C++ API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1

List of all members
Parameter Class Reference

Parameters for the decision forest algorithm. More...

Class Declaration

class DAAL_EXPORT Parameter
{
public:
Parameter() : nTrees(100),
seed(77),
bootstrap(true),
engine(engines::mt2203::Batch<>::create()) {}
size_t nTrees;
size_t featuresPerNode;
size_t maxTreeDepth;
size_t seed;
engines::EnginePtr engine;
DAAL_UINT64 resultsToCompute;
bool bootstrap;
};

Member Data Documentation

bool bootstrap

If true then training set for a tree is a bootstrap of the whole training set

engines::EnginePtr engine

Engine for the random numbers generator used by the algorithms

size_t featuresPerNode

Number of features tried as possible splits per node. If 0 then sqrt(p) for classification, p/3 for regression, where p is the total number of features.

double impurityThreshold

Threshold value used as stopping criteria: if the impurity value in the node is smaller than the threshold then the node is not split anymore.

size_t maxTreeDepth

Maximal tree depth. Default is 0 (unlimited)

bool memorySavingMode

If true then use memory saving (but slower) mode

size_t minObservationsInLeafNode

Minimal number of observations in a leaf node. Default is 1 for classification, 5 for regression.

size_t nTrees

Number of trees in the forest. Default is 10

double observationsPerTreeFraction

Fraction of observations used for a training of one tree, 0 to 1. Default is 1 (sampling with replacement)

DAAL_UINT64 resultsToCompute

64 bit integer flag that indicates the results to compute

size_t seed

Seed for the random numbers generator used by the algorithms

Deprecated:
This item will be removed in a future release. Use engine instead.
VariableImportanceMode varImportance

Variable importance computation mode


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

For more complete information about compiler optimizations, see our Optimization Notice.