Add graph synthesizer.

gklearn/experiments/papers/PRL_2020/synthesized_graphs_N.py

@@ -0,0 +1,138 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Sep 21 10:34:26 2020
+
+@author: ljia
+"""
+Graph_Kernel_List = ['PathUpToH', 'WLSubtree', 'SylvesterEquation', 'Marginalized', 'ShortestPath', 'Treelet', 'ConjugateGradient', 'FixedPoint', 'SpectralDecomposition', 'CommonWalk'] 
+# Graph_Kernel_List = ['CommonWalk', 'Marginalized', 'SylvesterEquation', 'ConjugateGradient', 'FixedPoint', 'SpectralDecomposition', 'ShortestPath', 'StructuralSP', 'PathUpToH', 'Treelet', 'WLSubtree']
+
+def generate_graphs():
+	from gklearn.utils.graph_synthesizer import GraphSynthesizer
+	gsyzer = GraphSynthesizer()
+	graphs = gsyzer.unified_graphs(num_graphs=1000, num_nodes=20, num_edges=40, num_node_labels=0, num_edge_labels=0, seed=None, directed=False)
+	return graphs
+
+
+def compute_graph_kernel(graphs, kernel_name):
+	import multiprocessing
+	
+	if kernel_name == 'CommonWalk':
+		from gklearn.kernels.commonWalkKernel import commonwalkkernel
+		estimator = commonwalkkernel
+		params = {'compute_method': 'geo', 'weight': 0.1}
+		
+	elif kernel_name == 'Marginalized':
+		from gklearn.kernels.marginalizedKernel import marginalizedkernel
+		estimator = marginalizedkernel
+		params = {'p_quit': 0.5, 'n_iteration': 5, 'remove_totters': False}
+		
+	elif kernel_name == 'SylvesterEquation':
+		from gklearn.kernels.randomWalkKernel import randomwalkkernel
+		estimator = randomwalkkernel
+		params = {'compute_method': 'sylvester', 'weight': 0.1}
+		
+	elif kernel_name == 'ConjugateGradient':
+		from gklearn.kernels.randomWalkKernel import randomwalkkernel
+		estimator = randomwalkkernel
+		from gklearn.utils.kernels import deltakernel, gaussiankernel, kernelproduct
+		import functools
+		mixkernel = functools.partial(kernelproduct, deltakernel, gaussiankernel)
+		sub_kernel = {'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}
+		params = {'compute_method': 'conjugate', 'weight': 0.1, 'node_kernels': sub_kernel, 'edge_kernels': sub_kernel}
+		
+	elif kernel_name == 'FixedPoint':
+		from gklearn.kernels.randomWalkKernel import randomwalkkernel
+		estimator = randomwalkkernel
+		from gklearn.utils.kernels import deltakernel, gaussiankernel, kernelproduct
+		import functools
+		mixkernel = functools.partial(kernelproduct, deltakernel, gaussiankernel)
+		sub_kernel = {'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}
+		params = {'compute_method': 'fp', 'weight': 1e-3, 'node_kernels': sub_kernel, 'edge_kernels': sub_kernel}
+		
+	elif kernel_name == 'SpectralDecomposition':
+		from gklearn.kernels.randomWalkKernel import randomwalkkernel
+		estimator = randomwalkkernel
+		params = {'compute_method': 'spectral', 'sub_kernel': 'geo', 'weight': 0.1}
+		
+	elif kernel_name == 'ShortestPath':
+		from gklearn.kernels.spKernel import spkernel
+		estimator = spkernel
+		from gklearn.utils.kernels import deltakernel, gaussiankernel, kernelproduct
+		import functools
+		mixkernel = functools.partial(kernelproduct, deltakernel, gaussiankernel)
+		sub_kernel = {'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}
+		params = {'node_kernels': sub_kernel}
+		
+	elif kernel_name == 'StructuralSP':
+		from gklearn.kernels.structuralspKernel import structuralspkernel
+		estimator = structuralspkernel
+		from gklearn.utils.kernels import deltakernel, gaussiankernel, kernelproduct
+		import functools
+		mixkernel = functools.partial(kernelproduct, deltakernel, gaussiankernel)
+		sub_kernel = {'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}
+		params = {'node_kernels': sub_kernel, 'edge_kernels': sub_kernel}
+		
+	elif kernel_name == 'PathUpToH':
+		from gklearn.kernels.untilHPathKernel import untilhpathkernel
+		estimator = untilhpathkernel
+		params = {'depth': 5, 'k_func': 'MinMax', 'compute_method': 'trie'}
+		
+	elif kernel_name == 'Treelet':
+		from gklearn.kernels.treeletKernel import treeletkernel
+		estimator = treeletkernel
+		from gklearn.utils.kernels import polynomialkernel
+		import functools
+		sub_kernel = functools.partial(polynomialkernel, d=4, c=1e+8)
+		params = {'sub_kernel': sub_kernel}
+		
+	elif kernel_name == 'WLSubtree':
+		from gklearn.kernels.weisfeilerLehmanKernel import weisfeilerlehmankernel
+		estimator = weisfeilerlehmankernel
+		params = {'base_kernel': 'subtree', 'height': 5}
+		
+	params['n_jobs'] = multiprocessing.cpu_count()
+	params['verbose'] = True
+	results = estimator(graphs, **params)
+	
+	return results[0], results[1]
+
+
+def xp_synthesied_graphs_dataset_size():
+	
+	# Generate graphs.
+	graphs = generate_graphs()
+	
+	# Run and save.
+	import pickle
+	import os
+	save_dir = 'outputs/'
+	if not os.path.exists(save_dir):
+		os.makedirs(save_dir)
+
+	run_times = {}
+	
+	for kernel_name in Graph_Kernel_List:
+		print()
+		print('Kernel:', kernel_name)
+		
+		run_times[kernel_name] = []
+		for num_graphs in [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000]:
+			print()
+			print('Number of graphs:', num_graphs)
+			
+			sub_graphs = [g.copy() for g in graphs[0:num_graphs]]
+			gram_matrix, run_time = compute_graph_kernel(sub_graphs, kernel_name)
+			run_times[kernel_name].append(run_time)
+			
+			pickle.dump(run_times, open(save_dir + 'run_time.' + kernel_name + '.' + str(num_graphs) + '.pkl', 'wb'))
+		
+	# Save all.	
+	pickle.dump(run_times, open(save_dir + 'run_times.pkl', 'wb'))	
+	
+	return
+
+
+if __name__ == '__main__':
+	xp_synthesied_graphs_dataset_size()

