incline.pspline_trend

incline.pspline_trend(df, column_value='value', time_column=None, lam=None, **kwargs)[source]

Estimate the trend with a penalized smoothing spline.

With lam fixed this is a linear smoother and standard errors are exact. Leaving lam as None selects it by generalized cross-validation, which makes the fit data-dependent and routes uncertainty to the bootstrap.

Parameters:

  • df (pd.DataFrame) – Time series data.

  • column_value (str) – Column holding the values.

  • time_column (str | None) – Numeric time column.

  • lam (float | None) – Roughness penalty.

  • **kwargs (Any) – Uncertainty options; see estimate().

Returns:

The input frame plus the estimate columns.

Return type:

pd.DataFrame