plot.mo.plot_mo

plot.mo.plot_mo(
    target_names,
    combinations,
    pareto,
    y_rf=None,
    pareto_front=False,
    y_best=None,
    y_add=None,
    y_add2=None,
    y_add_color='blue',
    y_add2_color='green',
    title='',
    y_orig=None,
    pareto_front_orig=False,
    pareto_label=False,
    y_rf_color='blue',
    y_best_color='red',
    x_axis_transformation='id',
    y_axis_transformation='id',
    y_best_label='Best',
    y_add_label='Add',
    y_add2_label='Add2',
    filename=None,
    figsize=(9, 6),
)

Generates scatter plots for each combination of two targets from a multi-output prediction while highlighting Pareto optimal points.

Parameters

Name	Type	Description	Default
y_rf	np.ndarray	The predicted target values with shape (n_samples, n_targets).	`None`
target_names	list	A list of target names corresponding to the columns of y_rf.	required
combinations	list	A list of tuples, where each tuple contains the indices of the target combinations to plot.	required
pareto	str	Specifies whether to compute Pareto front based on ‘min’ or ‘max’ criterion.	required
pareto_front	bool	If True, connect Pareto optimal points with a red line for y_rf.	`False`
y_best	np.ndarray	A NumPy array representing the best point to highlight in red. Defaults to None.	`None`
y_add	np.ndarray	A NumPy array representing the additional points to highlight in blue. Defaults to None.	`None`
y_add2	np.ndarray	A NumPy array representing the additional points to highlight in green. Defaults to None.	`None`
y_add_color	str	The color of the additional points. Defaults to “blue”.	`'blue'`
y_add2_color	str	The color of the additional points. Defaults to “green”.	`'green'`
y_best_label	str	The label for the best point. Defaults to “Best”.	`'Best'`
y_add_label	str	The label for the additional points. Defaults to “Add”.	`'Add'`
y_add2_label	str	The label for the additional points. Defaults to “Add2”.	`'Add2'`
title	str	The title of the plot. Defaults to “” (empty string).	`''`
y_orig	np.ndarray	The original target values with shape (n_samples, n_targets). Defaults to None.	`None`
pareto_front_orig	bool	If True, connect Pareto optimal points with a light blue line for y_orig. Defaults to False.	`False`
pareto_label	bool	If True, label Pareto points with their index. Defaults to False.	`False`
y_rf_color	str	The color of the predicted points. Defaults to “blue”.	`'blue'`
y_best_color	str	The color of the best point. Defaults to “red”.	`'red'`
x_axis_transformation	str	Transformation for the x-axis. Options are “id” (linear), “log” (logarithmic), and “loglog” (log-log). Defaults to “id”.	`'id'`
y_axis_transformation	str	Transformation for the y-axis. Options are “id” (linear), “log” (logarithmic), and “loglog” (log-log). Defaults to “id”.	`'id'`
filename	str	If provided, saves the plot to the specified file. Supports “pdf” and “png” formats. Defaults to None.	`None`
figsize	tuple	Figure size (width, height) in inches. Default is (9, 6).	`(9, 6)`

Returns

Name	Type	Description
None	None	Displays or saves the plot.

Examples

>>> from spotoptim.plot.mo import plot_mo
>>> import numpy as np
>>> target_names = ["Target 1", "Target 2"]
>>> combinations = [(0, 1)]
>>> pareto = "min"
>>> y_rf = np.random.rand(100, 2)
>>> y_orig = np.random.rand(100, 2)
>>> plot_mo(target_names, combinations, pareto, y_rf=y_rf, y_orig=y_orig, filename="plot.png")