statsmodels.regression.process_regression.ProcessMLE.from_formula#

classmethod ProcessMLE.from_formula(formula, data, subset=None, drop_cols=None, *args, **kwargs)[source]#

Create a ProcessMLE model instance using a formula.

Parameters:

formulastr: The formula for the mean structure, used to construct exog.
dataarray_like: The data to which the formulas are applied.
subsetarray_like, optional: Not currently supported, must be None if provided.
drop_colsarray_like, optional: Not currently supported, must be None if provided.
scale_formulastr: The formula for the scaling structure (required keyword argument).
smooth_formulastr: The formula for the smoothness structure (required keyword argument).
noise_formulaNone or str, optional: The formula for the (log) standard deviation of the additive white noise (optional keyword argument). If not provided, the model does not include additive white noise.
timearray_like or str: The univariate index values used to calculate distances between observations in the same group (required keyword argument). If a string, this is the name of a column in data.
groupsarray_like or str: The group values (required keyword argument). If a string, this is the name of a column in data.

Returns: