CMIMSelector<T>
Models & Types · AiDotNet.Preprocessing.FeatureSelection.Multivariate
Conditional Mutual Information Maximization (CMIM) Feature Selection.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → CMIMSelector<T>
Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>
For Beginners
CMIM asks “what new information does this feature give me that I don’t already have?” It selects features that add something new, conditioned on what you’ve already picked. This avoids redundant features more rigorously than simple redundancy penalties.
How It Works
Selects features by maximizing mutual information with the target conditioned on already selected features, ensuring each new feature adds unique information.
Constructors
| Constructor | Summary |
|---|---|
CMIMSelector(int nFeaturesToSelect, int nBins, int[] columnIndices) |
Properties
| Property | Summary |
|---|---|
Vector<T> CMIMScores { get; } |
|
bool SupportsInverseTransform { get; } |
|
int NBins { get; } |
|
int NFeaturesToSelect { 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) |