def test_heuristics(dataset_name, min_k, max_k, k_step, nSamples, results_file, tau_scale, cores):
n = LinkServerCP(dataset_name).getNumNodes()
nBFS_theoretic = int(n *log(n, 2))
f = open(results_file,'w')
f.write('# Dataset: %s\n'%dataset_name)
f.write('\t'.join('INFEST(%d,%d)'%(init_samples, iter_samples) for init_samples, iter_samples in \
infest_heuristics) + '\n')
f.write('\t'.join('Vanilla(%d)'%(vanilla_samples) for vanilla_samples in vanilla_heuristics) + '\n')
f.close()
for k_frac in np.arange(min_k, max_k, k_step):
print "k_frac = ", k_frac
k = int(n * k_frac)
seeds_fname = "%s-seeds-%d.cp"%(dataset_name, k)
for i in xrange(nSamples):
print "sample #",i
print "Testing heuristics for dataset: ", dataset_name
generateSeedFiles(k, k+1, 1, range(n), 1, dataset_name + "-seeds-")
seeds=cp.load(open(seeds_fname,'r'))
true_value, num_cycles_full = 0, 0
print "taking %d samples to evaluate the true value of spread"%nBFS_samples
true_value, num_cycles_full = runVanilla(dataset = dataset_name, seeds = seeds_fname, nCores = cores, min_samples = min_nSamples, min_relative_std_error = min_relative_error)
print "true value is: ", true_value
num_cycles_full = int(1. * nBFS_theoretic / nBFS_samples * num_cycles_full)
infest_results = []
print "Running INFEST based heuristics"
for init_samples, iter_samples in infest_heuristics:
print "INFEST(%d,%d)"%(init_samples, iter_samples)
approx_estimate, num_cycles_approx = runApproxHeuristic(dataset_name, seeds_fname, tau_scale, cores,\
init_samples, iter_samples)
infest_results.append((approx_estimate, num_cycles_approx))
vanilla_results = []
print "Running Vanilla based heuristics"
for samples in vanilla_heuristics:
seq_estimate, num_cycles_seq = runVanilla(dataset_name, seeds_fname, samples, cores)
vanilla_results.append((seq_estimate, num_cycles_seq))
removeFile(seeds_fname)
f = open(results_file, 'a')
f.write('%.6f\t%.6f\t%d\t'%(k_frac, true_value, num_cycles_full) + '\t'.join('%d\t%d'%results for results in infest_results) + '\t' + \
'\t'.join('%d\t%d'%results for results in vanilla_results) + '\n')
f.close()
#n = len(V)
print "Number of nodes: ", n
nBFS_samples = 1000
running_times_file = results_dir + output + '-running_times-ratios_k_min-%.3f-k_max-%.3f-samples-%d-bfs_samples-%d-large'%(min_frac,max_frac,nSamples,nBFS_samples)
running_times_file_raw = running_times_file + "-raw"
removeFile(running_times_file)
f = open(running_times_file, 'w')
f_raw = open(running_times_file_raw,'w')
nBFS_samples = 1000
nBFS_samples_theoretic = n * log(n,2)
for nSeeds in xrange(int(min_frac * n), int(max_frac * n), int(interval * n)):
print "k = ", nSeeds
seeds_fname = output + "-seeds-" + str(nSeeds) + '.cp'
runtimes_approx, runtimes_seq = [], []
for i in xrange(nSamples):
generateSeedFiles(nSeeds, nSeeds+1, int(interval * n), range(n), 1, output + "-seeds-")
perf_csv_fname = dataset + 'runtimes_large.csv'
subprocess.Popen("perf stat -x, -o %s python ic_bfs_eval.py -dataset %s -res_fname %s -seeds %s -output_mode 3 -cores %d"%\
(perf_csv_fname, dataset, output + "-approx-" + str(nSeeds), seeds_fname, parameters.cores), \
shell = True, stdout = subprocess.PIPE).stdout.read()
num_cycles_approx = getNumCycles(perf_csv_fname)
runtimes_approx.append(num_cycles_approx)
print "Done approximating, now running naive sequential algorithm"
removeFile(perf_csv_fname)
subprocess.Popen("perf stat -x, -o %s python seq_estimation.py -dataset %s -seeds_file %s -results_file %s -output_mode 3 -nSamples %d -cores %d"%(perf_csv_fname, dataset, seeds_fname, output + "-seq-" + str(nSeeds), nBFS_samples, parameters.cores), shell=True,stdout=subprocess.PIPE).stdout.read()
runtime_seq_samples = getNumCycles(perf_csv_fname)
theoretic_num_cycles = 1.0 * runtime_seq_samples / nBFS_samples * nBFS_samples_theoretic
runtimes_seq.append(theoretic_num_cycles)
