Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 16 additions & 1 deletion pretab/compose/factory.py
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@

import warnings

import numpy as np
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import FeatureUnion, Pipeline
Expand Down Expand Up @@ -49,6 +50,20 @@
_KNOT_SPLINE_METHODS = _BMI_SPLINE_METHODS | frozenset({"cubicspline", "naturalspline"})


class _PositiveMinMaxScaler(MinMaxScaler):
"""MinMaxScaler whose output is floored at ``feature_range[0]``.

Rescales into ``(1e-3, 1)`` ahead of Box-Cox, which requires strictly
positive input. Fitted on the training data, a plain MinMaxScaler maps an
unseen value below the training minimum to ``<= 0``; flooring only the lower
end makes such values transform like the training minimum while every other
output (including values above the training maximum) is unchanged.
"""

def transform(self, X):
return np.maximum(super().transform(X), self.feature_range[0])


def _filter_kwargs(allowed, kwargs):
"""Keep only the ``allowed`` keyword arguments that are present in ``kwargs``."""
return {key: kwargs[key] for key in allowed if key in kwargs}
Expand Down Expand Up @@ -154,7 +169,7 @@ def get_numerical_transformer_steps(
placement = _placement_kwargs(spec, kwargs)

if method == "box-cox":
steps.append(("scale_positive", MinMaxScaler(feature_range=(1e-3, 1))))
steps.append(("scale_positive", _PositiveMinMaxScaler(feature_range=(1e-3, 1))))
steps.append(("boxcox", cls(method="box-cox", **filtered)))
elif method == "yeo-johnson":
steps.append(("yeojohnson", cls(method="yeo-johnson", **filtered)))
Expand Down
5 changes: 5 additions & 0 deletions pretab/preprocessor.py
Original file line number Diff line number Diff line change
Expand Up @@ -331,6 +331,11 @@ class Preprocessor(TransformerMixin, BaseEstimator):
``"naturalspline"``, ``"pspline"``, ``"bspline"``, ``"mspline"``, ``"ispline"``,
``"fourier"``.

Box-Cox requires strictly positive input, so ``"box-cox"`` first rescales each column into
``[1e-3, 1]`` with a min-max scaler fitted on the training data. That scaler's output is
floored at ``1e-3``: a value below the training minimum transforms like the minimum, while
values above the training maximum still extrapolate.

Available ``categorical_method`` values: ``"int"``, ``"one-hot"``, ``"onehot_from_ordinal"``,
``"pretrained"``, ``"none"``. The ``"pretrained"`` method requires the optional
``sentence-transformers`` dependency (``pip install "pretab[embeddings]"``).
Expand Down
37 changes: 37 additions & 0 deletions tests/integration/test_preprocessor.py
Original file line number Diff line number Diff line change
Expand Up @@ -377,3 +377,40 @@ def test_unknown_feature_preprocessing_key_raises(sample_data):
X, y = sample_data
with pytest.raises(InvalidParamError, match="feature_preprocessing"):
Preprocessor(feature_preprocessing={"nnum1": "minmax"}).fit(X, y)


# --- box-cox on unseen low values (issue #59) -------------------------------------


@pytest.fixture
def boxcox_fitted():
X = pd.DataFrame({"x": np.random.default_rng(0).normal(10, 2, 200)})
return X, Preprocessor(numerical_method="box-cox").fit(X)


def test_boxcox_transforms_values_below_the_training_minimum(boxcox_fitted):
"""Regression guard for issue #59: the positivity scaler mapped them to <= 0."""
X, pre = boxcox_fitted
low = pre.transform(pd.DataFrame({"x": [X.x.min() - 5.0, X.x.min() - 0.5]}))
at_min = pre.transform(pd.DataFrame({"x": [X.x.min()]}))
assert np.isfinite(low).all()
np.testing.assert_allclose(low, np.repeat(at_min, 2, axis=0))


def test_boxcox_still_extrapolates_above_the_training_maximum(boxcox_fitted):
X, pre = boxcox_fitted
out = pre.transform(pd.DataFrame({"x": [X.x.max(), X.x.max() + 3.0]})).ravel()
assert np.isfinite(out).all()
assert out[1] > out[0]


def test_boxcox_survives_cross_validation():
from sklearn.datasets import make_regression
from sklearn.linear_model import Ridge
from sklearn.model_selection import cross_val_score
from sklearn.pipeline import make_pipeline

data = make_regression(n_samples=500, n_features=3, noise=1.0, random_state=0)
X, y = data[0], data[1]
scores = cross_val_score(make_pipeline(Preprocessor(numerical_method="box-cox"), Ridge()), X, y, cv=5)
assert np.isfinite(scores).all()
Loading