def test_cuttree0(self):
G = graph()
nations_of_the_world(G)
ct = cut_tree( G )
import pdb
pdb.set_trace()
def test_cut_tree(self):
#set up the graph (see example on wikipedia page for Gomory-Hu tree)
gr = graph()
gr.add_nodes([0,1,2,3,4,5])
gr.add_edge((0,1), wt=1)
gr.add_edge((0,2), wt=7)
gr.add_edge((1,3), wt=3)
gr.add_edge((1,2), wt=1)
gr.add_edge((1,4), wt=2)
gr.add_edge((2,4), wt=4)
gr.add_edge((3,4), wt=1)
gr.add_edge((3,5), wt=6)
gr.add_edge((4,5), wt=2)
ct = cut_tree(gr)
#check ct
assert ct[(2,0)] == 8
assert ct[(4,2)] == 6
assert ct[(1,4)] == 7
assert ct[(3,1)] == 6
assert ct[(5,3)] == 8
def test_cut_tree(self):
#set up the graph (see example on wikipedia page for Gomory-Hu tree)
gr = graph()
gr.add_nodes([0, 1, 2, 3, 4, 5])
gr.add_edge((0, 1), wt=1)
gr.add_edge((0, 2), wt=7)
gr.add_edge((1, 3), wt=3)
gr.add_edge((1, 2), wt=1)
gr.add_edge((1, 4), wt=2)
gr.add_edge((2, 4), wt=4)
gr.add_edge((3, 4), wt=1)
gr.add_edge((3, 5), wt=6)
gr.add_edge((4, 5), wt=2)
ct = cut_tree(gr)
#check ct
assert ct[(2, 0)] == 8
assert ct[(4, 2)] == 6
assert ct[(1, 4)] == 7
assert ct[(3, 1)] == 6
assert ct[(5, 3)] == 8
def test_cut_tree_with_random_graph(self):
gr = testlib.new_graph()
ct = cut_tree(gr)
def test_cut_tree_with_empty_graph(self):
gr = graph()
ct = cut_tree(gr)
assert ct == {}
def graph_features(self):
"""Generating topological features including vertice orders for future use."""
gr_nodes = self.gr.nodes()
gr_edges = self.gr.edges()
node_count = len(gr_nodes)
edge_count = len(gr_edges) / 2.0
average_order = 0.0
clustering_coefficient = 0.0
max_order = 0
for each_node in gr_nodes:
#for orders
current_node_order = self.gr.node_order(each_node)
average_order += current_node_order
max_order = max(max_order, current_node_order)
#now for clustering coefficient
direct_neighbors = self.gr.neighbors(each_node)
tmp_v_edge_count = 0.0
tmp_r_edge_count = 0.0
for virtual_edge in itertools.product(direct_neighbors,
direct_neighbors):
if virtual_edge[0] != virtual_edge[1]:
tmp_v_edge_count += 1.0
if self.gr.has_edge(tuple(virtual_edge)):
tmp_r_edge_count += 1.0
if tmp_v_edge_count == 0:
clustering_coefficient += 0.0
else:
clustering_coefficient += (tmp_r_edge_count / tmp_v_edge_count)
clustering_coefficient /= float(node_count)
average_order /= float(node_count)
#for kernel order
cut_dict = cut_tree(self.gr)
cut_places = set(cut_dict.values())
how_many_kernel_orders = list(range(5))
kernel_orders = []
bloods = 0.0
for kernel_tick in how_many_kernel_orders:
if kernel_tick in cut_places:
bloods += 1.0
kernel_orders.append(bloods)
#for redundant edges and missing edges
redundant_edges = 0.0
missing_edges = 0.0
for each_edge in gr_edges:
node0 = each_edge[0]
node1 = each_edge[1]
#find common set of nodes' neighbors
common_set = set(self.gr.neighbors(node0)).intersection(
set(self.gr.neighbors(node1)))
if len(common_set) == 0:
missing_edges += 1.0
elif len(common_set) > 1:
in_cell_edges = list(
itertools.combinations(list(common_set), 2))
cell_judge = True
for cell_edge in in_cell_edges:
if self.gr.has_edge(cell_edge):
cell_judge = False
if cell_judge == False:
redundant_edges += 1.0
if edge_count != 0.0:
redundant_edges /= float(edge_count)
missing_edges /= float(edge_count)
#average edge lenghth
total_length = 0.0
for each_edge in gr_edges:
node0 = each_edge[0]
node1 = each_edge[1]
total_length += sqrt(
sum((self.nodes[node0] - self.nodes[node1])**2))
if len(gr_edges) == 0:
average_length = 0.0
else:
average_length = total_length / float(len(gr_edges))
return [
average_length, node_count, edge_count, average_order, max_order,
redundant_edges, missing_edges
] + kernel_orders
def group(setN, gr, write_mark, minimum_cluster, alpha):
## print gr
## print write_mark
N = len(setN)
## print N
density = zeros(N)
for i in range(N):
distances = 0.0
neighbor_set = gr.neighbors(i)
for each_node in neighbor_set:
tmp_d = setN[i] - setN[each_node]
distances += sqrt(inner(tmp_d, tmp_d))
if distances == 0.0 or len(neighbor_set) == 0:
