def get_swstat_bits(frame_filenames, swstat_channel_name, start_time,
end_time):
''' This function just checks the first time in the SWSTAT channel
to see if the filter was on, it doesn't check times beyond that.
This is just for a first test on a small chunck of data.
To read the SWSTAT bits, reference: https://dcc.ligo.org/DocDB/0107/T1300711/001/LIGO-T1300711-v1.pdf
Bit 0-9 = Filter on/off switches for the 10 filters in an SFM.
Bit 10 = Filter module input switch on/off
Bit 11 = Filter module offset switch on/off
Bit 12 = Filter module output switch on/off
Bit 13 = Filter module limit switch on/off
Bit 14 = Filter module history reset momentary switch
'''
# read frames
swstat = frame.read_frame(frame_filenames,
swstat_channel_name,
start_time=start_time,
end_time=end_time)
# convert number in channel to binary
bits = bin(int(swstat[0]))
# check if filterbank input or output was off
filterbank_off = False
if len(bits) < 14 or int(bits[-13]) == 0 or int(bits[-11]) == 0:
filterbank_off = True
return bits[-10:], filterbank_off
def strain(self, ifo, duration=32, sample_rate=4096):
""" Return strain around the event
Currently this will return the strain around the event in the smallest
format available. Selection of other data is not yet available.
Parameters
----------
ifo: str
The name of the observatory you want strain for. Ex. H1, L1, V1
Returns
-------
strain: pycbc.types.TimeSeries
Strain around the event.
"""
from astropy.utils.data import download_file
from pycbc.frame import read_frame
if sample_rate == 4096:
sampling = "4KHz"
elif sample_rate == 16384:
sampling = "16KHz"
channel = "{}:GWOSC-{}_R1_STRAIN".format(ifo, sampling.upper())
for fdict in self.data['strain']:
if (fdict['detector'] == ifo and fdict['duration'] == duration and
fdict['sampling_rate'] == sample_rate and
fdict['format'] == 'gwf'):
url = fdict['url']
break
filename = download_file(url, cache=True)
return read_frame(str(filename), str(channel))
def get_noise(detector):
from pycbc import frame
import random as randi
import os
h1_list = ['H-H1_LOSC_16_V1-1126084608-4096.gwf', 'H-H1_LOSC_16_V1-1126109184-4096.gwf',
'H-H1_LOSC_16_V1-1126264832-4096.gwf', 'H-H1_LOSC_16_V1-1126293504-4096.gwf',
'H-H1_LOSC_16_V1-1127194624-4096.gwf',
'H-H1_LOSC_16_V1-1128042496-4096.gwf', 'H-H1_LOSC_16_V1-1128345600-4096.gwf',
'H-H1_LOSC_16_V1-1128407040-4096.gwf', 'H-H1_LOSC_16_V1-1128624128-4096.gwf',
'H-H1_LOSC_16_V1-1128665088-4096.gwf',
'H-H1_LOSC_16_V1-1129127936-4096.gwf', 'H-H1_LOSC_16_V1-1129664512-4096.gwf']
h1_begin = [1126084608, 1126109184, 1126264832, 1126293504, 1127194624, 1128042496, 1128345600, 1128407040,
1128624128, 1128665088, 1129127936, 1129664512]
if detector == 'O1-H':
file = 'H-H1_LOSC_16_V1-1126084608-4096.gwf'
strain = frame.read_frame(file, 'H1:GWOSC-16KHZ_R1_STRAIN',1126084608,1126084608+32)
return strain
def strain(self, ifo):
""" Return strain around the event
Currently this will return the strain around the event in the smallest
format available. Selection of other data is not yet available.
Parameters
----------
ifo: str
The name of the observatory you want strain for. Ex. H1, L1, V1
Returns
-------
strain: pycbc.types.TimeSeries
Strain around the event.
"""
import tempfile, requests, shutil
from pycbc.frame import read_frame
channel = '%s:LOSC-STRAIN' % ifo
url = self.data['frames'][ifo]
f = tempfile.NamedTemporaryFile(suffix='.gwf')
r = requests.get(url, stream=True)
if r.status_code != 200:
raise ValueError("Could not download file, %s", r.status_code)
shutil.copyfileobj(r.raw, f)
f.flush()
return read_frame(f.name, channel)
def loadts(self, inj):
"""Loads an injection time series.
After the first time a time series is loaded it will be added to an
internal buffer for faster in case another injection uses the same
series.
"""
if self._buffer is None:
# create the buffer
self._buffer = LimitedSizeDict(size_limit=self._buffersize)
try:
return self._buffer[inj.filename]
except KeyError:
pass
# not in buffer, so load
if inj.filename.endswith('.gwf'):
try:
channel = inj.channel
except AttributeError as _err:
# Py3.XX: uncomment the "from _err" when we drop 2.7
raise ValueError("Must provide a channel for "
"frame files") #from _err
ts = frame.read_frame(inj.filename, channel)
else:
ts = load_timeseries(inj.filename)
# cache
self._buffer[inj.filename] = ts
return ts
def strain(self, ifo):
""" Return strain around the event
Currently this will return the strain around the event in the smallest
format available. Selection of other data is not yet available.
Parameters
----------
ifo: str
The name of the observatory you want strain for. Ex. H1, L1, V1
Returns
-------
strain: pycbc.types.TimeSeries
Strain around the event.
"""
import tempfile, requests, shutil
from pycbc.frame import read_frame
channel = '%s:LOSC-STRAIN' % ifo
url = self.data['frames'][ifo]
f = tempfile.NamedTemporaryFile(suffix='.gwf')
r = requests.get(url, stream=True)
if r.status_code != 200:
raise ValueError("Could not download file, %s", r.status_code)
shutil.copyfileobj(r.raw, f)
f.flush()
return read_frame(f.name, channel)
def strain(self, ifo, duration=32, sample_rate=4096):
""" Return strain around the event
Currently this will return the strain around the event in the smallest
format available. Selection of other data is not yet available.
Parameters
----------
ifo: str
The name of the observatory you want strain for. Ex. H1, L1, V1
Returns
-------
strain: pycbc.types.TimeSeries
Strain around the event.
"""
from astropy.utils.data import download_file
from pycbc.frame import read_frame
# Information is currently wrong on GWOSC!
# channels = self.data['files']['FrameChannels']
# for channel in channels:
# if ifo in channel:
# break
length = "{}sec".format(duration)
if sample_rate == 4096:
sampling = "4KHz"
elif sample_rate == 16384:
sampling = "16KHz"
channel = "{}:GWOSC-{}_R1_STRAIN".format(ifo, sampling.upper())
url = self.data['files'][ifo][length][sampling]['GWF']
filename = download_file(url, cache=True)
return read_frame(str(filename), str(channel))
def get_swstat_bits(frame_filenames, swstat_channel_name, start_time, end_time):
''' This function just checks the first time in the SWSTAT channel
to see if the filter was on, it doesn't check times beyond that.
This is just for a first test on a small chunck of data.
To read the SWSTAT bits, reference: https://dcc.ligo.org/DocDB/0107/T1300711/001/LIGO-T1300711-v1.pdf
Bit 0-9 = Filter on/off switches for the 10 filters in an SFM.
Bit 10 = Filter module input switch on/off
Bit 11 = Filter module offset switch on/off
Bit 12 = Filter module output switch on/off
Bit 13 = Filter module limit switch on/off
Bit 14 = Filter module history reset momentary switch
'''
# read frames
swstat = frame.read_frame(frame_filenames, swstat_channel_name,
start_time=start_time, end_time=end_time)
# convert number in channel to binary
bits = bin(int(swstat[0]))
# check if filterbank input or output was off
filterbank_off = False
if len(bits) < 14 or int(bits[-13]) == 0 or int(bits[-11]) == 0:
filterbank_off = True
return bits[-10:], filterbank_off
def strain(self, ifo, duration=32, sample_rate=4096):
""" Return strain around the event
Currently this will return the strain around the event in the smallest
format available. Selection of other data is not yet available.