f_raw.write('%.3f\t%.3f\t%.3f\n'%(1.*nSeeds/n, num_cycles_approx, theoretic_num_cycles))
removeFile('runtimes_large_seq.csv')
print "runtimes_approx: ", runtimes_seq
n = L.getNumNodes()
if k_mode == 0:
nSeeds = int(n * k)
else:
nSeeds = int(k)
perf_csv_fname = "perf_out" + str(sample(range(1000),1)[0]) + ".csv"
print "Number of nodes: ", n
print "nSeeds = ", nSeeds
results_file = results_dir + output + '-influence_values_samples_min-%d-samples_max-%d-k-%.3f-prob_method-%d'%(min_samples,max_samples, k, prob_method)
removeFile(results_file)
seeds_fname = "%s-seeds-%d.cp"%(dataset,nSeeds)
generateSeedFiles(nSeeds, nSeeds+1, 1, range(n), 1, dataset + "-seeds-")
removeFile(results_file)
values = []
for samples in xrange(min_samples, max_samples+1, samples_step):
print "number of samples = ", samples
output_fname = results_dir + 'nReached%d.txt'%random.randint(1,1000)
subprocess.Popen("python seq_estimation.py -dataset %s -cores %d -seeds_file %s -results_file %s -output_mode 3 -nSamples %d -get_n_reached 1 -reached_nodes_file %s"%(dataset, parameters.cores, seeds_fname, output + "-seq-" + str(nSeeds), samples_step, output_fname), shell=True,stdout=subprocess.PIPE).stdout.read()
removeFile(output + "-seq-" + str(nSeeds))
f_values = open(output_fname,'r')
values += [int(v) for v in f_values.readline().strip().split()]
f_values.close()
removeFile(output_fname)
print "spread values for %d samples: %s"%(samples,str(values))
f = open(results_file, 'a')
f.write('%d\t%.5f\t%s\n'%(samples, np.std(values), "\t".join(str(val) for val in values)))
f.close()
print "creating link-server object"
if parameters.prob_method == 0:
edge_prob = 0.2
else:
edge_prob = [0.1,0.01]
L=LinkServerCP(dataset, edges_csv, create_new=True, prob_method=parameters.prob_method, prob=edge_prob, delim=delimiter, undirected=parameters.undirected)
print "n = ", L.getNumNodes()
V = LoadNodesFromFile(edges_csv, delimiter)
n = len(V)
print 'min_frac', min_frac
k_min = int(n * min_frac)
k_max = int(n * max_frac) + 1
k_step = int(n * interval)
generateSeedFiles(k_min, k_max, k_step, V, nSamples, 'experiments/' + output + "-seeds-")
mean_errors, std_errors = [], []
for k in xrange(k_min, k_max,k_step):
approx_fname = 'experiments/results/' + output + "-approx_errors-k_min-%d-k_max-%d-k-%d-samples-%d"%(k_min,k_max,k,nSamples)
seq_fname = 'experiments/results/' + output + "-seq-approx-errors-k-%d-samples-%d"%(k,nSamples)
print approx_fname
print seq_fname
removeFile(approx_fname)
seeds_fname = 'experiments/' + output + "-seeds-" + str(k) + ".cp"
print "Running approx algorithm for k=: ", k
subprocess.Popen("python ic_bfs_eval.py -dataset %s -res_fname %s -seeds %s -output_mode 2"%\
(dataset, approx_fname, seeds_fname), \
shell = True, stdout = subprocess.PIPE).stdout.read()
print "creating link-server object"
if parameters.prob_method == 0:
edge_prob = 0.2
else:
edge_prob = [0.1,0.01]
L=LinkServerCP(dataset, edges_csv, create_new=True, prob_method=parameters.prob_method, prob=edge_prob, delim=delimiter)
print "n = ", L.getNumNodes()
V = LoadNodesFromFile(edges_csv, delimiter)
n = len(V)
k = int(n * k_frac)
print "n=", n
print "k=", k
seeds_fname = output + "-seeds-" + str(k) + ".cp"
removeFile(seeds_fname)
removeFile(dataset)
generateSeedFiles(k, k+1, 1, V, nSamples, output + "-seeds-")
approx_fnames = ['experiments/results/' + output + "-approx-k-%d-samples-%d-scale-%.5f"%(k,nSamples,scale) for scale in drange(min_frac,max_frac,interval)]
seq_fname = 'experiments/results/' + output + "-seq-k-%d-samples-%d-eps-%.5f"%(k,nSamples,eps)
for i, scale in enumerate(drange(min_frac, max_frac, interval)):
removeFile(approx_fnames[i])
print "Running approx algorithm for scale factor: ", scale
subprocess.Popen("python ic_bfs_eval.py -dataset %s -scale %.5f -res_fname %s -seeds %s -output_mode 0"%\
(dataset, scale, approx_fnames[i], seeds_fname), \
shell = True, stdout = subprocess.PIPE).stdout.read()
