def build_ktransit_model(ticid, lc, rprs=0.02, vary_transit=True):
from ktransit import FitTransit
fitT = FitTransit()
model = BoxLeastSquares(lc.time, lc.flux)
results = model.autopower(0.16, minimum_period=2., maximum_period=21.)
period = results.period[np.argmax(results.power)]
t0 = results.transit_time[np.argmax(results.power)]
if rprs is None:
depth = results.depth[np.argmax(results.power)]
rprs = depth ** 2
fitT.add_guess_star(rho=0.022, zpt=0, ld1=0.6505,ld2=0.1041) #come up with better way to estimate this using AS
fitT.add_guess_planet(T0=t0, period=period, impact=0.5, rprs=rprs)
ferr = np.ones_like(lc.time) * 0.00001
fitT.add_data(time=lc.time,flux=lc.flux,ferr=ferr)#*1e-3)
vary_star = ['zpt'] # free stellar parameters
if vary_transit:
vary_planet = (['period', 'impact', # free planetary parameters
'T0', #'esinw', 'ecosw',
'rprs']) #'impact', # free planet parameters are the same for every planet you model
else:
vary_planet = (['rprs'])
fitT.free_parameters(vary_star, vary_planet)
fitT.do_fit() # run the fitting
return fitT
def pdf_summary(self, ticid, out_fname):
"""
"""
self.ticid = ticid
with PdfPages(out_fname) as pdf:
ql_fig = self.plot(self.ticid, save_postcard=True)
pdf.savefig(ql_fig)
plt.close()
lc = self.lc
time, flux, flux_err = lc.time, lc.flux, lc.flux_err
model = BoxLeastSquares(time, flux)
results = model.autopower(0.16,
minimum_period=2.,
maximum_period=21.)
period = results.period[np.argmax(results.power)]
t0 = results.transit_time[np.argmax(results.power)]
vt_fig = plot_transit_vetting(self.ticid, period, t0, lc=self.lc)
pdf.savefig(vt_fig)
plt.close()
ica_fig = make_ica_plot(self.ticid)
pdf.savefig(ica_fig)
plt.close()
star_fig = self.plot_starry_model(lc)
pdf.savefig(star_fig)
plt.close()
def periodogram(time, lightcurve):
period_grid = np.exp(np.linspace(np.log(1), np.log(15), 50000))
bls = BoxLeastSquares(time, lightcurve)
bls_power = bls.power(period_grid, 0.1, oversample=20)
return bls, bls_power, period_grid
def make_transit_periodogram(t, y, dy=0.01):
"""
Plots a periodogram to determine likely period of planet transit candidtaes
in a dataset, based on a box least squared method.
"""
model = BoxLeastSquares(t * u.day, y, dy=0.01)
periodogram = model.autopower(0.2, objective="snr")
plt.figure()
plt.plot(periodogram.period, periodogram.power, 'k')
plt.xlabel('Period [days]')
plt.ylabel('Power')
max_power_i = np.argmax(periodogram.power)
best_fit = periodogram.period[max_power_i]
print('Best Fit Period: {} days'.format(best_fit))
stats = model.compute_stats(periodogram.period[max_power_i],
periodogram.duration[max_power_i],
periodogram.transit_time[max_power_i])
return stats, best_fit
def get_bls_features(x, t):
features = []
# print(x[0])
for i in range(x.shape[0]):
# adapted from http://docs.astropy.org/en/stable/stats/bls.html#peak-statistics
bls = BoxLeastSquares(t, x[i])
periodogram = bls.autopower(
40, minimum_n_transit=5
) # arg is the granularity of considered durations
max_power = np.argmax(periodogram.power)
stats = bls.compute_stats(periodogram.period[max_power],
periodogram.duration[max_power],
periodogram.transit_time[max_power])
# TODO: use dataframe?
features.append([stats[s][0] / stats[s][1] for s in stat_names])
# based on https://arxiv.org/pdf/astro-ph/0206099.pdf
# ratios.append(stats["depth"][0] / stats["depth"][1]) # depth over uncertainty
if (i + 1) % 10 == 0:
print(".", end="")
if (i + 1) % 500 == 0:
print()
print()
return np.array(features)
def _parallel_bls_worker(task):
'''
This wraps Astropy's BoxLeastSquares for use with bls_parallel_pfind below.