Parameters
----------
ifo: str
The name of the observatory you want strain for. Ex. H1, L1, V1
Returns
-------
strain: pycbc.types.TimeSeries
Strain around the event.
"""
from astropy.utils.data import download_file
from pycbc.frame import read_frame
# Information is currently wrong on GWOSC!
# channels = self.data['files']['FrameChannels']
# for channel in channels:
# if ifo in channel:
# break
length = "{}sec".format(duration)
if sample_rate == 4096:
sampling = "4KHz"
elif sample_rate == 16384:
sampling = "16KHz"
channel = "{}:GWOSC-{}_R1_STRAIN".format(ifo, sampling.upper())
url = self.data['files'][ifo][length][sampling]['GWF']
filename = download_file(url, cache=True)
return read_frame(str(filename), str(channel))
def setUp(self):
###### Get data for references analysis of 170817
m = Merger("GW170817")
ifos = ['H1', 'V1', 'L1']
self.psds = {}
self.data = {}
for ifo in ifos:
print("Processing {} data".format(ifo))
# Download the gravitational wave data for GW170817
url = "https://dcc.ligo.org/public/0146/P1700349/001/"
url += "{}-{}1_LOSC_CLN_4_V1-1187007040-2048.gwf"
fname = download_file(url.format(ifo[0], ifo[0]), cache=True)
ts = read_frame(fname,
"{}:LOSC-STRAIN".format(ifo),
start_time=int(m.time - 260),
end_time=int(m.time + 40))
ts = highpass(ts, 15.0)
ts = resample_to_delta_t(ts, 1.0 / 2048)
ts = ts.time_slice(m.time - 112, m.time + 16)
self.data[ifo] = ts.to_frequencyseries()
psd = interpolate(ts.psd(4), ts.delta_f)
psd = inverse_spectrum_truncation(psd,
int(4 * psd.sample_rate),
trunc_method='hann',
low_frequency_cutoff=20.0)
self.psds[ifo] = psd
self.static = {
'mass1': 1.3757,
'mass2': 1.3757,
'f_lower': 20.0,
'approximant': "TaylorF2",
'polarization': 0,
'ra': 3.44615914,
'dec': -0.40808407,
'tc': 1187008882.42840,
}
self.variable = (
'distance',
'inclination',
)
self.flow = {'H1': 25, 'L1': 25, 'V1': 25}
inclination_prior = SinAngle(inclination=None)
distance_prior = Uniform(distance=(10, 100))
tc_prior = Uniform(tc=(m.time - 0.1, m.time + 0.1))
self.prior = JointDistribution(self.variable, inclination_prior,
distance_prior)
###### Expected answers
# Answer taken from marginalized gaussian model
self.q1 = {'distance': 42.0, 'inclination': 2.5}
self.a1 = 541.8235746138382
# answer taken from brute marginize pol + phase
self.a2 = 542.581
self.pol_samples = 200
def read_gain_from_frames(frame_filenames, gain_channel_name, start_time, end_time):
'''
Returns the gain from the file.
'''
# get timeseries from frame
gain = frame.read_frame(frame_filenames, gain_channel_name,
start_time=start_time, end_time=end_time)
return gain[0]
def read_gain_from_frames(frame_filenames, gain_channel_name, start_time, end_time):
'''
Returns the gain from the file.
'''
# get timeseries from frame
gain = frame.read_frame(frame_filenames, gain_channel_name,
start_time=start_time, end_time=end_time)
return gain[0]
def get_GWSC_Full_strain(pth, tstart, tend):
"""This function, require the strain .gwf name, without the detector definition
(H-H1,L-L1), and loads the entire frame file downloaded from GW OSC,
applies a high-pass filter at 15 Hz, then return the whole data without cutting that
"""
strain = {}
for ifo in ifos:
fname = '%s-%s_%s' % (ifo[0], ifo, pth)
channel_name = '%s:GWOSC-4KHZ_R1_STRAIN' % ifo
strain[ifo] = read_frame(fname, channel_name, tstart, tend)
strain[ifo] = highpass(strain[ifo], 15.0)
return strain
def get_strain_from_gwf_files(
gwf_files: Dict[str, List[Union[str, bytes, os.PathLike]]],
gps_start: int,
window: int,
original_sampling_rate: int = 4096,
target_sampling_rate: int = 4096,
as_pycbc_timeseries: bool = True,
channel: str = 'GDS-CALIB_STRAIN',
check_integrity: bool = True,
):
assert isinstance(gps_start, int), 'time is not an int'
assert isinstance(window, int), 'interval_width is not an int'
assert isinstance(original_sampling_rate,
int), 'original_sampling_rate is not an int'
assert isinstance(target_sampling_rate,
int), 'target_sampling_rate is not an int'
assert (original_sampling_rate % target_sampling_rate) == 0, (
'Invalid target_sampling_rate: Not a divisor of original_sampling_rate!'
)
sampling_factor = int(original_sampling_rate / target_sampling_rate)
samples = defaultdict(list)
for ifo in gwf_files:
detector_channel = f'{ifo}:{channel}'
for file_path in gwf_files[ifo]:
strain = read_frame(
str(file_path),
detector_channel,
start_time=gps_start,
end_time=gps_start + window,
check_integrity=check_integrity,
)
samples[ifo].append(strain[::sampling_factor])
samples[ifo] = np.ascontiguousarray(np.concatenate(samples[ifo]))
if not as_pycbc_timeseries:
return samples
else:
# Convert strain of both detectors to a TimeSeries object
timeseries = {
ifo: TimeSeries(initial_array=samples[ifo],
delta_t=1.0 / target_sampling_rate,
epoch=LIGOTimeGPS(gps_start))
for ifo in samples
}
return timeseries
def get_raw_strain(window=512):
"""This function loads the entire frame file downloaded from GW OSC,
applies a high-pass filter at 15 Hz, then keeps the data around
``event_time`` +/-``window``. The ``event_time`` is from above; the
default window is 512 (s).
"""
strain = {}
for ifo in ifos:
fname = '%s-%s_LOSC_4_V2-1126257414-4096.gwf' % (ifo[0], ifo)
channel_name = '%s:LOSC-STRAIN' % ifo
strain[ifo] = read_frame(fname, channel_name)
strain[ifo] = highpass(strain[ifo], 15.0)
strain[ifo] = strain[ifo].time_slice(event_time-window/2, event_time+window/2)
return strain
def get_LSC_NoNan_strain(pth, tev, tstart, tend, window):
"""This function, require the strain .gwf name, without the detector definition
(H-H1,L-L1), and loads the entire frame file downloaded from GW OSC,
applies a high-pass filter at 15 Hz, then keeps the data around
``event_time`` +/-``window``. The ``event_time`` is from above; the
default window is 512 (s).
"""
strain = {}
for ifo in ifos:
fname = '%s-%s_%s' % (ifo[0], ifo, pth)
channel_name = '%s:LOSC-STRAIN' % ifo
strain[ifo] = read_frame(fname, channel_name, tstart, tend)
strain[ifo] = highpass(strain[ifo], 15.0)
strain[ifo] = strain[ifo].time_slice(tev - window / 2,
tev + window / 2)
return strain
def get_raw_strain(window=198):
"""This function loads the entire frame file downloaded from GW OSC,
applies a high-pass filter at 15 Hz, then keeps the data around
``event_time`` +/-``window``. The ``event_time`` is from above; the
default window is 512 (s).