print "Running sequential algorithm on seed sets with eps=%.5f"%eps
removeFile(seq_fname)
subprocess.Popen("python seq_estimation.py -dataset %s -seeds_file %s -results_file %s -output_mode 2 -min_samples 500 -min_relative_standard_error 0.01 "%\
(dataset, seeds_fname, seq_fname), shell=True,stdout=subprocess.PIPE).stdout.read()
if k_mode == 0:
nSeeds = int(n * k)
else:
nSeeds = int(k)
approx_results_fname = output + "-equal_times-approx-" + str(k) + '-' + str(sample(range(1000),1)[0])
perf_csv_fname = "perf_out" + str(sample(range(1000),1)[0]) + ".csv"
nBFS_samples = 1000
print "Number of nodes: ", n
print "nSeeds = ", nSeeds
results_file = results_dir + output + '-influence_concentration_samples_min-%d-samples_max-%d-k-%.3f-prob_method-%d-nSeeds_sets-%d'%(min_samples,max_samples, k, prob_method, seed_sets)
removeFile(results_file)
seeds_fname = "%s-seeds-%d.cp"%(results_dir + output, nSeeds)
generateSeedFiles(nSeeds, nSeeds+1, 1, range(n), seed_sets, results_dir + output + "-seeds-")
values = []
for samples in xrange(min_samples, max_samples+1, samples_step):
print "number of samples = ", samples
output_fname = results_dir + 'nReached%d.txt'%random.randint(1,1000)
subprocess.Popen("python seq_estimation.py -dataset %s -cores %d -seeds_file %s -results_file %s -output_mode 3 -nSamples %d -get_n_reached 1 -reached_nodes_file %s"%(dataset, parameters.cores, seeds_fname, output + "-seq-" + str(nSeeds), samples_step, output_fname), shell=True,stdout=subprocess.PIPE).stdout.read()
removeFile(output + "-seq-" + str(nSeeds))
f_values = open(output_fname,'r')
f = open(results_file, 'a')
for i, line in enumerate(f_values.readlines()):
values += [int(v) for v in line.strip().split()]
f.write('%d\t%.5f\n'%(samples, sem(values)/np.mean(values)))
f.close()
f_values.close()
removeFile(output_fname)
'-approx-heuristic-prob_method-%d-k_min-%.4f-k_max-%.4f-tau_scale-%.3f-samples-%d-bfs_samples-%d-init_samples-%d-iter_samples-%d'%\
(parameters.prob_method, min_k, max_k, tau_scale, nSamples, nBFS_samples, init_samples, iter_samples)
removeFile(results_file)
# Record time to load link-server file
subprocess.Popen("perf stat -x, -o %s python load_link_server.py -cp %s"%\
(perf_csv_fname, dataset), shell = True, stdout = subprocess.PIPE).stdout.read()
nCycles_link_server = getNumCycles(perf_csv_fname)
print "Number of cycles for loading link server: ", nCycles_link_server
removeFile(perf_csv_fname)
for k in xrange(int(min_k),int(max_k + 1), int(k_step)):
print "k = ", k
seeds_fname = "%s-seeds-%d.cp"%(output, k)
for i in xrange(nSamples):
print "sample #",i
generateSeedFiles(k, k+1, 1, range(n), 1, output + "-seeds-")
seeds=cp.load(open(seeds_fname,'r'))
print "Running Vanilla with %d samples"%(nBFS_samples)
true_value, num_cycles_full = runVanilla(dataset, seeds_fname, nBFS_samples, parameters.cores)
print "Done. Number of cycles: %d"%num_cycles_full
nCycles_per_bfs = 1.*(num_cycles_full - nCycles_link_server) / nBFS_samples
print "Number of cycles per sample", nCycles_per_bfs
print "Running approximation algorithm"
approx_estimate, num_cycles_approx = runApproxHeuristic(dataset, seeds_fname, tau_scale, parameters.cores,\
parameters.init_samples, parameters.iter_samples, nCycles_link_server)
print "Number of cycles without link-server loading: ", num_cycles_approx
print "Done approximating, now running naive sequential algorithm"
nVanilla_samples = int(ceil(1. * num_cycles_approx / nCycles_per_bfs))
print "Running Vanilla for %s samples"%nVanilla_samples
seq_estimate, num_cycles_seq = runVanilla(dataset, seeds_fname, nVanilla_samples, parameters.cores)
create_new=True,
prob_method=parameters.prob_method,
prob=edge_prob,
delim=delimiter,
undirected=parameters.undirected)
print "n = ", L.getNumNodes()
V = LoadNodesFromFile(edges_csv, delimiter)
n = len(V)
k_min = int(n * min_frac)
k_max = int(n * max_frac) + 1
