def extract_ruptures(dstore, what):
"""
Extract some information about the ruptures, including the boundary.
Example:
http://127.0.0.1:8800/v1/calc/30/extract/ruptures?min_mag=6
"""
qdict = parse(what)
if 'min_mag' in qdict:
[min_mag] = qdict['min_mag']
else:
min_mag = 0
bio = io.StringIO()
first = True
trts = list(dstore.getitem('full_lt').attrs['trts'])
for rgetter in getters.gen_rgetters(dstore):
rups = [
rupture._get_rupture(proxy.rec, proxy.geom, rgetter.trt)
for proxy in rgetter.get_proxies(min_mag)
]
arr = rupture.to_csv_array(rups)
if first:
header = None
comment = dict(trts=trts)
first = False
else:
header = 'no-header'
comment = None
writers.write_csv(bio, arr, header=header, comment=comment)
return bio.getvalue()
def save_events(self, rup_array):
"""
:param rup_array: an array of ruptures with fields grp_id
:returns: a list of RuptureGetters
"""
# this is very fast compared to saving the ruptures
eids = rupture.get_eids(rup_array, self.samples_by_grp,
self.num_rlzs_by_grp)
self.check_overflow() # check the number of events
events = numpy.zeros(len(eids), rupture.events_dt)
# when computing the events all ruptures must be considered,
# including the ones far away that will be discarded later on
rgetters = gen_rgetters(self.datastore)
# build the associations eid -> rlz sequentially or in parallel
# this is very fast: I saw 30 million events associated in 1 minute!
logging.info('Building assocs event_id -> rlz_id for {:_d} events'
' and {:_d} ruptures'.format(len(events), len(rup_array)))
if len(events) < 1E5:
it = map(RuptureGetter.get_eid_rlz, rgetters)
else:
# parallel composite array with the associations eid->rlz
it = parallel.Starmap(RuptureGetter.get_eid_rlz,
((rgetter, ) for rgetter in rgetters),
progress=logging.debug,
h5=self.datastore.hdf5)
i = 0
for eid_rlz in it:
for er in eid_rlz:
events[i] = er
i += 1
if i >= TWO32:
raise ValueError('There are more than %d events!' % i)
events.sort(order='rup_id') # fast too
# sanity check
n_unique_events = len(numpy.unique(events[['id', 'rup_id']]))
assert n_unique_events == len(events), (n_unique_events, len(events))
events['id'] = numpy.arange(len(events))
# set event year and event ses starting from 1
itime = int(self.oqparam.investigation_time)
nses = self.oqparam.ses_per_logic_tree_path
extra = numpy.zeros(len(events), [('year', U16), ('ses_id', U16)])
# seed for year and ses_id
numpy.random.seed(self.oqparam.ses_seed)
extra['year'] = numpy.random.choice(itime, len(events)) + 1
extra['ses_id'] = numpy.random.choice(nses, len(events)) + 1
self.datastore['events'] = util.compose_arrays(events, extra)
eindices = get_indices(events['rup_id'])
arr = numpy.array(list(eindices.values()))[:, 0, :]
self.datastore['ruptures']['e0'] = arr[:, 0]
self.datastore['ruptures']['e1'] = arr[:, 1]
def extract_rupture(dstore, rup_id):
"""
Extract information about the given event index.
Example:
http://127.0.0.1:8800/v1/calc/30/extract/rupture/1066
"""
ridx = list(dstore['ruptures']['id']).index(int(rup_id))
[getter] = getters.gen_rgetters(dstore, slice(ridx, ridx + 1))
[ebr] = getter.get_ruptures()
return ArrayWrapper((), ebr.rupture.todict())
def save_events(self, rup_array):
"""
:param rup_array: an array of ruptures with fields grp_id
:returns: a list of RuptureGetters
"""
# this is very fast compared to saving the ruptures
eids = rupture.get_eids_for_erf_based(rup_array, self.num_rlzs_by_grp)
#eids = rupture.get_eids(rup_array, self.samples_by_grp, self.num_rlzs_by_grp)
self.check_overflow() # check the number of events
events = numpy.zeros(len(eids), rupture.events_dt)
# when computing the events all ruptures must be considered,
# including the ones far away that will be discarded later on
rgetters = gen_rgetters(self.datastore)
# build the associations eid -> rlz sequentially or in parallel
# this is very fast: I saw 30 million events associated in 1 minute!
logging.info('Building assocs event_id -> rlz_id for {:_d} events'
' and {:_d} ruptures'.format(len(events), len(rup_array)))
if len(events) < 1E5:
it = map(RuptureGetter.get_eid_rlz, rgetters)
else:
# parallel composite array with the associations eid->rlz
it = parallel.Starmap(RuptureGetter.get_eid_rlz,
((rgetter, ) for rgetter in rgetters),
progress=logging.debug,
h5=self.datastore.hdf5)
i = 0
for eid_rlz in it:
for er in eid_rlz:
events[i] = er
i += 1
if i >= TWO32:
raise ValueError('There are more than %d events!' % i)
events.sort(order='rup_id') # fast too
events['id'] = numpy.arange(
len(events)) # one event per event -> same id of ruptures
self.datastore['events'] = events
eindices = get_indices(events['rup_id'])
arr = numpy.array(list(eindices.values()))[:, 0, :]
self.datastore['ruptures']['e0'] = arr[:, 0]
self.datastore['ruptures']['e1'] = arr[:, 1]
def extract_event_info(dstore, eidx):
"""
Extract information about the given event index.
