def make_childmap(self):
visited = set([])
q = Queue()
q.put((self.git.head.commit, None)) # (commit, child_hash)
progress = Progress(u'[%s] making git childmap' % self.__name__, 500,
10000, False)
progress.set_point(0)
progress.start()
while q.empty() is False:
progress.check()
commit, child_hash = q.get()
commit_hash = str(commit)[:7]
# create child map
if commit_hash not in self.childmap:
self.childmap[commit_hash] = set([])
if child_hash is not None:
self.childmap[commit_hash].add(child_hash)
if commit_hash in visited: continue
visited.add(commit_hash)
# pass itself to parent
for parent in commit.parents:
q.put((parent, commit_hash))
# add ancestors if this commit has no parents
if len(commit.parents) == 0:
self.ancestors.add(commit_hash)
progress.done()
pass
def _encode(self):
logger.info('encoding lua tables')
Progress.start('Decoding MIZ file', length=3)
Progress.set_label('Encoding map resource')
logger.debug('encoding map resource')
with open(self.map_res_file, mode='w', encoding=ENCODING) as f:
f.write(SLTP().encode(self._map_res, self._map_res_qual))
Progress.set_value(1)
Progress.set_label('Encoding map resource')
logger.debug('encoding l10n dictionary')
with open(self.dictionary_file, mode='w', encoding=ENCODING) as f:
f.write(SLTP().encode(self.l10n, self._l10n_qual))
Progress.set_value(2)
Progress.set_label('Encoding map resource')
logger.debug('encoding mission dictionary')
with open(self.mission_file, mode='w', encoding=ENCODING) as f:
f.write(SLTP().encode(self.mission.d, self._mission_qual))
Progress.set_value(3)
logger.info('encoding done')
def loads(self):
'''
loads a raw file of bug report
:return:
'''
fileConnt = self.getFileCounts(self.SourceBugPath)
bugitems = []
# show progress
progress = Progress(u'[%s] Loading bug reports' % self.__name__, 2, 10,
True)
progress.set_upperbound(fileConnt)
progress.start()
for root, dirs, files in os.walk(self.SourceBugPath):
for f in files:
if f[:f.find(u'-')].strip().lower() != self.ProjectName.lower(
):
continue
#shutil.copy(os.path.join(root, f), os.path.join(_dest, f))
bugitem = self.get_bugitem(os.path.join(root, f))
if bugitem is not None:
bugitems.append(bugitem)
progress.check()
progress.done()
return bugitems
def load(self, _force=False):
'''
Load commit info from GitLogPath
:return: {bugID:[{'hash':u'', 'author':u'', 'commit_date':u'', 'message':u'', 'fixedFiles':{}}, {}, ...], ...}
'''
if os.path.exists(self.GitLogPath) is False or _force is True:
self.make()
logfile = codecs.open(self.GitLogPath, 'r', 'utf-8')
progress = Progress(u'[%s] loading git log data' % self.__name__, 1000,
20000, False)
progress.set_point(0)
progress.start()
for logitem in self.file_loader(logfile, _with_filter=False):
# filter unuseful logs
if len(logitem['fixedFiles']) == 0: continue
# We only use bug report id in log message
# mapping bug report ID
logitem['linked_bug'] = re.findall(
r'%s-[0-9]+' % self.ProjectName.upper(), logitem['message'])
logitem['linked_bug'] = set(logitem['linked_bug'])
for linked_id in logitem['linked_bug']:
if linked_id not in self.logs:
self.logs[linked_id] = [logitem]
else:
self.logs[linked_id].append(logitem)
progress.check()
progress.done()
logfile.close()
return self.logs
def _decode(self):
logger.info('decoding lua tables')
if not self.zip_content:
self.unzip(overwrite=False)
Progress.start('Decoding MIZ file', length=3)
Progress.set_label('Decoding map resource')
logger.debug('reading map resource file')
with open(self.map_res_file, encoding=ENCODING) as f:
self._map_res, self._map_res_qual = SLTP().decode(f.read())
Progress.set_value(1)
Progress.set_label('Decoding dictionary file')
logger.debug('reading l10n file')
with open(self.dictionary_file, encoding=ENCODING) as f:
