Triage

New Functionality
- Adds python 3.10 support (NOTE: **loses** python 3.7 support) (via 893)
- Support (and prefer) specifying a SQL file path for cohort and label queries (883)
- Adds information about cohort, label, and bias hashes to the `triage_runs` table (888)
- Allow specifying a cohort to be option, defaulting to the label query (877)

Bug Fixes
- Fixes issue with installing on macos with python 3.9 (via 893)
- Removes (buggy) support for groupings other than `entity_id` in feature generation (887)

Refactoring/Documentation
- Various dependency updates (893)
- Error on cohort or label duplicates (889)
- Various updates to documentation

New Functionality
- Adds support for postgres 12 and 13 (882)

Refactoring/Documentation
- Fixes typos in documentation

NOTE: This release adds python 3.9 support, but unfortunately eliminates python 3.6 support.

New Functionality
- Adds python 3.9 support (865)
- Adds `BaselineRankMultiFeature` baseline model to allow for ranking by more than one feature (871)

Bug Fixes
- Ensure attributes passed to `aequitas` are strings to avoid issues with crosstab calculation (876)

Refactoring/Usability
- Renames the `descend` parameter to `low_value_high_score` to improve clarity (871; see also 869)
- Use a `threading` backend for sklearn parallelization nested within triage multiprocessing to suppress a warning about nested parallelization (866)

WARNING: BREAKING CHANGES!
Note that several changes in triage 5 break backwards compatibility with triage 4. If you are upgrading a project from an earlier version of triage, it is **highly recommended that you first create a backup of your current database!**

These breaking changes include:
- Revision in the way the `model_hash` is calculated means that if you're re-running an experiment from an earlier version of triage, it will re-train your models and give them new `model_id`s even if the configuration hasn't changed.
- The `built_by_experiment` column has been removed from `triage_metadata.models` in preference of tracking the specific run that built the model. The `experiment_hash` can still be obtained by joining to `triage_metadata.triage_runs` (née `triage_metadata.experiment_runs`). Should you need the data that was in this column at the time of migration, it can be found in `triage_metadata.deprecated_models_built_by_experiment`, but it will not be restored to the table upon database downgrade.
- Changes in the structure of matrix metadata means the `matrix_hash` will no longer be backwards-compatible with oder version of triage (as with models, re-running an old config would result in matrices being re-created)
- The `random_seed` column has been removed from `triage_metadata.experiments` in preference of tracking it at the run level as well. A database upgrade followed by a downgrade would lose this data (but could be recovered from the runs table)

New Functionality
- Functionality for predicting forward, either with an existing model object or by retraining a new model with the most current data given a `model_group_id` (631)
- Utility for adding predictions to models previously trained/tested with `save_predictions=False` (836)
- Provisioner for easily setting up a postgresql database (via docker) that can be used with triage (840)
- More flexibility in parallelization for more resource-intensive model types, like random forests (853)

Bug Fixes
- Ensure model-level random seeds are re-used when the config and experiment-level random seed are unchanged (848)
- Remove the project path from the `model_hash` definition: the `model_id` shouldn't depend on where `triage` is being run (830)
- Ensure that feature groups are sorted in matrix metadata for consistency in downstream calculations (833)

Thanks To
tweddielin, thcrock, ecsalomon, KasunAmare

Primarily a bugfix release for anyone working on triage 4. New functionality will be introduced with the 5.0 release.

Bug Fixes
- Fix functionality of bias analysis using `aequitas` during experiment runs. Previously the attributes for bias analysis were getting scrambled relative to the scores and labels when the latter get sorted for "best case" and "worst case" analyses, invalidating any results produced by these analyses. This release fixes this bug, ensure the same set of entities is provided for attributes and labels/scores, and adds a unit test to cover this issue. (858)
- Close database sessions during unit tests to avoid intermittent exceptions during test cleanup. (851)