def test_reconstruct_graph(self):
"""
Test the reconstruction of an inputlayer.
"""
graph = gb.create_directed_barbell(10, 10)
random.seed(2)
for u in graph.nodes(data=True):
u[1]['label1'] = int(u[0])
u[1]['label2'] = random.uniform(0.0, 1.0)
gae = GraphAutoEncoder(graph,
learning_rate=0.01,
support_size=[5, 5],
dims=[3, 5, 7, 6, 2],
batch_size=12,
max_total_steps=100,
verbose=True)
l1_struct, graph2 = gae.get_l1_structure(15, show_graph=False)
# check if the nodes of the reconstructed graph is equal to 5
self.assertEqual(
graph2.number_of_nodes(), 5,
"Number of nodes in reconstructed graph does not match with expectations"
)
# check if the returned nodes are correct by summing the node values.
sum_values = np.sum(l1_struct, 1)
self.assertAlmostEqual(
sum_values[0, 1], 120, 4,
"sum of nodes ids in reconstructed graph does not match with expectations"
)
self.assertAlmostEqual(
sum_values[0, 0], 2.399999, 4,
"sum of edges in reconstructed graph does not match with expectations"
)
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
import pickle
import random
#%%
graph = gb.create_directed_barbell(10, 10)
random.seed(2)
for u in graph.nodes(data=True):
u[1]['label1'] = int(u[0])
u[1]['label2'] = random.uniform(0.0, 1.0)
gae = GraphAutoEncoder(graph, learning_rate=0.01, support_size=[5, 5], dims=[3, 5, 7, 6, 2],
batch_size=12, max_total_steps=10, verbose=True, useBN=True)
gae.fit()
embed = gae.calculate_embeddings()
l1_struct, graph2 = gae.get_l1_structure(15, show_graph=True, node_label='feat0')
#%%
# print(l1_struct)
# train_res = {}
# for i in range(len(gae.dims)):
# train_res["l"+str(i+1)] = gae.train_layer(i+1)
# train_res['all'] = gae.train_layer(len(gae.dims), all_layers=True, dropout=None)
# embed = gae.calculate_embeddings()
# filename = '/Users/tonpoppe/workspace/GraphCase/data/model1'
# gae.save_model(filename)
# gae2 = GraphAutoEncoder(graph, learning_rate=0.01, support_size=[5, 5], dims=[3, 5, 7, 6, 2],
# batch_size=12, max_total_steps=100, verbose=True)
2,
weight=1)
color_dict = {0: 'red', 1: 'lightblue', 2: 'lightgreen'}
for node in nt.nodes:
node["color"] = color_dict[length_dict[node['id']]]
node['shape'] = 'circle'
for edge in nt.edges:
edge['label'] = round(edge['weight'], 2)
nt.toggle_physics(False)
return nt
nt = plot_node(graph, 6)
nt.show(ROOT_FOLDER + "/temp/nx.html")
#%%
df, _, pv_graph = gae.get_l1_structure(6, node_label='feat0', get_pyvis=True)
# pv_graph.toggle_physics(False)
pv_graph.show(ROOT_FOLDER + "/temp/nx2.html")
pd_df = pd.DataFrame(data=np.squeeze(df),
columns=["edge", 'node_id', "label2"])
# %%
# nt = net.Network(directed=True, notebook=True)
# # populates the nodes and edges data structures
# nt.from_nx(graph)
# nt.set_edge_smooth('dynamic')
# nt.show("nx.html")
# %%