self._l10n, self._l10n_qual = SLTP().decode(f.read())
Progress.set_value(2)
Progress.set_label('Decoding mission file')
logger.debug('reading mission file')
with open(self.mission_file, encoding=ENCODING) as f:
mission_data, self._mission_qual = SLTP().decode(f.read())
self._mission = Mission(mission_data, self._l10n)
Progress.set_value(3)
logger.info('decoding done')
def fill_SubjectSheet(self, _sheet, _group, _srcCounts, _bugCounts, _dupCounts): projects = _bugCounts.keys() projects.sort() size = sum([len(_bugCounts[project]) for project in projects]) progress = Progress(u'[%s] fill subject' % self.__name__, 2, 10, True) progress.set_point(0).set_upperbound(size) progress.start() styles = [self.base_format, self.base_format, self.base_format, self.number_format, self.number_format] for project in projects: for version in _bugCounts[project].keys(): if version == 'all': continue values = [_group, project, version.upper(), _bugCounts[project][version], _srcCounts[project][version]] self.input_row(_sheet, self.subj_data_row, 6, values, styles) self.subj_data_row += 1 progress.check() progress.done() #summary styles = [self.subtitle_format, self.subtitle_format, self.number_format, self.number_format, self.number_format] for project in projects: values = [_group, project.upper(), _bugCounts[project]['all'], _dupCounts[project], _srcCounts[project]['all']] self.input_row(_sheet, self.subj_summary_row, 0, values, styles) self.subj_summary_row += 1 pass
def source_counting(self, _group, _project):
statistics = {}
progress = Progress('source counting', 2, 10, True)
progress.set_upperbound(len(self.S.versions[_project].keys()))
progress.start()
for version in self.S.versions[_project].keys():
vname = VersionUtil.get_versionName(version, _project)
repo = os.path.join(self.S.getPath_source(_group, _project,
vname), )
result = self.getCodeCount(repo)
if result is None: continue
statistics[vname] = result
progress.check()
progress.done()
maxValue = 0
for vname in statistics:
if maxValue < statistics[vname]:
maxValue = statistics[vname]
statistics['max'] = maxValue
pretty = PrettyStringBuilder(_indent_depth=2)
text = pretty.get_dicttext({_project: statistics})
f = open(
os.path.join(self.S.getPath_base(_group, _project),
u'sources.txt'), 'w')
f.write(text)
f.close()
def get_hump_error_per_type():
query = """SELECT DISTINCT run.aggregate_id, aggregate_type.type_id FROM `run`
LEFT OUTER JOIN aggregate_type
ON run.aggregate_id = aggregate_type.aggregate_id
WHERE dissipation < 0.01"""
session = get_session()
aggregate_ids = session.execute(query).fetchall()
session.close()
errors = {
1: [],
2: [],
3: [],
4: [],
5: []
}
p = Progress(len(aggregate_ids))
p.start()
cnt = 0
for aggregate_id,type_id in aggregate_ids:
err,alpha = get_hump_info(aggregate_id)
errors[type_id].append(err)
cnt += 1
p.update(cnt)
p.finish()
x = errors.keys()
y = [np.mean(yi) for yi in errors.values()]
yerr = [np.std(yi) for yi in errors.values()]
ymax = [np.max(yi) for yi in errors.values()]
ymin = [np.min(yi) for yi in errors.values()]
with file('./simulation_data/type_hump_error_ranges.bin','wb') as fp:
pickle.dump(errors,fp)
fig = pplot.figure()
ax = fig.add_subplot(311)
ax.bar(x,y,yerr=yerr,color='b')
ax.set_ylabel("Avergage power law error")
ax.set_xlabel("Type")
ax = fig.add_subplot(312)
ax.set_ylabel("Maximum power law error")
ax.set_xlabel("Type")
ax.bar(x,ymax, color='r')
ax = fig.add_subplot(313)
ax.set_ylabel("Minimum power law error")
ax.set_xlabel("Type")
ax.bar(x,ymin, color='g')
pplot.show()
def unhash_folder(_src, _dest):
'''
hashed folder ==> unshed folder
example) path/aa/00/filename ==> path/filename
:param _src:
:param _dest:
:return:
'''
if os.path.exists(_dest) is False:
os.makedirs(_dest)
