def _func(time, ind, df):
""" return waveforms from df of bulk parameters """
match_chars = {"*", "?", "[", "]"}
t1, t2 = time[0], time[1]
# filter index based on start/end times
in_time = ~((ind["starttime"] > t2) | (ind["endtime"] < t1))
ind = ind[in_time]
# create indices used to load data
ar = np.ones(len(ind)) # indices of ind to use to load data
df = df[(df.t1 == time[0]) & (df.t2 == time[1])]
# determine which columns use any matching or other select features
uses_matches = [_column_contains(df[x], match_chars) for x in NSLC]
match_ar = np.array(uses_matches).any(axis=0)
df_match = df[match_ar]
df_no_match = df[~match_ar]
# handle columns that need matches (more expensive)
if not df_match.empty:
match_bulk = df_match.to_records(index=False)
mar = np.array(
[filter_index(ind,
*tuple(b)[:4]) for b in match_bulk])
ar = np.logical_and(ar, mar.any(axis=0))
# handle columns that do not need matches
if not df_no_match.empty:
nslc1 = set(get_seed_id_series(df_no_match))
nslc2 = get_seed_id_series(ind)
ar = np.logical_and(ar, nslc2.isin(nslc1))
return self._index2stream(ind[ar], t1, t2)
def _func(time, ind, df, st):
""" return waveforms from df of bulk parameters """
match_chars = {"*", "?", "[", "]"}
ar = np.ones(len(ind)) # indices of ind to use to load data
_t1, _t2 = time[0], time[1]
df = df[(df.t1 == time[0]) & (df.t2 == time[1])]
# determine which columns use any matching or other select features
uses_matches = [_column_contains(df[x], match_chars) for x in NSLC]
match_ar = np.array(uses_matches).any(axis=0)
df_match = df[match_ar]
df_no_match = df[~match_ar]
# handle columns that need matches (more expensive)
if not df_match.empty:
match_bulk = df_match.to_records(index=False)
mar = np.array(
[filter_index(ind,
*tuple(b)[:4]) for b in match_bulk])
ar = np.logical_and(ar, mar.any(axis=0))
# handle columns that do not need matches
if not df_no_match.empty:
nslc1 = set(get_seed_id_series(df_no_match))
nslc2 = get_seed_id_series(ind)
ar = np.logical_and(ar, nslc2.isin(nslc1))
# get a list of used traces, combine and trim
st = obspy.Stream([x for x, y in zip(st, ar) if y])
return st.slice(starttime=to_utc(_t1), endtime=to_utc(_t2))
def get_waveforms(
self,
network=None,
station=None,
location=None,
channel=None,
starttime=None,
endtime=None,
) -> obspy.Stream:
"""
Get waveforms from the cache, read from disk and cache if needed.
See obplus.WaveBank.get_waveforms for param descriptions.
"""
filt = filter_index(self.index, network, station, location, channel,
starttime, endtime)
ser = self.index[filt].set_index("unique_key")["st_call"]
# drop duplicates
ser = ser[~ser.index.duplicated()]
# no waveforms found, return empty waveforms
if not len(ser):
return obspy.Stream()
st = reduce(add, (x() for x in ser))
if starttime is not None or endtime is not None:
# use start/endtime or set far out constants
starttime = starttime or 0
endtime = endtime or 32503680000
return st.trim(starttime=starttime, endtime=endtime)
else:
return st
def _get_bulk_args(self,
starttime=None,
endtime=None,
**kwargs) -> bulk_waveform_arg_type:
"""
Get the bulk waveform arguments based on given start/end times.
This method also takes into account data availability as contained
in the stations data.
Parameters
----------
starttime
Start times for query.
endtime
End times for query.
Returns
-------
List of tuples of the form:
[(network, station, location, channel, starttime, endtime)]
"""
station_df = self.station_df.copy()
inv = station_df[filter_index(station_df, **kwargs)]
# replace None/Nan with larger number
inv.loc[inv["end_date"].isnull(), "end_date"] = LARGEDT64
inv["end_date"] = inv["end_date"].astype("datetime64[ns]")
# get start/end of the inventory
inv_start = inv["start_date"].min()
inv_end = inv["end_date"].max()
# remove station/channels that dont have data for requested time
min_time = to_datetime64(starttime, default=inv_start).min()
max_time = to_datetime64(endtime, default=inv_end).max()
con1, con2 = (inv["start_date"] > max_time), (inv["end_date"] <
min_time)
df = inv[~(con1 | con2)].set_index("seed_id")[list(NSLC)]
if df.empty: # return empty list if no data found
return []
if isinstance(starttime, pd.Series):
# Have to get clever here to make sure only active stations get used
# and indices are not duplicated.
new_start = starttime.loc[set(starttime.index).intersection(
df.index)]
new_end = endtime.loc[set(endtime.index).intersection(df.index)]
df["starttime"] = new_start.loc[~new_start.index.duplicated()]
df["endtime"] = new_end.loc[~new_end.index.duplicated()]
else:
df["starttime"] = starttime
df["endtime"] = endtime
# remove any rows that don't have defined start/end times
out = df[~(df["starttime"].isnull() | df["endtime"].isnull())]
# ensure we have UTCDateTime objects
out["starttime"] = [to_utc(x) for x in out["starttime"]]
out["endtime"] = [to_utc(x) for x in out["endtime"]]
# convert to list of tuples and return
return [tuple(x) for x in out.to_records(index=False)]
def test_filter_index(self, crandall_dataset):
"""Tests for filtering index with filter index function."""
