ConfusionMatrix<T>

Models & Types · AiDotNet.LinearAlgebra

Represents a confusion matrix for evaluating the performance of a classification model.

Inheritance: MatrixBase<T> → ConfusionMatrix<T>

For Beginners

A confusion matrix helps you understand how well your AI model is performing when classifying data into categories.

How It Works

A confusion matrix is a table that summarizes the prediction results of a classification model. It supports both binary classification (2x2 matrix) and multi-class classification (NxN matrix).

Binary Classification: For 2-class problems, it shows four important numbers:

  • True PositivesWhen your model correctly predicted “Yes” (e.g., correctly identified a cat as a cat)
  • True NegativesWhen your model correctly predicted “No” (e.g., correctly identified a non-cat as not a cat)
  • False PositivesWhen your model incorrectly predicted “Yes” (e.g., identified a dog as a cat) - also called a “Type I error”
  • False NegativesWhen your model incorrectly predicted “No” (e.g., identified a cat as not a cat) - also called a “Type II error”

Multi-Class Classification: For 3+ class problems, the matrix is NxN where N is the number of classes. Rows represent predicted classes, columns represent actual classes. Cell [i,j] contains the count of samples predicted as class i but actually belonging to class j.

Constructors

Constructor Summary
ConfusionMatrix(T truePositives, T trueNegatives, T falsePositives, T falseNegatives) Initializes a new instance of the ConfusionMatrix class with the specified values.
ConfusionMatrix(int dimension) Initializes a new instance of the ConfusionMatrix class with the specified dimension.

Properties

Property Summary
T Accuracy { get; } Gets the accuracy of the classification model.
T F1Score { get; } Gets the F1 score of the classification model.
T FalseNegatives { get; } Gets the number of false negative predictions (incorrectly predicted negative cases).
T FalsePositives { get; } Gets the number of false positive predictions (incorrectly predicted positive cases).
T Precision { get; } Gets the precision of the classification model.
T Recall { get; } Gets the recall (sensitivity) of the classification model.
T Specificity { get; } Gets the specificity of the classification model.
T TrueNegatives { get; } Gets the number of true negative predictions (correctly predicted negative cases).
T TruePositives { get; } Gets the number of true positive predictions (correctly predicted positive cases).
int ClassCount { get; } Gets the number of classes represented in the confusion matrix.

Methods

Method Summary
T GetAccuracy() Gets the overall accuracy across all classes.
T GetCohenKappa() Gets the Cohen’s Kappa coefficient, measuring inter-rater agreement.
T GetF1Score(int classIndex) Gets the F1 score for a specific class.
T GetFalseNegatives(int classIndex) Gets the false negatives for a specific class.
T GetFalsePositives(int classIndex) Gets the false positives for a specific class.
T GetHammingLoss() Gets the Hamming Loss, measuring the fraction of incorrect predictions.
T GetJaccardScore() Gets the Jaccard Score (Jaccard Index) for classification.
T GetJaccardScore(int classIndex) Gets the Jaccard Score for a specific class.
T GetMacroF1Score() Gets the macro-averaged F1 score across all classes.
T GetMacroPrecision() Gets the macro-averaged precision across all classes.
T GetMacroRecall() Gets the macro-averaged recall across all classes.
T GetMatthewsCorrelationCoefficient() Gets the Matthews Correlation Coefficient (MCC) for classification.
T GetMicroF1Score() Gets the micro-averaged F1 score across all classes.
T GetMicroPrecision() Gets the micro-averaged precision across all classes.
T GetMicroRecall() Gets the micro-averaged recall across all classes.
T GetPrecision(int classIndex) Gets the precision for a specific class.
T GetRecall(int classIndex) Gets the recall for a specific class.
T GetTrueNegatives(int classIndex) Gets the true negatives for a specific class.
T GetTruePositives(int classIndex) Gets the true positives for a specific class.
T GetWeightedF1Score() Gets the weighted-averaged F1 score across all classes.
T GetWeightedPrecision() Gets the weighted-averaged precision across all classes.
T GetWeightedRecall() Gets the weighted-averaged recall across all classes.
void Increment(int predictedClass, int actualClass) Increments the count for a specific prediction-actual class pair.