Class PowerTransformer<T>

Namespace

AiDotNet.Preprocessing.PowerTransforms

Assembly

AiDotNet.dll

Applies power transformations (Box-Cox or Yeo-Johnson) to make data more Gaussian-like.

public class PowerTransformer<T> : TransformerBase<T, Matrix<T>, Matrix<T>>, IDataTransformer<T, Matrix<T>, Matrix<T>>

Type Parameters

T

The numeric type for calculations (e.g., float, double).

Inheritance

object

TransformerBase<T, Matrix<T>, Matrix<T>>

PowerTransformer<T>

Implements

IDataTransformer<T, Matrix<T>, Matrix<T>>

Inherited Members

TransformerBase<T, Matrix<T>, Matrix<T>>.NumOps

TransformerBase<T, Matrix<T>, Matrix<T>>.Engine

TransformerBase<T, Matrix<T>, Matrix<T>>.IsFitted

TransformerBase<T, Matrix<T>, Matrix<T>>.ColumnIndices

TransformerBase<T, Matrix<T>, Matrix<T>>.SupportsInverseTransform

TransformerBase<T, Matrix<T>, Matrix<T>>.Fit(Matrix<T>)

TransformerBase<T, Matrix<T>, Matrix<T>>.Transform(Matrix<T>)

TransformerBase<T, Matrix<T>, Matrix<T>>.FitTransform(Matrix<T>)

TransformerBase<T, Matrix<T>, Matrix<T>>.InverseTransform(Matrix<T>)

TransformerBase<T, Matrix<T>, Matrix<T>>.GetFeatureNamesOut(string[])

TransformerBase<T, Matrix<T>, Matrix<T>>.FitCore(Matrix<T>)

TransformerBase<T, Matrix<T>, Matrix<T>>.TransformCore(Matrix<T>)

TransformerBase<T, Matrix<T>, Matrix<T>>.InverseTransformCore(Matrix<T>)

TransformerBase<T, Matrix<T>, Matrix<T>>.ValidateInputData(Matrix<T>)

TransformerBase<T, Matrix<T>, Matrix<T>>.EnsureFitted()

TransformerBase<T, Matrix<T>, Matrix<T>>.GetColumnsToProcess(int)

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

PowerTransformer applies a power transformation to each feature to make it more Gaussian-like. Box-Cox requires strictly positive data, while Yeo-Johnson works with any values. The transformation can help stabilize variance and improve the fit of models that assume normality.

For Beginners: This transformer makes your data more "bell-curve shaped": - Box-Cox: For strictly positive data (prices, counts) - Yeo-Johnson: Works with any data including negatives and zeros

After transformation, features will have more normal (Gaussian) distributions, which helps many machine learning algorithms perform better.

Constructors

PowerTransformer(PowerTransformMethod, bool, int[]?)

Creates a new instance of PowerTransformer<T>.

public PowerTransformer(PowerTransformMethod method = PowerTransformMethod.YeoJohnson, bool standardize = true, int[]? columnIndices = null)

Parameters

method PowerTransformMethod

The transformation method. Defaults to YeoJohnson.

standardize bool

Whether to standardize after transformation. Defaults to true.

columnIndices int[]

The column indices to transform, or null for all columns.

Properties

Lambdas

Gets the optimal lambda parameters for each feature.

public Vector<T>? Lambdas { get; }

Property Value

Vector<T>

Method

Gets the power transformation method used.

public PowerTransformMethod Method { get; }

Property Value

PowerTransformMethod

Standardize

Gets whether standardization is applied after transformation.

public bool Standardize { get; }

Property Value

bool

SupportsInverseTransform

Gets whether this transformer supports inverse transformation.

public override bool SupportsInverseTransform { get; }

Property Value

bool

Methods

FitCore(Matrix<T>)

Learns the optimal lambda parameters for each feature.

protected override void FitCore(Matrix<T> data)

Parameters

data Matrix<T>

The training data matrix where each column is a feature.

GetFeatureNamesOut(string[]?)

Gets the output feature names after transformation.

public override string[] GetFeatureNamesOut(string[]? inputFeatureNames = null)

Parameters

inputFeatureNames string[]

The input feature names.

Returns

string[]

The same feature names (PowerTransformer doesn't change number of features).

InverseTransformCore(Matrix<T>)

Reverses the power transformation.

protected override Matrix<T> InverseTransformCore(Matrix<T> data)

Parameters

data Matrix<T>

The transformed data.

Returns

Matrix<T>

The original-scale data.

TransformCore(Matrix<T>)

Transforms the data by applying the power transformation.

protected override Matrix<T> TransformCore(Matrix<T> data)

Parameters

data Matrix<T>

The data to transform.

Returns

Matrix<T>

The transformed data.