Add exps.

Author: jajupmochi

Problems.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'
 
@@ -18,4 +18,6 @@ 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
 ```

README.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
 

gklearn/experiments/papers/PRL_2020/runtimes_diff_chunksizes.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/utils.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)