Use the parameter exist_ok=True in the function os.makedirs to check if a dir exists to avoid problems while paralleling.

gklearn/experiments/ged/stability/edit_costs.max_num_sols.ratios.bipartite.py

@@ -92,11 +92,11 @@ def save_trials_as_group(dataset, ds_name, max_num_solutions, ratio):
 		ged_mats.append(ged_mat)
 		runtimes.append(runtime)
 		
-	save_file_suffix = '.' + ds_name + '.mnum_sols_' + str(max_num_solutions) + '.ratio_' + "{:.2f}".format(ratio)
-	with open(save_dir + 'groups/ged_mats' + save_file_suffix + '.npy', 'wb') as f:
-		np.save(f, np.array(ged_mats))
-	with open(save_dir + 'groups/runtimes' + save_file_suffix + '.pkl', 'wb') as f:
-		pickle.dump(runtime, f)
+# 	save_file_suffix = '.' + ds_name + '.mnum_sols_' + str(max_num_solutions) + '.ratio_' + "{:.2f}".format(ratio)
+# 	with open(save_dir + 'groups/ged_mats' + save_file_suffix + '.npy', 'wb') as f:
+# 		np.save(f, np.array(ged_mats))
+# 	with open(save_dir + 'groups/runtimes' + save_file_suffix + '.pkl', 'wb') as f:
+# 		pickle.dump(runtime, f)
 	
 	
 def results_for_a_dataset(ds_name):
@@ -119,10 +119,8 @@ if __name__ == '__main__':
 		ds_name_list = ['MAO', 'Monoterpenoides', 'MUTAG', 'AIDS_symb']
 		
 	save_dir = 'outputs/edit_costs.max_num_sols.ratios.bipartite/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
-	if not os.path.exists(save_dir + 'groups/'):
-		os.makedirs(save_dir + 'groups/')
+	os.makedirs(save_dir, exist_ok=True)
+	os.makedirs(save_dir + 'groups/', exist_ok=True)
 		
 	for ds_name in ds_name_list:
 		print()

gklearn/experiments/ged/stability/edit_costs.nums_sols.ratios.IPFP.py

@@ -84,11 +84,11 @@ def save_trials_as_group(dataset, ds_name, num_solutions, ratio):
 		ged_mats.append(ged_mat)
 		runtimes.append(runtime)
 		
-	save_file_suffix = '.' + ds_name + '.num_sols_' + str(num_solutions) + '.ratio_' + "{:.2f}".format(ratio)
-	with open(save_dir + 'groups/ged_mats' + save_file_suffix + '.npy', 'wb') as f:
-		np.save(f, np.array(ged_mats))
-	with open(save_dir + 'groups/runtimes' + save_file_suffix + '.pkl', 'wb') as f:
-		pickle.dump(runtime, f)
+# 	save_file_suffix = '.' + ds_name + '.num_sols_' + str(num_solutions) + '.ratio_' + "{:.2f}".format(ratio)
+# 	with open(save_dir + 'groups/ged_mats' + save_file_suffix + '.npy', 'wb') as f:
+# 		np.save(f, np.array(ged_mats))
+# 	with open(save_dir + 'groups/runtimes' + save_file_suffix + '.pkl', 'wb') as f:
+# 		pickle.dump(runtime, f)
 		
 		
 def results_for_a_dataset(ds_name):
@@ -111,10 +111,8 @@ if __name__ == '__main__':
 		ds_name_list = ['MAO', 'Monoterpenoides', 'MUTAG', 'AIDS_symb']
 		
 	save_dir = 'outputs/edit_costs.num_sols.ratios.IPFP/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
-	if not os.path.exists(save_dir + 'groups/'):
-		os.makedirs(save_dir + 'groups/')
+	os.makedirs(save_dir, exist_ok=True)
+	os.makedirs(save_dir + 'groups/', exist_ok=True)
 		
 	for ds_name in ds_name_list:
 		print()

gklearn/experiments/ged/stability/edit_costs.repeats.ratios.IPFP.py

@@ -87,11 +87,11 @@ def save_trials_as_group(dataset, ds_name, repeats, ratio):
 		ged_mats.append(ged_mat)
 		runtimes.append(runtime)
 		
