Release v0.63.0

[chukarsten]

v0.63.0 Nov. 23, 2022

Enhancements

• Added fast mode to partial dependence Partial Dependence Fast Mode #3753
• Added the ability to serialize featuretools features into time series pipelines Add DFSTransformer to time series pipelines #3836

Fixes

• Fixed TimeSeriesFeaturizer potentially selecting lags outside of feature engineering window Only select lags within FE window dictated by FH and gap #3773
• Fixed bug where TimeSeriesFeaturizer could not encode Ordinal columns with non numeric categories Allow time series featurizer to encode Ordinal logical types #3812
• Updated demo dataset links to point to new endpoint Update demo dataset links to point to new endpoint #3826
• Updated STLDecomposer to infer the time index frequency if it's not present Clean up decomposer index logic #3829
• Updated _drop_time_index to move the time index from X to both X.index and y.index Clean up decomposer index logic #3829
• Added TimeSeriesPipeline.should_skip_featurization to fix bug where data would get featurized unnecessarily Add pipeline.should_skip_featurization flag #3849
• Fixed bug where engineered features lost their origin attribute in partial dependence, causing it to fail Allow engineered features in pipeline with dfs transfomer to have pd calculations done #3830
• Fixed bug where partial dependence's fast mode handling for the DFS Transformer wouldn't work with multi output features Allow engineered features in pipeline with dfs transfomer to have pd calculations done #3830
• Allowed target to be present and ignored in partial dependence's DFS Transformer fast mode handling Allow engineered features in pipeline with dfs transfomer to have pd calculations done #3830

Changes

• Consolidated decomposition frequency validation logic to Decomposer class Decomposer valid frequency logic #3811
• Removed Featuretools version upper bound and prevent Woodwork 0.20.0 from being installed Update Featuretools and Woodwork requirements #3813
• Updated min Featuretools version to 0.16.0, min nlp-primitives version to 2.9.0 and min Dask version to 2022.2.0 Bump min version for Featuretools (1.16.0), nlp-primitives (2.9.0) and Dask(2022.2.0) #3823
• Rename issue templates config.yaml to config.yml Rename issue templates config.yaml to config.yml #3844

Documentation Changes

• Added information about STL Decomposition to the time series docs Add STL to Time Series Documentation #3835

[codecov]

Codecov Report

Merging #3860 (00dc672) into main (3a1b0fc) will not change coverage.
The diff coverage is n/a.

@@          Coverage Diff          @@
##            main   #3860   +/-   ##
=====================================
  Coverage   99.7%   99.7%           
=====================================
  Files        344     344           
  Lines      36185   36185           
=====================================
  Hits       36048   36048           
  Misses       137     137           

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

[eccabay]

In merging this PR I introduced a bug when calling predict_in_sample for time series when featurizers are excluded, blocking until I can get either a fix or reversion in.

fixed