statsmodels.gam.generalized_additive_model.GLMGamResults.predict

GLMGamResults.predict(exog=None, exog_smooth=None, transform=True, **kwargs)

Compute prediction

Parameters:

exogarray_like, optional

The values for the linear explanatory variables

exog_smootharray_like

values for the variables in the smooth terms

transformbool, optional

If transform is True, then the basis representation of the smooth term will be constructed from the provided exog.

**kwargs

Some models can take additional arguments or keywords, see the predict method of the model for the details.

Returns:

predictionndarray, pandas.Series or pandas.DataFrame

predicted values

Notes

When predicting out of sample, provide the new values for variables in smooth terms through exog_smooth. If the model also has linear terms, provide their new values through exog. For example:

results.predict(exog=X_linear_test, exog_smooth=X_smooth_test)

Examples

>>> import numpy as np
>>> import statsmodels.api as sm
>>> from statsmodels.gam.api import GLMGam, BSplines

>>> rng = np.random.default_rng(0)
>>> x_linear = sm.add_constant(rng.uniform(-1, 1, size=200))
>>> x_smooth = np.linspace(-1, 1, 200)
>>> y = x_smooth + x_smooth ** 2 + rng.normal(scale=0.1, size=200)

>>> bs = BSplines(x_smooth, df=[10], degree=[3])
>>> gam_bs = GLMGam(y, exog=x_linear, smoother=bs, alpha=0.1)
>>> res_bs = gam_bs.fit()

Predict for new, out-of-sample values of the linear and smooth terms:

>>> exog_linear_test = sm.add_constant([0.1, -0.2])
>>> exog_smooth_test = [0.3, -0.4]
>>> res_bs.predict(exog=exog_linear_test, exog_smooth=exog_smooth_test)
array([ 0.39325773, -0.23569393])