Update MedianPreimageGenerator and MedianGraphEstimator for symbolic-labeled graphs and edit cost "CONSTANT".

.gitignore

@@ -29,6 +29,7 @@ gklearn/kernels/*_sym.py
 
 gklearn/preimage/*
 !gklearn/preimage/*.py
+!gklearn/preimage/experiments/*.py
 
 __pycache__
 ##*#

gklearn/ged/median/median_graph_estimator.py

@@ -70,6 +70,7 @@ class MedianGraphEstimator(object):
 		self.__num_increase_order = 0
 		self.__num_converged_descents = 0
 		self.__state = AlgorithmState.TERMINATED
+		self.__label_names = {}
 		
 		if ged_env is None:
 			raise Exception('The GED environment pointer passed to the constructor of MedianGraphEstimator is null.')
@@ -551,6 +552,7 @@ class MedianGraphEstimator(object):
 		self.__init_type_increase_order = 'K-MEANS++'
 		self.__max_itrs_increase_order = 10
 		self.__print_to_stdout = 2
+		self.__label_names = {}
 		
 		
 	def __construct_initial_medians(self, graph_ids, timer, initial_medians):
@@ -824,19 +826,49 @@ class MedianGraphEstimator(object):
 		for node in g.nodes:
 			cost += 0
 			
+			
+	def set_label_names(self, node_labels=[], edge_labels=[], node_attrs=[], edge_attrs=[]):
+		self.__label_names = {'node_labels': node_labels, 'edge_labels': edge_labels,
+						'node_attrs': node_attrs, 'edge_attrs': edge_attrs}
+			
 	
 	def __get_median_node_label(self, node_labels):
-		if True:
+		if len(self.__label_names['node_labels']) > 0:
+			return self.__get_median_label_symbolic(node_labels)
+		elif len(self.__label_names['node_attrs']) > 0:
 			return self.__get_median_label_nonsymbolic(node_labels)
 		else:
-			return self.__get_median_node_label_symbolic(node_labels)
+			raise Exception('Node label names are not given.')
 		
 			
 	def __get_median_edge_label(self, edge_labels):
-		if True:
+		if len(self.__label_names['edge_labels']) > 0:
+			return self.__get_median_label_symbolic(edge_labels)
+		elif len(self.__label_names['edge_attrs']) > 0:
 			return self.__get_median_label_nonsymbolic(edge_labels)
 		else:
-			return self.__get_median_edge_label_symbolic(edge_labels)
+			raise Exception('Edge label names are not given.')
+			
+			
+	def __get_median_label_symbolic(self, labels):
+		# Construct histogram.
+		hist = {}
+		for label in labels:
+			label = tuple([kv for kv in label.items()]) # @todo: this may be slow.
+			if label not in hist:
+				hist[label] = 1
+			else:
+				hist[label] += 1
+		
+		# Return the label that appears most frequently.
+		best_count = 0
+		median_label = {}
+		for label, count in hist.items():
+			if count > best_count:
+				best_count = count
+				median_label = {kv[0]: kv[1] for kv in label}
+				
+		return median_label
 		
 		
 	def __get_median_label_nonsymbolic(self, labels):
@@ -896,14 +928,10 @@ class MedianGraphEstimator(object):
 			for key, val in median.items():
 				median_label[key] = str(val)
 			return median_label
-		
-	
-	def __get_median_node_label_symbolic(self, node_labels):
-		pass
 
 		
-	def __get_median_edge_label_symbolic(self, edge_labels):
-		pass
+# 	def __get_median_edge_label_symbolic(self, edge_labels):
+# 		pass
 	
 	
 # 	def __get_median_edge_label_nonsymbolic(self, edge_labels):

gklearn/ged/median/utils.py

@@ -9,6 +9,10 @@ Created on Wed Apr  1 15:12:31 2020
 def constant_node_costs(edit_cost_name):
 	if edit_cost_name == 'NON_SYMBOLIC' or edit_cost_name == 'LETTER2' or edit_cost_name == 'LETTER':
 		return False
+	elif edit_cost_name == 'CONSTANT':
+		return True
+	else:
+		raise Exception('Can not recognize the given edit cost. Possible edit costs include: "NON_SYMBOLIC", "LETTER", "LETTER2", "CONSTANT".')
 #	 elif edit_cost_name != '':
 # # 		throw ged::Error("Invalid dataset " + dataset + ". Usage: ./median_tests <AIDS|Mutagenicity|Letter-high|Letter-med|Letter-low|monoterpenoides|SYNTHETICnew|Fingerprint|COIL-DEL>");
 #		 return False

gklearn/ged/util/util.py

@@ -58,7 +58,8 @@ def compute_geds(graphs, options={}, parallel=False):
 	ged_env.init_method()
 
