Update exps: Use Python to run sbatch.

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

@@ -12,10 +12,10 @@ import multiprocessing
 import pickle
 import logging
 from gklearn.ged.util import compute_geds
-import numpy as np
 import time
 from utils import get_dataset
 import sys
+from group_results import group_trials
 
 
 def xp_compute_ged_matrix(dataset, ds_name, max_num_solutions, ratio, trial):
@@ -92,11 +92,12 @@ 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)
+	# Group trials and Remove single files.
+	name_middle = '.' + ds_name + '.mnum_sols_' + str(max_num_solutions) + '.ratio_' + "{:.2f}".format(ratio) + '.'
+	name_prefix = 'ged_matrix' + name_middle
+	group_trials(save_dir, name_prefix, True, True, False)
+	name_prefix = 'runtime' + name_middle
+	group_trials(save_dir, name_prefix, True, True, False)
 	
 	
 def results_for_a_dataset(ds_name):

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

@@ -12,15 +12,19 @@ import multiprocessing
 import pickle
 import logging
 from gklearn.ged.util import compute_geds
-import numpy as np
 import time
 from utils import get_dataset
 import sys
+from group_results import group_trials
 
 
 def xp_compute_ged_matrix(dataset, ds_name, num_solutions, ratio, trial):
 
 	save_file_suffix = '.' + ds_name + '.num_sols_' + str(num_solutions) + '.ratio_' + "{:.2f}".format(ratio) + '.trial_' + str(trial)
+	
+	# Return if the file exists.
+	if os.path.isfile(save_dir + 'ged_matrix' + save_file_suffix + '.pkl'):
+		return None, None
 
 	"""**2.  Set parameters.**"""
 
@@ -39,8 +43,8 @@ def xp_compute_ged_matrix(dataset, ds_name, num_solutions, ratio, trial):
 				   }
 	
 	edit_cost_constants = [i * ratio for i in [1, 1, 1]] + [1, 1, 1]
-# 	edit_cost_constants = [item * 0.01 for item in edit_cost_constants]
-# 	pickle.dump(edit_cost_constants, open(save_dir + "edit_costs" + save_file_suffix + ".pkl", "wb"))
+#	edit_cost_constants = [item * 0.01 for item in edit_cost_constants]
+#	pickle.dump(edit_cost_constants, open(save_dir + "edit_costs" + save_file_suffix + ".pkl", "wb"))
 
 	options = ged_options.copy()
 	options['edit_cost_constants'] = edit_cost_constants
@@ -75,6 +79,12 @@ def xp_compute_ged_matrix(dataset, ds_name, num_solutions, ratio, trial):
 	
 	
 def save_trials_as_group(dataset, ds_name, num_solutions, ratio):
+	# Return if the group file exists.
+	name_middle = '.' + ds_name + '.num_sols_' + str(num_solutions) + '.ratio_' + "{:.2f}".format(ratio) + '.'
+	name_group = save_dir + 'groups/ged_mats' +  name_middle + 'npy'
+	if os.path.isfile(name_group):
+		return
+	
 	ged_mats = []
 	runtimes = []
 	for trial in range(1, 101):
@@ -84,24 +94,35 @@ 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)
+	# Group trials and Remove single files.
+	name_prefix = 'ged_matrix' + name_middle
+	group_trials(save_dir, name_prefix, True, True, False)
+	name_prefix = 'runtime' + name_middle
+	group_trials(save_dir, name_prefix, True, True, False)
 		
 		
 def results_for_a_dataset(ds_name):
 	"""**1.   Get dataset.**"""
 	dataset = get_dataset(ds_name)
 	
-	for num_solutions in [1, 20, 40, 60, 80, 100]:
+	for num_solutions in num_solutions_list:
 		print()
 		print('# of solutions:', num_solutions)
-		for ratio in [0.1, 0.3, 0.5, 0.7, 0.9, 1, 3, 5, 7, 9]:
+		for ratio in ratio_list:
 			print()
 			print('Ratio:', ratio)
 			save_trials_as_group(dataset, ds_name, num_solutions, ratio)
+			
+			
+def get_param_lists(ds_name):
+	if ds_name == 'AIDS_symb':
+		num_solutions_list = [1, 20, 40, 60, 80, 100]
+		ratio_list = [0.1, 0.3, 0.5, 0.7, 0.9, 1, 3, 5, 7, 9]
+	else:
+		num_solutions_list = [1, 20, 40, 60, 80, 100]
+		ratio_list = [0.1, 0.3, 0.5, 0.7, 0.9, 1, 3, 5, 7, 9]
+		
+	return num_solutions_list, ratio_list
 				
 
 if __name__ == '__main__':
@@ -117,4 +138,5 @@ if __name__ == '__main__':
 	for ds_name in ds_name_list:
 		print()
 		print('Dataset:', ds_name)
+		num_solutions_list, ratio_list = get_param_lists(ds_name)
 		results_for_a_dataset(ds_name)