# this is mainly here to test the time filtering, because the bank
# operations pass this off to the HDF5 kernel.
index = crandall_dataset.waveform_client.read_index(network="UU")
t1_ns = int(index["starttime"].astype(np.int64).mean())
t1 = np.datetime64(t1_ns, "ns")
t2 = index["endtime"].max()
kwargs = dict(network="UU", station="*", location="*", channel="*")
bool_ind = filter_index(index, starttime=t1, endtime=t2, **kwargs)
assert (~np.logical_not(bool_ind)).any()
def stream_bulk_split(st: Stream,
bulk: List[waveform_request_type],
fill_value: Any = None) -> List[Stream]:
"""
Split a stream into a list of streams that meet requirements in bulk.
This is similar to the get_waveforms_bulk methods of waveform_client, but
rather than merging any overlapping data it is returned in a list of traces.
Parameters
----------
st
A stream object
bulk
A bulk request. Wildcards not currently supported on str params.
fill_value
If not None fill any missing data in time range with this value.
Returns
-------
List of traces, each meeting the corresponding request in bulk.
"""
# return nothing if empty bulk or stream args
bulk = _get_bulk(bulk)
if not bulk or len(st) == 0:
return []
# # get dataframe of stream contents
sdf = _stream_data_to_df(st)
# iterate stream, return output
out = []
for barg in bulk:
assert len(
barg) == 6, f"{barg} is not a valid bulk arg, must have len 6"
need = filter_index(sdf, *barg)
traces = [tr for tr, bo in zip(st, need) if bo]
new_st = obspy.Stream(traces)
t1, t2 = to_utc(barg[-2]), to_utc(barg[-1])
new = new_st.slice(starttime=t1, endtime=t2)
# apply fill if needed
if fill_value is not None:
new = new.trim(starttime=t1,
endtime=t2,
fill_value=fill_value,
pad=True)
if new is None or not len(new):
out.append(obspy.Stream())
continue
new = merge_traces(new)
out.append(new)
assert len(out) == len(bulk), "output is not the same len as stream list"
return out
def _filter_index_to_bulk(time, index_df, bulk_df) -> pd.DataFrame:
"""
Using an index_df, apply conditions in request_df and return array indicating
if values in index meet requested conditions.
Parameters
----------
time
A tuple of mintime, maxtime
index_df
A dataframe indexing a waveform resource. Can be an index of traces
in a stream or an index from a wavebank.
bulk_df
The dataframe containing bulk requests.
"""
match_chars = {"*", "?", "[", "]"}
# filter out any index times not in current time pair
too_late = index_df["starttime"] > time[1]
too_early = index_df["endtime"] < time[0]
index_df = index_df[~(too_early | too_late)]
ar = np.ones(len(index_df)) # indices of ind to use to load data
# filter out any request times which are not for the current time pair
is_starttime = bulk_df["starttime"] == time[0]
is_endtime = bulk_df["endtime"] == time[1]
bulk_df = bulk_df[is_starttime & is_endtime]
# determine which columns use matching. These must be handled separately.
uses_matches = [_column_contains(bulk_df[x], match_chars) for x in NSLC]
match_ar = np.array(uses_matches).any(axis=0)
df_match = bulk_df[match_ar]
df_no_match = bulk_df[~match_ar]
# handle columns that need matches (more expensive)
if not df_match.empty:
match_bulk = df_match.to_records(index=False)
mar = np.array(
[filter_index(index_df,
*tuple(b)[:4]) for b in match_bulk])
ar = np.logical_and(ar, mar.any(axis=0))
# handle columns that do not need matches
if not df_no_match.empty:
nslc1 = set(get_seed_id_series(df_no_match))
nslc2 = get_seed_id_series(index_df)
ar = np.logical_and(ar, nslc2.isin(nslc1))
# get a list of used traces, combine and trim
return index_df[ar]
def read_index(
self,
network: Optional[str] = None,
station: Optional[str] = None,
location: Optional[str] = None,
channel: Optional[str] = None,
starttime: Optional[utc_time_type] = None,
endtime: Optional[utc_time_type] = None,
**kwargs,
) -> pd.DataFrame:
"""
Return a dataframe of the index, optionally applying filters.
Parameters
----------
{waveform_params}
kwargs
kwargs are passed to pandas.read_hdf function
"""
self.ensure_bank_path_exists()
if starttime is not None and endtime is not None:
if starttime > endtime:
msg = "starttime cannot be greater than endtime."
raise ValueError(msg)
if not self.index_path.exists():
self.update_index()
# if no file was created (dealing with empty bank) return empty index
if not self.index_path.exists():
return pd.DataFrame(columns=self.index_columns)
# grab index from cache
index = self._index_cache(starttime,
endtime,
buffer=self.buffer,
**kwargs)
# filter and return
filt = filter_index(index,
network=network,
station=station,
location=location,
channel=channel)
return index[filt]
