modelsight.curves.roc

Module Contents

Functions

average_roc_curves(, random_state, ax, ...)

Generate receiver-operating characteristic curves for each model in cv_preds.
modelsight.curves.roc.average_roc_curves(cv_preds: Dict[str, modelsight._typing.CVModellingOutput], colors: List[str], model_keys_map: Dict[str, str] = {}, show_ci: bool = True, n_boot: int = 1000, bars_pos: Tuple[int, int, int, int] = (0.41, 0.01, 0.53, 0.3), random_state: modelsight._typing.SeedType = 1234, ax: matplotlib.pyplot.Axes = None, **kwargs) → Tuple[matplotlib.pyplot.Axes, matplotlib.pyplot.Axes, matplotlib.container.BarContainer, Dict[str, Dict[str, float]]][source]

Generate receiver-operating characteristic curves for each model in cv_preds.

Parameters:

  • cv_preds (Dict[str, CVModellingOutput]) – A dictionary containing model-specific cross-validation modelling outputs.

  • colors (List[str]) – A list of colors that will be used to color both curves and bars.

  • model_keys_map (Dict[str, str] (default = {})) – A dictionary mapping model keys to model names.

  • show_ci (bool (default = True)) – Whether bootstrapped confidence bands around curves should be shown.

  • n_boot (int (default = 1000)) – Number of bootstrap iterations for generating confidence bands.

  • bars_pos (Tuple[int, int, int, int]) – A tuple of four integers specifying the shape and position of the bar plot inset. (x position, y position, width, height)

  • random_state (Seed (default = 1234)) – A seed for reproducibility.

  • ax (plt.Axes (default = None)) – Optional Axes to plot curves onto.

  • **kwargs –

    model_names_in_black: List[str]

    Names of models to show in black color, default is []

Returns:

First: the Axes containing the general plot. Second: the axes containing the bar plot inset. Third: the actual BarContainer of the bar plot inset. Fourth: A dictionary containing median (95%CI) area-under-curve over cross-validation

for each model.

Return type:

Tuple[plt.Axes, plt.Axes, matplotlib.container.BarContainer, Dict[str, Dict[str, float]]]