ExpressionTree<T, TInput, TOutput>

Models & Types · AiDotNet.LinearAlgebra

Represents a symbolic expression tree for mathematical operations that can be used for symbolic regression.

Inheritance: ModelBase<T, TInput, TOutput> → ExpressionTree<T, TInput, TOutput>

How It Works

For Beginners: An ExpressionTree is like a mathematical formula represented as a tree structure. Each node in the tree is either a number, a variable, or an operation (like addition or multiplication). This allows the AI to create and evolve mathematical formulas that can model your data.

Example

// A symbolic expression tree for (x0 * 2.5) + x1. Every node is the same constructor: a node type,
// a value for leaves, and two children for operations.
var x0 = new ExpressionTree<double, Matrix<double>, Vector<double>>(
    ExpressionNodeType.Variable, 0);
var scale = new ExpressionTree<double, Matrix<double>, Vector<double>>(
    ExpressionNodeType.Constant, 2.5);
var x1 = new ExpressionTree<double, Matrix<double>, Vector<double>>(
    ExpressionNodeType.Variable, 1);
            
var product = new ExpressionTree<double, Matrix<double>, Vector<double>>(
    ExpressionNodeType.Multiply, left: x0, right: scale);
var tree = new ExpressionTree<double, Matrix<double>, Vector<double>>(
    ExpressionNodeType.Add, left: product, right: x1);
            
double value = tree.Evaluate(new Vector<double>(new double[] { 3.0, 1.0 })); // (3.0 * 2.5) + 1.0

Constructors

Constructor Summary
ExpressionTree(ExpressionNodeType type, T value, ExpressionTree<T, TInput, TOutput> left, ExpressionTree<T, TInput, TOutput> right, ILossFunction<T> lossFunction) Creates a new expression tree node with the specified properties.

Properties

Property Summary
ExpressionNodeType Type { get; set; } Gets the type of this node (constant, variable, or operation).
ExpressionTree<T, TInput, TOutput> Left { get; set; } Gets the left child node of this node.
ExpressionTree<T, TInput, TOutput> Parent { get; set; } Gets the parent node of this node.
ExpressionTree<T, TInput, TOutput> Right { get; set; } Gets the right child node of this node.
ILossFunction<T> DefaultLossFunction { get; } Gets the default loss function used by this model for gradient computation.
T Value { get; set; } Gets the value stored in this node.
Vector<T> Coefficients { get; } Gets a vector containing all coefficient values in this expression tree.
int Complexity { get; } Gets the complexity of this expression tree, measured as the total number of nodes.
int FeatureCount { get; } Gets the number of features (variables) used in this expression tree.
int Id { get; } Gets the unique identifier for this node.
int RequiredFeatureCount { get; } Gets the minimum number of features required for input data to this expression tree.

Methods

Method Summary
Dictionary<string, T> GetFeatureImportance() Gets the feature importance scores for this expression tree.
ExpressionTree<T, TInput, TOutput> Deserialize(BinaryReader reader) Deserializes an expression tree from a binary reader.
ExpressionTree<T, TInput, TOutput> FindNodeById(int id) Finds a node in the tree by its unique identifier.
IEnumerable<int> GetActiveFeatureIndices() Gets the indices of all features (variables) used in this expression tree.
IFullModel<T, TInput, TOutput> Copy() Creates a deep copy of this expression tree.
IFullModel<T, TInput, TOutput> Crossover(IFullModel<T, TInput, TOutput> other, double crossoverRate) Combines this expression tree with another to create a new “offspring” expression tree.
IFullModel<T, TInput, TOutput> Mutate(double mutationRate) Creates a modified version of this expression tree by applying random mutations.
IFullModel<T, TInput, TOutput> UpdateCoefficients(Vector<T> newCoefficients) Creates a new expression tree with updated coefficient values.
IFullModel<T, TInput, TOutput> WithParameters(Vector<T> parameters) Creates a new expression tree with updated parameters.
List<ExpressionTree<T, TInput, TOutput>> GetAllNodes() Gets a list of all nodes in this expression tree.
ModelMetadata<T> GetModelMetadata() Gets metadata about this expression tree model.
T Evaluate(Vector<T> input) Evaluates this expression tree for a given input vector.
TOutput Predict(TInput input) Makes a prediction for an input example.
Vector<T> ComputeGradients(TInput input, TOutput target, ILossFunction<T> lossFunction) Computes gradients of the loss function with respect to model parameters WITHOUT updating parameters.
Vector<T> Predict(Matrix<T> input) Makes a prediction for an input example.
bool IsFeatureUsed(int featureIndex) Checks if a specific feature (variable) is used in this expression tree.
string ToString() Returns a string representation of this expression tree.
void ApplyGradients(Vector<T> gradients, T learningRate) Applies pre-computed gradients to update the model parameters (constants in the expression tree).
void Fit(Matrix<T> X, Vector<T> y) Fits the expression tree to the provided training data.
void LoadModel(string filePath) Loads an expression tree model from a file.
void LoadState(Stream stream) Loads the expression tree’s state (structure and values) from a stream.
void SaveModel(string filePath) Saves the expression tree model to a file.
void SaveState(Stream stream) Saves the expression tree’s current state (structure and values) to a stream.
void Serialize(BinaryWriter writer) Writes this expression tree to a binary stream.
void SetActiveFeatureIndices(IEnumerable<int> featureIndices) Sets the active feature indices for this expression tree.
void SetLeft(ExpressionTree<T, TInput, TOutput> left) Sets the left child of this node and updates the parent reference of the child.
void SetRight(ExpressionTree<T, TInput, TOutput> right) Sets the right child of this node and updates the parent reference of the child.
void SetType(ExpressionNodeType type) Sets the type of this node.
void SetValue(T value) Sets the value of this node.
void Train(Matrix<T> x, Vector<T> y) Trains the expression tree on a single input-output pair.
void Train(TInput input, TOutput expectedOutput) Trains the expression tree on a single input-output pair.