def networkSummary(G):
"""Provides summary values about the network
Args:
G (graph)
The network of strains from :func:`~constructNetwork`
Returns:
components (int)
The number of connected components (and clusters)
density (float)
The proportion of possible edges used
transitivity (float)
Network transitivity (triads/triangles)
score (float)
A score of network fit, given by :math:`\mathrm{transitivity} * (1-\mathrm{density})`
"""
component_assignments, component_frequencies = gt.label_components(G)
components = len(component_frequencies)
density = len(list(G.edges())) / (0.5 * len(list(G.vertices())) *
(len(list(G.vertices())) - 1))
transitivity = gt.global_clustering(G)[0]
score = transitivity * (1 - density)
return (components, density, transitivity, score)
def clusteringStats(g):
clustring_vertices = local_clustering(g).a
print("Clusterização")
stats(clustring_vertices)
print("\tGlobal", global_clustering(g)[0])
histogram(np.histogram(clustring_vertices),
"Distribuição de clusterização", "$C_i$", "$C$",
sys.argv[1][:-8] + ".clusterizacao")
edges = []
with open("{}".format(args_main.graph), 'r') as f:
for l in f:
edges.append((l.split("\t")[0], l.split("\t")[2].rstrip("\n")))
g.add_edge_list(edges, hashed=True)
number_of_vertices = len(list(g.vertices()))
number_of_edges = len(list(g.edges()))
print("### STATISTICS ###")
print("\tNumber of vertices: {}".format(number_of_vertices))
print("\tNumber of edges: {}".format(number_of_edges))
clustering_coeff, std_error = gt.global_clustering(g)
avg_degree, avg_degree_std = gt.vertex_average(g, "total")
avg_in_degree, avg_in_degree_std = gt.vertex_average(g, "in")
avg_out_degree, avg_out_degree_std = gt.vertex_average(g, "out")
zero_in_deg = 0
zero_out_deg = 0
isolated_entities = 0
for v in g.vertices():
if v.in_degree() == 0:
zero_in_deg += 1
if v.out_degree() == 0:
zero_out_deg += 1
if v.in_degree() == 0 and v.out_degree() == 0:
isolated_entities += 1
def topology(self):
g = self.arcgraph.copy()
components, chist = gt.label_components(
g, directed=False
) # directed = False because True would look for strongly connected components
self.__plot_component_hist(chist, 'componenthist')
start_components = set()
number_compounds_in_start_components = 0
for c in self.start_compounds:
for v in gt.find_vertex(g, g.vp.compound_ids, c):
start_components.add(components[v])
cg = gt.Graph()
cg.vertex_properties["size"] = cg.new_vertex_property("int", val=10)
for c in start_components:
v = cg.add_vertex()
cg.vp.size[v] = chist[c]
number_compounds_in_start_components += chist[c]
satellites = set()
clustering_coefficient = gt.global_clustering(g)
with open(join(self.statistics_path, "clustering_coefficient.txt"),
'w') as f:
f.write(
str(clustering_coefficient[0]) + '\t' +
str(clustering_coefficient[1]) + '\n')
with open(join(self.statistics_path, "compounds_components.txt"), 'w') as f, \
open(join(self.statistics_path, "component_hist.txt"), 'w') as f2:
for componentid, elem in enumerate(chist):
u = gt.GraphView(g, vfilt=components.a == componentid)
u = gt.Graph(u, prune=True)
f2.write(str(componentid + 1) + '\t' + str(elem) + '\n')
for v in u.vertices():
f.write(
str(componentid + 1) + '\t' + u.vp.compound_ids[v] +
'\t' + u.vp.name[v] + '\n')
if componentid not in start_components:
satellites.add(u.vp.compound_ids[v])
# gt.graph_draw(u, output=join(self.statistics_path, "component{i}.pdf".format(i=componentid)))
targets_in_main_component = self.targets - satellites
targets_in_satellites = self.targets & satellites
with open(join(self.statistics_path, "targets_in_main_component.txt"),
'w') as f:
for c in targets_in_main_component:
compound = self.builder.compounds[c]
f.write(c + '\t' + compound.names[0] + '\n')
with open(join(self.statistics_path, "targets_in_satellites.txt"),
'w') as f:
for c in targets_in_satellites:
compound = self.builder.compounds[c]
f.write(c + '\t' + compound.names[0] + '\n')
with open(
join(self.statistics_path,
"components_with_start_metabolites.txt"), 'w') as f:
for cid in start_components:
f.write(str(cid) + '\n')
p = number_compounds_in_start_components / g.num_vertices() * 100
with open(join(const.MECAT_BASE, "component_table.txt"), 'a') as f:
f.write(self.name + ' & ' + str(len(chist)) + ' & ' +
str(np.amax(chist)) + ' & ' + str(len(start_components)) +
' & ' + str(int(number_compounds_in_start_components)) +
' & ' + str(int(round(p, 0))) + '\%' + '\\\\ \n')
#largest = gt.label_largest_component(g, directed=False)
#gt.graph_draw(g, vertex_fill_color=largest, output=join(self.statistics_path,"largest_component.pdf"))
g.vertex_properties["start_components"] = g.new_vertex_property(
"string", val='white')
for v in g.vertices():
if components[v] in start_components:
g.vp.start_components[v] = 'red'
else:
g.vp.start_components[v] = 'blue'
