test_gmm.py 文件源码

def test_aic():
    # Test the aic and bic criteria
    n_samples, n_dim, n_components = 50, 3, 2
    X = rng.randn(n_samples, n_dim)
    SGH = 0.5 * (X.var() + np.log(2 * np.pi))  # standard gaussian entropy

    for cv_type in ['full', 'tied', 'diag', 'spherical']:
        g = mixture.GMM(n_components=n_components, covariance_type=cv_type,
                        random_state=rng, min_covar=1e-7)
        g.fit(X)
        aic = 2 * n_samples * SGH * n_dim + 2 * g._n_parameters()
        bic = (2 * n_samples * SGH * n_dim +
               np.log(n_samples) * g._n_parameters())
        bound = n_dim * 3. / np.sqrt(n_samples)
        assert_true(np.abs(g.aic(X) - aic) / n_samples < bound)
        assert_true(np.abs(g.bic(X) - bic) / n_samples < bound)