"""
#Here I have changed: _LOSC_4_V2-1126257414-4096.gwf to _GWOSC_4KHZ_R1-1135134303-4096.gwf (i.e. the data_file name)
#LOSC-STRAIN was changed as well to GWOSC-4KHZ_R1_STRAIN
strain = {}
for ifo in ifos:
fname = '%s-%s_GWOSC_4KHZ_R1-1135134303-4096.gwf' % (ifo[0], ifo)
channel_name = '%s:GWOSC-4KHZ_R1_STRAIN' % ifo
strain[ifo] = read_frame(fname, channel_name)
strain[ifo] = strain[ifo].time_slice(event_time - window / 2,
event_time + window / 2)
#strain[ifo] = highpass(strain[ifo], 15.0)
return strain
def read_frame_losc(channels, start_time, end_time):
""" Read channels from losc data
Parameters
----------
channels: str or list
The channel name to read or list of channel names.
start_time: int
The gps time in GPS seconds
end_time: int
The end time in GPS seconds
Returns
-------
ts: TimeSeries
Returns a timeseries or list of timeseries with the requested data.
"""
import urllib
from pycbc.frame import read_frame
if not isinstance(channels, list):
channels = [channels]
ifos = [c[0:2] for c in channels]
urls = {}
for ifo in ifos:
urls[ifo] = losc_frame_urls(ifo, start_time, end_time)
if len(urls[ifo]) == 0:
raise ValueError("No data found for %s so we "
"can't produce a time series" % ifo)
fnames = {ifo: [] for ifo in ifos}
for ifo in ifos:
for url in urls[ifo]:
fname, _ = urllib.urlretrieve(url)
fnames[ifo].append(fname)
ts = [
read_frame(fnames[channel[0:2]],
channel,
start_time=start_time,
end_time=end_time) for channel in channels
]
if len(ts) == 1:
return ts[0]
else:
return ts
def plot_gwfs( frame_location1, frame_location2, label=['frame1','frame2'] ):
#
import matplotlib as mpl
mpl.rc('font',family='Times New Roman')
from matplotlib.pyplot import plot,xlabel,ylabel,figure,legend,xlim,ylim,title
from pycbc import frame
import numpy
#
frame_location = [frame_location1,frame_location2]
#
figure( figsize=0.8*numpy.array([16,4]) )
clrspec = [ 'b', [0.8,0.8,0.8] ]
widspec = [ 1, 3 ]
for k in [1,0]:
#
data_L = frame.read_frame( frame_location[k], '%s1:HWINJ_INJECTED'%frame_location[k][0] )
#
trigger_time = data_L.end_time.gpsSeconds-10.0
time = data_L.delta_t * (numpy.array(range(len(data_L.data)))-1.0) + data_L.start_time - trigger_time
#channel_data_H = data_H.data.real
channel_data_L = data_L.data.real
#
xlim( numpy.array([-0.18,0.18]) )
#plot( time, channel_data_H, color=0.7*numpy.array([1,1,1]) )
# plot( time, channel_data_L, color=0.8*numpy.array([numpy.sin(numpy.pi/(k+1)),1,1]), label=label[k] )
plot( time, channel_data_L, color=clrspec[k], label=label[k], linewidth=widspec[k] )
#plot( trigger_time * numpy.array([1,1]) , ylim(), color='r' )
fs=22
hfont = {'fontname':'serif'}
title(frame_location[k][0]+'1')
xlabel(r'$t$ (sec)', fontsize=fs)
ylabel(r'$h(t)$', fontsize=fs)
legend(frameon=False, fontsize=fs )
def read_frame_losc(channels, start_time, end_time):
""" Read channels from losc data
Parameters
----------
channels: str or list
The channel name to read or list of channel names.
start_time: int
The gps time in GPS seconds
end_time: int
The end time in GPS seconds
Returns
-------
ts: TimeSeries
Returns a timeseries or list of timeseries with the requested data.
"""
import urllib
from pycbc.frame import read_frame
if not isinstance(channels, list):
channels = [channels]
ifos = [c[0:2] for c in channels]
urls = {}
for ifo in ifos:
urls[ifo] = losc_frame_urls(ifo, start_time, end_time)
if len(urls[ifo]) == 0:
raise ValueError("No data found for %s so we "
"can't produce a time series" % ifo)
fnames = {ifo:[] for ifo in ifos}
for ifo in ifos:
for url in urls[ifo]:
fname, _ = urllib.urlretrieve(url)
fnames[ifo].append(fname)
ts = [read_frame(fnames[channel[0:2]], channel,
start_time=start_time, end_time=end_time) for channel in channels]
if len(ts) == 1:
return ts[0]
else:
return ts
def strain(self, ifo):
""" Return strain around the event
Currently this will return the strain around the event in the smallest
format available. Selection of other data is not yet available.
Parameters
----------
ifo: str
The name of the observatory you want strain for. Ex. H1, L1, V1
Returns
-------
strain: pycbc.types.TimeSeries
Strain around the event.
"""
from astropy.utils.data import download_file
from pycbc.frame import read_frame
channel = '%s:LOSC-STRAIN' % ifo
url = self.data['frames'][ifo]
filename = download_file(url, cache=True)
return read_frame(filename, channel)
def strain(self, ifo, duration=32, sample_rate=4096):
""" Return strain around the event
Currently this will return the strain around the event in the smallest
format available. Selection of other data is not yet available.
Parameters
----------
ifo: str
The name of the observatory you want strain for. Ex. H1, L1, V1
Returns
-------
strain: pycbc.types.TimeSeries
Strain around the event.
"""
from pycbc.io import get_file
from pycbc.frame import read_frame
for fdict in self.data['strain']:
if (fdict['detector'] == ifo and fdict['duration'] == duration
and fdict['sampling_rate'] == sample_rate
and fdict['format'] == 'gwf'):
url = fdict['url']
break
else:
raise ValueError('no strain data is available as requested '
'for ' + self.common_name)
ver = url.split('/')[-1].split('-')[1].split('_')[-1]
sampling_map = {4096: "4KHZ", 16384: "16KHZ"}
channel = "{}:GWOSC-{}_{}_STRAIN".format(ifo,
sampling_map[sample_rate],
ver)
filename = get_file(url, cache=True)
return read_frame(str(filename), str(channel))
from pycbc.frame import read_frame
from pycbc.filter import highpass_fir, matched_filter
from pycbc.waveform import get_fd_waveform
from pycbc.psd import welch, interpolate
import urllib
# Read data and remove low frequency content
fname = 'H-H1_LOSC_4_V2-1126259446-32.gwf'
url = "https://www.gw-openscience.org/GW150914data/" + fname
urllib.urlretrieve(url, filename=fname)
h1 = read_frame('H-H1_LOSC_4_V2-1126259446-32.gwf', 'H1:LOSC-STRAIN')
h1 = highpass_fir(h1, 15, 8)
# Calculate the noise spectrum
psd = interpolate(welch(h1), 1.0 / h1.duration)
# Generate a template to filter with
hp, hc = get_fd_waveform(approximant="IMRPhenomD",
mass1=40,
mass2=32,
f_lower=20,
delta_f=1.0 / h1.duration)
hp.resize(len(h1) / 2 + 1)
# Calculate the complex (two-phase SNR)
snr = matched_filter(hp, h1, psd=psd, low_frequency_cutoff=20.0)
# Remove regions corrupted by filter wraparound
snr = snr[len(snr) / 4:len(snr) * 3 / 4]
import pylab
from pycbc.frame import read_frame
from pycbc.filter import highpass_fir, matched_filter
from pycbc.waveform import get_fd_waveform
from pycbc.psd import welch, interpolate
import urllib
# Read data and remove low frequency content
fname = 'H-H1_LOSC_4_V2-1126259446-32.gwf'
url = "https://losc.ligo.org/s/events/GW150914/" + fname
urllib.urlretrieve(url, filename=fname)
h1 = read_frame('H-H1_LOSC_4_V2-1126259446-32.gwf', 'H1:LOSC-STRAIN')
h1 = highpass_fir(h1, 15, 8)
# Calculate the noise spectrum
psd = interpolate(welch(h1), 1.0 / 32)
# Generate a template to filter with
hp, hc = get_fd_waveform(approximant="IMRPhenomD", mass1=40, mass2=32,
f_lower=20, delta_f=1.0/32)
hp.resize(len(h1) / 2 + 1)
# Calculate the complex (two-phase SNR)
snr = matched_filter(hp, h1, psd=psd, low_frequency_cutoff=20.0)
# Remove regions corrupted by filter wraparound
snr = snr[len(snr) / 4: len(snr) * 3 / 4]
import pylab
pylab.plot(snr.sample_times, abs(snr))
pylab.ylabel('signal-to-noise')
pylab.xlabel('GPS Time (s)')
from scipy import signal import matplotlib.pyplot as plt from pycbc.frame import read_frame file_name = "H-H1_GWOSC_16KHZ_R1-1187008867-32.gwf" merger = 1187008882.4 # LOSC bulk data typically uses the same convention for internal channels names # Strain is typically IFO:LOSC-STRAIN, where IFO can be H1/L1/V1. channel_name = "H1:GWOSC-16KHZ_R1_STRAIN" hc = 500 lc = 30 ts = read_frame(file_name, channel_name, 1187008867, 1187008867 + 32) start = ts.start_time ts = ts.highpass_fir(lc, 512) ts = ts.lowpass_fir(hc, 512) strain = ts.data psd = ts.psd(2) whitened = ts.whiten(4, 4, low_frequency_cutoff=20) fs = 10e3 N = 1e5 amp = 2 * np.sqrt(2)
def from_cli(opt, dyn_range_fac=1, precision='single'):
"""Parses the CLI options related to strain data reading and conditioning.
