summary.append("#" * 79)
trig = []
mutt = []
if st:
# preprocessing, backup original data for plotting at end
st.merge(0)
st.detrend("linear")
for tr in st:
tr.data = tr.data * cosTaper(len(tr), 0.01)
#st.simulate(paz_remove="self", paz_simulate=cornFreq2Paz(1.0), remove_sensitivity=False)
st.sort()
st.filter("bandpass", freqmin=PAR.LOW, freqmax=PAR.HIGH, corners=1, zerophase=True)
st.trim(T1, T2)
st_trigger = st.copy()
st.normalize(global_max=False)
# do the triggering
trig = coincidenceTrigger("recstalta", PAR.ON, PAR.OFF, st_trigger,
thr_coincidence_sum=PAR.MIN_STATIONS,
max_trigger_length=PAR.MAXLEN, trigger_off_extension=PAR.ALLOWANCE,
details=True, sta=PAR.STA, lta=PAR.LTA)
for t in trig:
info = "%s %ss %s %s" % (t['time'].strftime("%Y-%m-%dT%H:%M:%S"), ("%.1f" % t['duration']).rjust(4), ("%i" % t['cft_peak_wmean']).rjust(3), "-".join(t['stations']))
summary.append(info)
tmp = st.slice(t['time'] - 1, t['time'] + t['duration'])
outfilename = "%s/%s_%.1f_%i_%s-%s_%s.png" % (PLOTDIR, t['time'].strftime("%Y-%m-%dT%H:%M:%S"), t['duration'], t['cft_peak_wmean'], len(t['stations']), num_stations, "-".join(t['stations']))
tmp.plot(outfile=outfilename)
mutt += ("-a", outfilename)
summary.append("#" * 79)
summary.append("#" * 79)
trig = []
mutt = []
if st:
# preprocessing, backup original data for plotting at end
st.merge(0)
st.detrend("linear")
for tr in st:
tr.data = tr.data * cosTaper(len(tr), 0.01)
#st.simulate(paz_remove="self", paz_simulate=cornFreq2Paz(1.0), remove_sensitivity=False)
st.sort()
st.filter("bandpass", freqmin=PAR.LOW, freqmax=PAR.HIGH, corners=1, zerophase=True)
st.trim(T1, T2)
st_trigger = st.copy()
st.normalize(global_max=False)
# do the triggering
trig = coincidenceTrigger("recstalta", PAR.ON, PAR.OFF, st_trigger,
thr_coincidence_sum=PAR.MIN_STATIONS,
max_trigger_length=PAR.MAXLEN, trigger_off_extension=PAR.ALLOWANCE,
details=True, sta=PAR.STA, lta=PAR.LTA)
for t in trig:
info = "%s %ss %s %s" % (t['time'].strftime("%Y-%m-%dT%H:%M:%S"), ("%.1f" % t['duration']).rjust(4), ("%i" % t['cft_peak_wmean']).rjust(3), "-".join(t['stations']))
summary.append(info)
tmp = st.slice(t['time'] - 1, t['time'] + t['duration'])
outfilename = "%s/%s_%.1f_%i_%s-%s_%s.png" % (PLOTDIR, t['time'].strftime("%Y-%m-%dT%H:%M:%S"), t['duration'], t['cft_peak_wmean'], len(t['stations']), num_stations, "-".join(t['stations']))
tmp.plot(outfile=outfilename)
mutt += ("-a", outfilename)
summary.append("#" * 79)
def main(_):
stream_dirs = [file for file in os.listdir(FLAGS.stream_dir)]
print "List of streams to anlayze", stream_dirs
# Create dir to store tfrecords
if not os.path.exists(FLAGS.output_dir):
os.makedirs(FLAGS.output_dir)
# Dictionary of nb of events per tfrecords
metadata = {}
output_metadata = os.path.join(FLAGS.output_dir, "metadata.json")
# Load Catalog
#evlog = load_catalog(FLAGS.catalog)
#print ("+ Loading Catalog:",evlog)
for stream_dir in stream_dirs:
#cat = evlog[(evlog.stname == stream_dir)]
#print cat
# Load stream
stream_path = os.path.join(FLAGS.stream_dir, stream_dir, "event")
