QuantileTransformer<T>

Models & Types · AiDotNet.Preprocessing.PowerTransforms

Transforms features to follow a uniform or normal distribution using quantile information.

Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → QuantileTransformer<T>

For Beginners

This transformer redistributes your data to match a desired pattern:

  • Uniform: Spreads values evenly across [0, 1]
  • Normal: Creates a bell curve distribution

Example with uniform output: [1, 1, 2, 3, 5, 8, 13, 100, 1000] → [0.0, 0.0, 0.25, 0.375, 0.5, 0.625, 0.75, 0.875, 1.0] (values equal to the fitted minimum map to 0, as in scikit-learn) Notice how extreme values (100, 1000) no longer dominate.

How It Works

QuantileTransformer applies a non-linear transformation that maps the input distribution to either a uniform or normal (Gaussian) distribution. This is effective at reducing the impact of outliers and normalizing non-Gaussian distributions.

Constructors

Constructor Summary
QuantileTransformer(OutputDistributionType outputDistribution, int nQuantiles, int[] columnIndices) Creates a new instance of QuantileTransformer.

Properties

Property Summary
List<T[]> Quantiles { get; } Gets the quantiles for each feature computed during fitting.
OutputDistributionType OutputDistribution { get; } Gets the target output distribution.
bool SupportsInverseTransform { get; } Gets whether this transformer supports inverse transformation.
int NQuantiles { get; } Gets the number of quantiles used.

Methods

Method Summary
string[] GetFeatureNamesOut(string[] inputFeatureNames) Gets the output feature names after transformation.