Crate sklears_preprocessing 

Preprocessing utilities for sklears

This crate provides data preprocessing utilities including:

• Scaling (StandardScaler, MinMaxScaler, RobustScaler, MaxAbsScaler, Normalizer)
• Encoding (LabelEncoder, OneHotEncoder, OrdinalEncoder)
• Imputation (SimpleImputer, KNNImputer, IterativeImputer, GAINImputer)
• Feature engineering (PolynomialFeatures, SplineTransformer, PowerTransformer, FunctionTransformer)
• Text processing (TfIdfVectorizer, TextTokenizer, NgramGenerator, TextSimilarity, BagOfWordsEmbedding)
• Advanced pipelines (conditional steps, parallel branches, caching, dynamic construction)

Re-exports

pub use adaptive::AdaptationStrategy;

pub use adaptive::AdaptiveConfig;

pub use adaptive::AdaptiveParameterSelector;

pub use adaptive::DataCharacteristics;

pub use adaptive::DistributionType;

pub use adaptive::ImputationParameters;

pub use adaptive::OutlierDetectionParameters;

pub use adaptive::ParameterEvaluation;

pub use adaptive::ParameterRecommendations;

pub use adaptive::ScalingParameters;

pub use adaptive::TransformationParameters as AdaptiveTransformationParameters;

pub use automated_feature_engineering::AutoFeatureConfig;

pub use automated_feature_engineering::AutoFeatureEngineer;

pub use automated_feature_engineering::AutoFeatureEngineerFitted;

pub use automated_feature_engineering::Domain;

pub use automated_feature_engineering::GenerationStrategy;

pub use automated_feature_engineering::MathFunction;

pub use automated_feature_engineering::SelectionMethod;

pub use automated_feature_engineering::TransformationFunction;

pub use automated_feature_engineering::TransformationType;

pub use binarization::Binarizer;

pub use binarization::BinarizerConfig;

pub use binarization::DiscretizationStrategy;

pub use binarization::DiscretizerEncoding;

pub use binarization::KBinsDiscretizer;

pub use binarization::KBinsDiscretizerConfig;

pub use column_transformer::ColumnSelector;

pub use column_transformer::ColumnTransformer;

pub use column_transformer::ColumnTransformerConfig;

pub use column_transformer::DataType;

pub use column_transformer::RemainderStrategy;

pub use column_transformer::TransformerStep;

pub use column_transformer::TransformerWrapper;

pub use dimensionality_reduction::ICAConfig;

pub use dimensionality_reduction::ICAFitted;

pub use dimensionality_reduction::IcaAlgorithm;

pub use dimensionality_reduction::IcaFunction;

pub use dimensionality_reduction::LDAConfig;

pub use dimensionality_reduction::LDAFitted;

pub use dimensionality_reduction::LdaSolver;

pub use dimensionality_reduction::NMFConfig;

pub use dimensionality_reduction::NMFFitted;

pub use dimensionality_reduction::NmfInit;

pub use dimensionality_reduction::NmfSolver;

pub use dimensionality_reduction::PCAConfig;

pub use dimensionality_reduction::PCAFitted;

pub use dimensionality_reduction::PcaSolver;

pub use dimensionality_reduction::ICA;

pub use dimensionality_reduction::LDA;

pub use dimensionality_reduction::NMF;

pub use dimensionality_reduction::PCA;

pub use encoding::BinaryEncoder;

pub use encoding::BinaryEncoderConfig;

pub use encoding::CategoricalEmbedding;

pub use encoding::CategoricalEmbeddingConfig;

pub use encoding::FrequencyEncoder;

pub use encoding::FrequencyEncoderConfig;

pub use encoding::HashEncoder;

pub use encoding::HashEncoderConfig;

pub use encoding::LabelEncoder;

pub use encoding::OneHotEncoder;

pub use encoding::OrdinalEncoder;

pub use encoding::RareStrategy;

pub use encoding::TargetEncoder;

pub use feature_engineering::ExtrapolationStrategy;

pub use feature_engineering::FeatureOrder;

pub use feature_engineering::KnotStrategy;

pub use feature_engineering::PolynomialFeatures;

pub use feature_engineering::PowerMethod;

pub use feature_engineering::PowerTransformer;

pub use feature_engineering::PowerTransformerConfig;

pub use feature_engineering::SplineTransformer;

pub use feature_engineering::SplineTransformerConfig;

pub use feature_union::FeatureUnion;

pub use feature_union::FeatureUnionConfig;

pub use feature_union::FeatureUnionStep;

pub use image_preprocessing::ColorSpace;

pub use image_preprocessing::ColorSpaceTransformer;

pub use image_preprocessing::EdgeDetectionMethod;

pub use image_preprocessing::EdgeDetector;

pub use image_preprocessing::ImageAugmenter;

pub use image_preprocessing::ImageAugmenterConfig;

pub use image_preprocessing::ImageFeatureExtractor;

pub use image_preprocessing::ImageNormalizationStrategy;

