def create_directory(self):
""" create the directory with gaps in it """
# get a dataframe of the gaps
if self.gaps is not None:
df = pd.DataFrame(self.gaps, columns=["start", "end"])
df["start"] = df["start"].apply(lambda x: x.timestamp)
df["end"] = df["end"].apply(lambda x: x.timestamp)
else:
df = pd.DataFrame(columns=["start", "end"])
assert self.starttime and self.endtime, "needs defined times"
for t1, t2 in make_time_chunks(self.starttime, self.endtime,
self.duration, self.overlap):
# figure out of this time lies in a gap
gap = df[~((df.start >= t2) | (df.end <= t1))]
if not gap.empty:
try:
st = self.get_gap_stream(t1, t2, gap)
except ValueError:
continue
else:
st = self.create_stream(t1, t2)
finame = str(t1).split(".")[0].replace(":", "-") + ".mseed"
path = join(self.path, finame)
st.write(path, "mseed")
def yield_waveforms(
self,
network: Optional[str] = None,
station: Optional[str] = None,
location: Optional[str] = None,
channel: Optional[str] = None,
starttime: Optional[utc_able_type] = None,
endtime: Optional[utc_able_type] = None,
duration: float = 3600.0,
overlap: Optional[float] = None,
) -> Stream:
"""
Yield time-series segments.
Parameters
----------
{get_waveforms_params}
duration : float
The duration of the streams to yield. All channels selected
channels will be included in the waveforms.
overlap : float
If duration is used, the amount of overlap in yielded streams,
added to the end of the waveforms.
Notes
-----
All string parameters can use posix style matching with * and ? chars.
Total duration of yielded streams = duration + overlap.
"""
# get times in float format
starttime = to_datetime64(starttime, 0.0)
endtime = to_datetime64(endtime, "2999-01-01")
# read in the whole index df
index = self.read_index(
network=network,
station=station,
location=location,
channel=channel,
starttime=starttime,
endtime=endtime,
)
# adjust start/end times
starttime = max(starttime, index.starttime.min())
endtime = min(endtime, index.endtime.max())
# chunk time and iterate over chunks
time_chunks = make_time_chunks(starttime, endtime, duration, overlap)
for t1, t2 in time_chunks:
t1, t2 = to_datetime64(t1), to_datetime64(t2)
con1 = (index.starttime - self.buffer) > t2
con2 = (index.endtime + self.buffer) < t1
ind = index[~(con1 | con2)]
if not len(ind):
continue
yield self._index2stream(ind, t1, t2)
def yield_waveforms(
self,
network: Optional[str] = None,
station: Optional[str] = None,
location: Optional[str] = None,
channel: Optional[str] = None,
starttime: Optional[obspy.UTCDateTime] = None,
endtime: Optional[obspy.UTCDateTime] = None,
duration: float = 3600.0,
overlap: Optional[float] = None,
) -> Stream:
"""
Yield time-series segments from the waveform client.
Parameters
----------
{get_waveforms_params}
duration : float
The duration of the streams to yield. All channels selected
channels will be included in the waveforms.
overlap : float
If duration is used, the amount of overlap in yielded streams,
added to the end of the waveforms.
Notes
-----
All string parameters can use posix style matching with * and ? chars.
Total duration of yielded streams = duration + overlap.
If no starttime or endtime is provided the min/max indicated by the
stations will be used.
"""
# Note: although WaveBank has a yield waveforms method, we want
# fetcher to work with any client so we don't use its implementation.
starttime = to_utc(starttime or self.station_df["start_date"].min())
endtime = to_utc(endtime or self.station_df["end_date"].max())
time_chunks = make_time_chunks(starttime, endtime, duration, overlap)
for t1, t2 in time_chunks:
kwargs = dict(network=network,
station=station,
location=location,
channel=channel)
yield self.get_waveforms(starttime=t1, endtime=t2, **kwargs)
def build_archive(self, st, starttime=None, endtime=None):
"""
Build the archive.
"""
starttime = starttime or self.starttime
endtime = endtime or self.endtime
for utc1, utc2 in make_time_chunks(starttime, endtime, duration=3600):
stt = st.copy()
stt.trim(starttime=utc1, endtime=utc2)
channels = {x.stats.channel for x in st}
for channel in channels:
ts = stt.select(channel=channel)
if not len(ts):
continue
stats = ts[0].stats
net, sta = stats.network, stats.station
loc, cha = stats.location, stats.channel
utc_str = str(utc1).split(".")[0].replace(":", "-")
end = utc_str + ".mseed"
fpath = self.waveform_path / net / sta / loc / cha / end
fpath.parent.mkdir(parents=True, exist_ok=True)
ts.write(str(fpath), "mseed")