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 generate_workspace():
"""Generate simple HDF5 with ASDF layout for testing."""
PCOMMANDS = [
"assemble",
"process",
]
EVENTID = "us1000778i"
LABEL = "ptest"
datafiles, event = read_data_dir("geonet", EVENTID, "*.V1A")
tdir = tempfile.mkdtemp()
tfilename = os.path.join(tdir, "workspace.h5")
raw_data = []
for dfile in datafiles:
raw_data += read_data(dfile)
write_asdf(tfilename, raw_data, event, label="unprocessed")
del raw_data
config = update_config(os.path.join(datadir, "config_min_freq_0p2.yml"))
workspace = StreamWorkspace.open(tfilename)
raw_streams = workspace.getStreams(EVENTID,
labels=["unprocessed"],
config=config)
pstreams = process_streams(raw_streams, event, config=config)
workspace.addStreams(event, pstreams, label=LABEL)
workspace.calcMetrics(event.id, labels=[LABEL], config=config)
return tfilename
def test_metrics():
eventid = "usb000syza"
datafiles, event = read_data_dir("knet", eventid, "*")
datadir = os.path.split(datafiles[0])[0]
raw_streams = StreamCollection.from_directory(datadir)
config = update_config(os.path.join(datadir, "config_min_freq_0p2.yml"))
# turn off sta/lta check and snr checks
# newconfig = drop_processing(config, ['check_sta_lta', 'compute_snr'])
# processed_streams = process_streams(raw_streams, event, config=newconfig)
newconfig = config.copy()
newconfig["processing"].append(
{"NNet_QA": {
"acceptance_threshold": 0.5,
"model_name": "CantWell"
}})
processed_streams = process_streams(raw_streams.copy(),
event,
config=newconfig)
tdir = tempfile.mkdtemp()
try:
tfile = os.path.join(tdir, "test.hdf")
workspace = StreamWorkspace(tfile)
workspace.addEvent(event)
workspace.addStreams(event, raw_streams, label="raw")
workspace.addStreams(event, processed_streams, label="processed")
stream1 = raw_streams[0]
# Get metrics from station summary for raw streams
summary1 = StationSummary.from_config(stream1)
s1_df_in = summary1.pgms.sort_values(["IMT", "IMC"])
array1 = s1_df_in["Result"].to_numpy()
# Compare to metrics from getStreamMetrics for raw streams
workspace.calcMetrics(eventid, labels=["raw"])
summary1_a = workspace.getStreamMetrics(event.id,
stream1[0].stats.network,
stream1[0].stats.station,
"raw")
s1_df_out = summary1_a.pgms.sort_values(["IMT", "IMC"])
array2 = s1_df_out["Result"].to_numpy()
np.testing.assert_allclose(array1, array2, atol=1e-6, rtol=1e-6)
workspace.close()
except Exception as e:
raise (e)
finally:
shutil.rmtree(tdir)
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_metrics2():
eventid = "usb000syza"
datafiles, event = read_data_dir("knet", eventid, "*")
datadir = os.path.split(datafiles[0])[0]
raw_streams = StreamCollection.from_directory(datadir)
config = update_config(os.path.join(datadir, "config_min_freq_0p2.yml"))
config["metrics"]["output_imts"].append("Arias")
config["metrics"]["output_imcs"].append("arithmetic_mean")
# Adjust checks so that streams pass checks for this test
newconfig = drop_processing(config, ["check_sta_lta"])
csnr = [s for s in newconfig["processing"] if "compute_snr" in s.keys()][0]
csnr["compute_snr"]["check"]["threshold"] = -10.0
processed_streams = process_streams(raw_streams, event, config=newconfig)
tdir = tempfile.mkdtemp()
try:
tfile = os.path.join(tdir, "test.hdf")
workspace = StreamWorkspace(tfile)
workspace.addEvent(event)
workspace.addStreams(event, processed_streams, label="processed")
workspace.calcMetrics(event.id, labels=["processed"])