`task` is a tuple::
task[0] = times
task[1] = mags
task[2] = errs
task[3] = magsarefluxes
task[4] = minfreq
task[5] = nfreq
task[6] = stepsize
task[7] = ndurations
task[8] = mintransitduration
task[9] = maxtransitduration
task[10] = blsobjective
task[11] = blsmethod
task[12] = blsoversample
'''
try:
times, mags, errs = task[:3]
magsarefluxes = task[3]
minfreq, nfreq, stepsize = task[4:7]
ndurations, mintransitduration, maxtransitduration = task[7:10]
blsobjective, blsmethod, blsoversample = task[10:]
frequencies = minfreq + nparange(nfreq) * stepsize
periods = 1.0 / frequencies
# astropy's BLS requires durations in units of time
durations = nplinspace(mintransitduration * periods.min(),
maxtransitduration * periods.min(), ndurations)
# set up the correct units for the BLS model
if magsarefluxes:
blsmodel = BoxLeastSquares(times * u.day,
mags * u.dimensionless_unscaled,
dy=errs * u.dimensionless_unscaled)
else:
blsmodel = BoxLeastSquares(times * u.day,
mags * u.mag,
dy=errs * u.mag)
blsresult = blsmodel.power(periods * u.day,
durations * u.day,
objective=blsobjective,
method=blsmethod,
oversample=blsoversample)
return {
'blsresult': blsresult,
'blsmodel': blsmodel,
'durations': durations,
'power': nparray(blsresult.power)
}
except Exception as e:
LOGEXCEPTION('BLS for frequency chunk: (%.6f, %.6f) failed.' %
(frequencies[0], frequencies[-1]))
return {
'blsresult': None,
'blsmodel': None,
'durations': durations,
'power': nparray([npnan for x in range(nfreq)]),
}
def from_lightcurve(lc, **kwargs):
"""Creates a Periodogram from a LightCurve using the Box Least Squares (BLS) method."""
time_unit = (kwargs.pop("time_unit", "day"))
if time_unit not in dir(u):
raise ValueError('{} is not a valid unit for time.'.format(time_unit))
try:
from astropy.stats import BoxLeastSquares
except ImportError:
raise Exception("BLS requires AstroPy v3.1 or later")
# BoxLeastSquares will not work if flux or flux_err contain NaNs
lc = lc.remove_nans()
if np.isfinite(lc.flux_err).all():
dy = lc.flux_err
else:
dy = None
bls = BoxLeastSquares(lc.time, lc.flux, dy)
duration = kwargs.pop("duration", 0.25)
minimum_period = kwargs.pop("minimum_period", None)
maximum_period = kwargs.pop("maximum_period", None)
period = kwargs.pop("period", None)
if minimum_period is None:
if 'period' in kwargs:
minimum_period = period.min()
else:
minimum_period = np.max([np.median(np.diff(lc.time)) * 4,
np.max(duration) + np.median(np.diff(lc.time))])
if maximum_period is None:
if 'period' in kwargs:
maximum_period = period.max()
else:
maximum_period = (np.max(lc.time) - np.min(lc.time)) / 3.
frequency_factor = kwargs.pop("frequency_factor", 10)
df = frequency_factor * np.min(duration) / (np.max(lc.time) - np.min(lc.time))**2
npoints = int(((1/minimum_period) - (1/maximum_period))/df)
# Too many points
if npoints > 1e5:
log.warning('`period` contains {} points.'
'Periodogram is likely to be large, and slow to evaluate. '
'Consider setting `frequency_factor` to a higher value.'
''.format(np.round(npoints, 4)))
# Way too many points
if npoints > 1e7:
raise ValueError('`period` contains {} points.'
'Periodogram is too large to evaluate. '
'Consider setting `frequency_factor` to a higher value.'
