Release v0.39.0

[chukarsten]

v0.39.0 Dec. 9, 2021

Enhancements

• Renamed DelayedFeatureTransformer to TimeSeriesFeaturizer and enhanced it to compute rolling features Rolling Mean features for time series #3028
• Added ability to impute only specific columns in PerColumnImputer Add ability to only impute specific columns #3123
• Added TimeSeriesParametersDataCheck to verify the time series parameters are valid given the number of splits in cross validation Add DataCheck to validate time series problem configuration parameters #3111

Fixes

• Default parameters for RFRegressorSelectFromModel and RFClassifierSelectFromModel has been fixed to avoid selecting all features Change default parameters for feature selectors #3110

Changes

• Removed reliance on a datetime index for ARIMARegressor and ProphetRegressor Refactor ARIMA/Prophet #3104
• Included target leakage check when fitting ARIMARegressor to account for the lack of TimeSeriesFeaturizer in ARIMARegressor based pipelines Refactor ARIMA/Prophet #3104
• Cleaned up and refactored InvalidTargetDataCheck implementation and docstring Clean up and refactor InvalidTargetDataCheck #3122
• Removed indices information from the output of HighlyNullDataCheck's validate() method Move out indices information from output of HighlyNullDataCheck's validate() method #3092
• Added ReplaceNullableTypes component to prepare for handling pandas nullable types. ReplaceNullableTypes Component #3090
• Removed unused EnsembleMissingPipelinesError exception definition Remove EnsembleMissingPipelinesError exception #3131

Documentation Changes

Testing Changes

• Refactored tests to avoid using importorskip Refactor tests to avoid using importorskip #3126
• Added skip_during_conda test marker to skip tests that are not supposed to run during conda build Skip tests that are not supposed to run during conda #3127
• Added skip_if_39 test marker to skip tests that are not supposed to run during python 3.9 Mark which tests should be skipped for python 3.9 #3133

Breaking Changes

• Renamed DelayedFeatureTransformer to TimeSeriesFeaturizer Rolling Mean features for time series #3028
• ProphetRegressor now requires a datetime column in X represented by the date_index parameter Refactor ARIMA/Prophet #3104
• Renamed module evalml.data_checks.invalid_target_data_check to evalml.data_checks.invalid_targets_data_check Clean up and refactor InvalidTargetDataCheck #3122
• Removed unused EnsembleMissingPipelinesError exception definition Remove EnsembleMissingPipelinesError exception #3131

[codecov]

Codecov Report

Merging #3136 (9f08b03) into main (bd2b9b2) will increase coverage by 0.8%.
The diff coverage is 100.0%.

@@           Coverage Diff           @@
##            main   #3136     +/-   ##
=======================================
+ Coverage   99.0%   99.7%   +0.8%     
=======================================
  Files        317     317             
  Lines      30711   30711             
=======================================
+ Hits       30374   30607    +233     
+ Misses       337     104    -233     

Impacted Files	Coverage Δ
evalml/__init__.py	100.0% <100.0%> (ø)
evalml/tests/automl_tests/test_automl.py	99.5% <0.0%> (+0.1%)	⬆️
evalml/automl/automl_search.py	99.9% <0.0%> (+0.2%)	⬆️
evalml/automl/utils.py	100.0% <0.0%> (+1.7%)	⬆️
...lml/tests/automl_tests/test_iterative_algorithm.py	100.0% <0.0%> (+7.8%)	⬆️
evalml/tests/automl_tests/test_automl_utils.py	100.0% <0.0%> (+9.4%)	⬆️
.../automl_tests/test_automl_search_classification.py	100.0% <0.0%> (+10.3%)	⬆️
...ests/automl_tests/test_automl_search_regression.py	100.0% <0.0%> (+15.8%)	⬆️
...l/tests/automl_tests/test_pipeline_search_plots.py	100.0% <0.0%> (+76.8%)	⬆️
evalml/automl/pipeline_search_plots.py	100.0% <0.0%> (+82.2%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update bd2b9b2...9f08b03. Read the comment docs.

[angela97lin]

LGTM, thanks @chukarsten! 😁

[jeremyliweishih]

looks good!