Interface RobustStandardizer

public interface RobustStandardizer
Robustly standardizes numeric feature by subtracting the median and dividing by the IQR.

Quantiles (median, 25th, 75th percentile) are computed via IQAgent, which produces approximate results. On very small datasets (< 20 rows) results may differ slightly from exact sort-based quantiles. When the IQR is zero (e.g. constant column), the scale falls back to 1.0 so that only centering is applied.

  • Method Details

    • fit

      static InvertibleColumnTransform fit(DataFrame data, String... columns)
      Fits the data transformation.
      Parameters:
      data - the training data.
      columns - the columns to transform. If empty, transform all the numeric columns.
      Returns:
      the transform.
      Throws:
      IllegalArgumentException - if the data frame is empty or a specified column is non-numeric.