def getpath(self, date, mseed_dir):
"""
Gets path to mseed file (normally residing in subdir 'basedir/yyyy-mm/')
can also reside in subdir basedir/yyyy/
@type date: L{UTCDateTime} or L{datetime} or L{date}
@rtype: unicode
"""
files, subdir_len = psutils.filelist(mseed_dir, ext='mseed', subdirs=True)
if subdir_len == 7:
subdir = '{y:04d}-{m:02d}'.format(y=date.year, m=date.month)
elif subdir_len == 4:
subdir = '{y:04d}'.format(y=date.year)
if not subdir in self.subdirs:
s = 'No data for station {s} at date {d}!!'
raise Exception(s.format(s=self.name, d=date.date))
path = os.path.join(self.basedir, subdir, self.file)
return path
def getpath(self, date, mseed_dir):
"""
Gets path to mseed file (normally residing in subdir 'basedir/yyyy-mm/')
can also reside in subdir basedir/yyyy/
@type date: L{UTCDateTime} or L{datetime} or L{date}
@rtype: unicode
"""
files, subdir_len = psutils.filelist(mseed_dir,
ext='mseed',
subdirs=True)
if subdir_len == 7:
subdir = '{y:04d}-{m:02d}'.format(y=date.year, m=date.month)
elif subdir_len == 4:
subdir = '{y:04d}'.format(y=date.year)
if not subdir in self.subdirs:
s = 'No data for station {s} at date {d}!!'
raise Exception(s.format(s=self.name, d=date.date))
path = os.path.join(self.basedir, subdir, self.file)
return path
def get_stations(mseed_dir=MSEED_DIR,
xml_inventories=(),
dataless_inventories=(),
networks=None,
startday=None,
endday=None,
coord_tolerance=1E-4,
verbose=True):
"""
Gets the list of stations from miniseed files, and
extracts information from StationXML and dataless
inventories.
@type mseed_dir: str or unicode
@type xml_inventories: list of L{obspy.station.inventory.Inventory}
@type dataless_inventories: list of L{obspy.xseed.parser.Parser})
@type networks: list of str
@type startday: L{datetime.date}
@type endday: L{datetime.date}
@rtype: list of L{Station}
"""
if verbose:
print "Scanning stations in dir: " + mseed_dir
# initializing list of stations by scanning name of miniseed files
stations = []
files, subdir_len = psutils.filelist(mseed_dir,
ext='mseed',
subdirs=True,
verbose=True)
#if verbose:
# print(subdir_len); print(files)
for f in files:
# splitting subdir/basename
subdir, filename = os.path.split(f)
# subdir = e.g., 1990-03 if len = 7 else subdir can equal just a year e.g. 1999
if len(subdir) == 7:
year, month = int(subdir.split('-')[0]), int(subdir.split('-')[1])
# checking that month is within selected intervals
if startday and (year, month) < (startday.year, startday.month):
continue
if endday and (year, month) > (endday.year, endday.month):
continue
elif len(subdir) == 4:
year = int(subdir)
# checking that year is within selected intervals
# network, station name and station channel in basename,
# e.g., BL.CACB.BHZ.mseed
network, name, channel = filename.split('.')[0:3]
if networks and network not in networks:
continue
# looking for station in list
try:
match = lambda s: [s.network, s.name, s.channel
] == [network, name, channel]
station = next(s for s in stations if match(s))
except StopIteration:
# appending new station, with current subdir
station = Station(name=name,
network=network,
channel=channel,
filename=filename,
basedir=mseed_dir,
subdirs=[subdir])
stations.append(station)
else:
# appending subdir to list of subdirs of station
station.subdirs.append(subdir)
if verbose:
print 'Found {0} stations'.format(len(stations))
# adding lon/lat of stations from inventories
if verbose:
print "Inserting coordinates to stations from inventories"
for sta in copy(stations):
# coordinates of station in dataless inventories
coords_set = set(
(c['longitude'], c['latitude']) for inv in dataless_inventories
for c in inv.getInventory()['channels']
if c['channel_id'].split('.')[:2] == [sta.network, sta.name])
# coordinates of station in xml inventories
coords_set = coords_set.union(
(s.longitude, s.latitude) for inv in xml_inventories for net in inv
for s in net.stations
if net.code == sta.network and s.code == sta.name)
if not coords_set:
# no coords found: removing station
if verbose:
print "WARNING: skipping {} as no coords were found".format(
repr(sta))
stations.remove(sta)
elif len(coords_set) == 1:
# one set of coords found
sta.coord = list(coords_set)[0]
else:
# several sets of coordinates: calculating max diff
lons = [lon for lon, _ in coords_set]
lons_combinations = list(it.combinations(lons, 2))
lats = [lat for _, lat in coords_set]
lats_combinations = list(it.combinations(lats, 2))
maxdiff_lon = np.abs(np.diff(lons_combinations)).max()
maxdiff_lat = np.abs(np.diff(lats_combinations)).max()
if maxdiff_lon <= coord_tolerance and maxdiff_lat <= coord_tolerance:
# coordinates differences are within tolerance:
# assigning means of coordinates
if verbose:
s = ("{} has several sets of coords within "
"tolerance: assigning mean coordinates")
print s.format(repr(sta))
sta.coord = (np.mean(lons), np.mean(lats))
else:
# coordinates differences are not within tolerance:
# removing station
if verbose:
s = (
"WARNING: skipping {} with several sets of coords not "
"within tolerance (max lon diff = {}, max lat diff = {})"
)
print s.format(repr(sta), maxdiff_lon, maxdiff_lat)
stations.remove(sta)
return stations, subdir_len
def get_stations(mseed_dir=MSEED_DIR, xml_inventories=(), dataless_inventories=(),
networks=None, startday=None, endday=None, coord_tolerance=1E-4,
verbose=True):
"""
Gets the list of stations from miniseed files, and
extracts information from StationXML and dataless
inventories.