progress = Progress(u'Bug reports is merging', 20, 1000, False)
progress.start()
for root, dirs, files in os.walk(_src):
for f in files:
shutil.copy(os.path.join(root, f), os.path.join(_dest, f))
progress.check()
progress.done()
def make_tagmap(self, ):
q = Queue()
visited = set([])
# root node find (queue init)
for item in list(self.ancestors):
q.put((item, None)) # (commit_hash, tagname)
# For each item in queue
progress = Progress(u'[%s] making git tagmaps' % self.__name__, 500,
10000, False)
progress.set_point(0)
progress.start()
while q.empty() is False:
commit_hash, parent_tag = q.get()
# If this commit in tags, map with commit_hash and tag
if commit_hash in self.tags:
commit_tag = self.tags[commit_hash]
self.tagmap[commit_hash] = commit_tag
# if this commit not in tags, map with child commit_hash and tag
else:
if commit_hash not in self.tagmap:
self.tagmap[commit_hash] = parent_tag
else:
# compare time previous_tag and parent_tag
previous_tag = self.tagmap[commit_hash]
pre_time = self.tagtimes[previous_tag]
par_time = self.tagtimes[parent_tag]
if par_time > pre_time:
self.tagmap[commit_hash] = parent_tag
commit_tag = parent_tag
if commit_hash not in visited:
visited.add(commit_hash)
for child_hash in self.childmap[commit_hash]:
q.put((child_hash, commit_tag))
progress.check()
progress.done()
pass
def download(url,
local_file,
progress_title: str,
progress_text: str = '',
file_size: int = None):
logger.info('downloading {} -> {}'.format(url, local_file))
Progress.start(progress_title)
Progress.set_label(progress_text)
def hook(data):
Progress.set_value(float(data['percent_complete']))
dl = Downloader(
url=url,
filename=local_file,
progress_hooks=[hook],
content_length=file_size,
)
return dl.download()
def load_raw(self, _force=False):
'''
Load commit info from GitLogPath
:return: {bugID:[{'hash':u'', 'author':u'', 'commit_date':u'', 'message':u'', 'fixedFiles':{}}, {}, ...], ...}
'''
if os.path.exists(self.GitLogPath) is False or _force is True:
self.make()
self.logs = []
logfile = codecs.open(self.GitLogPath, 'r', 'utf-8')
progress = Progress(u'[%s] loading git log data' % self.__name__, 1000,
20000, False)
progress.set_point(0)
progress.start()
for logitem in self.file_loader(logfile):
# filter unuseful logs
#if len(logitem['fixedFiles'])==0: continue
if logitem['hash'] == '': continue
self.logs.insert(0, logitem)
progress.check()
progress.done()
logfile.close()
return self.logs
def run(self):
agstart = time.time()
for i in xrange(self.no_sims):
logging.info("Going for simulation %d"%(i+1))
gc.collect()
run_id = str(uuid4())
with DataContainer(self.config,run_id,self.aggregate_id) as dc:
p = Progress(self.config['model']['no_steps'])
model_class = None
if(self.market_type == 1):
logging.info("Using default Market")
model_class = Market
elif(self.market_type == 2):
logging.info("Using ShuffleIRSMarket")
model_class = ShuffleIRSMarket
elif(self.market_type == 3):
logging.info("Using SortedIRSMarket")
model_class = SortedIRSMarket
elif(self.market_type == 4):
logging.info("Using RandomSortedIRSMarket")
model_class = SortedRandomIRSMarket
elif(self.market_type == 5):
logging.info("Using RandomShuffleIRSMarket")
model_class = ShuffleRandomIRSMarket
elif(self.market_type == 6):
logging.info("Using ConstantRandomShuffleIRSMarket")
model_class = ConstShuffleIRSMarket
elif(self.market_type == 7):
logging.info("Using quick CRS-IRS-Mkt")
model_class = sim
else:
raise "No such market type"
p.start()
start = time.time()
with model_class(self.config['model'],dc,p.update) as m:
m.run()
t = time.time()-start
p.finish()
print ""
logging.info("Run took %f seconds"%t)
if(self.config['analysis']['do_analysis']):
start = time.time()
self.do_analysis(dc,run_id)
