Simplify function gklearn.utils.graph_file.load_from_ds().

gklearn/preimage/experiments/xp_median_preimage.py

@@ -12,6 +12,70 @@ from gklearn.preimage.utils import generate_median_preimages_by_class
 from gklearn.utils import compute_gram_matrices_by_class
 
 
+def xp_median_preimage_9_1():
+	"""xp 9_1: Acyclic, sspkernel, using CONSTANT.
+	"""
+	# set parameters.
+	ds_name = 'Acyclic' #
+	mpg_options = {'fit_method': 'k-graphs',
+				   'init_ecc': [4, 4, 2, 1, 1, 1], #
+				   'ds_name': ds_name,
+				   'parallel': True, # False
+				   'time_limit_in_sec': 0,
+				   'max_itrs': 100, # 
+				   'max_itrs_without_update': 3,
+				   'epsilon_residual': 0.01,
+				   'epsilon_ec': 0.1,
+				   'verbose': 2}
+	mixkernel = functools.partial(kernelproduct, deltakernel, gaussiankernel)
+	sub_kernels = {'symb': deltakernel, 'nsymb': gaussiankernel, 'mix': mixkernel}
+	kernel_options = {'name': 'structuralspkernel',
+					  'edge_weight': None,
+					  'node_kernels': sub_kernels,
+					  'edge_kernels': sub_kernels, 
+					  'compute_method': 'naive',
+ 					  'parallel': 'imap_unordered', 
+                      # 'parallel': None, 
+					  'n_jobs': multiprocessing.cpu_count(),
+					  'normalize': True,
+					  'verbose': 2}
+	ged_options = {'method': 'IPFP',
+				   'initialization_method': 'RANDOM', # 'NODE'
+				   'initial_solutions': 10, # 1
+				   'edit_cost': 'CONSTANT', # 
+				   'attr_distance': 'euclidean',
+				   'ratio_runs_from_initial_solutions': 1,
+				   'threads': multiprocessing.cpu_count(),
+				   'init_option': 'EAGER_WITHOUT_SHUFFLED_COPIES'}
+	mge_options = {'init_type': 'MEDOID',
+				   'random_inits': 10,
+				   'time_limit': 600,
+				   'verbose': 2,
+				   'refine': False}
+	save_results = True
+	dir_save='../results/xp_median_preimage/'
+	irrelevant_labels = {'node_attrs': ['x', 'y', 'z'], 'edge_labels': ['bond_stereo']} #
+	edge_required = False #
+	
+	# print settings.
+	print('parameters:')
+	print('dataset name:', ds_name)
+	print('mpg_options:', mpg_options)
+	print('kernel_options:', kernel_options)
+	print('ged_options:', ged_options)
+	print('mge_options:', mge_options)
+	print('save_results:', save_results)
+	print('irrelevant_labels:', irrelevant_labels)
+	print()
+	
+	# generate preimages.
+	for fit_method in ['k-graphs', 'expert', 'random', 'random', 'random']:
+		print('\n-------------------------------------')
+		print('fit method:', fit_method, '\n')
+		mpg_options['fit_method'] = fit_method
+		generate_median_preimages_by_class(ds_name, mpg_options, kernel_options, ged_options, mge_options, save_results=save_results, save_medians=True, plot_medians=True, load_gm='auto', dir_save=dir_save, irrelevant_labels=irrelevant_labels, edge_required=edge_required)
+
+
 def xp_median_preimage_8_1():
 	"""xp 8_1: Monoterpenoides, sspkernel, using CONSTANT.
 	"""
@@ -546,4 +610,7 @@ if __name__ == "__main__":
  	# xp_median_preimage_7_1()
 	 
     #### xp 8_1: Monoterpenoides, sspkernel, using CONSTANT.
-	xp_median_preimage_8_1()
+# 	xp_median_preimage_8_1()
+
+	#### xp 9_1: Acyclic, sspkernel, using CONSTANT.
+	xp_median_preimage_9_1()

gklearn/utils/dataset.py

@@ -68,7 +68,8 @@ class Dataset(object):
 	def load_predefined_dataset(self, ds_name):
 		current_path = os.path.dirname(os.path.realpath(__file__)) + '/'
 		if ds_name == 'Acyclic':
-			pass
+			ds_file = current_path + '../../datasets/Acyclic/dataset_bps.ds'
+			self.__graphs, self.__targets, label_names = load_dataset(ds_file)
 		elif ds_name == 'COIL-DEL':
 			ds_file = current_path + '../../datasets/COIL-DEL/COIL-DEL_A.txt'
 			self.__graphs, self.__targets, label_names = load_dataset(ds_file)

