What’s New
* We now have a formulation descriptor and two formulations-related predictors (https://github.com/CitrineInformatics/citrine-python/pull/324)
* LabelFractionsPredictor will compute total fraction of all inputs with a particular label (https://github.com/CitrineInformatics/citrine-python/pull/332)
* SimpleMixturePredictor will provide features based upon fraction-weighted averaging of mixture components (https://github.com/CitrineInformatics/citrine-python/pull/333)
* Data Sources now have the concept of an identifier, or a column that contains values that reference another row of the table
* Supporting Molecular Structure value types, we now support Ara Columns for SMILES or InChI representations of those structures
* Retrieving the responses of a predictors from the Citrine platform (https://github.com/CitrineInformatics/citrine-python/pull/331)
Improvements
* More documentation. Specifically, we've added descriptions of how to build data sources and predictors for mixtures
* And, of course, it all get unit tests.