Python sklearn.cluster.k_means() Examples

def test_k_means_non_collapsed():
    # Check k_means with a bad initialization does not yield a singleton
    # Starting with bad centers that are quickly ignored should not
    # result in a repositioning of the centers to the center of mass that
    # would lead to collapsed centers which in turns make the clustering
    # dependent of the numerical unstabilities.
    my_X = np.array([[1.1, 1.1], [0.9, 1.1], [1.1, 0.9], [0.9, 1.1]])
    array_init = np.array([[1.0, 1.0], [5.0, 5.0], [-5.0, -5.0]])
    km = KMeans(init=array_init, n_clusters=3, random_state=42, n_init=1)
    km.fit(my_X)

    # centers must not been collapsed
    assert_equal(len(np.unique(km.labels_)), 3)

    centers = km.cluster_centers_
    assert_true(np.linalg.norm(centers[0] - centers[1]) >= 0.1)
    assert_true(np.linalg.norm(centers[0] - centers[2]) >= 0.1)
    assert_true(np.linalg.norm(centers[1] - centers[2]) >= 0.1) 

def kmeans(xs, k):
    assert xs.ndim == 2
    try:
        from sklearn.cluster import k_means
        _, labels, _ = k_means(xs.astype('float64'), k)
    except ImportError:
        from scipy.cluster.vq import kmeans2
        _, labels = kmeans2(xs, k, missing='raise')
    return labels 

def kmeans(xs, k):
    assert xs.ndim == 2
    try:
        from sklearn.cluster import k_means
        _, labels, _ = k_means(xs.astype('float64'), k)
    except ImportError:
        from scipy.cluster.vq import kmeans2
        _, labels = kmeans2(xs, k, missing='raise')
    return labels 

def kmeans(xs, k):
    assert xs.ndim == 2
    try:
        from sklearn.cluster import k_means
        _, labels, _ = k_means(xs.astype('float64'), k)
    except ImportError:
        from scipy.cluster.vq import kmeans2
        _, labels = kmeans2(xs, k, missing='raise')
    return labels 

def kmeans(xs, k):
    assert xs.ndim == 2
    try:
        from sklearn.cluster import k_means
        _, labels, _ = k_means(xs.astype('float64'), k)
    except ImportError:
        from scipy.cluster.vq import kmeans2
        _, labels = kmeans2(xs, k, missing='raise')
    return labels 

def kmeans(xs, k):
    assert xs.ndim == 2
    try:
        from sklearn.cluster import k_means
        _, labels, _ = k_means(xs.astype('float64'), k)
    except ImportError:
        from scipy.cluster.vq import kmeans2
        _, labels = kmeans2(xs, k, missing='raise')
    return labels 

def kmeans(xs, k):
    assert xs.ndim == 2
    try:
        from sklearn.cluster import k_means
        _, labels, _ = k_means(xs.astype('float64'), k)
    except ImportError:
        from scipy.cluster.vq import kmeans2
        _, labels = kmeans2(xs, k, missing='raise')
    return labels 

def kmeans(xs, k):
    assert xs.ndim == 2
    try:
        from sklearn.cluster import k_means
        _, labels, _ = k_means(xs.astype('float64'), k)
    except ImportError:
        from scipy.cluster.vq import kmeans2
        _, labels = kmeans2(xs, k, missing='raise')
    return labels 

def kmeans(xs, k):
    assert xs.ndim == 2
    try:
        from sklearn.cluster import k_means
        _, labels, _ = k_means(xs.astype('float64'), k)
    except ImportError:
        from scipy.cluster.vq import kmeans2
        _, labels = kmeans2(xs, k, missing='raise')
    return labels 

def _spectral_clustering(self):
        affinity_matrix_ = check_symmetric(self.affinity_matrix_)
        random_state = check_random_state(self.random_state)
        
        laplacian = sparse.csgraph.laplacian(affinity_matrix_, normed=True)
        _, vec = sparse.linalg.eigsh(sparse.identity(laplacian.shape[0]) - laplacian, 
                                     k=self.n_clusters, sigma=None, which='LA')
        embedding = normalize(vec)
        _, self.labels_, _ = cluster.k_means(embedding, self.n_clusters, 
                                             random_state=random_state, n_init=self.n_init) 

def test_k_means(self):
        iris = datasets.load_iris()
        df = pdml.ModelFrame(iris)

        result = df.cluster.k_means(3, random_state=self.random_state)
        expected = cluster.k_means(iris.data, 3, random_state=self.random_state)

        self.assertEqual(len(result), 3)
        self.assert_numpy_array_almost_equal(result[0], expected[0])

        self.assertIsInstance(result[1], pdml.ModelSeries)
        tm.assert_index_equal(result[1].index, df.index)
        tm.assert_numpy_array_equal(result[1].values, expected[1])

        self.assertAlmostEqual(result[2], expected[2]) 

def _kmeans_initialization(self, residuals):
        """Computes k-means with k = 2 to find the initial components (rows or columns) of a new layer/bicluster."""
        _, labels, _ = k_means(residuals, n_clusters=2, n_init=self.initialization_iterations, init='random', n_jobs=1)
        count0, count1 = np.bincount(labels)

        if count0 <= count1:
            return np.where(labels == 0)[0]

        return np.where(labels == 1)[0] 

def test_k_means_function():
    # test calling the k_means function directly
    # catch output
    old_stdout = sys.stdout
    sys.stdout = StringIO()
    try:
        cluster_centers, labels, inertia = k_means(X, n_clusters=n_clusters,
                                                   verbose=True)
    finally:
        sys.stdout = old_stdout
    centers = cluster_centers
    assert_equal(centers.shape, (n_clusters, n_features))

    labels = labels
    assert_equal(np.unique(labels).shape[0], n_clusters)

    # check that the labels assignment are perfect (up to a permutation)
    assert_equal(v_measure_score(true_labels, labels), 1.0)
    assert_greater(inertia, 0.0)

    # check warning when centers are passed
    assert_warns(RuntimeWarning, k_means, X, n_clusters=n_clusters,
                 init=centers)

    # to many clusters desired
    assert_raises(ValueError, k_means, X, n_clusters=X.shape[0] + 1)