def print_evaluate(A_matrix,sampled_graph): stats = utils.compute_graph_statistics(sampled_graph) sps_truth = utils.sp(A_matrix) sps_gen = utils.sp(sampled_graph) stats['sp_emd']= utils.emd(sps_truth,sps_gen) s = utils.specGap(A_matrix) stats['spec_gap']=(s-utils.specGap(sampled_graph))**2 print(stats)
def gen_graphs(X_from_walks, target):
X = genExpected_fromWalks(X_from_walks, target.sum())
print(X)
sps_truth = utils.sp(target)
sp_emds = []
sgl2s = []
for i in range(20):
sampled_graph = gnp(X)
sps_gen = utils.sp(sampled_graph)
sp_emd = utils.emd(sps_truth, sps_gen)
sgl2 = (utils.specGap(target) - utils.specGap(sampled_graph))**2
sp_emds.append(sp_emd)
sgl2s.append(sgl2)
return sp_emds, sgl2s
def global_comp(A, X, sps_truth, spec):
sp_emds = []
specs = []
ccs = []
for i in range(100):
sampled_graph = gnp(X)
sps_gen = utils.sp(sampled_graph)
sp_emds.append(utils.emd(sps_truth, sps_gen))
specs.append((spec - utils.specGap(sampled_graph))**2)
ccs.append(3 * utils.statistics_triangle_count(sampled_graph) /
utils.statistics_claw_count(sampled_graph))
stats = {}
stats['shortest path emds'] = sp_emds
stats['spec gaps'] = specs
stats['clustering coefficients'] = ccs
print('Shortest path')
print(np.mean(sp_emds))
print(np.std(sp_emds))
print('Specs')
print(np.mean(specs))
print(np.std(specs))
print('Clusterig Coefficient')
print(np.mean(ccs))
print(np.std(ccs))
print('True CC')
tc = 3 * utils.statistics_triangle_count(
np.array(A)) / utils.statistics_claw_count(np.array(A))
print(tc)
print('ABS diff')
print(tc - np.mean(ccs))
return stats
def graphEval(X, truth_spec, true_sp, true_cc, true_dd, true_bc):
sp_emd_cur = []
cc_emd_cur = []
dd_emd_cur = []
assorts_cur = []
spec_l2_cur = []
spec_l2_lin_cur = []
bc_emd_cur = []
for j in range(20):
A = gnp(X)
G = nx.from_numpy_matrix(A)
print(nx.is_connected(G))
if not nx.is_connected(G):
Gc = max(nx.connected_component_subgraphs(G), key=len)
print(len(Gc.nodes()))
sp = utils.sp(A)
cc = utils.cc(A)
dd = utils.degree_sequence(A)
spec_weight_l2 = l2_exp_weight(truth_spec, utils.spectrum(A))
spec_weight_l2_lin = l2_lin_weight(truth_spec, utils.spectrum(A))
bc = sorted(nx.betweenness_centrality(G).values())
sp_emd_cur.append(utils.emd(sp, true_sp))
cc_emd_cur.append(utils.emd(cc, true_cc))
dd_emd_cur.append(utils.emd(dd, true_dd))
assorts_cur.append(nx.degree_assortativity_coefficient(G))
spec_l2_cur.append(spec_weight_l2)
spec_l2_lin_cur.append(spec_weight_l2_lin)
bc_emd_cur.append(utils.emd(bc, true_bc))
return np.mean(sp_emd_cur), np.mean(cc_emd_cur), np.mean(
dd_emd_cur), np.mean(assorts_cur), np.mean(spec_l2_cur), np.mean(
bc_emd_cur), np.mean(spec_l2_lin_cur)
def global_comp(A,X,sps_truth,spec):
sp_emds = []
specs = []
for i in range(100):
sampled_graph = gnp(X)
sps_gen = utils.sp(sampled_graph)
sp_emds.append(utils.emd(sps_truth,sps_gen))
specs.append((spec-utils.specGap(sampled_graph))**2)
return np.mean(sp_emds), np.std(sp_emds), np.mean(specs), np.std(specs)
def return_node(self, phrase):
non_stop_phrase = ' '.join([token.text for token in utils.sp(phrase)])
if len(non_stop_phrase) > 1:
phrase = non_stop_phrase
if self.node_index is None:
self.add_node(phrase)
nearest_neighbor = self.node_index.knn_query(utils.model([phrase]))
if nearest_neighbor != []:
closest_neighbor, closest_distance = nearest_neighbor
if closest_neighbor[0] == []:
self.add_node(phrase)
return phrase
if closest_distance[0][0] > self.distance_threshold:
self.add_node(phrase)
return phrase
return self.phrase_corpus[closest_neighbor[0][0]]
for [u, v] in valid:
trueScores.append(A[int(u)][int(v)])
predScores.append(X[int(u)][int(v)])
auc = roc_auc_score(trueScores, predScores)
ap = average_precision_score(trueScores, predScores)
return auc, ap
G = nx.read_gml('../data/football.gml')
_A_obs = nx.adjacency_matrix(G)
A_matrix = _A_obs.todense()
valid_edges = np.loadtxt('plots/football_val_edges.txt').tolist()
valid_nonEdges = np.loadtxt('plots/football_val_non_edges.txt').tolist()
valid = valid_edges + valid_nonEdges
sps_truth = utils.sp(A_matrix)
spec_truth = utils.specGap(A_matrix)
X = np.loadtxt(
'plots/football_walk_em/trainingIteration_1200_expectedGraph.txt')
print('Random Walks Size 16')
global_comp(A_matrix, X, sps_truth, spec_truth)
print(auc_p(X, np.asarray(A_matrix), valid))
X = np.loadtxt(
'plots/football_edge_em_nbs/trainingIteration_3200_expectedGraph.txt')
print('Random Walks Size 2 No BS adj')
global_comp(A_matrix, X, sps_truth, spec_truth)
print(auc_p(X, np.asarray(A_matrix), valid))
X = np.loadtxt(
'plots/football_edge_em_adj_bs/trainingIteration_1200_expectedGraph.txt')
print('Random Walks Size 2 BS adj')
A_full = np.loadtxt(target_path)
N = A_full.shape[0]
truth_spec = utils.spectrum(A_full)
step = 400
k = maxIter / step
sp_emds = []
cc_emds = []
dd_emds = []
assorts = []
spectrum_weighted_distances = []
bc_emds = []
true_sp = utils.sp(A_full)
true_cc = utils.cc(A_full)
true_dd = utils.degree_sequence(A_full)
G_true = nx.from_numpy_matrix(A_full)
true_assort = nx.degree_assortativity_coefficient(G_true)
true_bc = sorted(nx.betweenness_centrality(G_true))
true_assorts = []
#initialize all params
for i in range(start, k + 1):
iterNum = i * step
X = np.loadtxt(path + '/samples_{}.txt'.format(iterNum))
def lemmatize(self, phrase):
return " ".join([word.lemma_ for word in utils.sp(phrase)])