hex.tree

Class FriedmanPopescusH

java.lang.Object

hex.tree.FriedmanPopescusH

public class FriedmanPopescusH
extends java.lang.Object

Calculates Friedman and Popescu's H statistics, in order to test for the presence of an interaction between specified variables in h2o gbm and xgb models. H varies from 0 to 1. It will have a value of 0 if the model exhibits no interaction between specified variables and a correspondingly larger value for a stronger interaction effect between them. NaN is returned if a computation is spoiled by weak main effects and rounding errors. See Jerome H. Friedman and Bogdan E. Popescu, 2008, "Predictive learning via rule ensembles", *Ann. Appl. Stat.* **2**:916-954, http://projecteuclid.org/download/pdfview_1/euclid.aoas/1223908046, s. 8.1. Reference implementation: https://pypi.org/project/sklearn-gbmi/

Constructor Summary

Constructors

Constructor and Description
FriedmanPopescusH()

Method Summary

Modifier and Type	Method and Description
static double[]	add(double[] first, double[] second)
static double	h(water.fvec.Frame frame, java.lang.String[] vars, double learnRate, hex.genmodel.algos.tree.SharedTreeSubgraph[][] sharedTreeSubgraphs)
static water.fvec.Vec	partialDependenceTree(hex.genmodel.algos.tree.SharedTreeSubgraph tree, java.lang.Integer[] targetFeature, double learnRate, water.fvec.Frame grid) For each row in ``X`` a tree traversal is performed.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

FriedmanPopescusH

public FriedmanPopescusH()

Method Detail

h

public static double h(water.fvec.Frame frame,
                       java.lang.String[] vars,
                       double learnRate,
                       hex.genmodel.algos.tree.SharedTreeSubgraph[][] sharedTreeSubgraphs)

add

public static double[] add(double[] first,
                           double[] second)

partialDependenceTree

public static water.fvec.Vec partialDependenceTree(hex.genmodel.algos.tree.SharedTreeSubgraph tree,
                                                   java.lang.Integer[] targetFeature,
                                                   double learnRate,
                                                   water.fvec.Frame grid)

For each row in ``X`` a tree traversal is performed. Each traversal starts from the root with weight 1.0. At each non-terminal node that splits on a target variable either the left child or the right child is visited based on the feature value of the current sample and the weight is not modified. At each non-terminal node that splits on a complementary feature both children are visited and the weight is multiplied by the fraction of training samples which went to each child. At each terminal node the value of the node is multiplied by the current weight (weights sum to 1 for all visited terminal nodes).

Parameters:

tree - tree to traverse

targetFeature - the set of target features for which the partial dependence should be evaluated

learnRate - constant scaling factor for the leaf predictions

grid - the grid points on which the partial dependence should be evaluated

Returns:

Vec with the resulting partial dependence values for each point of the input grid