''.format(np.round(npoints, 4)))
period = kwargs.pop("period",
bls.autoperiod(duration,
minimum_period=minimum_period,
maximum_period=maximum_period,
frequency_factor=frequency_factor))
result = bls.power(period, duration, **kwargs)
if not isinstance(result.period, u.quantity.Quantity):
result.period = u.Quantity(result.period, time_unit)
if not isinstance(result.power, u.quantity.Quantity):
result.power = result.power * u.dimensionless_unscaled
return BoxLeastSquaresPeriodogram(frequency=1. / result.period,
power=result.power,
default_view='period',
label=lc.label,
targetid=lc.targetid,
transit_time=result.transit_time,
duration=result.duration,
depth=result.depth,
bls_result=result,
snr=result.depth_snr,
bls_obj=bls,
time=lc.time,
flux=lc.flux,
time_unit=time_unit)
f = []
for fn in files:
ti, fi = np.genfromtxt(fn, usecols=(0,1), unpack=True)
t.append(ti)
f.append(fi / np.nanmedian(fi))
t = np.concatenate(t)
f = np.concatenate(f)
fig, ax = plt.subplots(figsize=[15,3])
ax.plot(t, f, '-k', lw=1, zorder=-2)
ax.scatter(t, f, c='gold', edgecolor='black', s=15, lw=.5, zorder=-1)
durations = np.linspace(0.05, 0.2, 50)# * u.day
model = BLS(t,f)
result = model.autopower(durations, frequency_factor=5.0, maximum_period=30.0)
idx = np.argmax(result.power)
period = result.period[idx]
t0 = result.transit_time[idx]
dur = result.duration[idx]
depth = result.depth[idx]
ph = (t - t0 + 0.5*period) % period - 0.5*period
fig2, ax2 = plt.subplots(figsize=[8,2])
ax2.scatter(ph, f, c='gold', edgecolor='black', s=15, lw=.5)
plt.show()
def build_model(x, y, yerr, period_prior, t0_prior, depth, minimum_period=2, maximum_period=30, r_star_prior=5.0, t_star_prior=5000, m_star_prior=None, start=None):
"""Build an exoplanet model for a dataset and set of planets
Paramters
---------
x : array-like
The time series (in days); this should probably be centered
y : array-like
The relative fluxes (in parts per thousand)
yerr : array-like
The uncertainties on ``y``
period_prior : list
The literature values for periods of the planets (in days)
t0_prior : list
The literature values for phases of the planets in the same
coordinates as `x`
rprs_prior : list
The literature values for the ratio of planet radius to star
radius
start : dict
A dictionary of model parameters where the optimization
should be initialized
Returns:
A PyMC3 model specifying the probabilistic model for the light curve
"""
model = BoxLeastSquares(x, y)
results = model.autopower(0.16, minimum_period=minimum_period, maximum_period=maximum_period)
if period_prior is None:
period_prior = results.period[np.argmax(results.power)]
if t0_prior is None:
t0_prior = results.transit_time[np.argmax(results.power)]
if depth is None:
depth = results.depth[np.argmax(results.power)]
period_prior = np.atleast_1d(period_prior)
t0_prior = np.atleast_1d(t0_prior)
# rprs_prior = np.atleast_1d(rprs_prior)
with pm.Model() as model:
# Set model variables
model.x = np.asarray(x, dtype=np.float64)
model.y = np.asarray(y, dtype=np.float64)
model.yerr = np.asarray(yerr + np.zeros_like(x), dtype=np.float64)
'''Stellar Parameters'''
# The baseline (out-of-transit) flux for the star in ppt
mean = pm.Normal("mean", mu=0.0, sd=10.0)
try:
r_star_mu = target_list[target_list['ID'] == ticid]['rad'].values[0]
except:
r_star_mu = r_star_prior
if m_star_prior is None:
try:
m_star_mu = target_list[target_list['ID'] == ticid]['mass'].values[0]
except:
m_star_mu = 1.2
if np.isnan(m_star_mu):
m_star_mu = 1.2
else:
m_star_mu = m_star_prior
r_star = pm.Normal("r_star", mu=r_star_mu, sd=1.)
m_star = pm.Normal("m_star", mu=m_star_mu, sd=1.)
t_star = pm.Normal("t_star", mu=t_star_prior, sd=200)
rho_star_mu = ((m_star_mu*u.solMass).to(u.g) / ((4/3) * np.pi * ((r_star_mu*u.solRad).to(u.cm))**3)).value
rho_star = pm.Normal("rho_star", mu=rho_star_mu, sd=.25)
'''Orbital Parameters'''
# The time of a reference transit for each planet
t0 = pm.Normal("t0", mu=t0_prior, sd=2., shape=1)
period = pm.Uniform("period", testval=period_prior,
lower=minimum_period,
upper=maximum_period,
shape=1)
b = pm.Uniform("b", testval=0.5, shape=1)
# Set up a Keplerian orbit for the planets
model.orbit = xo.orbits.KeplerianOrbit(
period=period, t0=t0, b=b, r_star=r_star, m_star=m_star)#rho_star=rho_star)
# track additional orbital parameters
a = pm.Deterministic("a", model.orbit.a)
incl = pm.Deterministic("incl", model.orbit.incl)
'''Planet Parameters'''
# quadratic limb darkening paramters
u_ld = xo.distributions.QuadLimbDark("u_ld")
estimated_rpl = r_star*(depth)**(1/2)
# logr = pm.Normal("logr", testval=np.log(estimated_rpl), sd=1.)
r_pl = pm.Uniform("r_pl",
testval=estimated_rpl,
lower=0.,
upper=1.)
