Jdb/api

[jeremiedb]

Breaking changes:

Model constructors (EvoTreeRegressor, EvoTreeClassifier...) now include the following arguments:

• device
• early_stopping_rounds
• metric

Example:

config = EvoTreeRegressor(; loss=:mse, device=:gpu, L2=100)

Change in naming of variables identity in the Tables / DataFrames based internal API, which were previously kwargs of fit:

• fnames => feature_names
• w_name => weight_names

m = fit_evotree(config, dtrain; target_name="y", feature_names=["x1", "x2"])

Changes related to losses:

• L1 / l1 loss is no longer supported. Use loss=:mae in EvoTreeRegressor instead.

Fixes and improvements to GPU:

• Models trained through MLJ now support the :gpu argument.
• Inference is now properly dispatch to :gpu when using: m(dtrain; device=:gpu)
• Both :mae and :quantile losses are now now suported on GPU (device = :gpu)