Merge pull request #29 from jajupmochi/v0.2

V0.2

Author: jajupmochi

CHANGELOG.md

@@ -1,6 +1,6 @@
 # About graph kenrels.
 
-## (Random walk) Sylvester equation kernel.
+## (Random walk) Sylvester equation kernel.
 
 ### ImportError: cannot import name 'frange' from 'matplotlib.mlab'
 
@@ -10,12 +10,14 @@ Update your `control` package.
 
 ### Intel MKL FATAL ERROR: Cannot load libmkl_avx2.so or libmkl_def.so.
 
-The Intel Math Kernel Library (MKL) is missing or not properly set. I assume the MKL is required by `control` module.
+The Intel Math Kernel Library (MKL) is missing or not properly set. I assume MKL is required by the `control` module.
 
 Install MKL. Then add the following to your path:
 
 ```
 export PATH=/opt/intel/bin:$PATH
 
 export LD_LIBRARY_PATH=/opt/intel/lib/intel64:/opt/intel/mkl/lib/intel64:$LD_LIBRARY_PATH
+
+export LD_PRELOAD=/opt/intel/mkl/lib/intel64/libmkl_def.so:/opt/intel/mkl/lib/intel64/libmkl_avx2.so:/opt/intel/mkl/lib/intel64/libmkl_core.so:/opt/intel/mkl/lib/intel64/libmkl_intel_lp64.so:/opt/intel/mkl/lib/intel64/libmkl_intel_thread.so:/opt/intel/lib/intel64_lin/libiomp5.so
 ```

Problems.md

@@ -60,7 +60,7 @@ Check [`notebooks`](https://github.com/jajupmochi/graphkit-learn/tree/master/not
 
 The docs of the library can be found [here](https://graphkit-learn.readthedocs.io/en/master/?badge=master).
 
-## Main contents
+## Main contents
 
 ### 1 List of graph kernels
 
@@ -131,6 +131,20 @@ A comparison of performances of graph kernels on benchmark datasets can be found
 
 Fork the library and open a pull request! Make your own contribute to the community!
 
+## Authors
+
+* [Linlin Jia](https://jajupmochi.github.io/), LITIS, INSA Rouen Normandie
+* [Benoit Gaüzère](http://pagesperso.litislab.fr/~bgauzere/#contact_en), LITIS, INSA Rouen Normandie
+* [Paul Honeine](http://honeine.fr/paul/Welcome.html), LITIS, Université de Rouen Normandie
+
+## Citation
+
+Still waiting...
+
+## Acknowledgments
+
+This research was supported by CSC (China Scholarship Council) and the French national research agency (ANR) under the grant APi (ANR-18-CE23-0014). The authors would like to thank the CRIANN (Le Centre Régional Informatique et d’Applications Numériques de Normandie) for providing computational resources.
+
 ## References
 [1] Thomas Gärtner, Peter Flach, and Stefan Wrobel. On graph kernels: Hardness results and efficient alternatives. Learning Theory and Kernel Machines, pages 129–143, 2003.
 
@@ -153,17 +167,3 @@ Fork the library and open a pull request! Make your own contribute to the commun
 [10] Gaüzere, B., Brun, L., Villemin, D., 2012. Two new graphs kernels in chemoinformatics. Pattern Recognition Letters 33, 2038–2047.
 
 [11] Shervashidze, N., Schweitzer, P., Leeuwen, E.J.v., Mehlhorn, K., Borgwardt, K.M., 2011. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research 12, 2539–2561.
-
-## Authors
-
-* [Linlin Jia](https://jajupmochi.github.io/), LITIS, INSA Rouen Normandie
-* [Benoit Gaüzère](http://pagesperso.litislab.fr/~bgauzere/#contact_en), LITIS, INSA Rouen Normandie
-* [Paul Honeine](http://honeine.fr/paul/Welcome.html), LITIS, Université de Rouen Normandie
-
-## Citation
-
-Still waiting...
-
-## Acknowledgments
-
-This research was supported by CSC (China Scholarship Council) and the French national research agency (ANR) under the grant APi (ANR-18-CE23-0014). The authors would like to thank the CRIANN (Le Centre Régional Informatique et d’Applications Numériques de Normandie) for providing computational resources.