# r_pl = pm.Deterministic("r_pl", tt.exp(logr))
rprs = pm.Deterministic("rprs", r_pl / r_star)
teff = pm.Deterministic('teff', t_star * tt.sqrt(0.5*(1/a)))
# Compute the model light curve using starry
model.light_curves = xo.StarryLightCurve(u_ld).get_light_curve(
orbit=model.orbit, r=r_pl, t=model.x)
model.light_curve = pm.math.sum(model.light_curves, axis=-1) + mean
pm.Normal("obs",
mu=model.light_curve,
sd=model.yerr,
observed=model.y)
# Fit for the maximum a posteriori parameters, I've found that I can get
# a better solution by trying different combinations of parameters in turn
if start is None:
start = model.test_point
map_soln = xo.optimize(start=start, vars=[period, t0])
map_soln = xo.optimize(start=map_soln, vars=[r_pl, mean])
map_soln = xo.optimize(start=map_soln, vars=[period, t0, mean])
map_soln = xo.optimize(start=map_soln, vars=[r_pl, mean])
map_soln = xo.optimize(start=map_soln)
model.map_soln = map_soln
return model
def plot_quicklook(lc, ticid, breakpoints, target_list, save_data=True, outdir=None):
if outdir is None:
outdir = os.path.join(self.PACKAGEDIR, 'outputs')
time, flux, flux_err = lc.time, lc.flux, lc.flux_err
model = BoxLeastSquares(time, flux)
results = model.autopower(0.16, minimum_period=2., maximum_period=21.)
period = results.period[np.argmax(results.power)]
t0 = results.transit_time[np.argmax(results.power)]
depth = results.depth[np.argmax(results.power)]
depth_snr = results.depth_snr[np.argmax(results.power)]
'''
Plot Filtered Light Curve
-------------------------
'''
plt.subplot2grid((4,4),(1,0),colspan=2)
plt.plot(time, flux, 'k', label="filtered")
for val in breakpoints:
plt.axvline(val, c='b', linestyle='dashed')
plt.legend()
plt.ylabel('Normalized Flux')
plt.xlabel('Time')
osample=5.
nyq=283.
# calculate FFT
freq, amp, nout, jmax, prob = lomb.fasper(time, flux, osample, 3.)
freq = 1000. * freq / 86.4
bin = freq[1] - freq[0]
fts = 2. * amp * np.var(flux * 1e6) / (np.sum(amp) * bin)
use = np.where(freq < nyq + 150)
freq = freq[use]
fts = fts[use]
# calculate ACF
acf = np.correlate(fts, fts, 'same')
freq_acf = np.linspace(-freq[-1], freq[-1], len(freq))
fitT = build_ktransit_model(ticid=ticid, lc=lc, vary_transit=False)
dur = _individual_ktransit_dur(fitT.time, fitT.transitmodel)
freq = freq
fts1 = fts/np.max(fts)
fts2 = scipy.ndimage.filters.gaussian_filter(fts/np.max(fts), 5)
fts3 = scipy.ndimage.filters.gaussian_filter(fts/np.max(fts), 50)
'''
Plot Periodogram
----------------
'''
plt.subplot2grid((4,4),(0,2),colspan=2,rowspan=4)
plt.loglog(freq, fts/np.max(fts))
plt.loglog(freq, scipy.ndimage.filters.gaussian_filter(fts/np.max(fts), 5), color='C1', lw=2.5)
plt.loglog(freq, scipy.ndimage.filters.gaussian_filter(fts/np.max(fts), 50), color='r', lw=2.5)
plt.axvline(283,-1,1, ls='--', color='k')
plt.xlabel("Frequency [uHz]")
plt.ylabel("Power")
plt.xlim(10, 400)
plt.ylim(1e-4, 1e0)
# annotate with transit info
font = {'family':'monospace', 'size':10}
plt.text(10**1.04, 10**-3.50, f'depth = {depth:.4f} ', fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.04, 10**-3.62, f'depth_snr = {depth_snr:.4f} ', fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.04, 10**-3.74, f'period = {period:.3f} days ', fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.04, 10**-3.86, f't0 = {t0:.3f} ', fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
try:
# annotate with stellar params
# won't work for TIC ID's not in the list
if isinstance(ticid, str):