-	save_file_suffix = '.' + ds_name + '.repeats_' + str(repeats) + '.ratio_' + "{:.2f}".format(ratio)
-	with open(save_dir + 'groups/ged_mats' + save_file_suffix + '.npy', 'wb') as f:
-		np.save(f, np.array(ged_mats))
-	with open(save_dir + 'groups/runtimes' + save_file_suffix + '.pkl', 'wb') as f:
-		pickle.dump(runtime, f)
+# 	save_file_suffix = '.' + ds_name + '.repeats_' + str(repeats) + '.ratio_' + "{:.2f}".format(ratio)
+# 	with open(save_dir + 'groups/ged_mats' + save_file_suffix + '.npy', 'wb') as f:
+# 		np.save(f, np.array(ged_mats))
+# 	with open(save_dir + 'groups/runtimes' + save_file_suffix + '.pkl', 'wb') as f:
+# 		pickle.dump(runtime, f)
 	
 	
 def results_for_a_dataset(ds_name):
@@ -114,10 +114,8 @@ if __name__ == '__main__':
 		ds_name_list = ['MAO', 'Monoterpenoides', 'MUTAG', 'AIDS_symb']
 		
 	save_dir = 'outputs/edit_costs.repeats.ratios.IPFP/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
-	if not os.path.exists(save_dir + 'groups/'):
-		os.makedirs(save_dir + 'groups/')
+	os.makedirs(save_dir, exist_ok=True)
+	os.makedirs(save_dir + 'groups/', exist_ok=True)
 		
 	for ds_name in ds_name_list:
 		print()

gklearn/experiments/ged/stability/edit_costs.repeats.ratios.bipartite.py

@@ -92,11 +92,11 @@ def save_trials_as_group(dataset, ds_name, repeats, ratio):
 		ged_mats.append(ged_mat)
 		runtimes.append(runtime)
 		
-	save_file_suffix = '.' + ds_name + '.repeats_' + str(repeats) + '.ratio_' + "{:.2f}".format(ratio)
-	with open(save_dir + 'groups/ged_mats' + save_file_suffix + '.npy', 'wb') as f:
-		np.save(f, np.array(ged_mats))
-	with open(save_dir + 'groups/runtimes' + save_file_suffix + '.pkl', 'wb') as f:
-		pickle.dump(runtime, f)
+# 	save_file_suffix = '.' + ds_name + '.repeats_' + str(repeats) + '.ratio_' + "{:.2f}".format(ratio)
+# 	with open(save_dir + 'groups/ged_mats' + save_file_suffix + '.npy', 'wb') as f:
+# 		np.save(f, np.array(ged_mats))
+# 	with open(save_dir + 'groups/runtimes' + save_file_suffix + '.pkl', 'wb') as f:
+# 		pickle.dump(runtime, f)
 	
 	
 def results_for_a_dataset(ds_name):
@@ -119,10 +119,8 @@ if __name__ == '__main__':
 		ds_name_list = ['MAO', 'Monoterpenoides', 'MUTAG', 'AIDS_symb']
 		
 	save_dir = 'outputs/edit_costs.repeats.ratios.bipartite/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
-	if not os.path.exists(save_dir + 'groups/'):
-		os.makedirs(save_dir + 'groups/')
+	os.makedirs(save_dir, exist_ok=True)
+	os.makedirs(save_dir + 'groups/', exist_ok=True)
 		
 	for ds_name in ds_name_list:
 		print()

gklearn/experiments/papers/PRL_2020/accuracy_diff_entropy.py

@@ -150,8 +150,7 @@ def xp_accuracy_diff_entropy():
 	import pickle
 	import os
 	save_dir = 'outputs/accuracy_diff_entropy/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
+	os.makedirs(save_dir, exist_ok=True)
 
 	accuracies = {}
 	confidences = {}

gklearn/experiments/papers/PRL_2020/runtimes_28cores.py

@@ -16,8 +16,7 @@ def xp_runtimes_of_all_28cores():
 	import pickle
 	import os
 	save_dir = 'outputs/runtimes_of_all_28cores/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
+	os.makedirs(save_dir, exist_ok=True)
 
 	run_times = {}
 	

gklearn/experiments/papers/PRL_2020/runtimes_diff_chunksizes.py

@@ -16,8 +16,7 @@ def xp_runtimes_diff_chunksizes():
 	import pickle
 	import os
 	save_dir = 'outputs/runtimes_diff_chunksizes/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
+	os.makedirs(save_dir, exist_ok=True)
 
 	run_times = {}
 

gklearn/experiments/papers/PRL_2020/synthesized_graphs_N.py

@@ -25,8 +25,7 @@ def xp_synthesized_graphs_dataset_size():
 	import pickle
 	import os
 	save_dir = 'outputs/synthesized_graphs_N/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
+	os.makedirs(save_dir, exist_ok=True)
 