README.md

@@ -10,19 +10,12 @@
 import logging
 
 
-# def get_graphs(ds_name):
-# 	from gklearn.utils.graph_synthesizer import GraphSynthesizer
-# 	gsyzer = GraphSynthesizer()
-# 	graphs = gsyzer.unified_graphs(num_graphs=100, num_nodes=num_nodes, num_edges=int(num_nodes*2), num_node_labels=0, num_edge_labels=0, seed=None, directed=False)
-# 	return graphs
-
-
-def xp_runtimes_of_all_7cores():
+def xp_runtimes_of_all_28cores():
 
 	# Run and save.
 	import pickle
 	import os
-	save_dir = 'outputs/runtimes_of_all_7cores/'
+	save_dir = 'outputs/runtimes_of_all_28cores/'
 	if not os.path.exists(save_dir):
 		os.makedirs(save_dir)
 
@@ -41,16 +34,16 @@ def xp_runtimes_of_all_7cores():
 			graphs, _ = load_predefined_dataset(ds_name)
 
 			# Compute Gram matrix.
+			run_time = 'error'
 			try:
 				gram_matrix, run_time = compute_graph_kernel(graphs, kernel_name, n_jobs=28)
-				run_times[kernel_name].append(run_time)
 			except Exception as exp:
-				run_times[kernel_name].append('error')
 				print('An exception occured when running this experiment:')
 				LOG_FILENAME = save_dir + 'error.txt'
 				logging.basicConfig(filename=LOG_FILENAME, level=logging.DEBUG)
 				logging.exception('')
 				print(repr(exp))
+			run_times[kernel_name].append(run_time)
 
 			pickle.dump(run_time, open(save_dir + 'run_time.' + kernel_name + '.' + ds_name + '.pkl', 'wb'))
 
@@ -61,4 +54,4 @@ def xp_runtimes_of_all_7cores():
 
 
 if __name__ == '__main__':
-	xp_runtimes_of_all_7cores()
+	xp_runtimes_of_all_28cores()

gklearn/experiments/papers/PRL_2020/runtimes_28cores.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Sep 21 10:34:26 2020
+
+@author: ljia
+"""
+from utils import Graph_Kernel_List, Dataset_List, compute_graph_kernel
+from gklearn.utils.graphdataset import load_predefined_dataset
+import logging
+
+
+def xp_runtimes_diff_chunksizes():
+		
+	# Run and save.
+	import pickle
+	import os
+	save_dir = 'outputs/runtimes_diff_chunksizes/'
+	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 ds_name in Dataset_List:
+			print()
+			print('Dataset:', ds_name)
+			
+			run_times[kernel_name].append([])
+			for chunksize in [1, 5, 10, 50, 100, 500, 1000, 5000, 10000, 50000, 100000]:
+				print()
+				print('Chunksize:', chunksize)
+			
+				# get graphs.
+				graphs, _ = load_predefined_dataset(ds_name)
+
+				# Compute Gram matrix.
+				run_time = 'error'
+				try:
+					gram_matrix, run_time = compute_graph_kernel(graphs, kernel_name, chunksize=chunksize)
+				except Exception as exp:
+					print('An exception occured when running this experiment:')
+					LOG_FILENAME = save_dir + 'error.txt'
+					logging.basicConfig(filename=LOG_FILENAME, level=logging.DEBUG)
+					logging.exception('')
+					print(repr(exp))			
+				run_times[kernel_name][-1].append(run_time)	
+				
+				pickle.dump(run_time, open(save_dir + 'run_time.' + kernel_name + '.' + ds_name + '.' + str(chunksize) + '.pkl', 'wb'))
+		
+	# Save all.	
+	pickle.dump(run_times, open(save_dir + 'run_times.pkl', 'wb'))	
+	
+	return
+
+
+if __name__ == '__main__':
+	xp_runtimes_diff_chunksizes()

gklearn/experiments/papers/PRL_2020/runtimes_diff_chunksizes.py

@@ -41,16 +41,16 @@ def xp_synthesied_graphs_dataset_size():
 
 			sub_graphs = [g.copy() for g in graphs[0:num_graphs]]
 
+			run_time = 'error'
 			try:
 				gram_matrix, run_time = compute_graph_kernel(sub_graphs, kernel_name, n_jobs=1)
-				run_times[kernel_name].append(run_time)
 			except Exception as exp:
-				run_times[kernel_name].append('error')
 				print('An exception occured when running this experiment:')
 				LOG_FILENAME = save_dir + 'error.txt'
 				logging.basicConfig(filename=LOG_FILENAME, level=logging.DEBUG)
 				logging.exception('')
 				print(repr(exp))
+			run_times[kernel_name].append(run_time)
 
 			pickle.dump(run_time, open(save_dir + 'run_time.' + kernel_name + '.' + str(num_graphs) + '.pkl', 'wb'))
 

gklearn/experiments/papers/PRL_2020/synthesized_graphs_N.py

@@ -40,16 +40,16 @@ def xp_synthesied_graphs_degrees():
 			graphs = generate_graphs(degree)
 
