Beispiel #1
0
def test_bic():
    """
    Expect 3 clusters from a 3 block model
    """
    np.random.seed(3)
    num_sims = 10

    # Generate adjacency and labels
    n = 50
    n_communites = [n, n, n]
    p = np.array([[0.8, 0.3, 0.2], [0.3, 0.8, 0.3], [0.2, 0.3, 0.8]])
    y = np.repeat([1, 2, 3], repeats=n)

    for _ in range(num_sims):
        A = sbm(n=n_communites, p=p)

        # Embed to get latent positions
        ase = AdjacencySpectralEmbed(n_components=5)
        X_hat = ase.fit_transform(A)

        # Compute clusters
        gclust = GaussianCluster(min_components=10)
        gclust.fit(X_hat, y)

        bics = gclust.bic_
        aris = gclust.ari_

        bic_argmin = bics.iloc[:, 0].values.argmin()

        assert_equal(2, bic_argmin)
        # The plus one is to adjust the index by min_components
        assert_allclose(1, aris.iloc[:, 0][bic_argmin + 1])
Beispiel #2
0
def test_ase_three_blocks():
    """
    Expect 3 clusters from a 3 block model
    """
    np.random.seed(3)
    num_sims = 10

    # Generate adjacency and labels
    n = 50
    n_communites = [n, n, n]
    p = np.array([[0.8, 0.3, 0.2], [0.3, 0.8, 0.3], [0.2, 0.3, 0.8]])
    y = np.repeat([1, 2, 3], repeats=n)

    for _ in range(num_sims):
        A = sbm(n=n_communites, p=p)

        # Embed to get latent positions
        ase = AdjacencySpectralEmbed(n_components=5)
        X_hat = ase.fit_transform(A)

        # Compute clusters
        gclust = GaussianCluster(min_components=10)
        gclust.fit(X_hat, y)

        n_components = gclust.n_components_

        # Assert that the three cluster model is the best
        assert_equal(n_components, 3)

        # Asser that we get perfect clustering
        assert_allclose(gclust.ari_.loc[n_components], 1)
Beispiel #3
0
def test_ase_three_blocks():
    """
    Expect 3 clusters from a 3 block model
    """
    np.random.seed(1)

    # Generate adjacency and labels
    n = 50
    n_communites = [n, n, n]
    p = np.array([[0.8, 0.3, 0.2], [0.3, 0.8, 0.3], [0.2, 0.3, 0.8]])
    y = np.repeat([1, 2, 3], repeats=n)

    A = sbm(n=n_communites, p=p)

    # Embed to get latent positions
    ase = AdjacencySpectralEmbed(n_components=5)
    X_hat = ase.fit_transform(A)

    # Compute clusters
    AutoGMM = AutoGMMCluster(max_components=10)
    AutoGMM.fit(X_hat, y)

    n_components = AutoGMM.n_components_

    # Assert that the three cluster model is the best
    assert_equal(n_components, 3)

    # Asser that we get perfect clustering
    assert_allclose(AutoGMM.ari_, 1)
 def test_input_checks(self):
     with self.assertRaises(TypeError):
         ase = AdjacencySpectralEmbed(diag_aug="over 9000")
         ase.fit()
 def test_unconnected_warning(self):
     A = er_nm(100, 10)
     with self.assertWarns(UserWarning):
         ase = AdjacencySpectralEmbed()
         ase.fit(A)