Immuneml

What's Changed
* Windows-specific bug fixes
* Kmer abundance encoder
* Bug fixes: CompAIRRSequenceAbundance encoder memory, other minor fixes

**Full Changelog**: https://github.com/uio-bmi/immuneML/compare/v2.1.2...v2.2.0

What's Changed

* added support for sequence dataset in word2vec encoder
* updated reference encoders with different summarizing strategies
* minor bug fixes

**Full Changelog**: https://github.com/uio-bmi/immuneML/compare/v2.1.1...v2.1.2

Minor updates:

- add keep_fraction option to FeatureComparison report
- fix optimization metric in sklearn
- copy reports to HTML output for ExploratoryAnalysis instruction
- fix encodings based on nucleotide sequences
- make the standard dataset name in Galaxy Tools "dataset"
- try to fix dependency issues (minor updates added to FAQ)

Major change: integrate immuneML with CompAIRR (https://github.com/uio-bmi/compairr):

- add CompAIRRSequenceAbundance and CompAIRRDistance encoder,
- update docker to include CompAIRR,
- minor bug fixes.

Minor updates:

- moved Metric.py from the `environment` package to the `ml_metrics` package
- updated YAML `load(..)` calls without specified Loader to `safe_load(..)` instead
- bugfix: removed caching from scikit-learn models
- updated cache location for multiple processes

Minor bug fixes and usability improvements:

- added checks for encoder-ML compatibility when parsing
- added Moristia-Horn distance metric and improved HTML output for DistanceEncoder
- added LabelHelper for parsing labels
- added label checks before starting ComparisonData matrix computation
- removed sequence_weight requirement from FullSequenceImplanting YAML (it was not used)
- improved docs