Spacekit v0.3.1

• Bug fix relating to the SVM predict.py Classification Report which mistakenly assumed all categorical types are represented in the data (not necessarily the case for prediction inputs). Fixing the encoder resolves the issue (see below)

• A custom encoder class PairEncoder was created, allowing a user to pass in explicit key-pair values (a dictionary) for categorical features and SvmEncoder was updated to use this for encoding “category" (scene/field), "detector" and "wcs".

• Additional tests added to test_encode.py for the above case

• Minor enhancements to SVM classification report for better readability.

What's Changed

• Testing/0.3.0rc2 by @alphasentaurii in https://github.com/alphasentaurii/spacekit/pull/17
• fix/svm-pred-encoding by @alphasentaurii in https://github.com/alphasentaurii/spacekit/pull/20

Full Changelog: alphasentaurii/spacekit@0.3.0...0.3.1