 	# compute ged.
-	neo_options = {'edit_cost': options['edit_cost'], 
+	neo_options = {'edit_cost': options['edit_cost'],
+				'node_labels': options['node_labels'], 'edge_labels': options['edge_labels'], 
 				'node_attrs': options['node_attrs'], 'edge_attrs': options['edge_attrs']}
 	ged_mat = np.zeros((len(graphs), len(graphs)))
 	if parallel:
@@ -147,12 +148,18 @@ def get_nb_edit_operations(g1, g2, forward_map, backward_map, edit_cost=None, **
 		edge_attrs = kwargs.get('edge_attrs', [])
 		return get_nb_edit_operations_nonsymbolic(g1, g2, forward_map, backward_map, 
 											node_attrs=node_attrs, edge_attrs=edge_attrs)
+	elif edit_cost == 'CONSTANT':
+		node_labels = kwargs.get('node_labels', [])
+		edge_labels = kwargs.get('edge_labels', [])
+		return get_nb_edit_operations_symbolic(g1, g2, forward_map, backward_map, 
+										 node_labels=node_labels, edge_labels=edge_labels)
 	else: 
 		return get_nb_edit_operations_symbolic(g1, g2, forward_map, backward_map)
 	
 
-def get_nb_edit_operations_symbolic(g1, g2, forward_map, backward_map):
-	"""Compute the number of each edit operations.
+def get_nb_edit_operations_symbolic(g1, g2, forward_map, backward_map,
+									node_labels=[], edge_labels=[]):
+	"""Compute the number of each edit operations for symbolic-labeled graphs.
 	"""
 	n_vi = 0
 	n_vr = 0
@@ -165,8 +172,13 @@ def get_nb_edit_operations_symbolic(g1, g2, forward_map, backward_map):
 	for i, map_i in enumerate(forward_map):
 		if map_i == np.inf:
 			n_vr += 1
-		elif g1.node[nodes1[i]]['atom'] != g2.node[map_i]['atom']:
-			n_vs += 1
+		else:
+			for nl in node_labels:
+				label1 = g1.nodes[nodes1[i]][nl]
+				label2 = g2.nodes[map_i][nl]
+				if label1 != label2:
+					n_vs += 1
+					break
 	for map_i in backward_map:
 		if map_i == np.inf:
 			n_vi += 1
@@ -185,15 +197,21 @@ def get_nb_edit_operations_symbolic(g1, g2, forward_map, backward_map):
 		elif (forward_map[idx1], forward_map[idx2]) in g2.edges():
 			nb_edges2_cnted += 1
 			# edge labels are different.
-			if g2.edges[((forward_map[idx1], forward_map[idx2]))]['bond_type'] \
-				!= g1.edges[(n1, n2)]['bond_type']:
+			for el in edge_labels:
+				label1 = g2.edges[((forward_map[idx1], forward_map[idx2]))][el]
+				label2 = g1.edges[(n1, n2)][el]
+				if label1 != label2:
 					n_es += 1
+					break
 		elif (forward_map[idx2], forward_map[idx1]) in g2.edges():
 			nb_edges2_cnted += 1
 			# edge labels are different.
-			if g2.edges[((forward_map[idx2], forward_map[idx1]))]['bond_type'] \
-				!= g1.edges[(n1, n2)]['bond_type']:
-					n_es += 1				
+			for el in edge_labels:
+				label1 = g2.edges[((forward_map[idx2], forward_map[idx1]))][el]
+				label2 = g1.edges[(n1, n2)][el]
+				if label1 != label2:
+					n_es += 1
+					break
 		# corresponding nodes are in g2, however the edge is removed.
 		else:
 			n_er += 1

