Python networkx.clustering() Examples

def test_k5(self):
        G = nx.complete_graph(5)
        assert_equal(nx.transitivity(G), 1.0)
        G.remove_edge(1, 2)
        assert_equal(nx.transitivity(G), 0.875)

    # def test_clustering_transitivity(self):
    #     # check that weighted average of clustering is transitivity
    #     G = nx.complete_graph(5)
    #     G.remove_edge(1,2)
    #     t1=nx.transitivity(G)
    #     (cluster_d2,weights)=nx.clustering(G,weights=True)
    #     trans=[]
    #     for v in G.nodes():
    #         trans.append(cluster_d2[v]*weights[v])
    #     t2=sum(trans)
    #     assert_almost_equal(abs(t1-t2),0) 

def decode_graph(adj, prefix):
    adj = np.asmatrix(adj)
    G = nx.from_numpy_matrix(adj)
    # G.remove_nodes_from(nx.isolates(G))
    print('num of nodes: {}'.format(G.number_of_nodes()))
    print('num of edges: {}'.format(G.number_of_edges()))
    G_deg = nx.degree_histogram(G)
    G_deg_sum = [a * b for a, b in zip(G_deg, range(0, len(G_deg)))]
    print('average degree: {}'.format(sum(G_deg_sum) / G.number_of_nodes()))
    if nx.is_connected(G):
        print('average path length: {}'.format(nx.average_shortest_path_length(G)))
        print('average diameter: {}'.format(nx.diameter(G)))
    G_cluster = sorted(list(nx.clustering(G).values()))
    print('average clustering coefficient: {}'.format(sum(G_cluster) / len(G_cluster)))
    cycle_len = []
    cycle_all = nx.cycle_basis(G, 0)
    for item in cycle_all:
        cycle_len.append(len(item))
    print('cycles', cycle_len)
    print('cycle count', len(cycle_len))
    draw_graph(G, prefix=prefix) 

def _directed_triangles_and_degree_iter(G, nodes=None):
    """ Return an iterator of
    (node, total_degree, reciprocal_degree, directed_triangles).

    Used for directed clustering.

    """
    nodes_nbrs = ((n, G._pred[n], G._succ[n]) for n in G.nbunch_iter(nodes))

    for i, preds, succs in nodes_nbrs:
        ipreds = set(preds) - {i}
        isuccs = set(succs) - {i}

        directed_triangles = 0
        for j in chain(ipreds, isuccs):
            jpreds = set(G._pred[j]) - {j}
            jsuccs = set(G._succ[j]) - {j}
            directed_triangles += sum((1 for k in
                                       chain((ipreds & jpreds),
                                             (ipreds & jsuccs),
                                             (isuccs & jpreds),
                                             (isuccs & jsuccs))))
        dtotal = len(ipreds) + len(isuccs)
        dbidirectional = len(ipreds & isuccs)
        yield (i, dtotal, dbidirectional, directed_triangles) 

def test_k5(self):
        G = nx.complete_graph(5)
        assert_equal(nx.transitivity(G), 1.0)
        G.remove_edge(1, 2)
        assert_equal(nx.transitivity(G), 0.875)

    # def test_clustering_transitivity(self):
    #     # check that weighted average of clustering is transitivity
    #     G = nx.complete_graph(5)
    #     G.remove_edge(1,2)
    #     t1=nx.transitivity(G)
    #     (cluster_d2,weights)=nx.clustering(G,weights=True)
    #     trans=[]
    #     for v in G.nodes():
    #         trans.append(cluster_d2[v]*weights[v])
    #     t2=sum(trans)
    #     assert_almost_equal(abs(t1-t2),0) 

def decode_graph(adj, prefix):
    adj = np.asmatrix(adj)
    G = nx.from_numpy_matrix(adj)
    # G.remove_nodes_from(nx.isolates(G))
    print('num of nodes: {}'.format(G.number_of_nodes()))
    print('num of edges: {}'.format(G.number_of_edges()))
    G_deg = nx.degree_histogram(G)
    G_deg_sum = [a * b for a, b in zip(G_deg, range(0, len(G_deg)))]
    print('average degree: {}'.format(sum(G_deg_sum) / G.number_of_nodes()))
    if nx.is_connected(G):
        print('average path length: {}'.format(nx.average_shortest_path_length(G)))
        print('average diameter: {}'.format(nx.diameter(G)))
    G_cluster = sorted(list(nx.clustering(G).values()))
    print('average clustering coefficient: {}'.format(sum(G_cluster) / len(G_cluster)))
    cycle_len = []
    cycle_all = nx.cycle_basis(G, 0)
    for item in cycle_all:
        cycle_len.append(len(item))
    print('cycles', cycle_len)
    print('cycle count', len(cycle_len))
    draw_graph(G, prefix=prefix) 

