Skip to content

Conversation

@rhiever
Copy link

@rhiever rhiever commented Feb 25, 2016

See #92 for details.

Previously, the TPOT predict and score methods needed the training data
to be passed to them again to provide the predictions and scores. Now,
TPOT stores an internal pointer to the training data such that this is
no longer required.
optimized_pipeline, training_features, and training_classes don’t need
to be directly accessed by the user. I have made them private variables
in the TPOT class.
The user should not need to access the TPOT classifier methods
directly. I have made them private.
The user should not have to access pset and toolbox directly. I have
made them private variables.
Updated the docs to reflect the changes to tpot.predict() and
tpot.score().
Since the model functions were changed to private functions, the unit
tests need to be updated to refer to the private functions properly.
rhiever pushed a commit that referenced this pull request Feb 25, 2016
@rhiever rhiever merged commit 32267a3 into master Feb 25, 2016
@rhiever rhiever deleted the predict-rework branch February 25, 2016 22:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants