EasyEnsembleClassifier<T>
Models & Types · AiDotNet.Classification.ImbalancedEnsemble
Easy Ensemble Classifier for extremely imbalanced datasets.
Inheritance: ClassifierBase<T> → EasyEnsembleClassifier<T>
For Beginners
Easy Ensemble is designed for highly imbalanced data. It creates multiple balanced subsets by undersampling the majority class, trains a base classifier (typically AdaBoost) on each subset, and combines their predictions.
How It Works
How it works:
- Keep all minority class samples
- For each subset: randomly undersample majority to match minority
- Train an AdaBoost classifier on each balanced subset
- Combine predictions using majority voting or averaging
Key advantages:
- Handles extreme imbalance: Works well even with 100:1 or 1000:1 ratios
- Uses all majority data: Through multiple subsets, all majority samples contribute
- Reduces variance: Ensemble approach gives stable predictions
When to use:
- Extremely imbalanced datasets (more than 10:1 ratio)
- When you need high recall for the minority class
- When losing some majority class accuracy is acceptable
References:
- Liu, X.Y., Wu, J., & Zhou, Z.H. (2009). “Exploratory Undersampling for Class-Imbalance Learning”
Example
var features = new Matrix<double>(new double[,] { { 1.0, 2.0 }, { 3.0, 4.0 }, { 5.0, 6.0 }, { 7.0, 8.0 } });
var labels = new Vector<double>(new double[] { 0.0, 1.0, 0.0, 1.0 });
var newSample = new Matrix<double>(new double[,] { { 1.0, 2.0 }, { 3.0, 4.0 }, { 5.0, 6.0 }, { 7.0, 8.0 } });
// Use AiModelBuilder facade for easy ensemble classification
var builder = new AiModelBuilder<double, Matrix<double>, Vector<double>>()
.ConfigureModel(new EasyEnsembleClassifier<double>());
var result = builder.Build(features, labels);
var prediction = result.Predict(newSample);
Constructors
| Constructor | Summary |
|---|---|
EasyEnsembleClassifier(int nSubsets, int nEstimatorsPerSubset, int maxDepth, double learningRate, string samplingStrategy, bool softVoting, int? seed) |
Initializes a new instance of EasyEnsembleClassifier. |
Methods
| Method | Summary |
|---|---|
Dictionary<string, T> GetFeatureImportance() |
Gets feature importance based on weak learner usage. |
IFullModel<T, Matrix<T>, Vector<T>> WithParameters(Vector<T> parameters) |
Creates a new instance with the specified parameters. |
Vector<T> Predict(Matrix<T> input) |
Predicts class labels using the ensemble. |
void Train(Matrix<T> x, Vector<T> y) |
Gets the model type. |