9d941d30962c211971ec316bf40c2ebfbf28a567,src/orion/analysis/lpi_utils.py,,lpi,#Any#Any#Any#Any#Any#,64

Before Change

        LPI value for each parameter. If ``mode`` is `linear`, then a list of
        param values and LPI metrics are returned in a DataFrame format.
    
    flattened_space = build_required_space(
        space,
        dist_requirement="linear",
        type_requirement="numerical",
        shape_requirement="flattened",
    )
    if trials.empty or trials.shape[0] == 0:
        return pd.DataFrame(
            data=[0] * len(flattened_space),
            index=flattened_space.keys(),
            columns=["LPI"],
        )

    data = to_numpy(trials, space)
    data = flatten_numpy(data, flattened_space)
    model = train_regressor(model, data, **kwargs)
    best_point = data[numpy.argmin(data[:, -1])]
    results = modes[mode](best_point, flattened_space, model, n_points)
    return results

After Change

    Last column is the objective predicted by the model for a given point.

    Parameters
    ----------
    point: numpy.ndarray
        A tuple representation of the best trials, (hyperparameters + objective)
    space: Space object
        A space object from an experiment. It must be flattened and linearized.
    model: `sklearn.base.RegressorMixin`
        Trained regressor used to compute predictions on the grid

Instances