stream_files = glob.glob(stream_path + '/*HZ.D.SAC')
#print waveforms[0]
output_name = stream_dir + ".tfrecords"
output_path = os.path.join(FLAGS.output_dir, output_name)
writer = DataWriter(output_path)
print("+ Creating tfrecords for {} events".format(len(stream_files)))
for stream_file in stream_files:
stream_file1 = re.sub('HZ.D.SAC', 'HE.D.SAC', str(stream_file))
stream_file2 = re.sub('HZ.D.SAC', 'HN.D.SAC', str(stream_file))
# Load stream
#print "+ Loading Stream {}".format(stream_path)
stream = read(stream_file)
stream += read(stream_file1)
stream += read(stream_file2)
#stream_filepath = os.path.join(stream_path, stream_file)
#stream = read(stream_filepath)
#print '+ Preprocessing stream',stream
#stream = preprocess_stream(stream)
# Filter catalog according to the loaded stream
start_date = stream[0].stats.starttime
end_date = stream[-1].stats.endtime
print("-- Start Date={}, End Date={}".format(start_date, end_date))
x = np.random.randint(0, 4)
print "+ Loading Stream selected\n {}\n ".format(stream)
if len(stream) < 3:
continue
st_event = stream.resample(100).trim(start_date + x,
start_date + x +
FLAGS.window_size,
pad=True,
fill_value=0.0).copy()
#st_event.resample(100)
print(st_event)
n_samples = len(st_event[0].data)
sample_rate = st_event[0].stats.sampling_rate
n_pts = sample_rate * FLAGS.window_size + 1
cluster_id_p = 5 - x
cluster_id_s = end_date - start_date - x - 15
if cluster_id_s >= 30:
continue
assert n_pts == n_samples, "n_pts and n_samples are not the same"
# Write event waveforms and cluster_id in .tfrecords
# for p picks
# u=0
# label = np.zeros((n_samples), dtype=np.float32)
label_obj = st_event.copy()
label_obj[0].data[...] = 1
label_obj[1].data[...] = 0
label_obj[2].data[...] = 0
u1 = cluster_id_p * sample_rate # mean value miu
lower = int(u1 - sample_rate)
upper = int(u1 + sample_rate)
label_obj[1].data[lower:upper] = 1
# label_obj.data[int(u1 - 0.5 * sample_rate):int(u1 + 0.5 * sample_rate)] = 1
# y_sig = np.random.normal(u1, sig, n_samples )
# for s pick
u2 = cluster_id_s * sample_rate # mean value miu
lower2, upper2 = int(u2 - sample_rate), int(u2 + sample_rate)
try:
label_obj[2].data[lower2:upper2] = 2
# label_obj.data[int(u2 - sample_rate):int(u2 + sample_rate)] =2
except:
nnn = int(n_samples) - int(u2 + sample_rate)
print(nnn, n_samples)
label_obj[2].data[lower2:n_samples] = 2
label_obj.normalize()
label_obj[0].data = label_obj[0].data - label_obj[
1].data - label_obj[2].data
# label_obj.data[int(u2 - sample_rate):n_samples] = 2
writer.write(st_event.copy().normalize(), label_obj)
if FLAGS.save_mseed:
output_label = "{}_{}.mseed".format(
st_event[0].stats.station,
str(st_event[0].stats.starttime).replace(':', '_'))
output_mseed_dir = os.path.join(FLAGS.output_dir, "mseed")
if not os.path.exists(output_mseed_dir):
os.makedirs(output_mseed_dir)
output_mseed = os.path.join(output_mseed_dir, output_label)
st_event.write(output_mseed, format="MSEED")
# Plot events
if FLAGS.plot:
#import matplotlib
#matplotlib.use('Agg')
