead used the global variable `cls`. This PR fixes that.
* Make backend deletion robust after fit * [FIX] smbo unittest * Output folder is needed for ensemble output * fit_ensemble also runs in manual spawning * fit_ensemble also runs in manual spawning * Rebase artifacts * Fix rebase * Missed arg in examples * Remove rebase artifacts Co-authored-by: Eddie Bergman <[email protected]>
…18.04 to 20.04 (#1198) * Updated docker distribution environment * Upgraded pytest workflow to use 20.04 * Updated values for 20.04
* Fix determinism for few preprocessing techniques * Code formatting * Fix: model deserialization when mutual_info score is used for select_percentile/rates Co-authored-by: Rohit Agarwal <[email protected]>
…ocessing and feature type split (#977) * making data preprocessing step configurable with two options no preprocessing and feature type split * Fix: execution fails when data_preprocessor is no_preprocesing * Incorporating review comments * Fixing test cases; updating metalearning with updated hyperparameters * Fixing examples * Updating portfolios with new config * Incorporated review comments and fix test case * Test fixes * Test fixes * Fix metalearning config * Remove unused imports * Fix test cases * Fix test cases and examples * Adding more checks for include and exclude params * Fix flake error * Fix flake error * Handling target_type in datatset_properties * Fixes * Fixes * Fix error * Fix test cases * Adding datatype annotations * Fix test cases * Fix build * Fix test case' * Update stale.yaml * Fix annotation type * Update portfolios with new config Co-authored-by: Rohit Agarwal <[email protected]>
The function `def get_runhistory_models_performance(automl):` didn't use the parameter `automl` and instead used the global variable `cls`. This PR fixes that.
* Make backend deletion robust after fit * [FIX] smbo unittest * Output folder is needed for ensemble output * fit_ensemble also runs in manual spawning * fit_ensemble also runs in manual spawning * Rebase artifacts * Fix rebase * Missed arg in examples * Remove rebase artifacts Co-authored-by: Eddie Bergman <[email protected]>
…18.04 to 20.04 (#1198) * Updated docker distribution environment * Upgraded pytest workflow to use 20.04 * Updated values for 20.04
* Added doc and made function more legible * Removed a rogue 'self' in abstract method * Cleaned up _model_predict, now gives errors instead of warning * Added test to catch issue 1169 and possibly others * doc fix * typo fix in docs * Added expected output shape to the test * flake8'd * Requested changes * Readded logger with simplified context manager * Mypy and flake8 fixes
* Moved fit validation to AutoML fit and fit_pipeline * Added test for target and feature types * Added convert if sparse throughout * type fixes, func doc * flake8'd * Added docstring to AutoML.fit * flake8'd
* Fix and test for stratification of unique labels * Made sure number of samples if respected * Flake8'd * review changes, TODO -> Note, remove warning.call_count assertion * Fix sparse y (#1213) * Moved fit validation to AutoML fit and fit_pipeline * Added test for target and feature types * Added convert if sparse throughout * type fixes, func doc * flake8'd * Added docstring to AutoML.fit * flake8'd * flake8'd after merge * Fix and test for stratification of unique labels * Made sure number of samples if respected * Flake8'd * review changes, TODO -> Note, remove warning.call_count assertion * flake8'd after merge * removed dupe test
…1229) * Cleaned up some code in the documentation
* added performance over time plot as attribute
* m * csvs * util file * Added .gitattributes: * Added generate-baselines * update * Fixed branch envvar * Removed excess path part * Fix branch extract * Typo fix * Typo fixes * branch extract? * filename fix * path fix * path fix * fix tadodedoo * 1 step closer to going home * sigh...typo * regression workflow stuff * Updated to new flow * switched to baseline off development * Fix yaml * fix again ... * first sigh * Event fixes, second sigh * third sigh * Finding issues * message * narrow down? * maybe multiple jobs? * create-comment issue? * Now? * Fixed maybe * UPdated to seek from development branch * Yah * Fix branch extraction * fix branch extraction * m * Fixed branch extraction * Someday * Moved back to 1 dataset for testing * updated path * sigh typo fix * Typo fix * typo typo typo * reorganized faster steps to top * new branch9 * Dependancies and update util file * ... * soon * new branch12 * new branch13 * *sad song lyrics* * new branch14 * sigh * . * reorder * filenaming fix * . * Fixed extract branch, changed to https clone * -- * typo fix * fixes * Fixes * Fxi * update * Update pip * soon * more fixes * Fix 678 * Almost there * new branch33 * Some fixes and convience in artifacts * view content changes * Fix path names * . * ... * fix paths * path fixes * More fixes * Fix output * Re-included full tests * Cleanup * cleanup old test file * Deleted old test files * Changed param types * Updates * Update to use system python * test method of passing python version to setup python * Update all of them * Grab just numeric part of version
* Fixed module idempotent tests to match sklearns descriptions * Added pytest.ini so examples with "test" in name don't run * random_state now documented and used properly * flake8'd * Removed stray print statement * Fixed failing tests * Added testing for pipeline steps random_states * Added random_state to Pipelines that have fit called * flake8'd * Made mlp tests less sensitive to platform differences * review changes
…from 45m) (#1239) * Update total test time out to be 60min * Update total test time out to be 60min
* update * Update doc/installation.rst Co-authored-by: Matthias Feurer <[email protected]> * Update doc/installation.rst Co-authored-by: Matthias Feurer <[email protected]> Co-authored-by: Matthias Feurer <[email protected]>
to show that we're on the development branch.
* Fix rare edge case with extremely inbalanced data For dataset 360112 Auto-sklearn would fail because the data would first be sub-sampled and then contain some classes only once. In the internal splitting, the StratifiedShuffleSplit would not be able to split the dataset into train and valid, and would resort to only a ShuffleSplit. This could put the single sample for a class into the test set. At predict time we would then miss one class. This commit creates two new splitters which move a sample from the test split to the training split if a class does not exist in the train split. * fix unit test
Codecov Report
@@ Coverage Diff @@
## master #1247 +/- ##
==========================================
- Coverage 88.19% 88.06% -0.13%
==========================================
Files 138 140 +2
Lines 10866 11144 +278
==========================================
+ Hits 9583 9814 +231
- Misses 1283 1330 +47
Continue to review full report at Codecov.
|
github-actions bot
pushed a commit
to dumpmemory/auto-sklearn
that referenced
this pull request
Sep 14, 2021
github-actions bot
pushed a commit
to iryna-savchuk/auto-sklearn
that referenced
this pull request
Sep 28, 2021
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.