OrdinalEncoder transformer.
Convert ordinal (ordered categorical) to numeric values.
Classes
Convert ordinal (ordered categorical) attributes to numeric.
Maps categories to integer values based on a specified or inferred order. This is suitable for features where the order carries meaning (e.g., "low", "medium", "high").
Constructor
__init__( self, categories: Optional[Dict[int, List]] = None, columns: Optional[List[int]] = None, )
Parameters
categories
dict or list
The order of categories for each column.
- •
Dict:{col_idx: [cat1, cat2, ...]} - •
List:[[cats_col0], [cats_col1], ...]
None, the order is inferred from the first occurrence in the data.
columns
list of int
Indices of columns to encode. If
None, all columns are encoded.
Attributes
category_maps_
dict
Mapping of categories to integers for each column.
Encode ordered categories:
python
>>> from tuiml.preprocessing.encoding import OrdinalEncoder
>>> import numpy as np
>>> X = np.array([['low'], ['medium'], ['high']], dtype=object)
>>> encoder = OrdinalEncoder(categories=[['low', 'medium', 'high']])
>>> X_encoded = encoder.fit_transform(X)
>>> print(X_encoded.flatten())
[0. 1. 2.]Methods
get_parameter_schema
(cls)
fit
(self, X: np.ndarray, y: Optional[np.ndarray]=None, feature_names: Optional[List[str]]=None) -> 'OrdinalEncoder'
transform
(self, X: np.ndarray) -> np.ndarray
__repr__
(self) -> str