t = time.time()-start
logging.info("Analysis took %f seconds"%t)
if(self.save_data):
start = time.time()
dc.save_data()
t = time.time()-start
logging.info("Saving data took %f seconds"%t)
gc.collect()
print ""
print ""
gc.collect()
dt = (time.time() - agstart) / 60
logging.info("Experiment took %f minutes"%dt)
if(self.config['aggregate']['do_aggregate'] and self.save_data):
start = time.time()
self.do_aggregate(dc,run_id)
logging.info('Aggregation took %f seconds'%(time.time()-start))
if (s.save_density_for_avalanche_size):
s.density_per_avalanche_size = defaultdict(list)
s.save_gross_risk_for_avalanche_size = save_gross_risk_for_avalanche_size
if (s.save_gross_risk_for_avalanche_size):
s.gross_risk_per_avalanche_size = defaultdict(list)
s.gross_risk_per_avalanche_size = defaultdict(list)
if (s.save_avalanche_tree):
os.makedirs(s.avalanche_tree_file_path)
if (save_giant_component): s.giant_components = np.zeros(s.no_steps)
start = time.time()
p.start()
s.run()
p.finish()
print
print "Run took %d seconds" % (time.time() - start)
if (save):
print "Saving data"
dc.save_defaults()
dc.save_run()
if s.save_avalanche_progression:
print "Saving avalanche progression"
file_path = './simulation_data/avalanche_progression/%s.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
def do_run(steps,
no_banks,
threshold,
max_tenure,
max_irs_value,
avalanche_fraction=0.9):
#steps = 10000
save = False
save_risk = False
save_risk_avalanche_time_series = False
save_dist = False
save_giant_component = False
save_avalanche_progression = False
save_critical_info = False
save_avalanche_tree = False
save_degree_distribution = False
no_connection_scatter_moments = 0
connection_scatter_moments = np.random.randint(
0, steps, no_connection_scatter_moments)
seed = np.random.randint(0, 1000)
dcconfig = {
'model': {
'no_banks': no_banks,
'no_steps': steps,
'threshold': threshold,
'sigma': 1,
'max_irs_value': max_irs_value,
'irs_threshold': -1,
'dissipation': 0.0,
'max_tenure': max_tenure
},
'analysis': {
'data_to_save': ['defaults']
},
'file_root': './simulation_data/',
'market_type': 7,
'seed': seed
}
measure_no_steps = 2 * dcconfig['model']['max_tenure']
###########################################################################
dc = DataContainer(dcconfig, str(uuid4()), str(uuid4()))
p = Progress(steps)
s = sim(dcconfig['model'],
dc,
p.update,
save_risk,
save_dist,
connection_scatter_moments,
seed,
avalanche_fraction=avalanche_fraction)
s.save_degree_distribution = save_degree_distribution
if (s.save_degree_distribution):
s.degrees = np.zeros((steps, dcconfig['model']['no_banks']))
s.no_irs = np.zeros((steps, dcconfig['model']['no_banks']))
s.save_avalanche_progression = save_avalanche_progression
s.save_risk_avalanche_time_series = save_risk_avalanche_time_series
s.collect_critical_info = save_critical_info
s.save_giant_component = save_giant_component
s.save_avalanche_tree = save_avalanche_tree
s.avalanche_tree_file_path = './simulation_data/trees/%s/' % dc.aggregate_id
s.irs_creations = np.zeros(steps)
s.irs_removals = np.zeros(steps)
if (s.save_avalanche_tree):
os.makedirs(s.avalanche_tree_file_path)
if (save_giant_component): s.giant_components = np.zeros(s.no_steps)
###########################################################################
start = time.time()
p.start()
tme, size = s.run()
print
p.finish()
defaulting_bank = s.defaulting_bank_no
start_at = tme - measure_no_steps + 1
print "Large enough avalanche found at %d of size %d" % (tme, size)
print
print "Run took %d seconds" % (time.time() - start)
print
print "Going for the analysis"
###########################################################################
## Actual stuff thats needed
dc = DataContainer(dcconfig, str(uuid4()), str(uuid4()))
