Struct ColumnTransformer 

pub struct ColumnTransformer<S = Untrained> { /* private fields */ }

Column Transformer

Apply different transformers to different subsets of features. This allows you to apply different preprocessing steps to different types of features (e.g., numerical vs. categorical).

Parameters

• transformers - List of (name, transformer, columns) tuples
• remainder - How to handle remaining columns (‘drop’, ‘passthrough’)
• sparse_threshold - Threshold for sparse output
• n_jobs - Number of parallel jobs
• transformer_weights - Weights for each transformer

Examples

use sklears_compose::ColumnTransformer;
use scirs2_core::ndarray::array;

let data = array![[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]];

let mut ct = ColumnTransformer::new();
ct.add_transformer("numeric".to_string(), vec![0, 1]);
ct.add_transformer("categorical".to_string(), vec![2]);

Implementations

impl ColumnTransformer<Untrained>

pub fn new() -> Self

Create a new ColumnTransformer instance

pub fn builder() -> ColumnTransformerBuilder

Create a column transformer builder

pub fn add_transformer(&mut self, name: String, columns: Vec<usize>)

Add a transformer for specific columns (legacy method)

pub fn add_transformer_step( &mut self, name: String, transformer: Box<dyn PipelineStep>, columns: Vec<usize>, )

Add a transformer with actual PipelineStep implementation

pub fn remainder(self, remainder: String) -> Self

Set what to do with remaining columns

pub fn sparse_threshold(self, threshold: f64) -> Self

Set the sparse threshold

pub fn n_jobs(self, n_jobs: Option<i32>) -> Self

Set the number of parallel jobs

pub fn transformer_weights(self, weights: HashMap<String, f64>) -> Self

Set transformer weights

impl ColumnTransformer<ColumnTransformerTrained>

pub fn transform_output( &self, x: &ArrayView2<'_, Float>, ) -> SklResult<ColumnTransformerOutput>

Transform data and return appropriate output format (dense or sparse)

pub fn get_transformer_info(&self) -> Vec<(String, Vec<usize>)>

Get information about fitted transformers

pub fn n_features_out(&self) -> usize

Get number of output features

Trait Implementations

impl<S: Clone> Clone for ColumnTransformer<S>

fn clone(&self) -> ColumnTransformer<S>

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl<S: Debug> Debug for ColumnTransformer<S>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ColumnTransformer<Untrained>

fn default() -> Self

Returns the “default value” for a type.

impl Estimator for ColumnTransformer<Untrained>

type Config = ColumnTransformerConfig

Configuration type for the estimator

type Error = SklearsError

Error type for the estimator

type Float = f64

The numeric type used by this estimator

fn config(&self) -> &Self::Config

Get estimator configuration

fn validate_config(&self) -> Result<(), SklearsError>

Validate estimator configuration with detailed error context

fn check_compatibility( &self, n_samples: usize, n_features: usize, ) -> Result<(), SklearsError>

Check if estimator is compatible with given data dimensions

fn metadata(&self) -> EstimatorMetadata

Get estimator metadata

impl Fit<ArrayBase<ViewRepr<&f64>, Dim<[usize; 2]>>, Option<&ArrayBase<ViewRepr<&f64>, Dim<[usize; 1]>>>> for ColumnTransformer<Untrained>

type Fitted = ColumnTransformer<ColumnTransformerTrained>

The fitted model type

fn fit( self, x: &ArrayView2<'_, Float>, y: &Option<&ArrayView1<'_, Float>>, ) -> SklResult<Self::Fitted>

Fit the model to the provided data with validation

fn fit_with_validation( self, x: &X, y: &Y, _x_val: Option<&X>, _y_val: Option<&Y>, ) -> Result<(Self::Fitted, FitMetrics), SklearsError>

where Self: Sized,

Fit with custom validation and early stopping

impl Transform<ArrayBase<ViewRepr<&f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>> for ColumnTransformer<ColumnTransformerTrained>

Transform trait implementation for trained ColumnTransformer

fn transform(&self, x: &ArrayView2<'_, Float>) -> SklResult<Array2<f64>>

Transform the input data