Source

orangecontrib-earth / docs / source / orangekit.earth.widgets.earth.rst

Earth Learner

Channels

Inputs:
  • Data (Table)
Outputs:
  • Learner

    The Earth learning algorithm with parameters as specified in the dialog.

  • Predictor

    Trained regressor

  • Basis Matrix (Table)

    A data table of induced basis terms.

Signal Predictor sends the regressor only if signal Data is present.

Description

This widget constructs a Earth learning algorithm (an implementation of the MARS - Multivariate Adaptive Regression Splines). As all widgets for classification and regression, this widget provides a learner and classifier/regressor on the output. Learner is a learning algorithm with settings as specified by the user. It can be fed into widgets for testing learners, for instance Test Learners.

images/Earth.png

After changing one or more settings, you need to push 5 Apply, which will put the new learner on the output and, if the training examples are given, construct a new predictor and output it as well.

Examples

Lets use the learner to train a model on a data subset and test it on unseen instances.

images/Earth-Schema.png