def get_waveforms_bulk(stream: Stream, bulk: bulk_waveform_arg_type,
**kwargs) -> Stream:
"""
Get a large number of waveforms with a bulk request.
Parameters
----------
stream
A stream object.
bulk
A list of any number of tuples containing the following:
(network, station, location, channel, starttime, endtime).
"""
# get a dataframe of stream contents
index = _get_waveform_df(stream)
# get a dataframe of the bulk arguments, convert time to datetime64
request_df = get_waveform_bulk_df(bulk)
if not len(request_df): # return empty string if no bulk reqs provided
return obspy.Stream()
# get unique times and check conditions for string columns
unique_times = np.unique(request_df[["starttime", "endtime"]].values,
axis=0)
traces = []
for (t1, t2) in unique_times:
sub = _filter_index_to_bulk((t1, t2),
index_df=index,
bulk_df=request_df)
new = obspy.Stream(traces=[x.data for x in sub["trace"]]).slice(
starttime=to_utc(t1), endtime=to_utc(t2))
traces.extend(new.traces)
return merge_traces(obspy.Stream(traces=traces))
def get_waveforms_bulk(
self,
bulk: bulk_waveform_arg_type,
index: Optional[pd.DataFrame] = None,
**kwargs,
) -> Stream:
"""
Get a large number of waveforms with a bulk request.
Parameters
----------
bulk
A list of any number of lists containing the following:
(network, station, location, channel, starttime, endtime).
index
A dataframe returned by read_index. Enables calling code to only
read the index from disk once for repetitive calls.
"""
df = get_waveform_bulk_df(bulk)
if not len(df):
return obspy.Stream()
# get index and filter to temporal extents of request.
t_min, t_max = df["starttime"].min(), df["endtime"].max()
if index is not None:
ind = index[~((index.starttime > t_max) | (index.endtime < t_min))]
else:
ind = self.read_index(starttime=t_min, endtime=t_max)
# for each unique time, apply other filtering conditions and get traces
unique_times = np.unique(df[["starttime", "endtime"]].values, axis=0)
traces = []
for utime in unique_times:
sub = _filter_index_to_bulk(utime, ind, df)
traces += self._index2stream(sub, utime[0], utime[1],
merge=False).traces
return merge_traces(obspy.Stream(traces=traces), inplace=True)
def test_dataframe_extra_column(self, bulk_df):
"""The dataframe should work even with out of order/extra columns."""
df = bulk_df.copy()
df["bob"] = "lightening"
# reverse column order
df = df[reversed(list(df.columns))]
out = get_waveform_bulk_df(df)
assert isinstance(out, pd.DataFrame)
assert len(out) == len(self.bulk1) == len(bulk_df)
# the new columns should have been dropped
cols = list(WAVEFORM_REQUEST_DTYPES)
assert list(out.columns) == cols
def test_missing_column_raises(self, bulk_df):
"""A missing column should raise."""
df = bulk_df.drop(columns=["network"])
with pytest.raises(ValidationError, match="network"):
get_waveform_bulk_df(df)
def test_dataframe(self, bulk_df):
"""Ensure a datframe with no extra columns works."""
out = get_waveform_bulk_df(bulk_df)
assert isinstance(out, pd.DataFrame)
assert len(out) == len(self.bulk1) == len(bulk_df)
def test_tuple(self):
"""Ensure standard tuples produce bulk df."""
out = get_waveform_bulk_df(self.bulk1)
assert isinstance(out, pd.DataFrame)
assert len(out) == len(self.bulk1)
def bulk_df(self):
"""Create a dataframe from bulk."""
df = pd.DataFrame(self.bulk1, columns=list(WAVEFORM_REQUEST_DTYPES))
out = get_waveform_bulk_df(df)
return out