 	run_times = {}
 	

gklearn/experiments/papers/PRL_2020/synthesized_graphs_degrees.py

@@ -22,8 +22,7 @@ def xp_synthesized_graphs_degrees():
 	import pickle
 	import os
 	save_dir = 'outputs/synthesized_graphs_degrees/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
+	os.makedirs(save_dir, exist_ok=True)
 
 	run_times = {}
 	

gklearn/experiments/papers/PRL_2020/synthesized_graphs_num_nl.py

@@ -22,8 +22,7 @@ def xp_synthesized_graphs_num_node_label_alphabet():
 	import pickle
 	import os
 	save_dir = 'outputs/synthesized_graphs_num_node_label_alphabet/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
+	os.makedirs(save_dir, exist_ok=True)
 
 	run_times = {}
 	

gklearn/experiments/papers/PRL_2020/synthesized_graphs_num_nodes.py

@@ -22,8 +22,7 @@ def xp_synthesized_graphs_num_nodes():
 	import pickle
 	import os
 	save_dir = 'outputs/synthesized_graphs_num_nodes/'
-	if not os.path.exists(save_dir):
-		os.makedirs(save_dir)
+	os.makedirs(save_dir, exist_ok=True)
 
 	run_times = {}
 	

gklearn/ged/median/test_median_graph_estimator.py

@@ -154,6 +154,6 @@ def test_median_graph_estimator_symb():
 	return set_median, gen_median
 
 
-if __name__ == '__main__':
+if _name_ == '_main_':
  	# set_median, gen_median = test_median_graph_estimator()
  	set_median, gen_median = test_median_graph_estimator_symb()

gklearn/preimage/generate_random_preimages_by_class.py

@@ -126,8 +126,7 @@ def generate_random_preimages_by_class(ds_name, rpg_options, kernel_options, sav
 			 
 		# save median graphs.
 		if save_preimages:
-			if not os.path.exists(dir_save + 'preimages/'):
-				os.makedirs(dir_save + 'preimages/')
+			os.makedirs(dir_save + 'preimages/', exist_ok=True)
 			print('Saving preimages to files...')
 			fn_best_dataset = dir_save + 'preimages/g_best_dataset.' + 'nbg' + str(num_graphs) + '.y' + str(target) + '.repeat' + str(1)
 			saveGXL(rpg.best_from_dataset, fn_best_dataset + '.gxl', method='default', 
@@ -167,8 +166,7 @@ def generate_random_preimages_by_class(ds_name, rpg_options, kernel_options, sav
 
 	
 def _init_output_file_preimage(ds_name, gkernel, dir_output):
-	if not os.path.exists(dir_output):
-		os.makedirs(dir_output)
+	os.makedirs(dir_output, exist_ok=True)
 	fn_output_detail = 'results_detail.' + ds_name + '.' + gkernel + '.csv'
 	f_detail = open(dir_output + fn_output_detail, 'a')
 	csv.writer(f_detail).writerow(['dataset', 'graph kernel', 'num graphs', 

gklearn/preimage/remove_best_graph.py

@@ -218,8 +218,7 @@ def remove_best_graph(ds_name, mpg_options, kernel_options, ged_options, mge_opt
 			 
 		# save median graphs.
 		if save_medians:
-			if not os.path.exists(dir_save + 'medians/'):
-				os.makedirs(dir_save + 'medians/')
+			os.makedirs(dir_save + 'medians/', exist_ok=True)
 			print('Saving median graphs to files...')
 			fn_pre_sm = dir_save + 'medians/set_median.' + mpg_options['fit_method'] + '.nbg' + str(num_graphs) + '.y' + str(target) + '.repeat' + str(1)
 			saveGXL(mpg.set_median, fn_pre_sm + '.gxl', method='default', 
@@ -375,8 +374,7 @@ def _compute_gram_matrix_unnorm(dataset, kernel_options):
 		
 		
 def _init_output_file(ds_name, gkernel, fit_method, dir_output):
-	if not os.path.exists(dir_output):
-		os.makedirs(dir_output)
+	os.makedirs(dir_output, exist_ok=True)
 	fn_output_detail = 'results_detail.' + ds_name + '.' + gkernel + '.csv'
 	f_detail = open(dir_output + fn_output_detail, 'a')
 	csv.writer(f_detail).writerow(['dataset', 'graph kernel', 'edit cost', 

gklearn/preimage/utils.py

@@ -230,8 +230,7 @@ def generate_median_preimages_by_class(ds_name, mpg_options, kernel_options, ged
 			 