pub use image_preprocessing::ImageNormalizer;

pub use image_preprocessing::ImageNormalizerConfig;

pub use image_preprocessing::ImageNormalizerFitted;

pub use image_preprocessing::ImageResizer;

pub use image_preprocessing::InterpolationMethod as ImageInterpolationMethod;

pub use imputation::BaseImputationMethod;

pub use imputation::DistanceMetric;

pub use imputation::FeatureMissingStats;

pub use imputation::GAINImputer;

pub use imputation::GAINImputerConfig;

pub use imputation::ImputationStrategy;

pub use imputation::IterativeImputer;

pub use imputation::KNNImputer;

pub use imputation::MissingPattern;

pub use imputation::MissingValueAnalysis;

pub use imputation::MissingnessType;

pub use imputation::MultipleImputationResult;

pub use imputation::MultipleImputer;

pub use imputation::MultipleImputerConfig;

pub use imputation::OutlierAwareImputer;

pub use imputation::OutlierAwareImputerConfig;

pub use imputation::OutlierAwareStatistics;

pub use imputation::OutlierAwareStrategy;

pub use imputation::OverallMissingStats;

pub use imputation::SimpleImputer;

pub use kernel_centerer::KernelCenterer;

pub use label_binarization::LabelBinarizer;

pub use label_binarization::LabelBinarizerConfig;

pub use label_binarization::MultiLabelBinarizer;

pub use label_binarization::MultiLabelBinarizerConfig;

pub use outlier_detection::FeatureOutlierParams;

pub use outlier_detection::OutlierDetectionMethod;

pub use outlier_detection::OutlierDetectionResult;

pub use outlier_detection::OutlierDetector;

pub use outlier_detection::OutlierDetectorConfig;

pub use outlier_detection::OutlierStatistics;

pub use outlier_detection::OutlierSummary;

pub use outlier_transformation::FeatureTransformationParams;

pub use outlier_transformation::GlobalTransformationParams;

pub use outlier_transformation::OutlierTransformationConfig;

pub use outlier_transformation::OutlierTransformationMethod;

pub use outlier_transformation::OutlierTransformer;

pub use outlier_transformation::TransformationParameters;

pub use pipeline::AdvancedPipeline;

pub use pipeline::AdvancedPipelineBuilder;

pub use pipeline::AdvancedPipelineConfig;

pub use pipeline::BranchCombinationStrategy;

pub use pipeline::CacheConfig;

pub use pipeline::CacheStats;

pub use pipeline::ConditionalStep;

pub use pipeline::ConditionalStepConfig;

pub use pipeline::DynamicPipeline;

pub use pipeline::ErrorHandlingStrategy;

pub use pipeline::ParallelBranchConfig;

pub use pipeline::ParallelBranches;

pub use pipeline::PipelineStep;

pub use pipeline::TransformationCache;

pub use quantile_transformer::QuantileOutput;

pub use quantile_transformer::QuantileTransformer;

pub use quantile_transformer::QuantileTransformerConfig;

pub use robust_preprocessing::MissingValueStats;

pub use robust_preprocessing::RobustPreprocessingStats;

pub use robust_preprocessing::RobustPreprocessor;

pub use robust_preprocessing::RobustPreprocessorConfig;

pub use robust_preprocessing::RobustStrategy;

pub use robust_preprocessing::TransformationStats;

pub use scaling::FeatureWiseScaler;

pub use scaling::FeatureWiseScalerConfig;

pub use scaling::MaxAbsScaler;

pub use scaling::MinMaxScaler;

pub use scaling::NormType;

pub use scaling::Normalizer;

pub use scaling::OutlierAwareScaler;

pub use scaling::OutlierAwareScalerConfig;

pub use scaling::OutlierAwareScalingStrategy;

pub use scaling::OutlierScalingStats;

pub use scaling::RobustScaler;

pub use scaling::RobustStatistic;

pub use scaling::ScalingMethod;

pub use scaling::StandardScaler;

pub use scaling::UnitVectorScaler;

pub use scaling::UnitVectorScalerConfig;

pub use simd_optimizations::add_scalar_f64_simd;

pub use simd_optimizations::add_vectors_f64_simd;

pub use simd_optimizations::mean_f64_simd;

pub use simd_optimizations::min_max_f64_simd;

pub use simd_optimizations::mul_scalar_f64_simd;

pub use simd_optimizations::ndarray_ops;

pub use simd_optimizations::sub_vectors_f64_simd;

pub use simd_optimizations::variance_f64_simd;

pub use simd_optimizations::SimdConfig;

pub use sparse_optimizations::sparse_matvec;

pub use sparse_optimizations::SparseConfig;

pub use sparse_optimizations::SparseFormat;

pub use sparse_optimizations::SparseMatrix;

pub use sparse_optimizations::SparseStandardScaler;

pub use sparse_optimizations::SparseStandardScalerFitted;

pub use streaming::AdaptiveConfig as StreamingAdaptiveConfig;