@type mseed_dir: str or unicode
@type xml_inventories: list of L{obspy.station.inventory.Inventory}
@type dataless_inventories: list of L{obspy.xseed.parser.Parser})
@type networks: list of str
@type startday: L{datetime.date}
@type endday: L{datetime.date}
@rtype: list of L{Station}
"""
if verbose:
print "Scanning stations in dir: " + mseed_dir
# initializing list of stations by scanning name of miniseed files
stations = []
files, subdir_len = psutils.filelist(mseed_dir, ext='mseed', subdirs=True, verbose=True)
#if verbose:
# print(subdir_len); print(files)
for f in files:
# splitting subdir/basename
subdir, filename = os.path.split(f)
# subdir = e.g., 1990-03 if len = 7 else subdir can equal just a year e.g. 1999
if len(subdir) == 7:
year, month = int(subdir.split('-')[0]), int(subdir.split('-')[1])
# checking that month is within selected intervals
if startday and (year, month) < (startday.year, startday.month):
continue
if endday and (year, month) > (endday.year, endday.month):
continue
elif len(subdir) == 4:
year = int(subdir)
# checking that year is within selected intervals
# network, station name and station channel in basename,
# e.g., BL.CACB.BHZ.mseed
network, name, channel = filename.split('.')[0:3]
if networks and network not in networks:
continue
# looking for station in list
try:
match = lambda s: [s.network, s.name, s.channel] == [network, name, channel]
station = next(s for s in stations if match(s))
except StopIteration:
# appending new station, with current subdir
station = Station(name=name, network=network, channel=channel,
filename=filename, basedir=mseed_dir, subdirs=[subdir])
stations.append(station)
else:
# appending subdir to list of subdirs of station
station.subdirs.append(subdir)
if verbose:
print 'Found {0} stations'.format(len(stations))
# adding lon/lat of stations from inventories
if verbose:
print "Inserting coordinates to stations from inventories"
for sta in copy(stations):
# coordinates of station in dataless inventories
coords_set = set((c['longitude'], c['latitude']) for inv in dataless_inventories
for c in inv.getInventory()['channels']
if c['channel_id'].split('.')[:2] == [sta.network, sta.name])
# coordinates of station in xml inventories
coords_set = coords_set.union((s.longitude, s.latitude) for inv in xml_inventories
for net in inv for s in net.stations
if net.code == sta.network and s.code == sta.name)
if not coords_set:
# no coords found: removing station
if verbose:
print "WARNING: skipping {} as no coords were found".format(repr(sta))
stations.remove(sta)
elif len(coords_set) == 1:
# one set of coords found
sta.coord = list(coords_set)[0]
else:
# several sets of coordinates: calculating max diff
lons = [lon for lon, _ in coords_set]
lons_combinations = list(it.combinations(lons, 2))
lats = [lat for _, lat in coords_set]
lats_combinations = list(it.combinations(lats, 2))
maxdiff_lon = np.abs(np.diff(lons_combinations)).max()
maxdiff_lat = np.abs(np.diff(lats_combinations)).max()
if maxdiff_lon <= coord_tolerance and maxdiff_lat <= coord_tolerance:
# coordinates differences are within tolerance:
# assigning means of coordinates
if verbose:
s = ("{} has several sets of coords within "
"tolerance: assigning mean coordinates")
print s.format(repr(sta))
sta.coord = (np.mean(lons), np.mean(lats))
else:
# coordinates differences are not within tolerance:
# removing station
if verbose:
s = ("WARNING: skipping {} with several sets of coords not "
"within tolerance (max lon diff = {}, max lat diff = {})")
print s.format(repr(sta), maxdiff_lon, maxdiff_lat)
stations.remove(sta)
return stations, subdir_len