Parameters
----------
opt : object
Result of parsing the CLI with OptionParser, or any object with the
required attributes (gps-start-time, gps-end-time, strain-high-pass,
pad-data, sample-rate, (frame-cache or frame-files), channel-name,
fake-strain, fake-strain-seed, gating_file).
dyn_range_fac: {float, 1}, optional
A large constant to reduce the dynamic range of the strain.
Returns
-------
strain : TimeSeries
The time series containing the conditioned strain data.
"""
gating_info = {}
if opt.frame_cache or opt.frame_files or opt.frame_type:
if opt.frame_cache:
frame_source = opt.frame_cache
if opt.frame_files:
frame_source = opt.frame_files
logging.info("Reading Frames")
if opt.frame_type:
strain = query_and_read_frame(opt.frame_type, opt.channel_name,
start_time=opt.gps_start_time-opt.pad_data,
end_time=opt.gps_end_time+opt.pad_data)
else:
strain = read_frame(frame_source, opt.channel_name,
start_time=opt.gps_start_time-opt.pad_data,
end_time=opt.gps_end_time+opt.pad_data)
if opt.zpk_z and opt.zpk_p and opt.zpk_k:
logging.info("Highpass Filtering")
strain = highpass(strain, frequency=opt.strain_high_pass)
logging.info("Applying zpk filter")
z = numpy.array(opt.zpk_z)
p = numpy.array(opt.zpk_p)
k = float(opt.zpk_k)
strain = filter_zpk(strain.astype(numpy.float64), z, p, k)
if opt.normalize_strain:
logging.info("Dividing strain by constant")
l = opt.normalize_strain
strain = strain / l
if opt.injection_file:
logging.info("Applying injections")
injections = InjectionSet(opt.injection_file)
injections.apply(strain, opt.channel_name[0:2],
distance_scale=opt.injection_scale_factor)
if opt.sgburst_injection_file:
logging.info("Applying sine-Gaussian burst injections")
injections = SGBurstInjectionSet(opt.sgburst_injection_file)
injections.apply(strain, opt.channel_name[0:2],
distance_scale=opt.injection_scale_factor)
logging.info("Highpass Filtering")
strain = highpass(strain, frequency=opt.strain_high_pass)
if precision == 'single':
logging.info("Converting to float32")
strain = (strain * dyn_range_fac).astype(float32)
if opt.gating_file is not None:
logging.info("Gating glitches")
gate_params = numpy.loadtxt(opt.gating_file)
if len(gate_params.shape) == 1:
gate_params = [gate_params]
strain = gate_data(strain, gate_params)
gating_info['file'] = \
[gp for gp in gate_params \
if (gp[0] + gp[1] + gp[2] >= strain.start_time) \
and (gp[0] - gp[1] - gp[2] <= strain.end_time)]
if opt.autogating_threshold is not None:
# the + 0 is for making a copy
glitch_times = detect_loud_glitches(
strain + 0., threshold=opt.autogating_threshold,
cluster_window=opt.autogating_cluster,
low_freq_cutoff=opt.strain_high_pass,
high_freq_cutoff=opt.sample_rate/2,
corrupted_time=opt.pad_data+opt.autogating_pad)
gate_params = [[gt, opt.autogating_width, opt.autogating_taper] \
for gt in glitch_times]
if len(glitch_times) > 0:
logging.info('Autogating at %s',
', '.join(['%.3f' % gt for gt in glitch_times]))
strain = gate_data(strain, gate_params)
gating_info['auto'] = gate_params
logging.info("Resampling data")
strain = resample_to_delta_t(strain, 1.0/opt.sample_rate, method='ldas')
logging.info("Highpass Filtering")
strain = highpass(strain, frequency=opt.strain_high_pass)
logging.info("Remove Padding")
start = opt.pad_data*opt.sample_rate
end = len(strain)-opt.sample_rate*opt.pad_data
strain = strain[start:end]
if opt.fake_strain:
logging.info("Generating Fake Strain")
duration = opt.gps_end_time - opt.gps_start_time
tlen = duration * opt.sample_rate
pdf = 1.0/128
plen = int(opt.sample_rate / pdf) / 2 + 1
logging.info("Making PSD for strain")
strain_psd = pycbc.psd.from_string(opt.fake_strain, plen, pdf,
opt.low_frequency_cutoff)
logging.info("Making colored noise")
strain = pycbc.noise.noise_from_psd(tlen, 1.0/opt.sample_rate,
strain_psd,
seed=opt.fake_strain_seed)
strain._epoch = lal.LIGOTimeGPS(opt.gps_start_time)
if opt.injection_file:
logging.info("Applying injections")
injections = InjectionSet(opt.injection_file)
injections.apply(strain, opt.channel_name[0:2],
distance_scale=opt.injection_scale_factor)
if opt.sgburst_injection_file:
logging.info("Applying sine-Gaussian burst injections")
injections = SGBurstInjectionSet(opt.sgburst_injection_file)
injections.apply(strain, opt.channel_name[0:2],
distance_scale=opt.injection_scale_factor)
if precision == 'single':
logging.info("Converting to float32")
strain = (dyn_range_fac * strain).astype(float32)
if opt.injection_file or opt.sgburst_injection_file:
strain.injections = injections
strain.gating_info = gating_info
return strain
import pylab
import numpy
from pycbc.frame import read_frame
from pycbc.types import load_timeseries
lal_out_file = "H1-INSPIRAL_lalsuite_FULL_DATA-968605000-2048.gwf"
# Take only the first 16 seconds to use as a small comparison
lal_raw = read_frame(lal_out_file, 'H1:LDAS-STRAIN_RAW', start_time=968605000, duration="16")
lal_resample = read_frame(lal_out_file, 'H1:LDAS-STRAIN_RAW_RESAMP', start_time=968605000, duration="16")
lal_conditioned = read_frame(lal_out_file, 'H1:LDAS-STRAIN_FILTER', start_time=968605000, duration="16")
# Take only the first 16 seconds to use as a small comparison
start_offset = 8 # This is the offest between the output that PyCBC gives and lalapps_inspiral
# lalapps_inspiral does not output the 8 second padding in the frame file
pycbc_raw = load_timeseries("raw_pycbc.npy")[start_offset*16384:(start_offset+16)*16384].astype(lal_raw.dtype)
pycbc_resample = load_timeseries("resampled_pycbc.npy")[start_offset*4096:(start_offset+16)*4096].astype(lal_raw.dtype)
# the lalapps_inspiral gwf file misreportes the epoch for some of the streams
pycbc_conditioned = load_timeseries("conditioned_pycbc.npy")[start_offset*4096:(start_offset+16)*4096].astype(lal_raw.dtype)
pycbc_conditioned._epoch = lal_conditioned._epoch
print float(pycbc_conditioned.start_time)
def p(a, b, an, bn):
t = numpy.arange(0, len(a), 1)
mindif = 1e-7
pylab.figure()
pylab.scatter(t, a, label=an, color="red", marker='x')
