pretab.transformers.OneHotFromOrdinalTransformer

class pretab.transformers.OneHotFromOrdinalTransformer

Bases: TransformerMixin, BaseEstimator

Convert ordinal-encoded features into a one-hot encoded representation.

This is useful when features have already been ordinal-encoded and a one-hot representation is required for model training.

Variables:

max_bins (ndarray of shape (n_features,)) – Array containing the maximum bin index (plus one) for each feature, which determines the width of the one-hot block for that feature.

Notes

Each input feature i is expanded into max_bins_[i] columns, so the total number of output columns is the sum of max_bins_ across all features.

Examples

>>> import numpy as np
>>> from pretab.transformers import OneHotFromOrdinalTransformer
>>> X = np.array([[0, 1], [1, 0], [2, 1]])
>>> transformer = OneHotFromOrdinalTransformer()
>>> transformer.fit_transform(X).shape
(3, 5)

__init__()

Methods

__init__()
fit(X[, y])	Learn the maximum bin index for each feature from the data.
fit_transform(X[, y])	Fit to data, then transform it.
get_feature_names_out([input_features])	Generate feature names for the one-hot encoded output.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
set_output(*[, transform])	Set output container.
set_params(**params)	Set the parameters of this estimator.
transform(X)	Convert ordinal-encoded features into one-hot encoded format.

fit(X, y=None)

Learn the maximum bin index for each feature from the data.

Parameters:

• X (array-like of shape (n_samples, n_features)) – The input data containing ordinal-encoded features.

• y (Ignored) – Not used, present for API consistency by convention.

Returns:

self (object) – Fitted transformer.

get_feature_names_out(input_features=None)

Generate feature names for the one-hot encoded output.

Parameters:

input_features (list of str) – The names of the input features that were ordinal-encoded.

Returns:

feature_names (ndarray of shape (n_output_features,)) – The names of the one-hot encoded features.

transform(X)

Convert ordinal-encoded features into one-hot encoded format.

Uses the max_bins_ learned during fitting.

Parameters:

X (array-like of shape (n_samples, n_features)) – The input data containing ordinal-encoded features.

Returns:

X_one_hot (ndarray of shape (n_samples, n_output_features)) – The one-hot encoded features.

Notes

Codes outside the range learned during fit() (negative values or values >= max_bins_[i]) are treated as unknown and encoded as an all-zero row, mirroring scikit-learn’s handle_unknown="ignore".