Common trainable processing object.
A Learner is a Node that can (maybe has to) be trained on a dataset, before it can perform its function.
Notes
Available conditional attributes:
(Conditional attributes enabled by default suffixed with +)
Parameters : | auto_train : bool
force_train : bool
enable_ca : None or list of str
disable_ca : None or list of str
space: str, optional :
postproc : Node instance, optional
descr : str
|
---|
Whether the Learner performs automatic trainingwhen called untrained.
Whether the Learner enforces training upon everycalled.
Whether the Learner is currently trained.
The default implementation calls _pretrain(), _train(), and finally _posttrain().
Parameters : | ds: Dataset :
|
---|---|
Returns : | None : |
Reverts changes in the state of this node caused by previous training