pylab.scatter(t, b, label=bn, color="blue", marker='+')
def get_noise(detector):
import pycbc.frame as frame
import random as randi
import os
h1_list = [
'H-H1_LOSC_16_V1-1126084608-4096.gwf',
'H-H1_LOSC_16_V1-1126109184-4096.gwf',
'H-H1_LOSC_16_V1-1126264832-4096.gwf',
'H-H1_LOSC_16_V1-1126293504-4096.gwf',
'H-H1_LOSC_16_V1-1127194624-4096.gwf',
'H-H1_LOSC_16_V1-1128042496-4096.gwf',
'H-H1_LOSC_16_V1-1128345600-4096.gwf',
'H-H1_LOSC_16_V1-1128407040-4096.gwf',
'H-H1_LOSC_16_V1-1128624128-4096.gwf',
'H-H1_LOSC_16_V1-1128665088-4096.gwf',
'H-H1_LOSC_16_V1-1129127936-4096.gwf',
'H-H1_LOSC_16_V1-1129664512-4096.gwf'
]
h1_begin = [
1126084608, 1126109184, 1126264832, 1126293504, 1127194624, 1128042496,
1128345600, 1128407040, 1128624128, 1128665088, 1129127936, 1129664512
]
l1_list = [
'L-L1_LOSC_16_V1-1126088704-4096.gwf',
'L-L1_LOSC_16_V1-1126105088-4096.gwf',
'L-L1_LOSC_16_V1-1127018496-4096.gwf',
'L-L1_LOSC_16_V1-1127022592-4096.gwf',
'L-L1_LOSC_16_V1-1127030784-4096.gwf',
'L-L1_LOSC_16_V1-1127051264-4096.gwf',
'L-L1_LOSC_16_V1-1127059456-4096.gwf',
'L-L1_LOSC_16_V1-1127096320-4096.gwf',
'L-L1_LOSC_16_V1-1129521152-4096.gwf',
'L-L1_LOSC_16_V1-1134870528-4096.gwf',
'L-L1_LOSC_16_V1-1136615424-4096.gwf',
'L-L1_LOSC_16_V1-1136631808-4096.gwf'
]
l1_begin = [
1126088704, 1126105088, 1127018496, 1127022592, 1127030784, 1127051264,
1127059456, 1127096320, 1129521152, 1134870528, 1136615424, 1136631808
]
if detector == 'O1-H':
file_index = randi.randrange(1, 12, 1)
print file_index
a = h1_begin[file_index]
print a
start_time = randi.randrange(a, a + 4054, 1)
print start_time
file = h1_list[file_index]
print file
strain = frame.read_frame(file, 'H1:GWOSC-16KHZ_R1_STRAIN')
elif detector == 'O1-L':
a = l1_begin[file_index]
print a
file_index = randi.randrange(1, 12, 1)
print file_index
start_time = randi.randrange(a, l1_begin[file_index] + 4054, 1)
print start_time
file = l1_list[file_index]
strain = frame.read_frame(file, 'L1:GWOSC-16KHZ_R1_STRAIN', start_time,
start_time + 32)
shift = randi.randrange(5, 27, 1)
return strain, shift
from pycbc.frame import read_frame
from pycbc.filter import highpass_fir, lowpass_fir, matched_filter
from pycbc.waveform import get_fd_waveform
from pycbc.psd import welch, interpolate
import urllib
import pylab
for ifo in ['H1', 'L1']:
# Read data and remove low frequency content
fname = '%s-%s_LOSC_4_V2-1126259446-32.gwf' % (ifo[0], ifo)
url = "https://losc.ligo.org/s/events/GW150914/" + fname
urllib.urlretrieve(url, filename=fname)
h1 = read_frame(fname, '%s:LOSC-STRAIN' % ifo)
h1 = highpass_fir(h1, 15, 8)
# Calculate the noise spectrum
psd = interpolate(welch(h1), 1.0 / h1.duration)
# whiten
white_strain = (h1.to_frequencyseries() / psd**0.5 *
psd.delta_f).to_timeseries()
# remove some of the high and low
smooth = highpass_fir(white_strain, 35, 8)
smooth = lowpass_fir(white_strain, 300, 8)
# time shift and flip L1
if ifo == 'L1':
smooth *= -1
smooth.roll(int(.007 / smooth.delta_t))
from pycbc.frame import read_frame
from pycbc.filter import highpass_fir, lowpass_fir, matched_filter
from pycbc.waveform import get_fd_waveform
from pycbc.psd import welch, interpolate
import urllib
import pylab
for ifo in ['H1', 'L1']:
# Read data and remove low frequency content
fname = '%s-%s_LOSC_4_V2-1126259446-32.gwf' % (ifo[0], ifo)
url = "https://losc.ligo.org/s/events/GW150914/" + fname
urllib.urlretrieve(url, filename=fname)
h1 = read_frame(fname, '%s:LOSC-STRAIN' % ifo)
h1 = highpass_fir(h1, 15, 8)
# Calculate the noise spectrum
psd = interpolate(welch(h1), 1.0 / h1.duration)
# whiten
white_strain = (h1.to_frequencyseries() / psd ** 0.5 * psd.delta_f).to_timeseries()
# remove some of the high and low
smooth = highpass_fir(white_strain, 35, 8)
smooth = lowpass_fir(white_strain, 300, 8)
# time shift and flip L1
if ifo == 'L1':
smooth *= -1
smooth.roll(int(.007 / smooth.delta_t))
pylab.plot(smooth.sample_times, smooth, label=ifo)
def principal(runs,archivo_nombre,local,ifo,hilo):
# Loading our modules
from modulos import gw_resample, gw_injection, gw_matched_filter
from modulos import gw_detection, gw_expected, gw_qtransform, gw_data, gw_chisqv2, gw_readtemplatev
from Noise_Sources import gw_load_noise, load
import numpy as np
import random as randi
from pycbc import frame, types
import urllib
grafica = 0
SNRthr = 5.5
NSegmnt = 128
#initial distance
i_d = 1
#final distance
f_d = 10
#number of slices
N_d = 128
#dic = np.linspace(i_d,f_d,N_d)
#di = []
#di = [1,5,10,15,20,25,30,35,40,45,50]
#di.extend(dic)
if local == False:
url = 'https://www.gw-openscience.org/archive/data/O1_16KHZ/1126170624/'+ifo+'-'+ifo+'1_LOSC_16_V1-'
urllib.urlretrieve(url+str(archivo_nombre)+'-4096.gwf', str(archivo_nombre)+'.gwf')
#-------------------------------------------------------------------------
#temporal stuff
aprox = 'NEW'
numero = 1
total_time = 32
fs = 8192 # Sampling frequency
fs_ligo = 16384
#---------------------------------------------------------------------------#
# loading files #
#---------------------------------------------------------------------------#
archivo = str(archivo_nombre)+'.gwf'
strain_initial = frame.read_frame(archivo, 'H1:GWOSC-16KHZ_R1_STRAIN')
strain_n = strain_initial.data
del strain_initial
strain_light = []
for i in range(NSegmnt):
a = i * total_time * fs_ligo
b = (i + 1) * total_time * fs_ligo
strain_light.append(strain_n[a:b])
###############################################################################
#
# vectores de resultados
#
###############################################################################
SNRrec = []
SNRexp = []
trigger_time = []
injection_time = []
total_flag = []
numero = 20
for i in range(numero):
for dat in range(len(strain_light)):
print dat, ' indice de segmento'
strain = strain_light[dat]
strain = types.TimeSeries(initial_array=strain, delta_t=1.0/fs_ligo , epoch=0)
rec = []
exp = []
flag = []
tt = []
ti = []
assert isinstance(runs, object)
