MarkovBlanketSelector<T>
Models & Types · AiDotNet.Preprocessing.FeatureSelection.Causal
Markov Blanket Feature Selection for finding causal features.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → MarkovBlanketSelector<T>
Implements: ISupervisedFeatureSelector<T>
For Beginners
Imagine the target variable has a “blanket” of features around it that shields it from all other features. If you know the blanket features, knowing any other feature doesn’t help predict the target. This method finds that protective blanket of features.
How It Works
Identifies the Markov blanket of the target variable - the minimal set of features that makes the target conditionally independent of all other features. These features are the most relevant for prediction.
Constructors
| Constructor | Summary |
|---|---|
MarkovBlanketSelector(int maxFeatures, double threshold, int nBins, int[] columnIndices) |
Properties
| Property | Summary |
|---|---|
Vector<T> RelevanceScores { get; } |
|
bool SupportsInverseTransform { get; } |
|
int MaxFeatures { get; } |
|
int[] SelectedIndices { get; } |
Methods
| Method | Summary |
|---|---|
Matrix<T> FitTransform(Matrix<T> data, Vector<T> target) |
|
bool[] GetSupportMask() |
|
string[] GetFeatureNamesOut(string[] inputFeatureNames) |
|
void Fit(Matrix<T> data, Vector<T> target) |