def test_multi_detectors(self):
"""Test the efficient looping in subspace."""
templates = copy.deepcopy(self.templates)
detector1 = subspace.Detector()
detector1.construct(streams=templates, lowcut=2, highcut=9,
filt_order=4, sampling_rate=20, multiplex=False,
name=str('Tester1'), align=True,
shift_len=6, reject=0.2).partition(4)
templates = copy.deepcopy(self.templates)
detector2 = subspace.Detector()
detector2.construct(streams=templates[0:20], lowcut=2, highcut=9,
filt_order=4, sampling_rate=20, multiplex=False,
name=str('Tester2'), align=True,
shift_len=6, reject=0.2).partition(4)
detections = subspace.subspace_detect(detectors=[detector1, detector2],
stream=self.st.copy(),
threshold=0.7,
trig_int=10, moveout=5,
min_trig=5,
parallel=False, num_cores=2)
self.assertEqual(len(detections), 6)
detections = subspace.subspace_detect(detectors=[detector1, detector2],
stream=self.st.copy(),
threshold=0.7,
trig_int=10, moveout=5,
min_trig=5,
parallel=True, num_cores=2)
self.assertEqual(len(detections), 6)
def test_refactor(self):
"""
Test subspace refactoring, checks that np.dot(U.T, U) is identity.
"""
templates = copy.deepcopy(self.templates)
# Test a multiplexed version
detector = subspace.Detector()
detector.construct(streams=templates, lowcut=2, highcut=9,
filt_order=4, sampling_rate=20, multiplex=True,
name=str('Tester'), align=False, shift_len=None)
for dim in range(2, len(detector.v[0])):
detector.partition(dim)
for u in detector.data:
identity = np.dot(u.T, u).astype(np.float16)
self.assertTrue(np.allclose(
identity, np.diag(np.ones(len(identity),
dtype=np.float16))))
# Test a non-multiplexed version
detector = subspace.Detector()
templates = copy.deepcopy(self.templates)
detector.construct(streams=templates, lowcut=2, highcut=9,
filt_order=4, sampling_rate=20, multiplex=False,
name=str('Tester'), align=True, shift_len=0.2,
reject=0.0)
for dim in range(2, len(detector.v[0])):
detector.partition(dim)
for u in detector.data:
identity = np.dot(u.T, u).astype(np.float16)
self.assertTrue(np.allclose(
identity, np.diag(np.ones(len(identity),
dtype=np.float16))))
def test_write(self):
"""Test writing to an hdf5 file"""
templates = copy.deepcopy(self.templates)
# Test a multiplexed version
detector = subspace.Detector()
detector.construct(streams=templates,
lowcut=2,
highcut=9,
filt_order=4,
sampling_rate=20,
multiplex=True,
name=str('Tester'),
align=True,
shift_len=0.8,
reject=0.2)
detector.write('Test_file.h5')
self.assertTrue(os.path.isfile('Test_file.h5'))
os.remove('Test_file.h5')
detector.construct(streams=templates,
lowcut=2,
highcut=9,
filt_order=4,
sampling_rate=20,
multiplex=False,
name=str('Tester'),
align=True,
shift_len=0.8,
reject=0.2)
detector.write('Test_file.h5')
self.assertTrue(os.path.isfile('Test_file.h5'))
os.remove('Test_file.h5')
def test_create_nonmultiplexed_unaligned(self):
"""Test creation of a non-multiplexed detector."""