# from obspy.core import Stream
traces = Stream()
traces += st_event[0].filter('bandpass',
freqmin=0.5,
freqmax=20)
traces += label_obj
# print traces
viz_dir = os.path.join(FLAGS.output_dir, "viz", stream_dir)
if not os.path.exists(viz_dir):
os.makedirs(viz_dir)
traces.normalize().plot(outfile=os.path.join(
viz_dir,
####changed at 2017/11/25,use max cluster_prob instead of cluster_id
# "event_{}_cluster_{}.png".format(idx,cluster_id)))
"event_{}_{}.png".format(
st_event[0].stats.station,
str(st_event[0].stats.starttime).replace(':', '_'))))
# Cleanup writer
print("Number of events written={}".format(writer._written))
writer.close()
# Write metadata
metadata[stream_dir] = writer._written
write_json(metadata, output_metadata)
def plot(self, filter=None, save=False, show=True, ttgrid=None):
st = Stream()
willy = seispy.burrow.Groundhog()
distance = sorted([
gps2dist_azimuth(self.lat, self.lon, arrival.station.lat,
arrival.station.lon)[0]
for arrival in self.arrivals
])
dmin, dmax = min(distance), max(distance)
startlag = dmin / 6000. - 7
endlag = dmax / 2000. + 5
for arrival in self.arrivals:
st += willy.fetch(arrival.station.name,
arrival.channel.code,
starttime=self.time + startlag,
endtime=self.time + endlag)
arrivals = sorted(
self.arrivals,
key=lambda arrival:
(arrival.station.network, arrival.station.name, arrival.channel))
if filter is not None:
st.filter(*filter[0], **filter[1])
st.trim(starttime=self.time + startlag + 2.)
st.normalize()
MAX_TRACES = 9
ncol = int(ceil(len(st) / float(MAX_TRACES))) + 1
nrow = int(ceil(len(st) / float(ncol - 1)))
gs = GridSpec(nrow, ncol)
gs.update(hspace=0, wspace=0)
width = 1600
height = width / float(ncol)
fig = st.plot(size=(width, height), handle=True)
row, col = 0, 0
for i in range(len(fig.axes)):
ax = fig.axes[i]
arrival = arrivals[i]
color = "r" if arrival.phase == "P"\
else "g" if arrival.phase == "S" else "b"
ax.axvline(arrival.time.toordinal() +
arrival.time._get_hours_after_midnight() / 24.,
color=color,
linewidth=2,
alpha=0.75)
if ttgrid is not None:
r, theta, phi = sp.geometry.geo2sph(self.lat, self.lon,
self.depth)
try:
predicted = self.time + ttgrid.get_tt(
arrival.station.name, arrival.phase, r, theta, phi)
except KeyError:
continue
ax.axvline(predicted.toordinal() +
predicted._get_hours_after_midnight() / 24.,
color=color,
linewidth=2,
linestyle="--",
alpha=0.75)
if row % nrow == 0:
col += 1
row = 0
position = gs[row, col].get_position(fig)
ax.set_position(position)
ax.get_yaxis().set_visible(False)
row += 1
for ax in fig.axes[nrow - 1::nrow] + [fig.axes[-1]]:
ax.set_xticklabels(ax.get_xticklabels(),
visible=True,
fontsize=10,
rotation=-15,
horizontalalignment="left")
gs.update(wspace=0.2)
postl = gs[0].get_position(fig)
posbl = gs[ncol * (nrow - 1)].get_position(fig)
bbox_map = Bbox(((posbl.x0, posbl.y0), (posbl.x1, postl.y1)))
ax = fig.add_axes(bbox_map)
self.plot_map(ax=ax)
fig.suptitle("%s (ID #%d)" % (self.time, self.evid))
if save:
plt.savefig("%s.png" % save, format="png")
if show:
plt.show()
else:
plt.close()