## print i,N,'in the pool'
## raw_input('ISB..')
distances = 0.0
else:
## print distances,float(len(neighbor_set))
distances = distances / float(len(neighbor_set))
density[i] = 1.0 / pow(1 + distances, 2.0)
density_copy = deepcopy(density)
## print density
#* 1 *
remain_set = set(range(N))
clusters = {}
for i in range(N):
if is_max(i, gr, density):
clusters[i] = i
remain_set.remove(i)
density_copy[i] = -1
## print 'remaining set',len(remain_set)
#* 2 *
while len(remain_set) > 0:
unlabeled_max = argmax(density_copy)
density_copy[unlabeled_max] = -1
#* 3 *
neighbor_set = gr.neighbors(unlabeled_max)
tmp_density = density[neighbor_set]
label_index = neighbor_set[argmax(tmp_density)]
clusters[unlabeled_max] = clusters[label_index]
remain_set.remove(unlabeled_max)
#algorithm 2
#find boundary edges
cluster_centers = clusters.values()
## print len(cluster_centers),cluster_centers
borders = []
for each_edge in gr.edges():
if clusters[each_edge[0]] != clusters[each_edge[1]]:
if each_edge[0] < each_edge[1]:
borders.append(each_edge)
#find big clusters
connected_groups = connected_components(gr)
group_count = len(set(connected_groups.values()))
big_cluster_head = []
tmp_set_appeared = set([])
for head, group_index in connected_groups.items():
if group_index not in tmp_set_appeared:
big_cluster_head.append(head)
tmp_set_appeared.add(group_index)
#construct edge set
heads_tails = accessibility(gr)
head_and_tail = {}
for head, tail in heads_tails.items():
if head in big_cluster_head:
head_and_tail[connected_groups[head]] = tail
#tresholds of the super clusters
Gc = {}
for head, tail in head_and_tail.items():
tmp_tresh = 0.0
count = 0.0
for each_edge in itertools.combinations(tail, 2):
if gr.has_edge(each_edge):
count += 1.0
tmp_tresh += abs(density[each_edge[0]] - density[each_edge[1]])
if count == 0.0:
## print('sigularity')
Gc[head] = 0.0
else:
Gc[head] = alpha * tmp_tresh / count
#* 2 *
## print 'group,tresh',borders,Gc
while len(borders) > 0:
## print borders,'borders'
current_border = borders.pop()
Dab = max(density[current_border[0]], density[current_border[1]])
Dca = density[clusters[current_border[0]]]
Dcb = density[clusters[current_border[1]]]
Gtresh = Gc[connected_groups[current_border[0]]]
## print Dca - Dab,Dcb - Dab,Gtresh,'x'
if connected_groups[current_border[0]] != connected_groups[
current_border[1]]:
raw_input('there be a problem')
if ((Dca - Dab < Gtresh) | (Dcb - Dab < Gtresh)) == False:
clusterA = clusters[current_border[0]]
clusterB = clusters[current_border[1]]
## print gr,'sb'
gr.del_edge(current_border)
tmp_borders = deepcopy(borders)
for each_edge in tmp_borders:
if (clusters[each_edge[0]] == clusterA
and clusters[each_edge[1]] == clusterB) or (
clusters[each_edge[1]] == clusterA
and clusters[each_edge[0]] == clusterB):
## raw_input('del')
gr.del_edge(each_edge)
borders.remove(each_edge)
## out_cast = []
## for i in range(len(setN)):
## if gr.neighbors(i) == 0:
## out_cast.append(i)
## for isolation in out_cast:
## gr.del_node(isolation)
## setN.remove(isolation)
## print len(setN)
## print write_mark
if write_mark:
connected_groups = connected_components(gr)
group_count = len(set(connected_groups.values()))
if minimum_cluster > group_count:
grade = minimum_cluster - group_count
from pygraph.algorithms.minmax import cut_tree
yourcut = cut_tree(gr)
## print 'cut tree',yourcut.values(),grade
yourset = yourcut.values()
for i in range(grade):
print min(yourset)
yourset.remove(min(yourset))
max_degree = min(yourset)
## print max_degree,yourset
for edge_name, cut_degree in yourcut.items():
if (cut_degree < max_degree + 1) and (gr.has_edge(edge_name)):
## print edge_name
gr.del_edge(edge_name)
print 'cluster break x 1', edge_name
def test_cut_tree_with_random_graph(self):
gr = testlib.new_graph()
ct = cut_tree(gr)
def test_cut_tree_with_empty_graph(self):
gr = graph()
ct = cut_tree(gr)
assert ct == {}
