Class PreprocessingRegistry<T, TInput>

Namespace

AiDotNet.Preprocessing

Assembly

AiDotNet.dll

Global registry for the preprocessing pipeline.

public static class PreprocessingRegistry<T, TInput>

Type Parameters

T

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

TInput

The input data type.

Inheritance

object

PreprocessingRegistry<T, TInput>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

PreprocessingRegistry provides a singleton pattern for managing the active preprocessing pipeline. By default, a standard pipeline with imputation and scaling is used. Users can configure custom preprocessing via AiModelBuilder.ConfigurePreprocessing().

For Beginners: This is like a global settings panel for data preprocessing. You don't need to interact with this directly - just use AiModelBuilder:

var result = new AiModelBuilder<double, Matrix<double>, Vector<double>>()
    .ConfigurePreprocessing(pipeline => pipeline
        .Add(new SimpleImputer<double>(ImputationStrategy.Mean))
        .Add(new StandardScaler<double>()))
    .ConfigureModel(new LogisticRegression<double>())
    .Build(X, y);

The configured preprocessing is automatically applied to all models.

Properties

Current

Gets or sets the current preprocessing pipeline.

public static IDataTransformer<T, TInput, TInput>? Current { get; set; }

Property Value

IDataTransformer<T, TInput, TInput>

Remarks

This is set automatically when you call AiModelBuilder.ConfigurePreprocessing(). The pipeline is global and thread-safe.

For Beginners: You typically don't set this directly. Use AiModelBuilder.ConfigurePreprocessing() instead.

IsConfigured

Gets whether a preprocessing pipeline is currently configured.

public static bool IsConfigured { get; }

Property Value

bool

Methods

Clear()

Clears the current preprocessing pipeline.

public static void Clear()

Remarks

This resets the preprocessing to no-op (pass-through) behavior.

FitTransform(TInput)

Fits the current preprocessing pipeline to data and transforms it.

public static TInput FitTransform(TInput input)

Parameters

input TInput

The data to fit and transform.

Returns

TInput

The preprocessed data, or the original input if no pipeline is configured.

Transform(TInput)

Transforms input data using the current preprocessing pipeline.

public static TInput Transform(TInput input)

Parameters

input TInput

The input data to preprocess.

Returns

TInput

The preprocessed data, or the original input if no pipeline is configured.

Remarks

If no preprocessing pipeline has been configured, this method returns the input unchanged. This allows models to safely call this method without checking if preprocessing is configured.