# for d in range(len(di)):
distancia = 3#di[d]
n=numero
print distancia, ' distancia'
# Reading template
h,dt,nombre = gw_readtemplatev.lectura(n,aprox)
# Distance
hh, dts,dtf = gw_resample.interpolacion(h,dt,grafica,fs)
hh = hh/distancia
shift = 28
template, noise = gw_resample.resampleado(strain,hh,grafica,fs,fs_ligo)
# Making uniform the distribution of the dt in the template
# These function returns the resampled strain,
#Resampling and resizing data
# Making the injection of the template into the data
strain_inj,tmax,injection_shift = gw_injection.make(noise,template,shift,grafica)
# The limit values for the frequency in the filters
fc = 15
hc = 1200
mc = 733
# Making the matched filter
# This function give us the timeseries object of the snr over the time, the maximum value of the snr and
# the time that it occurs
snr,psd,index_snr_trigger,time,rho,psd_o,rho_0 = gw_matched_filter.make(strain_inj,template,fc,mc,hc,grafica)
# Getting the Chi^2 value
snr2,HSNR2_time,nsnr = gw_chisqv2.xis(snr,template,strain_inj,psd_o,fc,grafica,time,dtf,hc,shift,index_snr_trigger)
# Getting the theoretical value of snr
#-------------------------------------------------------------------------------------------------------------------------
# Detection part
desicion = gw_detection.decision(rho,SNRthr)
#--------------------------------------------------------------------------------------------------------------------------
# The time, amplitude, and phase of the SNR peak tell us how to align
# our proposed signal with the data.
rec.append(abs(rho))
exp.append(abs(rho_0))
flag.append(desicion)
tt.append(shift)
ti.append(time)
SNRrec.extend(rec)
SNRexp.extend(exp)
total_flag.extend(flag)
trigger_time.extend(ti)
injection_time.extend(tt)
rec = []
exp = []
flag = []
tt = []
ti = []
np.savetxt('Total'+str(archivo_nombre)+ifo+'Hilo'+hilo+'.out',(SNRrec,SNRexp,total_flag,trigger_time,injection_time),fmt='%3.2f')
return
def from_cli(opt, dyn_range_fac=1, precision='single'):
"""Parses the CLI options related to strain data reading and conditioning.
Parameters
----------
opt : object
Result of parsing the CLI with OptionParser, or any object with the
required attributes (gps-start-time, gps-end-time, strain-high-pass,
pad-data, sample-rate, (frame-cache or frame-files), channel-name,
fake-strain, fake-strain-seed, gating_file).
dyn_range_fac: {float, 1}, optional
A large constant to reduce the dynamic range of the strain.
Returns
-------
strain : TimeSeries
The time series containing the conditioned strain data.
"""
if opt.frame_cache or opt.frame_files:
if opt.frame_cache:
frame_source = opt.frame_cache
if opt.frame_files:
frame_source = opt.frame_files
logging.info("Reading Frames")
strain = read_frame(frame_source, opt.channel_name,
start_time=opt.gps_start_time-opt.pad_data,
end_time=opt.gps_end_time+opt.pad_data)
if opt.zpk_z and opt.zpk_p and opt.zpk_k:
logging.info("Highpass Filtering")
strain = highpass(strain, frequency=opt.strain_high_pass)
logging.info("Applying zpk filter")
z = numpy.array(opt.zpk_z)
p = numpy.array(opt.zpk_p)
k = float(opt.zpk_k)
strain = filter_zpk(strain.astype(numpy.float64), z, p, k)
if opt.normalize_strain:
logging.info("Dividing strain by constant")
l = opt.normalize_strain
strain = strain / l
if opt.injection_file:
logging.info("Applying injections")
injections = InjectionSet(opt.injection_file)
injections.apply(strain, opt.channel_name[0:2])
if opt.sgburst_injection_file:
logging.info("Applying sine-Gaussian burst injections")
injections = SGBurstInjectionSet(opt.sgburst_injection_file)
injections.apply(strain, opt.channel_name[0:2])
logging.info("Highpass Filtering")
strain = highpass(strain, frequency=opt.strain_high_pass)
if precision == 'single':
logging.info("Converting to float32")
strain = (strain * dyn_range_fac).astype(float32)
if opt.gating_file is not None:
logging.info("Gating glitches")
gate_params = numpy.loadtxt(opt.gating_file)
if len(gate_params.shape) == 1:
gate_params = [gate_params]
strain = gate_data(
strain, gate_params,
data_start_time=(opt.gps_start_time - opt.pad_data))
logging.info("Resampling data")
strain = resample_to_delta_t(strain, 1.0/opt.sample_rate, method='ldas')
logging.info("Highpass Filtering")
strain = highpass(strain, frequency=opt.strain_high_pass)
logging.info("Remove Padding")
start = opt.pad_data*opt.sample_rate
end = len(strain)-opt.sample_rate*opt.pad_data
strain = strain[start:end]
if opt.fake_strain:
logging.info("Generating Fake Strain")
duration = opt.gps_end_time - opt.gps_start_time
tlen = duration * opt.sample_rate
pdf = 1.0/128
plen = int(opt.sample_rate / pdf) / 2 + 1
logging.info("Making PSD for strain")
strain_psd = psd.from_string(opt.fake_strain, plen,
pdf, opt.low_frequency_cutoff)
logging.info("Making colored noise")
strain = pycbc.noise.noise_from_psd(tlen, 1.0/opt.sample_rate,
strain_psd,
seed=opt.fake_strain_seed)
strain._epoch = lal.LIGOTimeGPS(opt.gps_start_time)
if opt.injection_file:
logging.info("Applying injections")
injections = InjectionSet(opt.injection_file)
injections.apply(strain, opt.channel_name[0:2])
if opt.sgburst_injection_file:
logging.info("Applying sine-Gaussian burst injections")
injections = SGBurstInjectionSet(opt.sgburst_injection_file)
injections.apply(strain, opt.channel_name[0:2])
if precision == 'single':
logging.info("Converting to float32")
strain = (dyn_range_fac * strain).astype(float32)
if opt.injection_file:
strain.injections = injections
return strain
type=int,
help='Value of DQ vector indicating good data')
parser.add_argument('--dq-bad-times',
type=float,
nargs='+',
metavar='TIME',
help='Center time(s) of bad DQ epoch(s)')
parser.add_argument('--dq-bad-pad',
type=float,
help='Duration of bad DQ epoch(s)')
args = parser.parse_args()
# load frame file
strain = read_frame(args.input_file, args.strain_channel)
out_channel_names = [args.strain_channel]
out_timeseries = [strain]
# add state vector
if args.state_vector is not None:
state_dt = 1. / 16.
