Module preprocessing 

Data preprocessing utilities for scientific computing

This module provides common data preprocessing operations used across the SciRS2 ecosystem, including scaling, encoding, imputation, and outlier detection.

Scalers

• StandardScaler - Standardize features by removing the mean and scaling to unit variance
• MinMaxScaler - Scale features to a given range (default [0, 1])
• RobustScaler - Scale features using statistics robust to outliers (median, IQR)
• MaxAbsScaler - Scale each feature by its maximum absolute value

Encoders

• LabelEncoder - Encode string labels as integers
• OneHotEncoder - Encode categorical features as one-hot numeric arrays
• OrdinalEncoder - Encode categorical features as ordinal integers

Imputation

• Imputer - Fill missing values using various strategies

Outlier Detection

• OutlierDetector - Detect outliers using Z-score or IQR methods

Structs

Imputer

Impute missing values in numeric data.

LabelEncoder

Encode string (or any hashable) labels as integer indices.

MaxAbsScaler

Scale each feature by its maximum absolute value so values are in [-1, 1].

MinMaxScaler

Scale features to a given range [feature_min, feature_max] (default [0, 1]).

OneHotEncoder

One-hot encode categorical features.

OrdinalEncoder

Encode categorical features as ordinal integers.

OutlierDetector

Detect outliers in numeric data.

RobustScaler

Scale features using statistics robust to outliers.

StandardScaler

Standardize features by removing the mean and scaling to unit variance.

Enums

ImputeStrategy

Strategy for imputing missing values.

OutlierMethod

Method used for outlier detection.