def test_process_streams():
# Loma Prieta test station (nc216859)
data_files, origin = read_data_dir("geonet", "us1000778i", "*.V1A")
streams = []
for f in data_files:
streams += read_data(f)
sc = StreamCollection(streams)
sc.describe()
config = update_config(os.path.join(datadir, "config_min_freq_0p2.yml"))
test = process_streams(sc, origin, config=config)
logging.info(f"Testing trace: {test[0][1]}")
assert len(test) == 3
assert len(test[0]) == 3
assert len(test[1]) == 3
assert len(test[2]) == 3
# Apparently the traces end up in a different order on the Travis linux
# container than on my local mac. So testing individual traces need to
# not care about trace order.
trace_maxes = np.sort(
[np.max(np.abs(t.data)) for t in test.select(station="HSES")[0]])
np.testing.assert_allclose(trace_maxes,
np.array([157.812449, 240.379521, 263.601519]),
rtol=1e-5)
def test_process_streams():
# Loma Prieta test station (nc216859)
data_files, origin = read_data_dir('geonet', 'us1000778i', '*.V1A')
streams = []
for f in data_files:
streams += read_data(f)
sc = StreamCollection(streams)
sc.describe()
config = update_config(os.path.join(datadir, 'config_min_freq_0p2.yml'))
test = process_streams(sc, origin, config=config)
logging.info('Testing trace: %s' % test[0][1])
assert len(test) == 3
assert len(test[0]) == 3
assert len(test[1]) == 3
assert len(test[2]) == 3
# Apparently the traces end up in a different order on the Travis linux
# container than on my local mac. So testing individual traces need to
# not care about trace order.
trace_maxes = np.sort(
[np.max(np.abs(t.data)) for t in test.select(station='HSES')[0]])
np.testing.assert_allclose(trace_maxes,
np.array(
[157.81975508, 240.33718094, 263.67804256]),
rtol=1e-5)
def test_check_instrument():
data_files, origin = read_data_dir("fdsn", "nc51194936", "*.mseed")
streams = []
for f in data_files:
streams += read_data(f)
sc = StreamCollection(streams)
sc.describe()
config = update_config(os.path.join(datadir,
"config_test_check_instr.yml"))
test = process_streams(sc, origin, config=config)
for sta, expected in [("CVS", True), ("GASB", True), ("SBT", False)]:
st = test.select(station=sta)[0]
logging.info(f"Testing stream: {st}")
assert st.passed == expected
def test_check_instrument():
data_files, origin = read_data_dir('fdsn', 'nc51194936', '*.mseed')
streams = []
for f in data_files:
streams += read_data(f)
sc = StreamCollection(streams)
sc.describe()
config = update_config(os.path.join(datadir,
'config_test_check_instr.yml'))
test = process_streams(sc, origin, config=config)
for sta, expected in [('CVS', True), ('GASB', True), ('SBT', False)]:
st = test.select(station=sta)[0]
logging.info('Testing stream: %s' % st)
assert st.passed == expected
def download(event, event_dir, config, directory, create_workspace=True):
"""Download data or load data from local directory, turn into Streams.
Args:
event (ScalarEvent):
Object containing basic event hypocenter, origin time, magnitude.
event_dir (str):
Path where raw directory should be created (if downloading).
config (dict):
Dictionary with gmprocess configuration information.
directory (str):
Path where data already exists. Must be organized in a 'raw'
directory, within directories with names as the event ids. For
example, if `directory` is 'proj_dir' and you have data for
event id 'abc123' then the raw data to be read in should be
located in `proj_dir/abc123/raw/`.
create_workspace (bool):
Create workspace file?
Returns:
tuple:
- StreamWorkspace: Contains the event and raw streams.
- str: Name of workspace HDF file.
- StreamCollection: Raw data StationStreams.
- str: Path to the rupture file.
"""
# Make raw directory
rawdir = get_rawdir(event_dir)
if directory is None:
tcollection, terrors = fetch_data(event.time.datetime,
event.latitude,
event.longitude,
event.depth_km,
event.magnitude,
config=config,
rawdir=rawdir)
# create an event.json file in each event directory,
# in case user is simply downloading for now
create_event_file(event, event_dir)
rup_file = get_rupture_file(event_dir)
else:
# Make raw directory
in_event_dir = os.path.join(directory, event.id)
rup_file = get_rupture_file(in_event_dir)
in_raw_dir = get_rawdir(in_event_dir)
logging.debug('in_raw_dir: %s' % in_raw_dir)
streams, bad, terrors = directory_to_streams(in_raw_dir)
logging.debug('streams:')
logging.debug(streams)
tcollection = StreamCollection(streams, **config['duplicate'])
create_event_file(event, event_dir)
if len(tcollection):
logging.debug('tcollection.describe():')
logging.debug(tcollection.describe())
# Plot the raw waveforms
with warnings.catch_warnings():
warnings.simplefilter("ignore", category=UserWarning)
pngfiles = glob.glob(os.path.join(rawdir, '*.png'))
if not len(pngfiles):
plot_raw(rawdir, tcollection, event)
if create_workspace:
# Create the workspace file and put the unprocessed waveforms in it
workname = os.path.join(event_dir, WORKSPACE_NAME)
# Remove any existing workspace file
if os.path.isfile(workname):
os.remove(workname)
workspace = StreamWorkspace(workname)
workspace.addEvent(event)
logging.debug('workspace.dataset.events:')
logging.debug(workspace.dataset.events)
workspace.addStreams(event, tcollection, label='unprocessed')
logging.debug('workspace.dataset.waveforms.list():')
logging.debug(workspace.dataset.waveforms.list())
else:
workspace = None
workname = None
return (workspace, workname, tcollection, rup_file)