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

@@ -12,10 +12,10 @@ import multiprocessing
 import pickle
 import logging
 from gklearn.ged.util import compute_geds
-import numpy as np
 import time
 from utils import get_dataset
 import sys
+from group_results import group_trials
 
 
 def xp_compute_ged_matrix(dataset, ds_name, repeats, ratio, trial):
@@ -87,11 +87,12 @@ 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)
+	# Group trials and Remove single files.
+	name_middle = '.' + ds_name + '.repeats_' + str(repeats) + '.ratio_' + "{:.2f}".format(ratio) + '.'
+	name_prefix = 'ged_matrix' + name_middle
+	group_trials(save_dir, name_prefix, True, True, False)
+	name_prefix = 'runtime' + name_middle
+	group_trials(save_dir, name_prefix, True, True, False)
 	
 	
 def results_for_a_dataset(ds_name):

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

@@ -12,10 +12,10 @@ import multiprocessing
 import pickle
 import logging
 from gklearn.ged.util import compute_geds
-import numpy as np
 import time
 from utils import get_dataset
 import sys
+from group_results import group_trials
 
 
 def xp_compute_ged_matrix(dataset, ds_name, repeats, ratio, trial):
@@ -92,11 +92,12 @@ 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)
+	# Group trials and Remove single files.
+	name_middle = '.' + ds_name + '.repeats_' + str(repeats) + '.ratio_' + "{:.2f}".format(ratio) + '.'
+	name_prefix = 'ged_matrix' + name_middle
+	group_trials(save_dir, name_prefix, True, True, False)
+	name_prefix = 'runtime' + name_middle
+	group_trials(save_dir, name_prefix, True, True, False)
 	
 	
 def results_for_a_dataset(ds_name):

gklearn/experiments/ged/stability/group_results.py

@@ -16,6 +16,7 @@ from tqdm import tqdm
 import sys
 
 
+# This function is used by other scripts. Modify it carefully.
 def group_trials(dir_folder, name_prefix, override, clear, backup):
 	
 	# Get group name.
@@ -47,8 +48,20 @@ def group_trials(dir_folder, name_prefix, override, clear, backup):
 			file_name = dir_folder + name_prefix + 'trial_' + str(trial) + '.pkl'
 			if os.path.isfile(file_name):
 				with open(file_name, 'rb') as f:
-					data = pickle.load(f)
+					try:
+						data = pickle.load(f)
+					except EOFError:
+						print('EOF Error occurred.')
+						return
 					data_group.append(data)
+
+# 					unpickler = pickle.Unpickler(f)
+# 					data = unpickler.load()
+# 					if not isinstance(data, np.array):
+# 						return
+# 					else:
+# 						data_group.append(data)
+
 			else: # Not all trials are completed.
 				return
 	
@@ -81,11 +94,9 @@ def group_trials(dir_folder, name_prefix, override, clear, backup):
 def group_all_in_folder(dir_folder, override=False, clear=True, backup=True):
 	
 	# Create folders.
-	if not os.path.exists(dir_folder + 'groups/'):
-		os.makedirs(dir_folder + 'groups/')
+	os.makedirs(dir_folder + 'groups/', exist_ok=True)
 	if backup:
-		if not os.path.exists(dir_folder + 'backups'):
-			os.makedirs(dir_folder + 'backups')
+		os.makedirs(dir_folder + 'backups', exist_ok=True)
 			
 	# Iterate all files.
 	cur_file_prefix = ''
@@ -105,4 +116,10 @@ if __name__ == '__main__':
  	group_all_in_folder(dir_folder)
 	
  	dir_folder = 'outputs/CRIANN/edit_costs.repeats.ratios.IPFP/'
+ 	group_all_in_folder(dir_folder)
+	 
+ 	dir_folder = 'outputs/CRIANN/edit_costs.max_num_sols.ratios.bipartite/'
+ 	group_all_in_folder(dir_folder)
+	 
+ 	dir_folder = 'outputs/CRIANN/edit_costs.repeats.ratios.bipartite/'
  	group_all_in_folder(dir_folder)

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

@@ -0,0 +1,47 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Nov  3 20:23:25 2020
+
+@author: ljia
+"""
+import os
+import re
+
+
+def get_job_script(arg):
+	script = r"""
+#!/bin/bash
+
+#SBATCH --exclusive
+#SBATCH --job-name="st.""" + arg + r""".IPFP"
+#SBATCH --partition=tlong
+#SBATCH --mail-type=ALL
+#SBATCH --mail-user=jajupmochi@gmail.com
+#SBATCH --output="outputs/output_edit_costs.nums_sols.ratios.IPFP.""" + arg + """.txt"
+#SBATCH --error="errors/error_edit_costs.nums_sols.ratios.IPFP.""" + arg + """.txt"
+#
+#SBATCH --ntasks=1
+#SBATCH --nodes=1
+#SBATCH --cpus-per-task=1
+#SBATCH --time=300:00:00
+#SBATCH --mem-per-cpu=4000
+
+srun hostname
+srun cd /home/2019015/ljia02/graphkit-learn/gklearn/experiments/ged/stability
+srun python3 edit_costs.nums_sols.ratios.IPFP.py """ + arg
+	script = script.strip()
+	script = re.sub('\n\t+', '\n', script)
+	script = re.sub('\n +', '\n', script)
+	
+	return script
+
+if __name__ == '__main__':
+	ds_list = ['MAO', 'Monoterpenoides', 'MUTAG', 'AIDS_symb']
+	for ds_name in [ds_list[i] for i in [0, 3]]:
+		job_script = get_job_script(ds_name)
+		command = 'sbatch <<EOF\n' + job_script + '\nEOF'
+# 		print(command)
+		os.system(command)
+# 		os.popen(command)
+# 		output = stream.readlines()