pub use streaming::AdaptiveParameterManager;

pub use streaming::AdaptiveStreamingMinMaxScaler;

pub use streaming::AdaptiveStreamingStandardScaler;

pub use streaming::IncrementalPCA;

pub use streaming::IncrementalPCAStats;

pub use streaming::MiniBatchConfig;

pub use streaming::MiniBatchIterator;

pub use streaming::MiniBatchPipeline;

pub use streaming::MiniBatchStats;

pub use streaming::MiniBatchStreamingTransformer;

pub use streaming::MiniBatchTransformer;

pub use streaming::MultiQuantileEstimator;

pub use streaming::OnlineMADEstimator;

pub use streaming::OnlineMADStats;

pub use streaming::OnlineQuantileEstimator;

pub use streaming::OnlineQuantileStats;

pub use streaming::ParameterUpdate;

pub use streaming::StreamCharacteristics;

pub use streaming::StreamingConfig;

pub use streaming::StreamingLabelEncoder;

pub use streaming::StreamingMinMaxScaler;

pub use streaming::StreamingPipeline;

pub use streaming::StreamingRobustScaler;

pub use streaming::StreamingRobustScalerStats;

pub use streaming::StreamingSimpleImputer;

pub use streaming::StreamingStandardScaler;

pub use streaming::StreamingStats;

pub use streaming::StreamingTransformer;

pub use temporal::ChangePointDetector;

pub use temporal::ChangePointDetectorConfig;

pub use temporal::ChangePointMethod;

pub use temporal::DateComponents;

pub use temporal::DateTime;

pub use temporal::DecompositionMethod;

pub use temporal::FillMethod;

pub use temporal::FourierFeatureGenerator;

pub use temporal::FourierFeatureGeneratorConfig;

pub use temporal::InterpolationMethod;

pub use temporal::LagFeatureGenerator;

pub use temporal::LagFeatureGeneratorConfig;

pub use temporal::MultiVariateTimeSeriesAligner;

pub use temporal::ResamplingMethod;

pub use temporal::SeasonalDecomposer;

pub use temporal::SeasonalDecomposerConfig;

pub use temporal::StationarityMethod;

pub use temporal::StationarityTransformer;

pub use temporal::StationarityTransformerConfig;

pub use temporal::StationarityTransformerFitted;

pub use temporal::TemporalFeatureExtractor;

pub use temporal::TemporalFeatureExtractorConfig;

pub use temporal::TimeSeriesInterpolator;

pub use temporal::TimeSeriesResampler;

pub use temporal::TrendDetector;

pub use temporal::TrendDetectorConfig;

pub use temporal::TrendMethod;

pub use text::BagOfWordsConfig;

pub use text::BagOfWordsEmbedding;

pub use text::NgramGenerator;

pub use text::NgramGeneratorConfig;

pub use text::NgramType;

pub use text::NormalizationStrategy;

pub use text::SimilarityMetric;

pub use text::TextSimilarity;

pub use text::TextSimilarityConfig;

pub use text::TextTokenizer;

pub use text::TextTokenizerConfig;

pub use text::TfIdfVectorizer;

pub use text::TfIdfVectorizerConfig;

pub use text::TokenizationStrategy;

pub use winsorization::NanStrategy;

pub use winsorization::WinsorizationStats;

pub use winsorization::Winsorizer;

pub use winsorization::WinsorizerConfig;

pub use functional::add_dummy_feature;

pub use functional::binarize;

pub use functional::label_binarize;

pub use functional::maxabs_scale;

pub use functional::minmax_scale;

pub use functional::normalize;

pub use functional::robust_scale;

pub use functional::scale;

Modules

adaptive

Adaptive preprocessing parameters that automatically tune based on data characteristics

automated_feature_engineering

Automated Feature Engineering

binarization

Binarization transformers

column_transformer

Column Transformer

dimensionality_reduction

Dimensionality Reduction Transformers

encoding

Data encoding and categorical feature transformation utilities

feature_engineering

Feature engineering utilities

feature_union

Feature Union

functional

Functional APIs for preprocessing

image_preprocessing

Image Preprocessing for Computer Vision Applications

imputation

Missing value imputation utilities

kernel_centerer

Kernel Centerer for centering kernel matrices

label_binarization

Label Binarization transformers

outlier_detection

Outlier detection utilities

outlier_transformation

Outlier transformation methods for handling extreme values

pipeline

Advanced Pipeline Features for Preprocessing Transformations

prelude

Prelude module for convenient imports

quantile_transformer

Quantile Transformer

robust_preprocessing

Robust preprocessing module for outlier-resilient data preprocessing

scaling

Data scaling utilities

simd_optimizations

SIMD optimizations for preprocessing operations

sparse_optimizations

Sparse Matrix Optimizations for Preprocessing

streaming

Streaming data preprocessing for large datasets

temporal

Temporal feature engineering utilities

text

Text preprocessing utilities for sklears

winsorization

Winsorization utilities for capping extreme outliers