comments added

Author: Aditya Grover

src/main.py

@@ -80,14 +80,20 @@ def read_graph():
 	return G
 
 def learn_embeddings(walks):
-
+	'''
+	Learn embeddings by optimizing the Skipgram objective using SGD.
+	'''
 	walks = [map(str, walk) for walk in walks]
 	model = Word2Vec(walks, size=args.dimensions, window=args.window_size, min_count=0, 
 		workers=args.workers, iter=args.iter)
 	model.save_word2vec_format(args.output)
+	
 	return
 
 def main(args):
+	'''
+	Pipeline for representational learning for all nodes in a graph.
+	'''
 	nx_G = read_graph()
 	G = node2vec.Graph(nx_G, args.directed, args.p, args.q)
 	G.preprocess_transition_probs()

src/node2vec.py

@@ -95,6 +95,7 @@ def simulate_walks(self, num_walks, walk_length):
 			random.shuffle(nodes)
 			for node in nodes:
 				walks.append(self.node2vec_walk(walk_length=walk_length, start_node=node))
+				
 		return walks
 
 	def get_alias_edge(self, src, dst):
@@ -115,6 +116,7 @@ def get_alias_edge(self, src, dst):
 				unnormalized_probs.append(G[dst][dst_nbr]['weight']/q)
 		norm_const = sum(unnormalized_probs)
 		normalized_probs =  [float(u_prob)/norm_const for u_prob in unnormalized_probs]
+
 		return alias_setup(normalized_probs)
 
 	def preprocess_transition_probs(self):