k_step = int(n * interval)
print "max_k = ", max_frac
print "Minimum k value: %d, maximum k value: %d" % (k_min, k_max)
removeFile(dataset)
generateSeedFiles(k_min, k_max, k_step, V, nSamples,
'experiments/' + output + "-seeds-")
results_fname = "experiments/results/" + output + '-approximations-nSamples-%d-k_frac-%.3f-%.3f' % (
nSamples, min_frac, max_frac)
removeFile(results_fname)
mean_errors, std_errors = [], []
for k in xrange(k_min, k_max, k_step):
approx_fname = 'experiments/results/' + output + \
"-approx_errors-k_min-%d-k_max-%d-k-%d-samples-%d"%(k_min,k_max,k,nSamples)
seq_fname = 'experiments/results/' + output + "-seq-approx-errors-k-%d-samples-%d" % (
k, nSamples)
seeds_fname = 'experiments/' + output + "-seeds-" + str(k) + ".cp"
removeFile(seq_fname)
print "Running sequential algorithm for k=%d" % k
subprocess.Popen("python seq_estimation.py -dataset %s -seeds_file %s -cores 40 -results_file %s -output_mode 2 -min_samples 500\
L = LinkServerCP(dataset,
edges_csv,
create_new=True,
prob_method=parameters.prob_method,
prob=edge_prob,
delim=delimiter)
print "n = ", L.getNumNodes()
V = LoadNodesFromFile(edges_csv, delimiter)
n = len(V)
k = int(n * k_frac)
print "n=", n
print "k=", k
seeds_fname = output + "-seeds-" + str(k) + ".cp"
removeFile(seeds_fname)
removeFile(dataset)
generateSeedFiles(k, k + 1, 1, V, nSamples, output + "-seeds-")
approx_fnames = [
'experiments/results/' + output +
"-approx-k-%d-samples-%d-scale-%.5f" % (k, nSamples, scale)
for scale in drange(min_frac, max_frac, interval)
]
seq_fname = 'experiments/results/' + output + "-seq-k-%d-samples-%d-eps-%.5f" % (
k, nSamples, eps)
for i, scale in enumerate(drange(min_frac, max_frac, interval)):
removeFile(approx_fnames[i])
print "Running approx algorithm for scale factor: ", scale
subprocess.Popen("python ic_bfs_eval.py -dataset %s -scale %.5f -res_fname %s -seeds %s -output_mode 0"%\
(dataset, scale, approx_fnames[i], seeds_fname), \
shell = True, stdout = subprocess.PIPE).stdout.read()
L=LinkServerCP('input/datasets/' + dataset, csv_fname, create_new=True, prob_method=parameters.prob_method, prob=[0.1,0.01], delim='\t', undirected = 1)
# record loading time of link-server -- for interpolation
removeFile(perf_output_fname)
subprocess.Popen("perf stat -x, -o %s python load_link_server.py -cp %s"%\
(perf_output_fname, "input/datasets/" + dataset), shell = True, stdout = subprocess.PIPE).stdout.read()
nCycles_link_server = getNumCycles(perf_output_fname)
removeFile(perf_output_fname)
#removeFile(csv_fname)
V = xrange(n)
for nSeeds in xrange(int(min_frac * n), int(max_frac * n), int(interval * n)):
for i in xrange(nSamples):
seeds_fname = output + "-seeds-%d-%d.cp"%(i, nSeeds)
generateSeedFiles(nSeeds, nSeeds+1, int(interval * n), V, 1, output + "-seeds-%d-"%i)
subprocess.Popen("perf stat -x, -o %s python ic_bfs_eval.py -dataset %s -cores %d -res_fname %s -seeds %s -output_mode 3 -undirected 1"%\
(perf_output_fname, 'input/datasets/' + dataset, parameters.cores, output + "-approx-" + str(nSeeds), seeds_fname), \
shell = True, stdout = subprocess.PIPE).stdout.read()
cycles_approx = getNumCycles(perf_output_fname)
cycles_seq = {}
print "Done approximating, now running naive sequential algorithm"
for eps in eps_list:
print "Running sequential for eps = ", eps
removeFile(perf_output_fname)
subprocess.Popen("perf stat -x, -o %s python seq_estimation.py -dataset %s -cores %d -seeds_file %s -results_file %s -output_mode 3 -nSamples %d"%(perf_output_fname, 'input/datasets/' + dataset, parameters.cores, seeds_fname, output + "-seq-" + str(nSeeds), nBFS_samples), shell=True,stdout=subprocess.PIPE).stdout.read()
cycles_seq[eps] = (n*log(n,2) / nBFS_samples) * (getNumCycles(perf_output_fname) - nCycles_link_server) + nCycles_link_server
removeFile(perf_output_fname)
for i, eps in enumerate(eps_list):
f = open(running_times_files[i],'a')