 		# save median graphs.
 		if save_medians:
-			if not os.path.exists(dir_save + 'medians/'):
-				os.makedirs(dir_save + 'medians/')
+			os.makedirs(dir_save + 'medians/', exist_ok=True)
 			print('Saving median graphs to files...')
 			fn_pre_sm = dir_save + 'medians/set_median.' + mpg_options['fit_method'] + '.nbg' + str(num_graphs) + '.y' + str(target) + '.repeat' + str(1)
 			saveGXL(mpg.set_median, fn_pre_sm + '.gxl', method='default', 
@@ -308,8 +307,7 @@ def generate_median_preimages_by_class(ds_name, mpg_options, kernel_options, ged
 
 	
 def _init_output_file_preimage(ds_name, gkernel, fit_method, dir_output):
-	if not os.path.exists(dir_output):
-		os.makedirs(dir_output)
+	os.makedirs(dir_output, exist_ok=True)
 #	fn_output_detail = 'results_detail.' + ds_name + '.' + gkernel + '.' + fit_method + '.csv'
 	fn_output_detail = 'results_detail.' + ds_name + '.' + gkernel + '.csv'
 	f_detail = open(dir_output + fn_output_detail, 'a')

gklearn/utils/graph_files.py

@@ -70,13 +70,11 @@ def save_dataset(Gn, y, gformat='gxl', group=None, filename='gfile', **kwargs):
 	dirname_ds = os.path.dirname(filename)
 	if dirname_ds != '':
 		dirname_ds += '/'
-		if not os.path.exists(dirname_ds) :
-			os.makedirs(dirname_ds)
+		os.makedirs(dirname_ds, exist_ok=True)
 				
 	if 'graph_dir' in kwargs:
 		graph_dir = kwargs['graph_dir'] + '/'
-		if not os.path.exists(graph_dir):
-			os.makedirs(graph_dir)
+		os.makedirs(graph_dir, exist_ok=True)
 		del kwargs['graph_dir']
 	else:
 		graph_dir = dirname_ds 

gklearn/utils/graphfiles.py

@@ -671,13 +671,11 @@ def saveDataset(Gn, y, gformat='gxl', group=None, filename='gfile', xparams=None
 	dirname_ds = os.path.dirname(filename)
 	if dirname_ds != '':
 		dirname_ds += '/'
-		if not os.path.exists(dirname_ds) :
-			os.makedirs(dirname_ds)
+		os.makedirs(dirname_ds, exist_ok=True)
 				
 	if xparams is not None and 'graph_dir' in xparams:
 		graph_dir = xparams['graph_dir'] + '/'
-		if not os.path.exists(graph_dir):
-			os.makedirs(graph_dir)
+		os.makedirs(graph_dir, exist_ok=True)
 	else:
 		graph_dir = dirname_ds 
 			

gklearn/utils/model_selection_precomputed.py

@@ -91,8 +91,7 @@ def model_selection_for_precomputed_kernel(datafile,
 	tqdm.monitor_interval = 0
 
 	output_dir += estimator.__name__
-	if not os.path.exists(output_dir):
-		os.makedirs(output_dir)
+	os.makedirs(output_dir, exist_ok=True)
 	# a string to save all the results.
 	str_fw = '###################### log time: ' + datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S") + '. ######################\n\n'
 	str_fw += '# This file contains results of ' + estimator.__name__ + ' on dataset ' + ds_name + ',\n# including gram matrices, serial numbers for gram matrix figures and performance.\n\n'
@@ -604,8 +603,7 @@ def model_selection_for_precomputed_kernel(datafile,
 		str_fw += 'training time with hyper-param choices who did not participate in calculation of gram matrices: {:.2f}s\n\n'.format(tt_poster)
 
 		# open file to save all results for this dataset.
-		if not os.path.exists(output_dir):
-			os.makedirs(output_dir)
+		os.makedirs(output_dir, exist_ok=True)
 			
 	# print out results as table.
 	str_fw += printResultsInTable(param_list, param_list_pre_revised, average_val_scores,

gklearn/utils/utils.py

@@ -458,8 +458,7 @@ def compute_gram_matrices_by_class(ds_name, kernel_options, save_results=True, d
 	print()
 	print('4. saving results...')
 	if save_results:
-		if not os.path.exists(dir_save):
-			os.makedirs(dir_save)
+		os.makedirs(dir_save, exist_ok=True)
 		np.savez(dir_save + 'gram_matrix_unnorm.' + ds_name + '.' + kernel_options['name'] + '.gm', gram_matrix_unnorm_list=gram_matrix_unnorm_list, run_time_list=run_time_list)	
 
 	print('\ncomplete.')