 			# Compute Gram matrix.
+			run_time = 'error'
 			try:
 				gram_matrix, run_time = compute_graph_kernel(graphs, kernel_name, n_jobs=1)
-				run_times[kernel_name].append(run_time)
 			except Exception as exp:
-				run_times[kernel_name].append('error')
 				print('An exception occured when running this experiment:')
 				LOG_FILENAME = save_dir + 'error.txt'
 				logging.basicConfig(filename=LOG_FILENAME, level=logging.DEBUG)
 				logging.exception('')
 				print(repr(exp))
+			run_times[kernel_name].append(run_time)
 
 			pickle.dump(run_time, open(save_dir + 'run_time.' + kernel_name + '.' + str(degree) + '.pkl', 'wb'))
 

gklearn/experiments/papers/PRL_2020/synthesized_graphs_degrees.py

@@ -40,16 +40,16 @@ def xp_synthesied_graphs_num_edge_label_alphabet():
 			graphs = generate_graphs(num_el_alp)
 
 			# Compute Gram matrix.
+			run_time = 'error'
 			try:
 				gram_matrix, run_time = compute_graph_kernel(graphs, kernel_name, n_jobs=1)
-				run_times[kernel_name].append(run_time)
 			except Exception as exp:
-				run_times[kernel_name].append('error')
 				print('An exception occured when running this experiment:')
 				LOG_FILENAME = save_dir + 'error.txt'
 				logging.basicConfig(filename=LOG_FILENAME, level=logging.DEBUG)
 				logging.exception('')
 				print(repr(exp))
+			run_times[kernel_name].append(run_time)
 
 			pickle.dump(run_time, open(save_dir + 'run_time.' + kernel_name + '.' + str(num_el_alp) + '.pkl', 'wb'))
 

gklearn/experiments/papers/PRL_2020/synthesized_graphs_num_el.py

@@ -40,16 +40,17 @@ def xp_synthesied_graphs_num_node_label_alphabet():
 			graphs = generate_graphs(num_nl_alp)
 
 			# Compute Gram matrix.
+			run_time = 'error'
 			try:
 				gram_matrix, run_time = compute_graph_kernel(graphs, kernel_name, n_jobs=1)
-				run_times[kernel_name].append(run_time)
 			except Exception as exp:
 				run_times[kernel_name].append('error')
 				print('An exception occured when running this experiment:')
 				LOG_FILENAME = save_dir + 'error.txt'
 				logging.basicConfig(filename=LOG_FILENAME, level=logging.DEBUG)
 				logging.exception('')
 				print(repr(exp))
+			run_times[kernel_name].append(run_time)
 
 			pickle.dump(run_time, open(save_dir + 'run_time.' + kernel_name + '.' + str(num_nl_alp) + '.pkl', 'wb'))
 

gklearn/experiments/papers/PRL_2020/synthesized_graphs_num_nl.py

@@ -40,16 +40,17 @@ def xp_synthesied_graphs_num_nodes():
 			graphs = generate_graphs(num_nodes)
 
 			# Compute Gram matrix.
+			run_time = 'error'
 			try:
 				gram_matrix, run_time = compute_graph_kernel(graphs, kernel_name, n_jobs=1)
-				run_times[kernel_name].append(run_time)
 			except Exception as exp:
 				run_times[kernel_name].append('error')
 				print('An exception occured when running this experiment:')
 				LOG_FILENAME = save_dir + 'error.txt'
 				logging.basicConfig(filename=LOG_FILENAME, level=logging.DEBUG)
 				logging.exception('')
 				print(repr(exp))
+			run_times[kernel_name].append(run_time)
 
 			pickle.dump(run_time, open(save_dir + 'run_time.' + kernel_name + '.' + str(num_nodes) + '.pkl', 'wb'))
 

gklearn/experiments/papers/PRL_2020/synthesized_graphs_num_nodes.py

@@ -27,7 +27,7 @@
 Dataset_List = ['Alkane', 'Acyclic', 'MAO', 'PAH', 'MUTAG', 'Letter-med', 'ENZYMES', 'AIDS', 'NCI1', 'NCI109', 'DD']
 
 
-def compute_graph_kernel(graphs, kernel_name, n_jobs=multiprocessing.cpu_count()):
+def compute_graph_kernel(graphs, kernel_name, n_jobs=multiprocessing.cpu_count(), chunksize=None):
 
 	if kernel_name == 'CommonWalk':
 		from gklearn.kernels.commonWalkKernel import commonwalkkernel
@@ -105,6 +105,7 @@ def compute_graph_kernel(graphs, kernel_name, n_jobs=multiprocessing.cpu_count()
 
 # 	params['parallel'] = None
 	params['n_jobs'] = n_jobs
+	params['chunksize'] = chunksize
 	params['verbose'] = True
 	results = estimator(graphs, **params)