p = Progress(steps)
s = sim(dcconfig['model'],
dc,
p.update,
save_risk,
save_dist,
connection_scatter_moments,
seed,
start_at,
defaulting_bank,
avalanche_fraction=avalanche_fraction)
nb = dcconfig['model']['no_banks']
s.measured_balances = np.zeros((measure_no_steps, nb))
s.measured_gross_balances = np.zeros((measure_no_steps, nb))
s.degrees = np.zeros((measure_no_steps, nb))
s.no_irs = np.zeros((measure_no_steps, nb))
#s.giant_component = []
s.defaulted_nodes = []
s.irs_pb = []
s.network = np.zeros((nb, nb))
s.irs_creations = np.zeros(steps)
s.irs_removals = np.zeros(steps)
#################
s.save_degree_distribution = save_degree_distribution
s.save_avalanche_progression = save_avalanche_progression
s.save_risk_avalanche_time_series = save_risk_avalanche_time_series
s.collect_critical_info = save_critical_info
s.save_giant_component = save_giant_component
s.save_avalanche_tree = save_avalanche_tree
s.avalanche_tree_file_path = './simulation_data/trees/%s/' % dc.aggregate_id
if (s.save_avalanche_tree):
os.makedirs(s.avalanche_tree_file_path)
if (save_giant_component): s.giant_components = np.zeros(s.no_steps)
###########################################################################
start = time.time()
p.start()
tme, size = s.run()
p.finish()
print
print "Large enough avalanche found at %d of size %d" % (tme, size)
if s.save_avalanche_progression:
print "Saving avalanche progression"
file_path = './simulation_data/avalanche_progression/%s.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.avalanche_progressions, fp)
pickle.dump(dcconfig, fp)
if s.collect_critical_info:
print "Critical info"
file_path = './simulation_data/critical/%s.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.critical_info, fp)
pickle.dump(s.max_default_size_t.tolist(), fp)
if (s.save_giant_component):
pickle.dump(s.giant_components.tolist(), fp)
pickle.dump(dcconfig, fp)
if len(connection_scatter_moments) > 0:
print "Connection Scatters"
file_path = './simulation_data/connection_scatters/%s.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.connection_scatters, fp)
if save_dist:
file_path = './simulation_data/dists/%s.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.trials, fp)
pickle.dump(dcconfig['model']['no_banks'], fp)
if (True):
os.makedirs("./simulation_data/large_avalanche_data/%s" %
dc.aggregate_id)
print "Saving stuff"
file_path = './simulation_data/large_avalanche_data/%s/degrees.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.degrees.tolist(), fp)
file_path = './simulation_data/large_avalanche_data/%s/no_irs.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.no_irs.tolist(), fp)
pickle.dump(s.irs_pb, fp)
file_path = './simulation_data/large_avalanche_data/%s/balances.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.measured_balances.tolist(), fp)
pickle.dump(s.measured_gross_balances.tolist(), fp)
#file_path = './simulation_data/large_avalanche_data/%s/gc.bin'%dc.aggregate_id
#with file(file_path,'wb') as fp:
# pickle.dump(s.giant_component,fp)
file_path = './simulation_data/large_avalanche_data/%s/network.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.network.tolist(), fp)
file_path = './simulation_data/large_avalanche_data/%s/defaulted.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.defaulted_nodes, fp)
file_path = './simulation_data/large_avalanche_data/%s/irs_data.bin' % dc.aggregate_id
with file(file_path, 'wb') as fp:
pickle.dump(s.irs_creations.tolist(), fp)
pickle.dump(s.irs_removals.tolist(), fp)
dcconfig['failed_bank'] = s.defaulting_bank_no
file_path = './simulation_data/large_avalanche_data/%s/config.json' % dc.aggregate_id
with open(file_path, 'w') as fp:
json.dump(dcconfig, fp, indent=4)
print dc.aggregate_id