state_size = int(strain.duration / state_dt)
state_data = np.zeros(state_size, dtype=np.uint32)
state_data[:] = args.state_vector_good
state_ts = TimeSeries(state_data,
delta_t=state_dt,
epoch=strain.start_time)
from pycbc.frame import read_frame
from pycbc.filter import highpass_fir, lowpass_fir
from pycbc.psd import welch, interpolate
from pycbc.types import TimeSeries
import urllib
# Read data and remove low frequency content
fname = 'H-H1_LOSC_4_V2-1126259446-32.gwf'
url = "https://losc.ligo.org/s/events/GW150914/" + fname
urllib.urlretrieve(url, filename=fname)
h1 = highpass_fir(read_frame(fname, 'H1:LOSC-STRAIN'), 15.0, 8)
# Calculate the noise spectrum and whiten
psd = interpolate(welch(h1), 1.0 / 32)
white_strain = (h1.to_frequencyseries() / psd ** 0.5 * psd.delta_f).to_timeseries()
# remove some of the high and low frequencies
smooth = highpass_fir(white_strain, 25, 8)
smooth = lowpass_fir(white_strain, 250, 8)
#strech out and shift the frequency upwards to aid human hearing
fdata = smooth.to_frequencyseries()
fdata.roll(int(1200 / fdata.delta_f))
smooth = TimeSeries(fdata.to_timeseries(), delta_t=1.0/1024)
#Take slice around signal
smooth = smooth[len(smooth)/2 - 1500:len(smooth)/2 + 3000]
smooth.save_to_wav('gw150914_h1_chirp.wav')
#!/usr/bin/env python
import numpy as np
from pycbc import frame
from glob import glob
import sys
filename = glob('./*{0:s}.gwf'.format(sys.argv[1]))[0]
data = frame.read_frame(
filename, '{0:s}:HWINJ_INJECTED'.format(sys.argv[1]))
idx_max = np.argmax(np.abs(data.numpy()))
time = data.get_sample_times().numpy()[idx_max]
with open('./time.txt', 'w+') as f:
f.write('{0:.2f}'.format(time))
"""Pick the event with the code *GW170817*. We pick the time frame from 224 seconds before merging and end 32 seconds after merging."""
# Commented out IPython magic to ensure Python compatibility.
# %matplotlib inline
import pylab
from pycbc.filter import highpass
from pycbc.catalog import Merger
from pycbc.frame import read_frame
merger = Merger("GW170817") # the merging part of the event, event = two black holes merging and causing gravitational wave
strain, stilde = {}, {}
for ifo in ['L1', 'H1']:
ts = read_frame("{}-{}_LOSC_CLN_4_V1-1187007040-2048.gwf".format(ifo[0], ifo),
'{}:LOSC-STRAIN'.format(ifo),
start_time=merger.time - 224, # merger.time = the time of merging
end_time=merger.time + 32,
check_integrity=False)
"""Cleaning and applying highpass filter. Downsample to 2048 Hz to make the data analysis more convenient. Power density of the noise is higher than the signal. At higher frequency the amplitude of the noise is lower. And then graph."""
from pycbc.catalog import Merger
from pycbc.filter import resample_to_delta_t, highpass
from pycbc.catalog import Merger
from pycbc.filter import resample_to_delta_t, highpass
merger = Merger("GW170817")
strain, stilde = {}, {} # tuple of directories: strain and stilde=cleaned data
for ifo in ['L1', 'H1']:
# We'll download the data and select 256 seconds that includes the event time
import pylab
import numpy
from pycbc.frame import read_frame
from pycbc.types import load_timeseries
lal_out_file = "H1-INSPIRAL_lalsuite_FULL_DATA-968605000-2048.gwf"
# Take only the first 16 seconds to use as a small comparison
lal_raw = read_frame(lal_out_file,
'H1:LDAS-STRAIN_RAW',
start_time=968605000,
duration="16")
lal_resample = read_frame(lal_out_file,
'H1:LDAS-STRAIN_RAW_RESAMP',
start_time=968605000,
duration="16")
lal_conditioned = read_frame(lal_out_file,
'H1:LDAS-STRAIN_FILTER',
start_time=968605000,
duration="16")
# Take only the first 16 seconds to use as a small comparison
start_offset = 8 # This is the offest between the output that PyCBC gives and lalapps_inspiral
# lalapps_inspiral does not output the 8 second padding in the frame file
pycbc_raw = load_timeseries("raw_pycbc.npy")[start_offset *
16384:(start_offset + 16) *
16384].astype(lal_raw.dtype)
pycbc_resample = load_timeseries(
"resampled_pycbc.npy")[start_offset * 4096:(start_offset + 16) *
4096].astype(lal_raw.dtype)
def from_cli(opt, dyn_range_fac=1, precision='single'):
"""Parses the CLI options related to strain data reading and conditioning.
Parameters
----------
opt : object
Result of parsing the CLI with OptionParser, or any object with the
required attributes (gps-start-time, gps-end-time, strain-high-pass,
pad-data, sample-rate, (frame-cache or frame-files), channel-name,
fake-strain, fake-strain-seed, gating_file).
dyn_range_fac: {float, 1}, optional
A large constant to reduce the dynamic range of the strain.
Returns
-------
strain : TimeSeries
The time series containing the conditioned strain data.
