Class TransformerBase<T, TInput, TOutput>

Namespace

AiDotNet.Preprocessing

Assembly

AiDotNet.dll

Abstract base class for all data transformers providing common functionality.

public abstract class TransformerBase<T, TInput, TOutput> : IDataTransformer<T, TInput, TOutput>

Type Parameters

T

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

TInput

The input data type.

TOutput

The output data type after transformation.

Inheritance

object

TransformerBase<T, TInput, TOutput>

Implements

IDataTransformer<T, TInput, TOutput>

Derived

ColumnTransformer<T>

DictionaryLearning<T>

DiffusionMaps<T>

FactorAnalysis<T>

FastICA<T>

HessianLLE<T>

IncrementalPCA<T>

Isomap<T>

KernelPCA<T>

LTSA<T>

LaplacianEigenmaps<T>

LargeVis<T>

LatentDirichletAllocation<T>

LocallyLinearEmbedding<T>

MDS<T>

MiniBatchSparsePCA<T>

ModifiedLLE<T>

NCA<T>

NMF<T>

PCA<T>

PHATE<T>

PaCMAP<T>

ProbabilisticPCA<T>

RandomProjection<T>

RandomizedPCA<T>

SparsePCA<T>

SpectralEmbedding<T>

TSNE<T>

TriMAP<T>

TruncatedSVD<T>

UMAP<T>

Binarizer<T>

KBinsDiscretizer<T>

BackwardDifferenceEncoder<T>

BaseNEncoder<T>

BinaryEncoder<T>

CatBoostEncoder<T>

CountEncoder<T>

HashingEncoder<T>

HelmertEncoder<T>

JamesSteinEncoder<T>

LabelEncoder<T>

LeaveOneOutEncoder<T>

MEstimateEncoder<T>

OneHotEncoder<T>

OrdinalEncoder<T>

SumEncoder<T>

TargetEncoder<T>

WOEEncoder<T>

FunctionTransformer<T>

InteractionFeatures<T>

PolynomialFeatures<T>

SplineTransformer<T>

GenericUnivariateSelect<T>

RFECV<T>

RFE<T>

SelectFdr<T>

SelectFpr<T>

SelectFromModel<T>

SelectFwe<T>

SelectKBest<T>

SelectPercentile<T>

SequentialFeatureSelector<T>

VarianceThreshold<T>

FeatureUnion<T>

IterativeImputer<T>

KNNImputer<T>

MissingIndicator<T>

SimpleImputer<T>

IQRClipper<T>

OutlierClipper<T>

Winsorizer<T>

PowerTransformer<T>

QuantileTransformer<T>

DecimalScaler<T>

GlobalContrastScaler<T>

LogMeanVarianceScaler<T>

LogScaler<T>

MaxAbsScaler<T>

MinMaxScaler<T>

Normalizer<T>

RobustScaler<T>

StandardScaler<T>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

This class provides the template method pattern for data transformation. Derived classes implement the core fitting and transformation logic while this base class handles validation, state management, and common operations.

For Beginners: This is the foundation that all transformers build on. It provides common features like: - Checking if the transformer is ready to use - Managing which columns to transform - Serialization for saving/loading transformers

When creating a new transformer, you extend this class and implement the abstract methods.

Constructors

TransformerBase(int[]?)

Creates a new instance of the transformer.

protected TransformerBase(int[]? columnIndices = null)

Parameters

columnIndices int[]

The column indices to operate on, or null for all columns.

Properties

ColumnIndices

Gets the column indices this transformer operates on.

public int[]? ColumnIndices { get; }

Property Value

int[]

Engine

Gets the computational engine for tensor operations.

protected IEngine Engine { get; }

Property Value

IEngine

IsFitted

Gets whether this transformer has been fitted to data.

public bool IsFitted { get; protected set; }

Property Value

bool

NumOps

Gets the numeric operations helper for type T.

protected INumericOperations<T> NumOps { get; }

Property Value

INumericOperations<T>

SupportsInverseTransform

Gets whether this transformer supports inverse transformation.

public abstract bool SupportsInverseTransform { get; }

Property Value

bool

Methods

EnsureFitted()

Ensures the transformer has been fitted before transformation.

protected void EnsureFitted()

Exceptions

InvalidOperationException

Thrown if not fitted.

Fit(TInput)

Fits the transformer to the training data.

public void Fit(TInput data)

Parameters

data TInput

The training data to fit.

FitCore(TInput)

Core fitting implementation. Override this in derived classes.

protected abstract void FitCore(TInput data)

Parameters

data TInput

The training data to fit.

FitTransform(TInput)

Fits the transformer and transforms the data in a single step.

public TOutput FitTransform(TInput data)

Parameters

data TInput

The data to fit and transform.

Returns

TOutput

The transformed data.

GetColumnsToProcess(int)

Gets the indices to operate on, defaulting to all if ColumnIndices is null.

protected int[] GetColumnsToProcess(int totalColumns)

Parameters

totalColumns int

The total number of columns in the data.

Returns

int[]

The column indices to process.

GetFeatureNamesOut(string[]?)

Gets the output feature names after transformation.

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

Parameters

inputFeatureNames string[]

The input feature names (optional).

Returns

string[]

The output feature names.

InverseTransform(TOutput)

Reverses the transformation.

public TInput InverseTransform(TOutput data)

Parameters

data TOutput

The transformed data.

Returns

TInput

The original-scale data.

Exceptions

NotSupportedException

Thrown if inverse transform is not supported.

InvalidOperationException

Thrown if Fit() has not been called.

InverseTransformCore(TOutput)

Core inverse transformation implementation. Override this in derived classes.

protected virtual TInput InverseTransformCore(TOutput data)

Parameters

data TOutput

The transformed data.

Returns

TInput

The original-scale data.

Transform(TInput)

Transforms the input data using fitted parameters.

public TOutput Transform(TInput data)

Parameters

data TInput

The data to transform.

Returns

TOutput

The transformed data.

Exceptions

InvalidOperationException

Thrown if Fit() has not been called.

TransformCore(TInput)

Core transformation implementation. Override this in derived classes.

protected abstract TOutput TransformCore(TInput data)

Parameters

data TInput

The data to transform.

Returns

TOutput

The transformed data.

ValidateInputData(TInput)

Validates input data before fitting or transforming.

protected virtual void ValidateInputData(TInput data)

Parameters

data TInput

The data to validate.

Exceptions

ArgumentNullException

Thrown if data is null.