ticid = int(re.search(r'\d+', str(ticid)).group())
Gmag = target_list[target_list['ID'] == ticid]['GAIAmag'].values[0]
Teff = target_list[target_list['ID'] == ticid]['Teff'].values[0]
R = target_list[target_list['ID'] == ticid]['rad'].values[0]
M = target_list[target_list['ID'] == ticid]['mass'].values[0]
plt.text(10**1.7, 10**-3.50, rf"G mag = {Gmag:.3f} ", fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.7, 10**-3.62, rf"Teff = {int(Teff)} K ", fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.7, 10**-3.74, rf"R = {R:.3f} $R_\odot$ ", fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.7, 10**-3.86, rf"M = {M:.3f} $M_\odot$ ", fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
except:
pass
# plot ACF inset
ax = plt.gca()
axins = inset_axes(ax, width=2.0, height=1.4)
axins.plot(freq_acf, acf)
axins.set_xlim(1,25)
axins.set_xlabel("ACF [uHz]")
'''
Plot BLS
--------
'''
plt.subplot2grid((4,4),(2,0),colspan=2)
plt.plot(results.period, results.power, "k", lw=0.5)
plt.xlim(results.period.min(), results.period.max())
plt.xlabel("period [days]")
plt.ylabel("log likelihood")
# Highlight the harmonics of the peak period
plt.axvline(period, alpha=0.4, lw=4)
for n in range(2, 10):
plt.axvline(n*period, alpha=0.4, lw=1, linestyle="dashed")
plt.axvline(period / n, alpha=0.4, lw=1, linestyle="dashed")
phase = (t0 % period) / period
foldedtimes = (((time - phase * period) / period) % 1)
foldedtimes[foldedtimes > 0.5] -= 1
foldtimesort = np.argsort(foldedtimes)
foldfluxes = flux[foldtimesort]
plt.subplot2grid((4,4), (3,0),colspan=2)
plt.scatter(foldedtimes, flux, s=2)
plt.plot(np.sort(foldedtimes), scipy.ndimage.filters.median_filter(foldfluxes, 40), lw=2, color='r', label=f'P={period:.2f} days, dur={dur:.2f} hrs')
plt.xlabel('Phase')
plt.ylabel('Flux')
plt.xlim(-0.5, 0.5)
plt.ylim(-0.0025, 0.0025)
plt.legend(loc=0)
fig = plt.gcf()
fig.patch.set_facecolor('white')
fig.suptitle(f'{ticid}', fontsize=14)
fig.set_size_inches(10, 7)
if save_data:
np.savetxt(outdir+'/timeseries/'+str(ticid)+'.dat.ts', np.transpose([time, flux]), fmt='%.8f', delimiter=' ')
np.savetxt(outdir+'/fft/'+str(ticid)+'.dat.ts.fft', np.transpose([freq, fts]), fmt='%.8f', delimiter=' ')
with open(os.path.join(outdir,"transit_stats.txt"), "a+") as file:
file.write(f"{ticid} {depth} {depth_snr} {period} {t0} {dur}\n")
return fig
data[d]))[0] #first (zero indexing in python) column
mag = np.transpose(np.loadtxt(
data[d]))[1] #second (zero indexing in python) column
magerror = np.transpose(np.loadtxt(
data[d]))[2] #third (zero indexing in python) column
flux = 10.0**(mag / -2.5) / np.mean(10.0**(mag / -2.5))
fluxerror = flux * (10.0**(magerror / 2.5) - 1.0)
#detrending
lc = lk.LightCurve(time, flux, fluxerror)
detrended_lc = lc.flatten(window_length=window_size).bin(
binsize=bin_size).remove_outliers(sigma=Nsig)
#doing BLS search:
bls = BoxLeastSquares(detrended_lc.time, detrended_lc.flux,
detrended_lc.flux_err)
periods = np.arange(0.23,
(max(detrended_lc.time) - min(detrended_lc.time)), 0.1)
durations = np.arange((1.0 / 24.0), (5.0 / 24.0), 0.1) #1 hr to 5 hrs
periodogram = bls.power(periods, durations, objective='snr')
#phase folding with best BLS model
index = np.argmax(periodogram.power)
print(index)
best_period = periodogram.period[index]
print(best_period)
best_t0 = periodogram.transit_time[index]
print(best_t0)
detrendedphasefoldedlc = [
detrended_lc.fold(period=best_period, t0=best_t0).phase,
detrended_lc.fold(period=best_period, t0=best_t0).flux,
def tess_lightcurves(filename, TIC):
import numpy as np
from astropy.io import fits
import matplotlib.pyplot as plt
tpf_url = str(filename)
with fits.open(tpf_url) as hdus:
tpf = hdus[1].data
tpf_hdr = hdus[1].header
tpf_mask = hdus[2].data
time = tpf["TIME"]
flux = tpf["FLUX"]
m = np.any(np.isfinite(flux), axis=(1, 2)) & (tpf["QUALITY"] == 0)
time = np.ascontiguousarray(time[m] - np.min(time[m]), dtype=np.float64)
flux = np.ascontiguousarray(flux[m], dtype=np.float64)
mean_img = np.median(flux, axis=0)
plt.imshow(mean_img.T, cmap="gray_r")
plt.title("TESS image of Pi Men")
plt.xticks([])
plt.yticks([])
from scipy.signal import savgol_filter
# Sort the pixels by median brightness
order = np.argsort(mean_img.flatten())[::-1]
# A function to estimate the windowed scatter in a lightcurve
def estimate_scatter_with_mask(mask):
f = np.sum(flux[:, mask], axis=-1)
smooth = savgol_filter(f, 1001, polyorder=5)
return 1e6 * np.sqrt(np.median((f / smooth - 1)**2))
# Loop over pixels ordered by brightness and add them one-by-one
# to the aperture
masks, scatters = [], []
for i in range(10, 100):
msk = np.zeros_like(tpf_mask, dtype=bool)
msk[np.unravel_index(order[:i], mean_img.shape)] = True
scatter = estimate_scatter_with_mask(msk)
masks.append(msk)
scatters.append(scatter)
# Choose the aperture that minimizes the scatter
pix_mask = masks[np.argmin(scatters)]
# Plot the selected aperture
plt.imshow(mean_img.T, cmap="gray_r")
plt.imshow(pix_mask.T, cmap="Reds", alpha=0.3)
plt.title("TIC" + str(TIC) + ": selected aperture ")
plt.xticks([])
plt.yticks([])
# plt.savefig('/Users/Admin/Documents/Research_Lisa/TESS/plots/'+str(TIC)+'_aperture.pdf')
plt.close()
plt.figure(figsize=(10, 5))
sap_flux = np.sum(flux[:, pix_mask], axis=-1)
sap_flux = (sap_flux / np.median(sap_flux) - 1) * 1e3
plt.plot(time, sap_flux, "k")
plt.xlabel("time [days]")
plt.ylabel("relative flux [ppt]")
plt.title("TIC" + str(TIC) + ": raw light curve")
plt.xlim(time.min(), time.max())
# plt.savefig('/Users/Admin/Documents/Research_Lisa/TESS/plots/'+str(TIC)+'_raw_lc.pdf')
plt.close()
# Build the first order PLD basis
X_pld = np.reshape(flux[:, pix_mask], (len(flux), -1))
X_pld = X_pld / np.sum(flux[:, pix_mask], axis=-1)[:, None]
# Build the second order PLD basis and run PCA to reduce the number of dimensions
X2_pld = np.reshape(X_pld[:, None, :] * X_pld[:, :, None], (len(flux), -1))
U, _, _ = np.linalg.svd(X2_pld, full_matrices=False)
X2_pld = U[:, :X_pld.shape[1]]
# Construct the design matrix and fit for the PLD model
X_pld = np.concatenate((np.ones((len(flux), 1)), X_pld, X2_pld), axis=-1)
XTX = np.dot(X_pld.T, X_pld)
w_pld = np.linalg.solve(XTX, np.dot(X_pld.T, sap_flux))
pld_flux = np.dot(X_pld, w_pld)
# Plot the de-trended light curve
plt.figure(figsize=(10, 5))
plt.plot(time, sap_flux - pld_flux, "k")
plt.xlabel("time [days]")
plt.ylabel("de-trended flux [ppt]")
plt.title("TIC" + str(TIC) + ": initial de-trended light curve")
plt.xlim(time.min(), time.max())
# plt.savefig('/Users/Admin/Documents/Research_Lisa/TESS/plots/'+str(TIC)+'_detrend_lc.pdf')
plt.close()
from astropy.stats import BoxLeastSquares
period_grid = np.exp(np.linspace(np.log(1), np.log(15), 50000))
bls = BoxLeastSquares(time, sap_flux - pld_flux)
bls_power = bls.power(period_grid, 0.1, oversample=20)
# Save the highest peak as the planet candidate
index = np.argmax(bls_power.power)
bls_period = bls_power.period[index]
bls_t0 = bls_power.transit_time[index]
bls_depth = bls_power.depth[index]
transit_mask = bls.transit_mask(time, bls_period, 0.2, bls_t0)
fig, axes = plt.subplots(2, 1, figsize=(10, 10))
# Plot the periodogram
ax = axes[0]
ax.axvline(np.log10(bls_period), color="C1", lw=5, alpha=0.8)
ax.plot(np.log10(bls_power.period), bls_power.power, "k")
ax.annotate("period = {0:.4f} d".format(bls_period), (0, 1),
xycoords="axes fraction",
xytext=(5, -5),
textcoords="offset points",
va="top",
ha="left",
fontsize=12)
ax.set_ylabel("bls power")
ax.set_yticks([])
ax.set_xlim(np.log10(period_grid.min()), np.log10(period_grid.max()))
ax.set_xlabel("log10(period)")
# Plot the folded transit
ax = axes[1]
x_fold = (time - bls_t0 + 0.5 * bls_period) % bls_period - 0.5 * bls_period
m = np.abs(x_fold) < 0.4
ax.plot(x_fold[m], sap_flux[m] - pld_flux[m], ".k")
# Overplot the phase binned light curve
bins = np.linspace(-0.41, 0.41, 32)
denom, _ = np.histogram(x_fold, bins)
num, _ = np.histogram(x_fold, bins, weights=sap_flux - pld_flux)
denom[num == 0] = 1.0
ax.plot(0.5 * (bins[1:] + bins[:-1]), num / denom, color="C1")
ax.set_xlim(-0.3, 0.3)
ax.set_ylabel("de-trended flux [ppt]")
ax.set_xlabel("time since transit")
plt.title("TIC" + str(TIC))
plt.savefig('/Users/Admin/Documents/Research_Lisa/TESS/plots/' + str(TIC) +
'_period_detrend_lc.pdf')
plt.close()
m = ~transit_mask
XTX = np.dot(X_pld[m].T, X_pld[m])
w_pld = np.linalg.solve(XTX, np.dot(X_pld[m].T, sap_flux[m]))
pld_flux = np.dot(X_pld, w_pld)
x = np.ascontiguousarray(time, dtype=np.float64)
y = np.ascontiguousarray(sap_flux - pld_flux, dtype=np.float64)
plt.figure(figsize=(10, 5))
plt.plot(time, y, "k")
plt.xlabel("time [days]")
plt.ylabel("de-trended flux [ppt]")
plt.title("TIC" + str(TIC) + ": final de-trended light curve")
plt.xlim(time.min(), time.max())
# plt.savefig('/Users/Admin/Documents/Research_Lisa/TESS/plots/'+str(TIC)+'_detrend_lc_final.pdf')
plt.close()
plt.figure(figsize=(10, 5))
x_fold = (x - bls_t0 + 0.5 * bls_period) % bls_period - 0.5 * bls_period
m = np.abs(x_fold) < 0.3
plt.plot(x_fold[m], pld_flux[m], ".k", ms=4)
bins = np.linspace(-0.5, 0.5, 60)
denom, _ = np.histogram(x_fold, bins)
num, _ = np.histogram(x_fold, bins, weights=pld_flux)
denom[num == 0] = 1.0
plt.plot(0.5 * (bins[1:] + bins[:-1]), num / denom, color="C1", lw=2)
plt.xlim(-0.2, 0.2)
plt.title("TIC" + str(TIC))
plt.xlabel("time since transit")
plt.ylabel("PLD model flux")
# plt.savefig('/Users/Admin/Documents/Research_Lisa/TESS/plots/'+str(TIC)+'_PLD_model.pdf')
plt.close()
def superplot(lc, ticid, breakpoints, target_list, save_data=False, outdir=None):
"""
"""
time, flux, flux_err = lc.time, lc.flux, lc.flux_err
model = BoxLeastSquares(time, flux)
results = model.autopower(0.16, minimum_period=2., maximum_period=21.)
period = results.period[np.argmax(results.power)]
t0 = results.transit_time[np.argmax(results.power)]
depth = results.depth[np.argmax(results.power)]
depth_snr = results.depth_snr[np.argmax(results.power)]
'''
Plot Filtered Light Curve
-------------------------
'''
plt.subplot2grid((8,16),(1,0),colspan=4, rowspan=1)
plt.plot(time, flux, 'k', label="filtered")
for val in breakpoints:
plt.axvline(val, c='b', linestyle='dashed')
plt.legend()
plt.ylabel('Normalized Flux')
plt.xlabel('Time')
osample=5.
nyq=283.
