Regression
Hoeffding Tree Regressor

HoeffdingTreeRegressor

The Hoeffding Tree Regressor (HTR) is an adaptation of the incremental tree algorithm of the same name for classification. Similarly to its classification counterpart, HTR uses the Hoeffding bound to control its split decisions. Differently from the classification algorithm, HTR relies on calculating the reduction of variance in the target space to decide among the split candidates. The smallest the variance at its leaf nodes, the more homogeneous the partitions are. At its leaf nodes, HTR fits either linear models or uses the target average as the predictor.

Parameters

  • grace_period(int, Default:200) → Number of instances a leaf should observe between split attempts.

  • delta(float, Default:1e-07) → Significance level to calculate the Hoeffding bound. The significance level is given by 1 - delta. Values closer to zero imply longer split decision delays.

  • tau(float,Default:0.05) → Threshold below which a split will be forced to break ties.

  • leaf_prediction(str,Default:mean) → Prediction mechanism used at leafs. For now, only Target mean (mean) is supported.

Example Usage

We can create an instance of the Hoeffding Tree Regressor model like this.

import turboml as tb
htc_model = tb.HoeffdingTreeRegressor()
FFM RegressorSGT Regressor