etable, imc_tables1, readmes1 = workspace.getTables("processed")
assert "ARITHMETIC_MEAN" not in imc_tables1
assert "ARITHMETIC_MEAN" not in readmes1
del workspace.dataset.auxiliary_data.WaveFormMetrics
del workspace.dataset.auxiliary_data.StationMetrics
workspace.calcMetrics(event.id, labels=["processed"], config=config)
etable2, imc_tables2, readmes2 = workspace.getTables("processed")
assert "ARITHMETIC_MEAN" in imc_tables2
assert "ARITHMETIC_MEAN" in readmes2
assert "ARIAS" in imc_tables2["ARITHMETIC_MEAN"]
testarray = readmes2["ARITHMETIC_MEAN"]["Column header"].to_numpy()
assert "ARIAS" in testarray
workspace.close()
except Exception as e:
raise (e)
finally:
shutil.rmtree(tdir)
def _test_workspace():
eventid = "us1000778i"
datafiles, event = read_data_dir("geonet", eventid, "*.V1A")
tdir = tempfile.mkdtemp()
try:
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=H5pyDeprecationWarning)
warnings.filterwarnings("ignore", category=YAMLError)
warnings.filterwarnings("ignore", category=FutureWarning)
config = update_config(
os.path.join(datadir, "config_min_freq_0p2.yml"))
tfile = os.path.join(tdir, "test.hdf")
raw_streams = []
for dfile in datafiles:
raw_streams += read_data(dfile)
workspace = StreamWorkspace(tfile)
t1 = time.time()
workspace.addStreams(event, raw_streams, label="raw")
t2 = time.time()
print("Adding %i streams took %.2f seconds" % (len(raw_streams),
(t2 - t1)))
str_repr = workspace.__repr__()
assert str_repr == "Events: 1 Stations: 3 Streams: 3"
eventobj = workspace.getEvent(eventid)
assert eventobj.origins[0].latitude == event.origins[0].latitude
assert eventobj.magnitudes[0].mag == event.magnitudes[0].mag
stations = workspace.getStations()
assert sorted(stations) == ["HSES", "THZ", "WTMC"]
stations = workspace.getStations()
assert sorted(stations) == ["HSES", "THZ", "WTMC"]
# test retrieving event that doesn't exist
with pytest.raises(KeyError):
workspace.getEvent("foo")
instream = None
for stream in raw_streams:
if stream[0].stats.station.lower() == "hses":
instream = stream
break
if instream is None:
raise ValueError("Instream should not be none.")
outstream = workspace.getStreams(eventid,
stations=["HSES"],
labels=["raw"])[0]
compare_streams(instream, outstream)
label_summary = workspace.summarizeLabels()
assert label_summary.iloc[0]["Label"] == "raw"
assert label_summary.iloc[0]["Software"] == "gmprocess"
sc = StreamCollection(raw_streams)
processed_streams = process_streams(sc, event, config=config)
workspace.addStreams(event, processed_streams, "processed")
idlist = workspace.getEventIds()
assert idlist[0] == eventid
outstream = workspace.getStreams(eventid,
stations=["HSES"],
labels=["processed"])[0]
provenance = workspace.getProvenance(eventid, labels=["processed"])
first_row = pd.Series({
"Record": "NZ.HSES.--.HN1_us1000778i_processed",
"Processing Step": "Remove Response",
"Step Attribute": "input_units",
"Attribute Value": "counts",
})
last_row = pd.Series({
"Record": "NZ.WTMC.--.HNZ_us1000778i_processed",
"Processing Step": "Lowpass Filter",
"Step Attribute": "number_of_passes",
"Attribute Value": 2,
})
assert provenance.iloc[0].equals(first_row)
assert provenance.iloc[-1].equals(last_row)
# compare the parameters from the input processed stream
# to it's output equivalent
instream = None
for stream in processed_streams:
if stream[0].stats.station.lower() == "hses":
instream = stream
break
if instream is None:
raise ValueError("Instream should not be none.")
