pulsatrix 1.1.0
Loading...
Searching...
No Matches
pulsatrix::SurrogateTreeOptions Struct Reference

How the tree is grown. More...

#include <surrogate_tree.hpp>

Public Attributes

SurrogateTask task = SurrogateTask::Classification
 
int64_t target = 0
 Regression: the output (flat index) imitated.
 
int max_depth = 3
 The deepest a leaf may be; the root is depth 0. Three or four levels stay readable.
 
int64_t min_samples_leaf = 1
 The fewest inputs a leaf may hold.
 
double test_fraction = 0.3
 FitSurrogateTree: the share of the inputs held out to measure fidelity, in [0, 1).
 
uint64_t seed = 0
 FitSurrogateTree: seeds the held-out split.
 

Detailed Description

How the tree is grown.

Member Data Documentation

◆ max_depth

int pulsatrix::SurrogateTreeOptions::max_depth = 3

The deepest a leaf may be; the root is depth 0. Three or four levels stay readable.

◆ min_samples_leaf

int64_t pulsatrix::SurrogateTreeOptions::min_samples_leaf = 1

The fewest inputs a leaf may hold.

◆ seed

uint64_t pulsatrix::SurrogateTreeOptions::seed = 0

FitSurrogateTree: seeds the held-out split.

◆ target

int64_t pulsatrix::SurrogateTreeOptions::target = 0

Regression: the output (flat index) imitated.

◆ task

SurrogateTask pulsatrix::SurrogateTreeOptions::task = SurrogateTask::Classification

◆ test_fraction

double pulsatrix::SurrogateTreeOptions::test_fraction = 0.3

FitSurrogateTree: the share of the inputs held out to measure fidelity, in [0, 1).


The documentation for this struct was generated from the following file: