def plot_hit(fil_filename, dat_filename, hit_id, bw=None, offset=0):
r"""Plot a candidate from a .dat file
Args:
fil_filename(str): Path to filterbank file to plot
dat_filename(str): Path to turbosSETI generated .dat output file of events
hit_id(int): ID of hit in the dat file to plot (TopHitNum)
offset(float, optional): Offset drift line on plot. Default 0.
bw: (Default value = None)
Returns:
"""
# Load hit details
dat = find_event.read_dat(dat_filename)
hit = dat.iloc[hit_id]
f0 = hit['Freq']
if bw is None:
bw_mhz = np.abs(hit['FreqStart'] - hit['FreqEnd'])
else:
bw_mhz = bw * 1e-6
fil = Waterfall(fil_filename,
f_start=f0 - bw_mhz / 2,
f_stop=f0 + bw_mhz / 2)
t_duration = (fil.n_ints_in_file - 1) * fil.header['tsamp']
fil.plot_waterfall()
plot_event.overlay_drift(f0, f0, f0, hit['DriftRate'], t_duration, offset)
def grab_parameters(dat_file, GBT_band):
"""
takes dat file of GBT data and returns frequency parameters
used to calculate where the DC spikes will be
Arguments
----------
dat_file : str
filepath to the .dat file
GBT_band : str
the band at which the data was collected
choose from {"L", "S", "C", "X"}
Returns : fch1, foff, nfpc
which will be used internally within remove_DC_spike
"""
tbl = find.read_dat(dat_file)
if GBT_band == "L":
fch1 = 1926.2695326677515 # LBAND -- this is hardcoded, it would be nice to fix that
if GBT_band == "C":
fch1 = 8201.66015625 # CBAND ""
if GBT_band == "S":
fch1 = 2720.80078125 # SBAND ""
if GBT_band == "X":
fch1 = 11102.05078125 # XBAND ""
foff = float(tbl["DELTAF"][0])*1e-6
nfpc=(1500.0/512.0)/abs(foff)
num_course_channels = np.max(tbl["CoarseChanNum"])
return fch1, foff, nfpc, num_course_channels
def validate_voyager_hits(filename_dat):
""" This checks voyager hits against known values.
Known values:
# --------------------------
# ID Drift_Rate SNR Unc_Freq Corr_Freq Index freq_start freq_end ...
# --------------------------
001 -0.392226 30.612128 8419.319368 8419.319368 739933 8419.319779 8419.318963 ...
002 -0.373093 245.707984 8419.297028 8419.297028 747929 8419.297439 8419.296623 ...
003 -0.392226 31.220652 8419.274374 8419.274374 756037 8419.274785 8419.273969 ...
(from flipped)
003 -0.392226 30.612118 8419.319366 8419.319366 308642 8419.318955 8419.319771 ...
002 -0.373093 245.707905 8419.297025 8419.297025 300646 8419.296614 8419.297430 ...
001 -0.392226 31.220642 8419.274372 8419.274372 292538 8419.273961 8419.274777 ...
"""
print("\n===== validate_voyager_hits =====")
h = find_event.read_dat(filename_dat)
print(h)
valid_data = [
{
'Freq': 8419.319368,
'FreqStart': 8419.319779,
'FreqEnd': 8419.318963,
'SNR': 30.612128,
'DriftRate': -0.392226,
},
{
'Freq': 8419.297028,
'FreqStart': 8419.297439,
'FreqEnd': 8419.296623,
'SNR': 245.707984,
'DriftRate': -0.373093,
},
{
'Freq': 8419.274374,
'FreqStart': 8419.274785,
'FreqEnd': 8419.273969,
'SNR': 31.220652,
'DriftRate': -0.392226,
}
]
atols = {'Freq': 0.000005, 'FreqStart': 0.00001, 'FreqEnd': 0.00001, 'SNR': 0.001, 'DriftRate': 0.02}
for vd in valid_data:
hmax = h[np.isclose(h['Freq'], vd['Freq'], rtol=0.000001)].iloc[0]
for key in vd.keys():
print(key, hmax[key], vd[key])
if key in ('FreqStart', 'FreqEnd'):
upper = np.isclose(hmax[key], vd['FreqStart'], atol=atols[key], rtol=0)
lower = np.isclose(hmax[key], vd['FreqEnd'], atol=atols[key], rtol=0)
assert upper or lower
else:
assert np.isclose(hmax[key], vd[key], atol=atols[key], rtol=0)
return hmax
def grab_parameters(dat_file, GBT_band, use_defaults, h5_fil_path):
"""
takes dat file of GBT data and returns frequency parameters
used to calculate where the DC spikes will be
Arguments
----------
dat_file : str
filepath to the .dat file
GBT_band : str
the band at which the data was collected
choose from {"L", "S", "C", "X"}
use_defaults : bool
if True, the program uses the preset,
hardcoded fch1 and foff values; if False,
fch1 and foff are retrieved from the h5/fil
files.
h5_fil_path : str
the file path to the h5 or fil file
corresponding to the given dat file.
Program will crash if use_defaults=False
and no h5_fil_path is specified.
Returns : fch1, foff, nfpc
which will be used internally within remove_DC_spike
"""
tbl = find.read_dat(dat_file)
if use_defaults:
if GBT_band == "L":
fch1 = 1926.2695326677515 # LBAND -- this is hardcoded, it would be nice to fix that
if GBT_band == "C":
fch1 = 8201.66015625 # CBAND ""
if GBT_band == "S":
fch1 = 2720.80078125 # SBAND ""
if GBT_band == "X":
fch1 = 11102.05078125 # XBAND ""
foff = float(tbl["DELTAF"][0]) * 1e-6
else:
fil = bp.Waterfall(h5_fil_path)
fch1 = fil.header['fch1']
foff = fil.header['foff']
#for Karen's files
fch1 = float(fch1 - (foff / 2.0))
nfpc = (1500.0 / 512.0) / abs(foff)
num_course_channels = np.max(tbl["CoarseChanNum"])
#print('fch1: {0}, foff: {1}'.format(fch1, foff))
return fch1, foff, nfpc, num_course_channels
def validate_voyager_hits(filename_dat):
r""" This checks voyager hits against known values.
"""
print("\n===== validate_voyager_hits =====")
df_hits = find_event.read_dat(filename_dat)
print(df_hits)
valid_data = [ # in unflipped order
{ # 001
'Freq': 8419.319368,
'FreqStart': 8419.32,
'FreqEnd': 8419.32,
'SNR': 30.612128,
},
{ # 002
'Freq': 8419.30,
'FreqStart': 8419.30,
'FreqEnd': 8419.30,
'SNR': 245.707984,
},
{ # 003
'Freq': 8419.274374,
'FreqStart': 8419.27,
'FreqEnd': 8419.27,
'SNR': 31.220652,
}
]
atols = {'Freq': 0.001, 'FreqStart': 0.001, 'FreqEnd': 0.001, 'SNR': 0.001}
for vd in valid_data:
hmax = df_hits[np.isclose(df_hits['Freq'], vd['Freq'],
rtol=0.000001)].iloc[0]
for key in vd.keys():
#print('validate_voyager_hits: key, hmax[key], vd[key]: ', key, hmax[key], vd[key])
if key in ('FreqStart', 'FreqEnd'):
upper = np.isclose(hmax[key], vd['FreqStart'], atol=atols[key])
lower = np.isclose(hmax[key], vd['FreqEnd'], atol=atols[key])
if not (upper and lower):
raise ValueError(
'validate_voyager_hits: upper or lower: hmax[key]={}, vd[FreqStart]={}, vd[FreqEnd]={}'
.format(hmax[key], vd['FreqStart'], vd['FreqEnd']))
else:
if not np.isclose(hmax[key], vd[key], atol=atols[key]):
raise ValueError(
'validate_voyager_hits: other: key={}, hmax[key]={}, vd[key]={}'
.format(key, hmax[key], vd[key]))
print('\nvalidate_voyager_hits: SUCCESS\n')
def calculate_hist(dat_file, GBT_band, bin_width=1, tbl=None):
"""
calculates a histogram of the number of hits for a single .dat file
Arguments
----------
dat_file : str
filepath to the .dat file
GBT_band : str
the band at which the data was collected
choose from {"L", "S", "C", "X"}
bin_width : float
width of the hisrogram bins in units of MHz
The default is 1 Mhz
tbl : pandas.core.frame.DataFrame
Alternate way of providing contents of a dat file
Returns
--------
hist : numpy.ndarray
the count of hits in each bin
bin_edges : numpy.ndarray
the edge values of each bin. Has length Nbins+1
"""
#read the file into a pandas dataframe
if type(tbl) != pandas.core.frame.DataFrame:
tbl = find.read_dat(dat_file)
#make the bins for the histogram
# band boundaries as listed in Traas 2021
if GBT_band == "L":
min_freq = 1100
max_freq = 1900
if GBT_band == "S":
min_freq = 1800
max_freq = 2800
if GBT_band == "C":
min_freq = 4000
max_freq = 7800
if GBT_band == "X":
min_freq = 7800
max_freq = 11200
bins = np.linspace(min_freq,
max_freq,
int((max_freq - min_freq) / bin_width),
endpoint=True)
hist, bin_edges = np.histogram(tbl["Freq"], bins=bins)
return hist, bin_edges
def plot_hits(filename_fil, filename_dat):
r""" Plot the hits in a .dat file. """
print("\n===== plot_hits =====")
table = find_event.read_dat(filename_dat)
print(table)
plt.figure(figsize=(10, 8))
N_hit = len(table)
if N_hit > 10:
print("Warning: More than 10 hits found. Only plotting first 10")
N_hit = 10
for ii in range(N_hit):
plt.subplot(N_hit, 1, ii + 1)
plot_hit(filename_fil, filename_dat, ii)
plt.tight_layout()
plt.savefig(filename_dat.replace('.dat', '.png'))