# Test a non-multiplexed version
detector = subspace.Detector()
templates = copy.deepcopy(self.templates)
templates = [template.select(station='TMWZ') for template in templates]
detector.construct(streams=templates, lowcut=2, highcut=9,
filt_order=4, sampling_rate=20, multiplex=False,
name=str('Tester'), align=False, shift_len=0)
for u in detector.data:
identity = np.dot(u.T, u).astype(np.float16)
self.assertTrue(np.allclose(
identity, np.diag(np.ones(len(identity), dtype=np.float16))))
comparison_detector = subspace.read_detector(
os.path.join(
os.path.abspath(os.path.dirname(__file__)),
'test_data', 'subspace', 'master_detector_unaligned.h5'))
for key in ['name', 'sampling_rate', 'multiplex', 'lowcut', 'highcut',
'filt_order', 'dimension', 'stachans']:
# print(key)
self.assertEqual(comparison_detector.__getattribute__(key),
detector.__getattribute__(key))
for key in ['data', 'u', 'v', 'sigma']:
# print(key)
list_item = detector.__getattribute__(key)
other_list = comparison_detector.__getattribute__(key)
self.assertEqual(len(list_item), len(other_list))
for item, other_item in zip(list_item, other_list):
if not np.allclose(np.abs(item), np.abs(other_item)):
print(item)
print(other_item)
self.assertTrue(np.allclose(np.abs(item), np.abs(other_item),
atol=0.001))
# Finally check that the __eq__ method works if all the above passes.
self.assertEqual(detector, comparison_detector)
def test_read_func(self):
"""Check that the read function works too."""
path = os.path.join(os.path.abspath(os.path.dirname(__file__)),
'test_data', 'Test_detector.h5')
detector = subspace.read_detector(path)
_detector = subspace.Detector()
_detector.read(path)
self.assertEqual(detector, _detector)
def partition_fail(self):
templates = copy.deepcopy(self.templates)
detector2 = subspace.Detector()
with self.assertRaises(IndexError):
detector2.construct(streams=templates[0:10], lowcut=2, highcut=9,
filt_order=4, sampling_rate=20,
multiplex=False, name=str('Tester'),
align=True, shift_len=6,
reject=0.2).partition(9)
def test_not_multiplexed(self):
"""Test that a non-multiplexed detector gets the same result."""
templates = copy.deepcopy(self.templates)
detector = subspace.Detector()
detector.construct(streams=templates, lowcut=2, highcut=9,
filt_order=4, sampling_rate=20, multiplex=False,
name=str('Tester'), align=True,
shift_len=4, reject=0.3).partition(4)
st = self.st
detections = detector.detect(st=st, threshold=0.5, trig_int=4,
debug=1, moveout=2, min_trig=5)
self.assertEqual(len(detections), 16)
def test_read(self):
"""Test reading from hdf5 file"""
detector = subspace.Detector()
path = os.path.join(os.path.abspath(os.path.dirname(__file__)),
'test_data', 'Test_detector.h5')
detector.read(path)
self.assertEqual(detector.name, 'Tester')
self.assertEqual(detector.multiplex, False)
self.assertEqual(detector.lowcut, 2)
self.assertEqual(detector.highcut, 9)
self.assertEqual(detector.filt_order, 4)
self.assertEqual(detector.dimension, 9)
self.assertEqual(detector.sampling_rate, 20)
def setUpClass(cls):
wavefiles = glob.glob(os.path.join(
os.path.dirname(os.path.abspath(__file__)), 'test_data', 'WAV',
'TEST_', '*'))
streams = [read(w) for w in wavefiles[1:10]]
cls.stream_list = []
for st in streams:
tr = st.select(station='GCSZ', channel='EHZ')
tr = tr.detrend('simple').resample(100).filter(
'bandpass', freqmin=2, freqmax=8)
cls.stream_list.append(tr)
cls.detector = subspace.Detector().read(os.path.join(
os.path.abspath(os.path.dirname(__file__)),
'..', 'tests', 'test_data', 'subspace', 'stat_test_detector.h5'))
def test_detect(self):
"""Test standard detection with known result."""
templates = copy.deepcopy(self.templates)
detector = subspace.Detector()
detector.construct(streams=templates, lowcut=2, highcut=9,
filt_order=4, sampling_rate=20, multiplex=True,
name=str('Tester'), align=True,
shift_len=4, reject=0.3,
no_missed=False).partition(4)
st = self.st
detections = detector.detect(st=st, threshold=0.2, trig_int=4,
debug=1)
self.assertEqual(len(detections), 34)
def test_stat(self):
"""Test that the statistic calculation is the same regardless of
system."""