gklearn/preimage/median_preimage_generator.py

@@ -262,6 +262,8 @@ class MedianPreimageGenerator(PreimageGenerator):
 		self.__edit_cost_constants = self.__init_ecc
 		options = self.__ged_options.copy()
 		options['edit_cost_constants'] = self.__edit_cost_constants # @todo
+		options['node_labels'] = self._dataset.node_labels
+		options['edge_labels'] = self._dataset.edge_labels
 		options['node_attrs'] = self._dataset.node_attrs
 		options['edge_attrs'] = self._dataset.edge_attrs
 		ged_vec_init, ged_mat, n_edit_operations = compute_geds(graphs, options=options, parallel=self.__parallel)
@@ -302,6 +304,8 @@ class MedianPreimageGenerator(PreimageGenerator):
 			# compute new GEDs and numbers of edit operations.
 			options = self.__ged_options.copy() # np.array([self.__edit_cost_constants[0], self.__edit_cost_constants[1], 0.75])
 			options['edit_cost_constants'] = self.__edit_cost_constants # @todo
+			options['node_labels'] = self._dataset.node_labels
+			options['edge_labels'] = self._dataset.edge_labels
 			options['node_attrs'] = self._dataset.node_attrs
 			options['edge_attrs'] = self._dataset.edge_attrs
 			ged_vec, ged_mat, n_edit_operations = compute_geds(graphs, options=options, parallel=self.__parallel)
@@ -451,7 +455,7 @@ class MedianPreimageGenerator(PreimageGenerator):
 				nb_cost_mat_new = nb_cost_mat[:,[0,1,3,4,5]]
 				x = cp.Variable(nb_cost_mat_new.shape[1])
 				cost_fun = cp.sum_squares(nb_cost_mat_new * x - dis_k_vec)
-				constraints = [x >= [0.001 for i in range(nb_cost_mat_new.shape[1])],
+				constraints = [x >= [0.01 for i in range(nb_cost_mat_new.shape[1])],
 							   np.array([1.0, 1.0, -1.0, 0.0, 0.0]).T@x >= 0.0]
 				prob = cp.Problem(cp.Minimize(cost_fun), constraints)
 				self.__execute_cvx(prob)
@@ -524,17 +528,17 @@ class MedianPreimageGenerator(PreimageGenerator):
 								   np.array([1.0, 1.0, -1.0, 0.0, 0.0, 0.0]).T@x >= 0.0,
 								   np.array([0.0, 0.0, 0.0, 1.0, 1.0, -1.0]).T@x >= 0.0]
 					prob = cp.Problem(cp.Minimize(cost_fun), constraints)
-					prob.solve()
+					self.__execute_cvx(prob)
 					edit_costs_new = x.value
 					residual = np.sqrt(prob.value)
 				elif is_n_attr and not is_e_attr:
 					nb_cost_mat_new = nb_cost_mat[:,[0,1,2,3,4]]
 					x = cp.Variable(nb_cost_mat_new.shape[1])
 					cost_fun = cp.sum_squares(nb_cost_mat_new * x - dis_k_vec)
-					constraints = [x >= [0.001 for i in range(nb_cost_mat_new.shape[1])],
+					constraints = [x >= [0.01 for i in range(nb_cost_mat_new.shape[1])],
 								   np.array([1.0, 1.0, -1.0, 0.0, 0.0]).T@x >= 0.0]
 					prob = cp.Problem(cp.Minimize(cost_fun), constraints)
-					self.execute_cvx(prob)
+					self.__execute_cvx(prob)
 					edit_costs_new = np.concatenate((x.value, np.array([0.0])))
 					residual = np.sqrt(prob.value)
 				elif not is_n_attr and is_e_attr:
@@ -544,7 +548,7 @@ class MedianPreimageGenerator(PreimageGenerator):
 					constraints = [x >= [0.01 for i in range(nb_cost_mat_new.shape[1])],
 								   np.array([0.0, 0.0, 1.0, 1.0, -1.0]).T@x >= 0.0]
 					prob = cp.Problem(cp.Minimize(cost_fun), constraints)
-					prob.solve()
+					self.__execute_cvx(prob)
 					edit_costs_new = np.concatenate((x.value[0:2], np.array([0.0]), x.value[2:]))
 					residual = np.sqrt(prob.value)
 				else:
@@ -553,10 +557,20 @@ class MedianPreimageGenerator(PreimageGenerator):
 					cost_fun = cp.sum_squares(nb_cost_mat_new * x - dis_k_vec)
 					constraints = [x >= [0.01 for i in range(nb_cost_mat_new.shape[1])]]
 					prob = cp.Problem(cp.Minimize(cost_fun), constraints)
-					prob.solve()
+					self.__execute_cvx(prob)
 					edit_costs_new = np.concatenate((x.value[0:2], np.array([0.0]), 
 													 x.value[2:], np.array([0.0])))
 					residual = np.sqrt(prob.value)
+		elif self.__ged_options['edit_cost'] == 'CONSTANT': # @todo: node/edge may not labeled.
+			x = cp.Variable(nb_cost_mat.shape[1])
+			cost_fun = cp.sum_squares(nb_cost_mat * x - dis_k_vec)
+			constraints = [x >= [0.01 for i in range(nb_cost_mat.shape[1])],
+						   np.array([1.0, 1.0, -1.0, 0.0, 0.0, 0.0]).T@x >= 0.0,
+						   np.array([0.0, 0.0, 0.0, 1.0, 1.0, -1.0]).T@x >= 0.0]
+			prob = cp.Problem(cp.Minimize(cost_fun), constraints)
+			self.__execute_cvx(prob)
+			edit_costs_new = x.value
+			residual = np.sqrt(prob.value)
 		else:
 	#	# method 1: simple least square method.
 	#	edit_costs_new, residual, _, _ = np.linalg.lstsq(nb_cost_mat, dis_k_vec,
@@ -588,7 +602,7 @@ class MedianPreimageGenerator(PreimageGenerator):
 						   np.array([1.0, 1.0, -1.0, 0.0, 0.0, 0.0]).T@x >= 0.0,
 						   np.array([0.0, 0.0, 0.0, 1.0, 1.0, -1.0]).T@x >= 0.0]
 			prob = cp.Problem(cp.Minimize(cost_fun), constraints)
-			prob.solve()
+			self.__execute_cvx(prob)
 			edit_costs_new = x.value
 			residual = np.sqrt(prob.value)
 		
