SVARMIQ¶

Stratified Monte Carlo with coalition-size and intersection stratification using SVARMIQ Kolpaczki et al.[1].

from __future__ import annotations

import numpy as np

import shapiq

N_PLAYERS = 8
BUDGET = 200
feature_names = [f"x{i}" for i in range(N_PLAYERS)]

weights = np.array([0.4, 0.3, 0.2, 0.1, 0.05, -0.1, -0.2, -0.3])


def game_fun(coalitions: np.ndarray) -> np.ndarray:
    coalitions = np.atleast_2d(coalitions)
    return (coalitions @ weights) + 0.5 * coalitions[:, 0] * coalitions[:, 1]

Approximate k-SII values¶

approximator = shapiq.SVARMIQ(n=N_PLAYERS, max_order=2, index="k-SII", random_state=42)
iv = approximator.approximate(BUDGET, game_fun)
print(iv)

InteractionValues(
    index=k-SII, max_order=2, min_order=0, estimated=True, estimation_budget=200,
    n_players=8, baseline_value=0.0,
    Top 10 interactions:
        (0, 1): 0.4368672342940366
        (0,): 0.3668436852655883
        (1,): 0.28244088761370334
        (2,): 0.21625591345499107
        (3, 4): 0.10775379099438982
        (1, 7): 0.10505728162931052
        (3,): 0.08900003971389242
        (2, 4): -0.12034960018526039
        (6,): -0.1981371729626564
        (7,): -0.29044365683106815
)

Force plot¶

iv.plot_force(feature_names=feature_names)

Network plot¶

iv.plot_network(feature_names=feature_names)

References¶

Total running time of the script: (0 minutes 0.439 seconds)