detector = subspace.Detector()
detector.read(
os.path.join(os.path.abspath(os.path.dirname(__file__)),
'test_data', 'subspace', 'stat_test_detector.h5'))
stream = read(
os.path.join(os.path.abspath(os.path.dirname(__file__)),
'test_data', 'subspace', 'test_trace.ms'))
tr_data = stream[0].data
stat = subspace_statistic.det_statistic(
detector.data[0].astype(np.float32), tr_data.astype(np.float32))
self.assertEqual((stat.max().round(6) - 0.252336).round(6), 0)
def test_stat(self):
"""Test that the statistic calculation is the same regardless of
system."""
detector = subspace.Detector()
detector.read(os.path.join(os.path.abspath(os.path.dirname(__file__)),
'test_data', 'subspace',
'stat_test_detector.h5'))
detector.partition(2)
stream = read(os.path.join(os.path.abspath(os.path.dirname(__file__)),
'test_data', 'subspace', 'test_trace.ms'))
st = [stream]
fft_vars = subspace._do_ffts(detector, st, len(detector.stachans))
stat = subspace._det_stat_freq(fft_vars[0][0], fft_vars[1][0],
fft_vars[2][0], fft_vars[3],
len(detector.stachans), fft_vars[4],
fft_vars[5])
self.assertEqual((stat.max().round(6) - 0.229755).round(6), 0)
def run_tutorial(plot=False,
multiplex=True,
return_streams=False,
cores=4,
verbose=False):
"""
Run the tutorial.
:return: detections
"""
client = Client("GEONET", debug=verbose)
cat = client.get_events(minlatitude=-40.98,
maxlatitude=-40.85,
minlongitude=175.4,
maxlongitude=175.5,
starttime=UTCDateTime(2016, 5, 1),
endtime=UTCDateTime(2016, 5, 20))
print(f"Downloaded a catalog of {len(cat)} events")
# This gives us a catalog of events - it takes a while to download all
# the information, so give it a bit!
# We will generate a five station, multi-channel detector.
cat = filter_picks(catalog=cat, top_n_picks=5)
stachans = list(
set([(pick.waveform_id.station_code, pick.waveform_id.channel_code)
for event in cat for pick in event.picks]))
# In this tutorial we will only work on one cluster, defined spatially.
# You can work on multiple clusters, or try to whole set.
clusters = catalog_cluster(catalog=cat,
metric="distance",
thresh=2,
show=False)
# We will work on the largest cluster
cluster = sorted(clusters, key=lambda c: len(c))[-1]
# This cluster contains 32 events, we will now download and trim the
# waveforms. Note that each chanel must start at the same time and be the
# same length for multiplexing. If not multiplexing EQcorrscan will
# maintain the individual differences in time between channels and delay
# the detection statistics by that amount before stacking and detection.
client = Client('GEONET')
design_set = []
st = Stream()
for event in cluster:
print(f"Downloading for event {event.resource_id.id}")
bulk_info = []
t1 = event.origins[0].time
t2 = t1 + 25.1 # Have to download extra data, otherwise GeoNet will
# trim wherever suits.
t1 -= 0.1
for station, channel in stachans:
try:
st += client.get_waveforms('NZ', station, '*',
channel[0:2] + '?', t1, t2)
except IncompleteRead:
print(f"Could not download for {station} {channel}")
print(f"Downloaded {len(st)} channels")
for event in cluster:
t1 = event.origins[0].time
t2 = t1 + 25
design_set.append(st.copy().trim(t1, t2))
# Construction of the detector will process the traces, then align them,
# before multiplexing.
print("Making detector")
detector = subspace.Detector()
detector.construct(streams=design_set,
lowcut=2.0,
highcut=9.0,
filt_order=4,
sampling_rate=20,
multiplex=multiplex,
name='Wairarapa1',
align=True,
reject=0.2,
shift_len=6,
plot=plot).partition(9)
print("Constructed Detector")
if plot:
detector.plot()
# We also want the continuous stream to detect in.
t1 = UTCDateTime(2016, 5, 11, 19)
t2 = UTCDateTime(2016, 5, 11, 20)
# We are going to look in a single hour just to minimize cost, but you can
# run for much longer.
bulk_info = [('NZ', stachan[0], '*', stachan[1][0] + '?' + stachan[1][-1],
t1, t2) for stachan in detector.stachans]
print("Downloading continuous data")
st = client.get_waveforms_bulk(bulk_info)
st.merge().detrend('simple').trim(starttime=t1, endtime=t2)
# We set a very low threshold because the detector is not that great, we
# haven't aligned it particularly well - however, at this threshold we make
# two real detections.
print("Computing detections")
detections, det_streams = detector.detect(st=st,
threshold=0.4,
trig_int=2,
extract_detections=True,
cores=cores)
if return_streams:
return detections, det_streams
else:
return detections
def run_tutorial(plot=False, multiplex=True, return_streams=False):
"""
Run the tutorial.