Example:
http://127.0.0.1:8800/v1/calc/30/extract/event_info/0
"""
event = dstore['events'][int(eidx)]
ridx = event['rup_id']
[getter] = getters.gen_rgetters(dstore, slice(ridx, ridx + 1))
rupdict = getter.get_rupdict()
rlzi = event['rlz_id']
rlzs_assoc = dstore['csm_info'].get_rlzs_assoc()
gsim = rlzs_assoc.gsim_by_trt[rlzi][rupdict['trt']]
for key, val in rupdict.items():
yield key, val
yield 'rlzi', rlzi
yield 'gsim', repr(gsim)
def export_ruptures_xml(ekey, dstore):
"""
:param ekey: export key, i.e. a pair (datastore key, fmt)
:param dstore: datastore object
"""
fmt = ekey[-1]
oq = dstore['oqparam']
num_ses = oq.ses_per_logic_tree_path
ruptures_by_grp = AccumDict(accum=[])
for rgetter in gen_rgetters(dstore):
ebrs = [ebr.export(rgetter.rlzs_by_gsim, num_ses)
for ebr in rgetter.get_ruptures()]
ruptures_by_grp[rgetter.grp_id].extend(ebrs)
dest = dstore.export_path('ses.' + fmt)
writer = hazard_writers.SESXMLWriter(dest)
writer.serialize(ruptures_by_grp, oq.investigation_time)
return [dest]
def export_ruptures_xml(ekey, dstore):
"""
:param ekey: export key, i.e. a pair (datastore key, fmt)
:param dstore: datastore object
"""
fmt = ekey[-1]
oq = dstore['oqparam']
events = group_array(dstore['events'][()], 'rup_id')
ruptures_by_grp = AccumDict(accum=[])
for rgetter in gen_rgetters(dstore):
ebrs = []
for proxy in rgetter.get_proxies():
events_by_ses = group_array(events[proxy['id']], 'ses_id')
ebr = proxy.to_ebr(rgetter.trt, rgetter.samples)
ebrs.append(ebr.export(events_by_ses))
ruptures_by_grp[rgetter.grp_id].extend(ebrs)
dest = dstore.export_path('ses.' + fmt)
writer = hazard_writers.SESXMLWriter(dest)
writer.serialize(ruptures_by_grp, oq.investigation_time)
return [dest]
def extract_rupture_info(dstore, what):
"""
Extract some information about the ruptures, including the boundary.
Example:
http://127.0.0.1:8800/v1/calc/30/extract/rupture_info?min_mag=6
"""
qdict = parse(what)
if 'min_mag' in qdict:
[min_mag] = qdict['min_mag']
else:
min_mag = 0
oq = dstore['oqparam']
dtlist = [('rup_id', U32), ('occurrence_rate', F32), ('multiplicity', U16),
('mag', F32), ('centroid_lon', F32), ('centroid_lat', F32),
('centroid_depth', F32), ('trt', '<S50'), ('strike', F32),
('dip', F32), ('rake', F32)]
rows = []
boundaries = []
for rgetter in getters.gen_rgetters(dstore):
proxies = rgetter.get_proxies(min_mag)
rup_data = RuptureData(rgetter.trt, rgetter.samples,
rgetter.rlzs_by_gsim)
for r in rup_data.to_array(proxies):
coords = ['%.5f %.5f' % xyz[:2] for xyz in zip(*r['boundaries'])]
coordset = sorted(set(coords))
if len(coordset) < 4: # degenerate to line
boundaries.append('LINESTRING(%s)' % ', '.join(coordset))
else: # good polygon
boundaries.append('POLYGON((%s))' % ', '.join(coords))
rows.append((r['rup_id'], r['occurrence_rate'], r['multiplicity'],
r['mag'], r['lon'], r['lat'], r['depth'], rgetter.trt,
r['strike'], r['dip'], r['rake']))
arr = numpy.array(rows, dtlist)
geoms = gzip.compress('\n'.join(boundaries).encode('utf-8'))
return ArrayWrapper(
arr, dict(investigation_time=oq.investigation_time, boundaries=geoms))
