# Input data paths
dataset = "MUTAG"
corpus_data_dir = "data/" + dataset
# Desired output paths
output_embedding_fh = "Graph2Vec_Embeddings.json"
# Hyper parameters
wl_depth = 2
min_count_patterns = 0 # min number of occurrences to be considered in vocabulary of subgraph patterns
#######
# Step 1 Create corpus data for neural language model
# We keep permanent files for sake of deeper post studies and testing
#######
graph_files = utils.get_files(corpus_data_dir, ".gexf", max_files=0)
wl_corpus(graph_files, wl_depth)
extension = ".wld" + str(wl_depth) # Extension of the graph document
######
# Step 2 Train a neural language model to learn distributed representations
# of the graphs directly or of its substructures. Here we learn it directly
# for an example of the latter check out the DGK models.
######
# Instantiate a PV-DBOW trainer to learn distributed reps directly.
trainer = InMemoryTrainer(corpus_dir=corpus_data_dir,
extension=extension,
max_files=0,
output_fh=output_embedding_fh,
emb_dimension=32,
batch_size=128,
import pandas
import geometric2dr.embedding_methods.utils as utils
# Setup parameters
perf_folder = "DGK_WL_Performance_MUTAG"
dgk, mode, performance, dataset = perf_folder.strip().split("_")
if mode == "GK":
# Dataframe setup
data = []
header = [
"dataset", "num_graphlet", "sample_size", "emb_dimension",
"batch_size", "epochs", "run", "accuracy", "std"
]
perf_files = utils.get_files(perf_folder, "", max_files=0)
for perf_file in perf_files:
perf_file_basename = os.path.basename(perf_file)
dataset, num_graphlet, sample_size, emb_dimension, batch_size, epochs, run = perf_file_basename.strip(
).split("_")
print(perf_file_basename.strip().split("_"))
# Get the accuracy and the std in it
with open(perf_file, "r") as fh:
lines = fh.readlines()
for line in lines:
mean_acc, std = line.strip().split(",")
mean_acc = float(mean_acc)
std = float(std)
graph = nx.read_gexf(file_handle)
adj_matrix = nx.to_numpy_matrix(graph)
return graph, adj_matrix
dataset = "MUTAG"
path_to_gexf_data = "data/"
graph_class_labels_fh = path_to_gexf_data + dataset + ".Labels"
dataset_path = path_to_gexf_data + dataset
# Yanardag style dataset
data = {}
labels = []
graph_files = {}
graph_files = utils.get_files(dataset_path, extension=".gexf", max_files=0)
label_tuples = utils.get_class_labels_tuples(graph_files,
graph_class_labels_fh)
graph_classes = np.array(
[y for z, y in sorted(label_tuples, key=lambda x: x[0])])
data['labels'] = graph_classes
gf = graph_files[0]
graph_data = {}
for gf in graph_files:
gindex = int(os.path.basename(gf).split(".")[0]) - 1
nx_graph, adj_matrix = load_graph(gf)
graph_data[gindex] = {}
for node_string in nx_graph.nodes():
corpus_data_dir = "data/" + dataset
class_labels_fh = data_path + dataset + ".Labels"
if method == "graph2vec":
embeddings_folder = "Graph2vec_Embeddings_" + dataset
csv_fh = method + "_" + dataset + "_results.csv"
csv_fh_avg = method + "_" + dataset + "fullCV_results.csv"
# Dataframe setup
data = []
header = [
"dataset", "wl_depth", "embedding_dimension", "batch_size", "epochs",
"initial_lr", "run", "accuracy", "std"
]
# if method == "graph2vec"
embedding_files = utils.get_files(embeddings_folder, "", max_files=0)
for embedding_file in embedding_files:
embedding_file_basename = os.path.basename(embedding_file)
dataset, wl_depth, embedding_dimension, batch_size, epochs, initial_lr, run = embedding_file_basename.split(
"_")
print(embedding_file_basename.strip().split("_"))
extension = ".wld" + wl_depth
classify_scores = cross_val_accuracy(
corpus_dir=corpus_data_dir,
extension=extension,
embedding_fname=embedding_file,
class_labels_fname=class_labels_fh)
mean_acc, std_dev = classify_scores
print("Mean accuracy using 10 cross fold accuracy: %s with std %s" %