gklearn/utils/graph_files.py

@@ -720,38 +720,26 @@ def load_from_ds(filename, filename_targets):
 	label_names = {'node_labels': [], 'edge_labels': [], 'node_attrs': [], 'edge_attrs': []}
 	content = open(filename).read().splitlines()
 	extension = splitext(content[0].split(' ')[0])[1][1:]
+	if extension == 'ct':
+		load_file_fun = load_ct
+	elif extension == 'gxl':
+		load_file_fun = load_gxl
+		
 	if filename_targets is None or filename_targets == '':
-		if extension == 'ct': 
-			for i in range(0, len(content)):
-				tmp = content[i].split(' ')
-				# remove the '#'s in file names
-				g, l_names = load_ct(dirname_dataset + '/' + tmp[0].replace('#', '', 1))
-				data.append(g)
-				__append_label_names(label_names, l_names)
-				y.append(float(tmp[1]))
-		elif extension == 'gxl':
-			for i in range(0, len(content)):
-				tmp = content[i].split(' ')
-				# remove the '#'s in file names
-				g, l_names = load_gxl(dirname_dataset + '/' + tmp[0].replace('#', '', 1))
-				data.append(g)
-				__append_label_names(label_names, l_names)
-				y.append(float(tmp[1]))
-	else:  # y in a seperate file
-		if extension == 'ct':
-			for i in range(0, len(content)):
-				tmp = content[i]
-				# remove the '#'s in file names
-				g, l_names = load_ct(dirname_dataset + '/' + tmp.replace('#', '', 1))
-				data.append(g)
-				__append_label_names(label_names, l_names)
-		elif extension == 'gxl':
-			for i in range(0, len(content)):
-				tmp = content[i]
-				# remove the '#'s in file names
-				g, l_names = load_gxl(dirname_dataset + '/' + tmp.replace('#', '', 1))
-				data.append(g)
-				__append_label_names(label_names, l_names)
+		for i in range(0, len(content)):
+			tmp = content[i].split(' ')
+			# remove the '#'s in file names
+			g, l_names = load_file_fun(dirname_dataset + '/' + tmp[0].replace('#', '', 1))
+			data.append(g)
+			__append_label_names(label_names, l_names)
+			y.append(float(tmp[1]))
+	else:  # targets in a seperate file
+		for i in range(0, len(content)):
+			tmp = content[i]
+			# remove the '#'s in file names
+			g, l_names = load_file_fun(dirname_dataset + '/' + tmp.replace('#', '', 1))
+			data.append(g)
+			__append_label_names(label_names, l_names)
 															   
 		content_y = open(filename_targets).read().splitlines()
 		# assume entries in filename and filename_targets have the same order.
@@ -774,16 +762,16 @@ if __name__ == '__main__':
 #	ds = {'name': 'Alkane', 'dataset': '../../datasets/Alkane/dataset.ds',
 #		'dataset_y': '../../datasets/Alkane/dataset_boiling_point_names.txt'}
 #	Gn, y = loadDataset(ds['dataset'], filename_y=ds['dataset_y'])
-	ds_file = '../../datasets/acyclic/dataset_bps.ds'  # node symb
-	Gn, targets, label_names = load_dataset(ds_file)
+# 	ds_file = '../../datasets/Acyclic/dataset_bps.ds'  # node symb
+# 	Gn, targets, label_names = load_dataset(ds_file)
 ##	ds = {'name': 'MAO', 'dataset': '../../datasets/MAO/dataset.ds'} # node/edge symb
 ##	Gn, y = loadDataset(ds['dataset'])
 ##	ds = {'name': 'PAH', 'dataset': '../../datasets/PAH/dataset.ds'} # unlabeled
 ##	Gn, y = loadDataset(ds['dataset'])
-	print(Gn[1].graph)
-	print(Gn[1].nodes(data=True))
-	print(Gn[1].edges(data=True))
-	print(targets[1])
+# 	print(Gn[1].graph)
+# 	print(Gn[1].nodes(data=True))
+# 	print(Gn[1].edges(data=True))
+# 	print(targets[1])
 	
 # 	# .gxl file.
 # 	ds_file = '../../datasets/monoterpenoides/dataset_10+.ds'  # node/edge symb