incline.gp_trend

incline.gp_trend(df, column_value='value', time_column=None, kernel='rbf', length_scale=None, **kwargs)

Estimate the trend with Gaussian process regression.

The derivative of a Gaussian process is itself a Gaussian process, so both the estimate and its standard error are exact posterior quantities.

Parameters:

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

• column_value (str) – Column holding the values.

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

• kernel (str) – 'rbf', 'matern32' or 'matern52'. Matern smoothness caps the derivative order.

• length_scale (float | None) – Initial length scale; optimized when None.

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

Returns:

The input frame plus the estimate columns.

Return type:

pd.DataFrame