def test_cubical(self):
        G = nx.cubical_graph()
        assert_equal(list(nx.clustering(G).values()),
                     [0, 0, 0, 0, 0, 0, 0, 0])
        assert_equal(nx.clustering(G, 1), 0)
        assert_equal(list(nx.clustering(G, [1, 2]).values()), [0, 0])
        assert_equal(nx.clustering(G, 1), 0)
        assert_equal(nx.clustering(G, [1, 2]), {1: 0, 2: 0}) 

def _create_node_feature_matrix(self, graph):
        """
        Calculating the node features.

        Arg types:
            * **graph** *(NetworkX graph)* - The graph of interest.

        Return types:
            * **X** *(NumPy array)* - The node features.
        """
        log_degree = np.array([math.log(graph.degree(node)+1) for node in range(graph.number_of_nodes())]).reshape(-1, 1)
        clustering_coefficient = np.array([nx.clustering(graph, node) for node in range(graph.number_of_nodes())]).reshape(-1, 1)
        X = np.concatenate([log_degree, clustering_coefficient], axis=1)
        return X 

def test_path(self):
        G = nx.path_graph(10, create_using=nx.DiGraph())
        assert_equal(list(nx.clustering(G).values()),
                     [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0])
        assert_equal(nx.clustering(G),
                     {0: 0.0, 1: 0.0, 2: 0.0, 3: 0.0, 4: 0.0,
                      5: 0.0, 6: 0.0, 7: 0.0, 8: 0.0, 9: 0.0}) 

def test_k5(self):
        G = nx.complete_graph(5, create_using=nx.DiGraph())
        assert_equal(list(nx.clustering(G).values()), [1, 1, 1, 1, 1])
        assert_equal(nx.average_clustering(G), 1)
        G.remove_edge(1, 2)
        assert_equal(list(nx.clustering(G).values()),
                     [11. / 12., 1.0, 1.0, 11. / 12., 11. / 12.])
        assert_equal(nx.clustering(G, [1, 4]), {1: 1.0, 4: 11. /12.})
        G.remove_edge(2, 1)
        assert_equal(list(nx.clustering(G).values()),
                     [5. / 6., 1.0, 1.0, 5. / 6., 5. / 6.])
        assert_equal(nx.clustering(G, [1, 4]), {1: 1.0, 4: 0.83333333333333337}) 

def test_triangle_and_edge(self):
        G = nx.cycle_graph(3, create_using=nx.DiGraph())
        G.add_edge(0, 4)
        assert_equal(nx.clustering(G)[0], 1.0 / 6.0) 

def test_clustering(self):
        G = nx.DiGraph()
        assert_equal(list(nx.clustering(G, weight='weight').values()), [])
        assert_equal(nx.clustering(G), {}) 

def test_path(self):
        G = nx.path_graph(10, create_using=nx.DiGraph())
        assert_equal(list(nx.clustering(G, weight='weight').values()),
                     [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0])
        assert_equal(nx.clustering(G, weight='weight'),
                     {0: 0.0, 1: 0.0, 2: 0.0, 3: 0.0, 4: 0.0,
                      5: 0.0, 6: 0.0, 7: 0.0, 8: 0.0, 9: 0.0}) 

def test_triangle_and_edge(self):
        G = nx.cycle_graph(3, create_using=nx.DiGraph())
        G.add_edge(0, 4, weight=2)
        assert_equal(nx.clustering(G)[0], 1.0 / 6.0)
        assert_equal(nx.clustering(G, weight='weight')[0], 1.0 / 12.0) 

def test_clustering(self):
        G = nx.Graph()
        assert_equal(list(nx.clustering(G, weight='weight').values()), [])
        assert_equal(nx.clustering(G), {}) 

def test_path(self):
        G = nx.path_graph(10)
        assert_equal(list(nx.clustering(G, weight='weight').values()),
                     [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0])
        assert_equal(nx.clustering(G, weight='weight'),
                     {0: 0.0, 1: 0.0, 2: 0.0, 3: 0.0, 4: 0.0,
                      5: 0.0, 6: 0.0, 7: 0.0, 8: 0.0, 9: 0.0}) 