@@ -647,6 +661,10 @@ class MedianPreimageGenerator(PreimageGenerator):
 		
 		# Select the GED algorithm.
 		mge.set_options(mge_options_to_string(options))
+		mge.set_label_names(node_labels=self._dataset.node_labels, 
+					  edge_labels=self._dataset.edge_labels, 
+					  node_attrs=self._dataset.node_attrs, 
+					  edge_attrs=self._dataset.edge_attrs)
 		mge.set_init_method(self.__ged_options['method'], ged_options_to_string(self.__ged_options))
 		mge.set_descent_method(self.__ged_options['method'], ged_options_to_string(self.__ged_options))
 		

gklearn/preimage/utils.py

@@ -37,7 +37,7 @@ def generate_median_preimages_by_class(ds_name, mpg_options, kernel_options, ged
 	dataset_all.trim_dataset(edge_required=edge_required)
 	if irrelevant_labels is not None:
 		dataset_all.remove_labels(**irrelevant_labels)
-# 	dataset_all.cut_graphs(range(0, 100))
+# 	dataset_all.cut_graphs(range(0, 10))
 	datasets = split_dataset_by_target(dataset_all)
 
 	if save_results:

gklearn/utils/dataset.py

@@ -67,24 +67,7 @@ class Dataset(object):
 		
 	def load_predefined_dataset(self, ds_name):
 		current_path = os.path.dirname(os.path.realpath(__file__)) + '/'
-		if ds_name == 'Letter-high': # node non-symb
-			ds_file = current_path + '../../datasets/Letter-high/Letter-high_A.txt'
-			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
-		elif ds_name == 'Letter-med': # node non-symb
-			ds_file = current_path + '../../datasets/Letter-high/Letter-med_A.txt'
-			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
-		elif ds_name == 'Letter-low': # node non-symb
-			ds_file = current_path + '../../datasets/Letter-high/Letter-low_A.txt'
-			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
-		elif ds_name == 'Fingerprint':
-			ds_file = current_path + '../../datasets/Fingerprint/Fingerprint_A.txt'
-			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
-		elif ds_name == 'SYNTHETIC':
-			pass
-		elif ds_name == 'SYNTHETICnew':
-			ds_file = current_path + '../../datasets/SYNTHETICnew/SYNTHETICnew_A.txt'
-			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
-		elif ds_name == 'Synthie':
+		if ds_name == 'acyclic':
 			pass
 		elif ds_name == 'COIL-DEL':
 			ds_file = current_path + '../../datasets/COIL-DEL/COIL-DEL_A.txt'
@@ -95,9 +78,31 @@ class Dataset(object):
 		elif ds_name == 'COLORS-3':
 			ds_file = current_path + '../../datasets/COLORS-3/COLORS-3_A.txt'
 			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
+		elif ds_name == 'Fingerprint':
+			ds_file = current_path + '../../datasets/Fingerprint/Fingerprint_A.txt'
+			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
 		elif ds_name == 'FRANKENSTEIN':
 			ds_file = current_path + '../../datasets/FRANKENSTEIN/FRANKENSTEIN_A.txt'
 			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
+		elif ds_name == 'Letter-high': # node non-symb
+			ds_file = current_path + '../../datasets/Letter-high/Letter-high_A.txt'
+			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
+		elif ds_name == 'Letter-low': # node non-symb
+			ds_file = current_path + '../../datasets/Letter-high/Letter-low_A.txt'
+			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
+		elif ds_name == 'Letter-med': # node non-symb
+			ds_file = current_path + '../../datasets/Letter-high/Letter-med_A.txt'
+			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
+		elif ds_name == 'MUTAG':
+			ds_file = current_path + '../../datasets/MUTAG/MUTAG_A.txt'
+			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
+		elif ds_name == 'SYNTHETIC':
+			pass
+		elif ds_name == 'SYNTHETICnew':
+			ds_file = current_path + '../../datasets/SYNTHETICnew/SYNTHETICnew_A.txt'
+			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
+		elif ds_name == 'Synthie':
+			pass
 	
 		self.__node_labels = label_names['node_labels']
 		self.__node_attrs = label_names['node_attrs']