compare_streams(instream, outstream)
workspace.close()
# read in data from a second event and stash it in the workspace
eventid = "nz2018p115908"
datafiles, event = read_data_dir("geonet", eventid, "*.V2A")
raw_streams = []
for dfile in datafiles:
raw_streams += read_data(dfile)
workspace = StreamWorkspace.open(tfile)
workspace.addStreams(event, raw_streams, label="foo")
stations = workspace.getStations()
eventids = workspace.getEventIds()
assert eventids == ["us1000778i", "nz2018p115908"]
instation = raw_streams[0][0].stats.station
this_stream = workspace.getStreams(eventid,
stations=[instation],
labels=["foo"])[0]
assert instation == this_stream[0].stats.station
usid = "us1000778i"
inventory = workspace.getInventory(usid)
workspace.close()
codes = [
station.code for station in inventory.networks[0].stations
]
assert sorted(set(codes)) == ["HSES", "THZ", "WPWS", "WTMC"]
except Exception as e:
raise (e)
finally:
shutil.rmtree(tdir)
def _test_vs30_dist_metrics():
KNOWN_DISTANCES = {
"epicentral": 5.1,
"hypocentral": 10.2,
"rupture": 2.21,
"rupture_var": np.nan,
"joyner_boore": 2.21,
"joyner_boore_var": np.nan,
"gc2_rx": 2.66,
"gc2_ry": 3.49,
"gc2_ry0": 0.00,
"gc2_U": 34.34,
"gc2_T": 2.66,
}
KNOWN_BAZ = 239.46
KNOWN_VS30 = 331.47
eventid = "ci38457511"
datafiles, event = read_data_dir("fdsn", eventid, "*")
datadir = os.path.split(datafiles[0])[0]
raw_streams = StreamCollection.from_directory(datadir)
config = update_config(os.path.join(datadir, "config_min_freq_0p2.yml"))
processed_streams = process_streams(raw_streams, event, config=config)
rupture_file = get_rupture_file(datadir)
grid_file = os.path.join(datadir, "test_grid.grd")
config["metrics"]["vs30"] = {
"vs30": {
"file": grid_file,
"column_header": "GlobalVs30",
"readme_entry": "GlobalVs30",
"units": "m/s",
}
}
tdir = tempfile.mkdtemp()
try:
tfile = os.path.join(tdir, "test.hdf")
ws = StreamWorkspace(tfile)
ws.addEvent(event)
ws.addStreams(event, raw_streams, label="raw")
ws.addStreams(event, processed_streams, label="processed")
ws.calcMetrics(event.id,
rupture_file=rupture_file,
labels=["processed"],
config=config)
sta_sum = ws.getStreamMetrics(event.id, "CI", "CLC", "processed")
for dist in sta_sum.distances:
np.testing.assert_allclose(sta_sum.distances[dist],
KNOWN_DISTANCES[dist],
rtol=0.01)
np.testing.assert_allclose(sta_sum._back_azimuth, KNOWN_BAZ, rtol=0.01)
np.testing.assert_allclose(sta_sum._vs30["vs30"]["value"],
KNOWN_VS30,
rtol=0.01)
event_df, imc_tables, readme_tables = ws.getTables("processed")
ws.close()
check_cols = set([
"EpicentralDistance",
"HypocentralDistance",
"RuptureDistance",
"RuptureDistanceVar",
"JoynerBooreDistance",
"JoynerBooreDistanceVar",
"GC2_rx",
"GC2_ry",
"GC2_ry0",
"GC2_U",
"GC2_T",
"GlobalVs30",
"BackAzimuth",
])
assert check_cols.issubset(set(readme_tables["Z"]["Column header"]))
assert check_cols.issubset(set(imc_tables["Z"].columns))
except Exception as e:
raise (e)
finally:
shutil.rmtree(tdir)