gt.graph_draw(g,
vertex_fill_color=g.vp.start_components,
output=join('/mnt', 'g', 'LisaDaten', 'Paper2',
'figures', 'arcgraph' + self.name + '.pdf'))
import graph_tool.all as gt
import matplotlib
FILE = '10000vertices.xml.gz'
print('loading ' + FILE + ' graph')
g = gt.load_graph(FILE)
N = len(list(g.vertices()))
M = len(list(g.edges()))
arr = []
for v in g.vertices():
arr.append(v.out_degree())
max_degree = max(arr)
min_degree = min(arr)
avg_degree = np.mean(arr)
std_degree = np.std(arr)
print(str(N) + ' vertices')
print(str(M) + ' edges')
print('Max degree: ' + str(max_degree))
print('Min degree: ' + str(min_degree))
print('Avg degree: ' + str(avg_degree) + ' / S.D.: ' + str(std_degree))
print('Density: ' + str((2.0 * M) / (N * (N - 1.0))))
print('Pseudo-diameter: ' + str(gt.pseudo_diameter(g)[0]))
print('Global clustering: ' + str(gt.global_clustering(g)))
# gt.graph_draw(g, output_size=(5000, 5000), vertex_size=1,
# vcmap=matplotlib.cm.gist_heat_r, output="view.png")
def graph_tool_statistics():
print("loading")
graph = gt.load_graph("graph.graphml")
print("computing")
print(gt.global_clustering(graph))
print(f"L = {L}")
## diameter
d = diameter(g)
print(f"diameter = {d}")
## <k>
avg_degree = L/N if g.is_directed() else 2*L/N
print(f"<k> = {avg_degree}")
## density
p = avg_degree/(N-1)
print(f"p = {p}")
## global clustering
gc = GT.global_clustering(g)[0]
print(f"gc = {gc}")
## average shortest path
avg_sp = avg_shortest_path(g)
print(f"avg shortest path = {avg_sp}")
## giant component size
gcs = giant_component_size(g)
if g.is_directed(): print(f"biggest strong component size = {gcs}")
else: print(f"giant component size = {gcs}")
##########
# Degree #
##########
degrees = g.get_total_degrees(g.get_vertices())
def gb_clus_coef(g):
return gt.global_clustering(g)[0]
#plt.title('Histogram of Degree Distribution\nLargest Component')
plt.xlabel('Degree (log)')
plt.ylabel('Frequency (log)')
plt.savefig("degree_hist_g_friend_LC_ap1.png")
plt.close()
print("\n\nDesciptives: Degree Distribution - done \n")
#-- Clustering Coefficiants (Global) - of Friendship Network--#
if descCCG_bool == True:
print("\nDesciptives: Global Clustering Coefficiants \n")
# coefficient, standard deviation
print('Global Clustering Coefficiants - Friendship Network: ',
gt.global_clustering(
g_friend)) # 0.101803664507653, 0.013292495836611278
print('Global Clustering Coefficiants - Largest Component: ',
gt.global_clustering(
g_friend_LC)) # 0.10158343197387348, 0.013265280343602718
print("\nDesciptives: Global Clustering Coefficiants - done\n")
### Deskriptives Friendship Network - Largest Component specific ###
#-- (Pseudo-) Diameter of Largest Component --#
if descDia_bool == True:
print(
"\n\nDeskriptives Friendship Network - Largest Component specific - (Pseudo-) Diameter\n"
)
else:
size1, size2 = hist[-1], 0
data.append(('size of 1st/2nd component',
'{} ({:.2f}%), {}/({:.2f}%)'.format(
size1, 100 * size1 / g.num_vertices(),
size2, 100 * size2 / g.num_vertices())))
data.append(('min/max/avg degree',
'{}/{}/{:.2f}'.format(int(deg.a.min()),
int(deg.a.max()),
float(deg.a.mean()))))
data.append(('density', '{:.7f}'.format(2 * g.num_edges() / g.num_vertices() / (g.num_vertices() - 1))))
data.append(('clustering coefficient (std)', '{:.2f} ({:.2f})'.format(*global_clustering(g))))
sampled_sources = np.random.permutation(g.num_vertices())[:100]
dist = np.max([pseudo_diameter(g, s)[0] for s in sampled_sources])
data.append(('pseudo diameter', dist))
data.append(('assortativity (std)', '{:.2f} ({:.2f})'.format(
*assortativity(g, 'total'))))
index, col = zip(*data)
s = pd.Series(col, index=index)
print(s.to_string())
# save it somewhere
g.vertex_properties["color_bytype"] = color_bytype
g.vertex_properties["subgraph"] = subgraph
g.vertex_properties["shape"] = shape
for j in range(len(egdays)):
[s, t, link] = egdays[j, [0, 1, 2]]
edge = g.add_edge(g.vertex(int(s)), g.vertex(int(t)))
edge_color[edge] = color_edge_dict[link] #[x for x in color]
edge_label[edge] = link
edge_width[edge] = width_edge_dict[link]
g.edge_properties["edge_color"] = edge_color
g.edge_properties["edge_label"] = edge_label
g.edge_properties["edge_width"] = edge_width
print('global_clustering', gt.global_clustering(g))
print('assortativity out', gt.assortativity(g, "out")) # correlations
print('assortativity in', gt.assortativity(g, "in"))
print('assortativity total', gt.assortativity(g, "total"))
g = gt.GraphView(g)
print('start drawing')
pos_fr = gt.fruchterman_reingold_layout(g, n_iter=1000)
g.vertex_properties["pos_fr"] = pos_fr
control = g.new_edge_property("vector<double>")
for e in g.edges():
d = sqrt(sum((pos_fr[e.source()].a - pos_fr[e.target()].a)**2)) / 5
control[e] = [0.3, d, 0.7, d]
g.edge_properties["control"] = control
