parameters = parser.parse_args()
min_frac, max_frac, interval, nSamples, edges_csv, delim_option, output, dataset, seq_samples_scale = parameters.min, \
parameters.max, parameters.interval, parameters.samples, parameters.csv, parameters.delim, parameters.output, parameters.dataset, parameters.seq_samples_scale#,\
#[float(x) for x in parameters.eps.split(',')], parameters.title
delim_dict = {0 : '\t', 1 : ' ', 2 : ','}
delimeter = delim_dict[delim_option]
results_dir = 'experiments/results/'
bUndirected = True if parameters.undirected == 1 else False
bfs_method = 'seq'
start_time = time()
print "creating link-server object"
if delimeter == "\t":
print "delimeter is tab"
L=LinkServerCP(dataset, edges_csv, create_new=True, prob_method=parameters.prob_method, prob=[0.1,0.01], delim=delimeter, undirected = bUndirected)
n = L.getNumNodes()
#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):
min_frac, max_frac, interval, nSamples, edges_csv, delim_option, output, dataset = parameters.min, \
parameters.max, parameters.interval, parameters.samples, parameters.csv, parameters.delim, parameters.output, parameters.dataset
print "Input file: ", edges_csv
print "Output file prefix: ", output
delimiter = delim_dict[delim_option]
start_time = time()
bfs_method = 'seq'
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)
parameters.min_samples, parameters.max_samples, parameters.samples_step, parameters.k_mode, parameters.k,\
parameters.csv, parameters.delim, parameters.output, parameters.dataset, parameters.prob_method, parameters.cores
print "Dataset: ", dataset
delim_dict = {0 : '\t', 1 : ' ', 2 : ','}
delimeter = delim_dict[delim_option]
results_dir = 'experiments/results/influence_values/'
bUndirected = True if parameters.undirected == 1 else False
bfs_method = 'seq'
start_time = time()
print "creating link-server object"
if delimeter == "\t":
print "delimeter is tab"
L=LinkServerCP(dataset, edges_csv, create_new=True, prob_method=parameters.prob_method, prob=[0.1,0.01], delim=delimeter, undirected = bUndirected)
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-")
delimiter = delim_dict[delim_option]
start_time = time()
bfs_method = 'seq'
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)
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 = [], []