def test_cubical(self):
        G = nx.cubical_graph()
        assert_equal(list(nx.clustering(G, weight='weight').values()),
                     [0, 0, 0, 0, 0, 0, 0, 0])
        assert_equal(nx.clustering(G, 1), 0)
        assert_equal(list(nx.clustering(G, [1, 2], weight='weight').values()), [0, 0])
        assert_equal(nx.clustering(G, 1, weight='weight'), 0)
        assert_equal(nx.clustering(G, [1, 2], weight='weight'), {1: 0, 2: 0}) 

def test_k5(self):
        G = nx.complete_graph(5)
        assert_equal(list(nx.clustering(G, weight='weight').values()), [1, 1, 1, 1, 1])
        assert_equal(nx.average_clustering(G, weight='weight'), 1)
        G.remove_edge(1, 2)
        assert_equal(list(nx.clustering(G, weight='weight').values()),
                     [5. / 6., 1.0, 1.0, 5. / 6., 5. / 6.])
        assert_equal(nx.clustering(G, [1, 4], weight='weight'), {1: 1.0, 4: 0.83333333333333337}) 

def test_clustering(self):
        G = nx.Graph()
        assert_equal(list(nx.clustering(G).values()), [])
        assert_equal(nx.clustering(G), {}) 

def test_path(self):
        G = nx.path_graph(10)
        assert_equal(list(nx.clustering(G).values()),
                     [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0])
        assert_equal(nx.clustering(G),
                     {0: 0.0, 1: 0.0, 2: 0.0, 3: 0.0, 4: 0.0,
                      5: 0.0, 6: 0.0, 7: 0.0, 8: 0.0, 9: 0.0}) 

def test_fast_versions_properties_threshold_graphs(self):
        cs = 'ddiiddid'
        G = nxt.threshold_graph(cs)
        assert_equal(nxt.density('ddiiddid'), nx.density(G))
        assert_equal(sorted(nxt.degree_sequence(cs)),
                     sorted(d for n, d in G.degree()))

        ts = nxt.triangle_sequence(cs)
        assert_equal(ts, list(nx.triangles(G).values()))
        assert_equal(sum(ts) // 3, nxt.triangles(cs))

        c1 = nxt.cluster_sequence(cs)
        c2 = list(nx.clustering(G).values())
        assert_almost_equal(sum([abs(c - d) for c, d in zip(c1, c2)]), 0)

        b1 = nx.betweenness_centrality(G).values()
        b2 = nxt.betweenness_sequence(cs)
        assert_true(sum([abs(c - d) for c, d in zip(b1, b2)]) < 1e-14)

        assert_equal(nxt.eigenvalues(cs), [0, 1, 3, 3, 5, 7, 7, 8])

        # Degree Correlation
        assert_true(abs(nxt.degree_correlation(cs) + 0.593038821954) < 1e-12)
        assert_equal(nxt.degree_correlation('diiiddi'), -0.8)
        assert_equal(nxt.degree_correlation('did'), -1.0)
        assert_equal(nxt.degree_correlation('ddd'), 1.0)
        assert_equal(nxt.eigenvalues('dddiii'), [0, 0, 0, 0, 3, 3])
        assert_equal(nxt.eigenvalues('dddiiid'), [0, 1, 1, 1, 4, 4, 7]) 

def test_k5(self):
        G = nx.complete_graph(5)
        assert_equal(list(nx.clustering(G).values()), [1, 1, 1, 1, 1])
        assert_equal(nx.average_clustering(G), 1)
        G.remove_edge(1, 2)
        assert_equal(list(nx.clustering(G).values()),
                     [5. / 6., 1.0, 1.0, 5. / 6., 5. / 6.])
        assert_equal(nx.clustering(G, [1, 4]), {1: 1.0, 4: 0.83333333333333337}) 

def fit(self, graph):
        """
        Fitting a Label Propagation clustering model.

        Arg types:
            * **graph** *(NetworkX graph)* - The graph to be clustered.
        """
        self._set_seed()
        self._check_graph(graph)
        self._graph = graph
        self._create_initial_partition()
        self._set_omega()
        self._set_nodes()
        for _ in range(self.iterations):
            self._do_refinement() 

def basic_stat_extractor(self):
        self.base_features = []
        self.sub_graph_container = {}
        for node in tqdm(range(0,len(self.nodes))):
            sub_g, overall_counts, nebs = inducer(self.graph, node)
            in_counts = len(nx.edges(sub_g))
            self.sub_graph_container[node] = nebs
            deg = nx.degree(sub_g, node)
            trans = nx.clustering(sub_g, node)
            self.base_features.append([in_counts, overall_counts, float(in_counts)/float(overall_counts), float(overall_counts - in_counts)/float(overall_counts),deg, trans])
        self.features = {}
        self.features[0] = np.array(self.base_features)
        print("") 
        del self.base_features 

def _weighted_triangles_and_degree_iter(G, nodes=None, weight='weight'):
    """ Return an iterator of (node, degree, weighted_triangles).