gklearn/utils/graph_synthesizer.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Sep 11 18:10:06 2020
+
+@author: ljia
+"""
+import numpy as np
+import networkx as nx
+import random
+
+
+class GraphSynthesizer(object):
+	
+	
+	def __init__(self):
+		pass
+	
+	
+	def unified_graphs(self, num_graphs=1000, num_nodes=100, num_edges=196, num_node_labels=0, num_edge_labels=0, seed=None, directed=False):
+		max_num_edges = int((num_nodes - 1) * num_nodes / 2)
+		if num_edges > max_num_edges:
+			raise Exception('Too many edges.')
+		all_edges = [(i, j) for i in range(0, num_nodes) for j in range(i + 1, num_nodes)] # @todo: optimize. No directed graphs.
+			
+		graphs = []
+		for idx in range(0, num_graphs):
+			g = nx.Graph()
+			if num_node_labels > 0:
+				for i in range(0, num_nodes):
+					node_labels = np.random.randint(0, high=num_node_labels, size=num_nodes)
+					g.add_node(str(i), node_label=node_labels[i])
+			else:
+				for i in range(0, num_nodes):
+					g.add_node(str(i))
+
+			if num_edge_labels > 0:
+				edge_labels = np.random.randint(0, high=num_edge_labels, size=num_edges)				
+				for i in random.sample(range(0, max_num_edges), num_edges):
+					node1, node2 = all_edges[i]
+					g.add_edge(node1, node2, edge_label=edge_labels[i])
+			else:
+				for i in random.sample(range(0, max_num_edges), num_edges):
+					node1, node2 = all_edges[i]
+					g.add_edge(node1, node2)
+		
+			graphs.append(g)
+			
+		return graphs

gklearn/utils/parallel.py

@@ -12,7 +12,7 @@ import sys
 
 def parallel_me(func, func_assign, var_to_assign, itr, len_itr=None, init_worker=None, 
                 glbv=None, method=None, n_jobs=None, chunksize=None, itr_desc='',
-                verbose=2):
+                verbose=True):
     '''
     '''
     if method == 'imap_unordered':
@@ -30,7 +30,7 @@ def parallel_me(func, func_assign, var_to_assign, itr, len_itr=None, init_worker
                     else:
                         chunksize = 100
                 for result in (tqdm(pool.imap_unordered(func, itr, chunksize),
-                    desc=itr_desc, file=sys.stdout) if verbose == 2 else 
+                    desc=itr_desc, file=sys.stdout) if verbose else 
                     pool.imap_unordered(func, itr, chunksize)):
                     func_assign(result, var_to_assign)
             pool.close()
@@ -45,7 +45,7 @@ def parallel_me(func, func_assign, var_to_assign, itr, len_itr=None, init_worker
                     else:
                         chunksize = 100
                 for result in (tqdm(pool.imap_unordered(func, itr, chunksize),
-                    desc=itr_desc, file=sys.stdout) if verbose == 2 else 
+                    desc=itr_desc, file=sys.stdout) if verbose else 
                     pool.imap_unordered(func, itr, chunksize)):
                     func_assign(result, var_to_assign)
             pool.close()