Package | Description |
---|---|
org.apache.ignite.ml.tree |
Root package for decision trees.
|
org.apache.ignite.ml.tree.impurity |
Root package for decision tree impurity measures and calculators.
|
org.apache.ignite.ml.tree.impurity.gini |
Contains Gini impurity measure and calculator.
|
org.apache.ignite.ml.tree.impurity.mse |
Contains mean squared error impurity measure and calculator.
|
org.apache.ignite.ml.tree.impurity.util |
Contains util classes used in decision tree impurity calculators.
|
Modifier and Type | Class and Description |
---|---|
class |
DecisionTree<T extends ImpurityMeasure<T>>
Distributed decision tree trainer that allows to fit trees using row-partitioned dataset.
|
Modifier and Type | Interface and Description |
---|---|
interface |
ImpurityMeasure<T extends ImpurityMeasure<T>>
Base interface for impurity measures that can be used in distributed decision tree algorithm.
|
class |
ImpurityMeasureCalculator<T extends ImpurityMeasure<T>>
Base interface for impurity measure calculators that calculates all impurity measures required to find a best split.
|
Modifier and Type | Class and Description |
---|---|
class |
GiniImpurityMeasure
Gini impurity measure which is calculated the following way:
\-frac{1}{L}\sum_{i=1}^{s}l_i^2 - \frac{1}{R}\sum_{i=s+1}^{n}r_i^2 . |
Modifier and Type | Class and Description |
---|---|
class |
MSEImpurityMeasure
Mean squared error (variance) impurity measure which is calculated the following way:
\frac{1}{L}\sum_{i=0}^{n}(y_i - \mu)^2 . |
Modifier and Type | Class and Description |
---|---|
class |
SimpleStepFunctionCompressor<T extends ImpurityMeasure<T>>
Simple step function compressor.
|
class |
StepFunction<T extends ImpurityMeasure<T>>
Step function described by
x and y points. |
interface |
StepFunctionCompressor<T extends ImpurityMeasure<T>>
Base interface for step function compressors which reduces step function size.
|
Modifier and Type | Method and Description |
---|---|
T[] |
StepFunction.getY() |
Constructor and Description |
---|
StepFunction(double[] x,
T[] y)
Constructs a new instance of step function.
|
GridGain In-Memory Computing Platform : ver. 8.9.15 Release Date : December 3 2024