    Used for weighted clustering.

    """
    if weight is None or G.number_of_edges() == 0:
        max_weight = 1
    else:
        max_weight = max(d.get(weight, 1) for u, v, d in G.edges(data=True))
    if nodes is None:
        nodes_nbrs = G.adj.items()
    else:
        nodes_nbrs = ((n, G[n]) for n in G.nbunch_iter(nodes))

    def wt(u, v):
        return G[u][v].get(weight, 1) / max_weight

    for i, nbrs in nodes_nbrs:
        inbrs = set(nbrs) - {i}
        weighted_triangles = 0
        seen = set()
        for j in inbrs:
            seen.add(j)
            # This prevents double counting.
            jnbrs = set(G[j]) - seen
            # Only compute the edge weight once, before the inner inner
            # loop.
            wij = wt(i, j)
            weighted_triangles += sum((wij * wt(j, k) * wt(k, i)) ** (1 / 3)
                                      for k in inbrs & jnbrs)
        yield (i, len(inbrs), 2 * weighted_triangles) 

def test_fast_versions_properties_threshold_graphs(self):
        cs = 'ddiiddid'
        G = nxt.threshold_graph(cs)
        assert_equal(nxt.density('ddiiddid'), nx.density(G))
        assert_equal(sorted(nxt.degree_sequence(cs)),
                     sorted(d for n, d in G.degree()))

        ts = nxt.triangle_sequence(cs)
        assert_equal(ts, list(nx.triangles(G).values()))
        assert_equal(sum(ts) // 3, nxt.triangles(cs))

        c1 = nxt.cluster_sequence(cs)
        c2 = list(nx.clustering(G).values())
        assert_almost_equal(sum([abs(c - d) for c, d in zip(c1, c2)]), 0)

        b1 = nx.betweenness_centrality(G).values()
        b2 = nxt.betweenness_sequence(cs)
        assert_true(sum([abs(c - d) for c, d in zip(b1, b2)]) < 1e-14)

        assert_equal(nxt.eigenvalues(cs), [0, 1, 3, 3, 5, 7, 7, 8])

        # Degree Correlation
        assert_true(abs(nxt.degree_correlation(cs) + 0.593038821954) < 1e-12)
        assert_equal(nxt.degree_correlation('diiiddi'), -0.8)
        assert_equal(nxt.degree_correlation('did'), -1.0)
        assert_equal(nxt.degree_correlation('ddd'), 1.0)
        assert_equal(nxt.eigenvalues('dddiii'), [0, 0, 0, 0, 3, 3])
        assert_equal(nxt.eigenvalues('dddiiid'), [0, 1, 1, 1, 4, 4, 7]) 

def test_clustering(self):
        G = nx.Graph()
        assert_equal(list(nx.clustering(G, weight='weight').values()), [])
        assert_equal(nx.clustering(G), {}) 

def test_path(self):
        G = nx.path_graph(10)
        assert_equal(list(nx.clustering(G, weight='weight').values()),
                     [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0])
        assert_equal(nx.clustering(G, weight='weight'),
                     {0: 0.0, 1: 0.0, 2: 0.0, 3: 0.0, 4: 0.0,
                      5: 0.0, 6: 0.0, 7: 0.0, 8: 0.0, 9: 0.0}) 

def test_k5(self):
        G = nx.complete_graph(5)
        assert_equal(list(nx.clustering(G, weight='weight').values()), [1, 1, 1, 1, 1])
        assert_equal(nx.average_clustering(G, weight='weight'), 1)
        G.remove_edge(1, 2)
        assert_equal(list(nx.clustering(G, weight='weight').values()),
                     [5. / 6., 1.0, 1.0, 5. / 6., 5. / 6.])
        assert_equal(nx.clustering(G, [1, 4], weight='weight'), {1: 1.0, 4: 0.83333333333333337}) 

def test_triangle_and_edge(self):
        G = nx.cycle_graph(3)
        G.add_edge(0, 4, weight=2)
        assert_equal(nx.clustering(G)[0], 1.0 / 3.0)
        assert_equal(nx.clustering(G, weight='weight')[0], 1.0 / 6.0) 

def test_clustering(self):
        G = nx.Graph()
        assert_equal(list(nx.clustering(G).values()), [])
        assert_equal(nx.clustering(G), {})