:return: detections
"""
# We are going to use data from the GeoNet (New Zealand) catalogue. GeoNet
# do not implement the full FDSN system yet, so we have a hack to get
# around this. It is not strictly part of EQcorrscan, so we haven't
# included it here, but you can find it in the tutorials directory of the
# github repository
import obspy
if int(obspy.__version__.split('.')[0]) >= 1:
from obspy.clients.fdsn import Client
else:
from obspy.fdsn import Client
from eqcorrscan.tutorials.get_geonet_events import get_geonet_events
from obspy import UTCDateTime
from eqcorrscan.utils.catalog_utils import filter_picks
from eqcorrscan.utils.clustering import space_cluster
from eqcorrscan.core import subspace
cat = get_geonet_events(minlat=-40.98,
maxlat=-40.85,
minlon=175.4,
maxlon=175.5,
startdate=UTCDateTime(2016, 5, 1),
enddate=UTCDateTime(2016, 5, 20))
# This gives us a catalog of events - it takes a while to download all
# the information, so give it a bit!
# We will generate a five station, multi-channel detector.
cat = filter_picks(catalog=cat, top_n_picks=5)
stachans = list(
set([(pick.waveform_id.station_code, pick.waveform_id.channel_code)
for event in cat for pick in event.picks]))
# In this tutorial we will only work on one cluster, defined spatially.
# You can work on multiple clusters, or try to whole set.
clusters = space_cluster(catalog=cat, d_thresh=2, show=False)
# We will work on the largest cluster
cluster = sorted(clusters, key=lambda c: len(c))[-1]
# This cluster contains 32 events, we will now download a trim the
# waveforms. Note that each chanel must start at the same time and be the
# same length for multiplexing. If not multiplexing EQcorrscan will
# maintain the individual differences in time between channels and delay
# the detection statistics by that amount before stacking and detection.
client = Client('GEONET')
design_set = []
bulk_info = []
for event in cluster:
t1 = event.origins[0].time
t2 = t1 + 25
for station, channel in stachans:
bulk_info.append(('NZ', station, '*', channel[0:2] + '?', t1, t2))
st = client.get_waveforms_bulk(bulk=bulk_info)
for event in cluster:
t1 = event.origins[0].time
t2 = t1 + 25
design_set.append(st.copy().trim(t1, t2))
# Construction of the detector will process the traces, then align them,
# before multiplexing.
detector = subspace.Detector()
detector.construct(streams=design_set,
lowcut=2.0,
highcut=9.0,
filt_order=4,
sampling_rate=20,
multiplex=multiplex,
name='Wairarapa1',
align=True,
reject=0.2,
shift_len=6,
plot=plot).partition(9)
if plot:
detector.plot()
# We also want the continuous stream to detect in.
t1 = UTCDateTime(2016, 5, 11, 19)
t2 = UTCDateTime(2016, 5, 11, 20)
# We are going to look in a single hour just to minimize cost, but you can \
# run for much longer.
bulk_info = [('NZ', stachan[0], '*', stachan[1][0] + '?' + stachan[1][-1],
t1, t2) for stachan in detector.stachans]
st = client.get_waveforms_bulk(bulk_info)
st.merge().detrend('simple').trim(starttime=t1, endtime=t2)
# We set a very low threshold because the detector is not that great, we
# haven't aligned it particularly well - however, at this threshold we make
# two real detections.
detections, det_streams = detector.detect(st=st,
threshold=0.005,
trig_int=2,
extract_detections=True)
if return_streams:
return detections, det_streams
else:
return detections