"""
gating_info = {}
if opt.frame_cache or opt.frame_files or opt.frame_type:
if opt.frame_cache:
frame_source = opt.frame_cache
if opt.frame_files:
frame_source = opt.frame_files
logging.info("Reading Frames")
if opt.frame_type:
strain = query_and_read_frame(opt.frame_type, opt.channel_name,
start_time=opt.gps_start_time-opt.pad_data,
end_time=opt.gps_end_time+opt.pad_data)
else:
strain = read_frame(frame_source, opt.channel_name,
start_time=opt.gps_start_time-opt.pad_data,
end_time=opt.gps_end_time+opt.pad_data)
if opt.zpk_z and opt.zpk_p and opt.zpk_k:
logging.info("Highpass Filtering")
strain = highpass(strain, frequency=opt.strain_high_pass)
logging.info("Applying zpk filter")
z = numpy.array(opt.zpk_z)
p = numpy.array(opt.zpk_p)
k = float(opt.zpk_k)
strain = filter_zpk(strain.astype(numpy.float64), z, p, k)
if opt.normalize_strain:
logging.info("Dividing strain by constant")
l = opt.normalize_strain
strain = strain / l
if opt.injection_file:
logging.info("Applying injections")
injections = InjectionSet(opt.injection_file)
injections.apply(strain, opt.channel_name[0:2],
distance_scale=opt.injection_scale_factor)
if opt.sgburst_injection_file:
logging.info("Applying sine-Gaussian burst injections")
injections = SGBurstInjectionSet(opt.sgburst_injection_file)
injections.apply(strain, opt.channel_name[0:2],
distance_scale=opt.injection_scale_factor)
logging.info("Highpass Filtering")
strain = highpass(strain, frequency=opt.strain_high_pass)
if precision == 'single':
logging.info("Converting to float32")
strain = (strain * dyn_range_fac).astype(pycbc.types.float32)
if opt.gating_file is not None:
logging.info("Gating glitches")
gate_params = numpy.loadtxt(opt.gating_file)
if len(gate_params.shape) == 1:
gate_params = [gate_params]
strain = gate_data(strain, gate_params)
gating_info['file'] = \
[gp for gp in gate_params \
if (gp[0] + gp[1] + gp[2] >= strain.start_time) \
and (gp[0] - gp[1] - gp[2] <= strain.end_time)]
if opt.autogating_threshold is not None:
# the + 0 is for making a copy
glitch_times = detect_loud_glitches(
strain + 0., threshold=opt.autogating_threshold,
cluster_window=opt.autogating_cluster,
low_freq_cutoff=opt.strain_high_pass,
high_freq_cutoff=opt.sample_rate/2,
corrupt_time=opt.pad_data+opt.autogating_pad)
gate_params = [[gt, opt.autogating_width, opt.autogating_taper] \
for gt in glitch_times]
if len(glitch_times) > 0:
logging.info('Autogating at %s',
', '.join(['%.3f' % gt for gt in glitch_times]))
strain = gate_data(strain, gate_params)
gating_info['auto'] = gate_params
logging.info("Resampling data")
strain = resample_to_delta_t(strain, 1.0/opt.sample_rate, method='ldas')
logging.info("Highpass Filtering")
strain = highpass(strain, frequency=opt.strain_high_pass)
logging.info("Remove Padding")
start = opt.pad_data*opt.sample_rate
end = len(strain)-opt.sample_rate*opt.pad_data
strain = strain[start:end]
if opt.fake_strain:
logging.info("Generating Fake Strain")
duration = opt.gps_end_time - opt.gps_start_time
tlen = duration * opt.sample_rate
pdf = 1.0/128
plen = int(opt.sample_rate / pdf) / 2 + 1
logging.info("Making PSD for strain")
strain_psd = pycbc.psd.from_string(opt.fake_strain, plen, pdf,
opt.low_frequency_cutoff)
logging.info("Making colored noise")
strain = pycbc.noise.noise_from_psd(tlen, 1.0/opt.sample_rate,
strain_psd,
seed=opt.fake_strain_seed)
strain._epoch = lal.LIGOTimeGPS(opt.gps_start_time)
if opt.injection_file:
logging.info("Applying injections")
injections = InjectionSet(opt.injection_file)
injections.apply(strain, opt.channel_name[0:2],
distance_scale=opt.injection_scale_factor)
if opt.sgburst_injection_file:
logging.info("Applying sine-Gaussian burst injections")
injections = SGBurstInjectionSet(opt.sgburst_injection_file)
injections.apply(strain, opt.channel_name[0:2],
distance_scale=opt.injection_scale_factor)
if precision == 'single':
logging.info("Converting to float32")
strain = (dyn_range_fac * strain).astype(pycbc.types.float32)
if opt.injection_file or opt.sgburst_injection_file:
strain.injections = injections
if opt.taper_data:
logging.info("Tapering data")
# Use auto-gating stuff for this, a one-sided gate is a taper
pd_taper_window = opt.taper_data
gate_params = [(strain.start_time, 0., pd_taper_window)]
gate_params.append( (strain.end_time, 0.,
pd_taper_window) )
gate_data(strain, gate_params)
strain.gating_info = gating_info
return strain
w_lal = lal.CreateHannREAL4Window(seg_len)
print "hann props pycbc", w_pycbc.sum(), w_pycbc.squared_norm().sum()
print "hann props lal", w_lal.sum, w_lal.sumofsquares
# Check that the median bias is the same
print "%s segments" % nsegs
print "BIAS pycbc", pycbc.psd.median_bias(nsegs)
print "BIAS lal", lal.RngMedBias(nsegs)
# Check the psd norm
print "PYCBC psd norm", 2.0 / float(sample_rate) / (
w_pycbc.squared_norm().sum()) / pycbc.psd.median_bias(nsegs)
# Same strain preparation for lal and pycbc psd estimation
strain = read_frame("LER2.lcf",
"H1:LDAS-STRAIN",
start_time=start_time - pad_data,
duration=duration + pad_data * 2)
strain = highpass(strain, frequency=30)
strain *= pycbc.DYN_RANGE_FAC
strain = TimeSeries(strain,
delta_t=strain.delta_t,
epoch=strain.start_time,
dtype=float32)
strain = resample_to_delta_t(strain, 1.0 / sample_rate)
strain = strain[int(pad_data * 1.0 / strain.delta_t):len(strain) -
int(1.0 / strain.delta_t * pad_data)]
psd_pycbc = pycbc.psd.welch(strain, seg_len=seg_len, seg_stride=stride)
psd_lal = lal_psd_estimate(seg_len, strain)
print psd_pycbc[-1]
from pycbc.frame import read_frame
from pycbc.filter import highpass_fir, lowpass_fir
from pycbc.psd import welch, interpolate
from pycbc.types import TimeSeries
try:
from urllib.request import urlretrieve
except ImportError: # python < 3
from urllib import urlretrieve
# Read data and remove low frequency content
fname = 'H-H1_LOSC_4_V2-1126259446-32.gwf'
url = "https://www.gw-openscience.org/GW150914data/" + fname
urlretrieve(url, filename=fname)
h1 = highpass_fir(read_frame(fname, 'H1:LOSC-STRAIN'), 15.0, 8)
# Calculate the noise spectrum and whiten
psd = interpolate(welch(h1), 1.0 / 32)
white_strain = (h1.to_frequencyseries() / psd ** 0.5 * psd.delta_f).to_timeseries()
# remove some of the high and low frequencies
smooth = highpass_fir(white_strain, 25, 8)
smooth = lowpass_fir(white_strain, 250, 8)
#strech out and shift the frequency upwards to aid human hearing
fdata = smooth.to_frequencyseries()
fdata.roll(int(1200 / fdata.delta_f))
smooth = TimeSeries(fdata.to_timeseries(), delta_t=1.0/1024)
#Take slice around signal
smooth = smooth[len(smooth)/2 - 1500:len(smooth)/2 + 3000]
smooth.save_to_wav('gw150914_h1_chirp.wav')
# Check that we are using the same hann window
w_pycbc = Array(numpy.hanning(seg_len).astype(float32))
w_lal = lal.CreateHannREAL4Window(seg_len)
print "hann props pycbc", w_pycbc.sum(), w_pycbc.squared_norm().sum()
print "hann props lal", w_lal.sum, w_lal.sumofsquares
# Check that the median bias is the same
print "%s segments" % nsegs
print "BIAS pycbc", pycbc.psd.median_bias(nsegs)
print "BIAS lal", lal.RngMedBias(nsegs)
# Check the psd norm
print "PYCBC psd norm", 2.0 / float(sample_rate) / (w_pycbc.squared_norm().sum()) / pycbc.psd.median_bias(nsegs)
# Same strain preparation for lal and pycbc psd estimation
strain = read_frame("LER2.lcf", "H1:LDAS-STRAIN", start_time=start_time-pad_data, duration=duration+pad_data*2)
strain = highpass(strain, frequency=30)
strain *= pycbc.DYN_RANGE_FAC
strain = TimeSeries(strain, delta_t=strain.delta_t, epoch=strain.start_time, dtype=float32)
strain = resample_to_delta_t(strain, 1.0/sample_rate)
strain = strain[int(pad_data*1.0/strain.delta_t):len(strain)-int(1.0/strain.delta_t*pad_data)]
psd_pycbc = pycbc.psd.welch(strain, seg_len=seg_len, seg_stride=stride)
psd_lal = lal_psd_estimate(seg_len, strain)
print psd_pycbc[-1]
print psd_lal[-1]
pylab.figure(1)
pylab.loglog(psd_pycbc.sample_frequencies.numpy(), psd_pycbc.numpy(), label="PyCBC")
pylab.loglog(psd_lal.sample_frequencies.numpy(), psd_lal.numpy(), label="LAL")