def gather_perf_data(alg, rev, index, latest):
"""Gathers performance data for a single revision of an algorithm"""
print 'gathering perf data for %s (rev=%s index=%u latest=%s)' % (alg, rev, index, str(latest))
# get the results
results = {} # maps (|V|, |E|) to ResultAccumulator
ds = DataSet.read_from_file(PerfResult, PerfResult.get_path_to(rev))
for data in ds.dataset.values():
key = (data.input().num_verts, data.input().num_edges)
result = results.get(key)
if result is None:
result = ResultAccumulator(data.time_sec)
result.defaultCI = DEFAULT_CI
results[key] = result
else:
result.add_data(data.time_sec)
# put the results in order
keys_density = results.keys()
keys_density.sort(density_compare)
keys_pom = results.keys()
keys_pom.sort(pom_compare)
keys = {}
keys['density'] = keys_density
keys['pom'] = keys_pom
# compute stats for all the results
for num_verts in results.keys():
results[num_verts].compute_stats()
# generate dat files for each x-axis cross important vertex counts
for xaxis in keys:
if xaxis == 'pom':
computex = lambda v, e : get_percent_of_max(v, e)
elif xaxis == 'density':
computex = lambda v, e : get_density(v, e)
else:
print >> sys.stderr, "unexpected x-axis value: " + str(xaxis)
sys.exit(-1)
header_txt = '#|V|\t|E|\t' + xaxis + '\tLower\tAverage\tUpper\t#Runs (Lower/Upper from ' + str(DEFAULT_CI) + '% CI)'
for vip in IMPORTANT_VERTS:
# open a file to output to
dat = get_output_dat_name(xaxis, alg, rev, index, vip)
print 'creating ' + dat
if latest:
latest_fn = make_latest(xaxis, alg, rev, index, vip)
try:
fh = open(dat, 'w')
# compute relevant stats and output them
print >> fh, header_txt
count = 0
for (v, e) in keys[xaxis]:
if vip=='all' or vip==v:
count += 1
r = results[(v, e)]
x = computex(v, e)
print >> fh, '%u\t%u\t%.6f\t%.3f\t%.3f\t%.3f\t%u' % (v, e, x, r.lower99, r.mean, r.upper99, len(r.values))
fh.close()
# don't create empty files
if count == 0:
quiet_remove(dat)
if latest:
quiet_remove(latest_fn)
except IOError, e:
print sys.stderr, "failed to write file: " + str(e)
return -1
elif options.inputs_list_file is not None:
input_solns = DataSet.read_from_file(InputSolution, options.inputs_list_file)
# prepare for a correctness data collection
if options.correctness:
num_on += 1
get_results_for_rev = lambda rev : DataSet.read_from_file(CorrResult, CorrResult.get_path_to(rev))
options.inputs_list_file_arg = '' if options.inputs_list_file is None else ' -l ' + options.inputs_list_file
collect_missing_data = lambda w,x,y,z: collect_missing_correctness_data(w,x,y,z,options.inputs_list_file_arg)
# make sure no more than 1 type of data collection was specified
if num_on > 1:
parser.error('at most one of -c, -d, and -e may be specified')
elif num_on == 0:
# prepare for a performance data collection (default if nothing else is specified)
get_results_for_rev = lambda rev : DataSet.read_from_file(PerfResult, PerfResult.get_path_to(rev))
collect_missing_data = collect_missing_performance_data
# prepare the inputs and revisions for non-weight data collection schemes
if options.num_vertices == 0:
# get all performance inputs if we are not collecting for a single graph
if input_solns is None:
input_path = InputSolution.get_path_to(1, 0, 0, 100000)
input_solns = DataSet.read_from_file(InputSolution, input_path)
# prepare the revisions to collect data for
if options.rev is not None:
if options.rev.lower() == 'all':
revs = get_tracked_revs()
else:
revs = [options.rev]
