Scikit-learn compatible GAM regressor.
Usage
GAMRegressor wraps whittaker.gam.GAM behind the scikit-learn BaseEstimator / RegressorMixin interface, exposing the familiar fit(X, y), predict(X), get_params()/set_params() methods instead of GAM’s formula-and-data-dictionary API. This makes it a drop-in estimator anywhere scikit-learn expects one: inside a Pipeline (e.g. chained after a StandardScaler or a ColumnTransformer), as the estimator tuned by GridSearchCV or RandomizedSearchCV (searching over formula, method, or select), scored with cross_val_score or cross_validate, or combined with other regressors inside a VotingRegressor or a stacking ensemble.
Because raw numpy feature columns carry no names, GAMRegressor assigns synthetic names x0, x1, …, x{n_features - 1} to the columns of X in order (see _make_feature_names). Unless an explicit formula is supplied, a default additive formula with one smooth s(xi) per feature is built automatically (see _build_formula), giving
\eta = \beta_0 + \sum_{i=0}^{p-1} f_i(x_i),
connected to the mean response through the link implied by family. Supplying formula overrides this default; it accepts either a bare right-hand side such as "s(x0) + s(x1)" — in which case the response name "y" is prepended automatically to form "y ~ s(x0) + s(x1)" — or a complete formula already containing "~", which is used as-is. This makes it possible to mix smooth and linear terms, use interactions (x0:x1), or omit features, exactly as with GAM directly.
formula: str = NoneGAM formula for the right-hand side (e.g. "s(x0) + s(x1)"), or a complete formula containing "~" (e.g. "y ~ s(x0) + x1"). If it contains "~" it is used verbatim; otherwise the response "y" is prepended. If None (the default), a formula with one s(xi) smooth per input feature is generated automatically.
family: Family = NoneResponse distribution family passed through to the underlying GAM. Defaults to Gaussian() (identity link), i.e. ordinary least-squares-style additive regression.
method: str = "GCV"Smoothing parameter selection criterion forwarded to GAM.fit: "GCV" (default), "REML", or "ML". See whittaker.gam.GAM.fit for the meaning of each option.
select: bool = FalseTrue, enable double-penalty smooth selection (an extra penalty that can shrink an entire smooth to zero), forwarded to GAM.fit. Defaults to False.
The hyperparameters exposed to GridSearchCV/RandomizedSearchCV via get_params() are exactly the constructor arguments — formula, family, method, and select — because scikit-learn’s get_params introspects the __init__ signature. The smoothing parameters \lambda_j themselves are never tunable hyperparameters of GAMRegressor: they are always chosen internally, for the given method, during fit(). To tune smoothing behavior via cross-validation, search over method and select (which change how \lambda_j are selected) rather than trying to pass \lambda_j values directly.
import numpy as np
from whittaker.sklearn import GAMRegressor
rng = np.random.default_rng(0)
X = rng.uniform(-2, 2, size=(200, 2))
y = np.sin(X[:, 0]) + 0.5 * X[:, 1] ** 2 + rng.normal(scale=0.2, size=200)
reg = GAMRegressor(formula="s(x0) + s(x1)")
reg.fit(X, y)
reg.predict(X[:5])array([0.89871156, 0.83528962, 2.44803234, 0.8379585 , 1.77990934])GAMRegressor works inside scikit-learn model-selection tooling, such as sklearn.model_selection.cross_val_score (requires pip install scikit-learn):
| Name | Description |
|---|---|
| fit() | Fit the GAM regressor. |
| predict() | Predict target values for X. |
Fit the GAM regressor.
Usage
Validates X and y with scikit-learn’s check_X_y, assigns synthetic feature names, builds the model formula (from formula if given, otherwise one s(xi) smooth per feature), and fits an internal whittaker.gam.GAM to the resulting data dictionary using method and select.
X: numpy.ndarrayFeature matrix, shape (n_samples, n_features). Coerced to float64 and checked by sklearn.utils.validation.check_X_y, which rejects non-finite values, non-2-D input, and samples with zero features.
y: numpy.ndarrayTarget values, shape (n_samples,). Coerced to float64 alongside X by check_X_y; must have the same number of samples as X.
**fit_params: Anyfit signature but currently unused.
GAMRegressorself, with fitted attributes n_features_in_ (number of input features), feature_names_ (the synthetic x0, x1, … names used internally), and gam_ (the underlying fitted whittaker.gam.GAM instance), so that scikit-learn’s fit(...).predict(...) chaining works as usual.
Predict target values for X.
Usage
Requires fit() to have been called first (checked via sklearn.utils.validation. check_is_fitted). Converts X into the internal data dictionary using the feature names recorded during fit(), and delegates to the fitted GAM’s predict().
X: numpy.ndarray(n_samples, n_features_in_), where n_features_in_ matches the number of features seen during fit(). Coerced to float64 and validated by sklearn.utils.validation.check_array.
NDArray(n_samples,), in the original (non-linear predictor) scale.