# calculate FFT
freq, amp, nout, jmax, prob = lomb.fasper(time, flux, osample, 3.)
freq = 1000. * freq / 86.4
bin = freq[1] - freq[0]
fts = 2. * amp * np.var(flux * 1e6) / (np.sum(amp) * bin)
use = np.where(freq < nyq + 150)
freq = freq[use]
fts = fts[use]
# calculate ACF
acf = np.correlate(fts, fts, 'same')
freq_acf = np.linspace(-freq[-1], freq[-1], len(freq))
fitT = build_ktransit_model(ticid=ticid, lc=lc, vary_transit=False)
dur = _individual_ktransit_dur(fitT.time, fitT.transitmodel)
freq = freq
fts1 = fts/np.max(fts)
fts2 = scipy.ndimage.filters.gaussian_filter(fts/np.max(fts), 5)
fts3 = scipy.ndimage.filters.gaussian_filter(fts/np.max(fts), 50)
'''
Plot Periodogram
----------------
'''
plt.subplot2grid((8,16),(0,4),colspan=4,rowspan=4)
plt.loglog(freq, fts/np.max(fts))
plt.loglog(freq, scipy.ndimage.filters.gaussian_filter(fts/np.max(fts), 5), color='C1', lw=2.5)
plt.loglog(freq, scipy.ndimage.filters.gaussian_filter(fts/np.max(fts), 50), color='r', lw=2.5)
plt.axvline(283,-1,1, ls='--', color='k')
plt.xlabel("Frequency [uHz]")
plt.ylabel("Power")
plt.xlim(10, 400)
plt.ylim(1e-4, 1e0)
# annotate with transit info
font = {'family':'monospace', 'size':10}
plt.text(10**1.04, 10**-3.50, f'depth = {depth:.4f} ', fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.04, 10**-3.62, f'depth_snr = {depth_snr:.4f} ', fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.04, 10**-3.74, f'period = {period:.3f} days ', fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.04, 10**-3.86, f't0 = {t0:.3f} ', fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
try:
# annotate with stellar params
# won't work for TIC ID's not in the list
if isinstance(ticid, str):
ticid = int(re.search(r'\d+', str(ticid)).group())
Gmag = target_list[target_list['ID'] == ticid]['GAIAmag'].values[0]
Teff = target_list[target_list['ID'] == ticid]['Teff'].values[0]
R = target_list[target_list['ID'] == ticid]['rad'].values[0]
M = target_list[target_list['ID'] == ticid]['mass'].values[0]
plt.text(10**1.7, 10**-3.50, rf"G mag = {Gmag:.3f} ", fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.7, 10**-3.62, rf"Teff = {int(Teff)} K ", fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.7, 10**-3.74, rf"R = {R:.3f} $R_\odot$ ", fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
plt.text(10**1.7, 10**-3.86, rf"M = {M:.3f} $M_\odot$ ", fontdict=font).set_bbox(dict(facecolor='white', alpha=.9, edgecolor='none'))
except:
pass
'''# plot ACF inset
ax = plt.gca()
axins = inset_axes(ax, width=2.0, height=1.4)
axins.plot(freq_acf, acf)
axins.set_xlim(1,25)
axins.set_xlabel("ACF [uHz]")'''
'''
Plot BLS
--------
'''
plt.subplot2grid((8,16),(2,0),colspan=4, rowspan=1)
plt.plot(results.period, results.power, "k", lw=0.5)
plt.xlim(results.period.min(), results.period.max())
plt.xlabel("period [days]")
plt.ylabel("log likelihood")
# Highlight the harmonics of the peak period
plt.axvline(period, alpha=0.4, lw=4)
for n in range(2, 10):
plt.axvline(n*period, alpha=0.4, lw=1, linestyle="dashed")
plt.axvline(period / n, alpha=0.4, lw=1, linestyle="dashed")
phase = (t0 % period) / period
foldedtimes = (((time - phase * period) / period) % 1)
foldedtimes[foldedtimes > 0.5] -= 1
foldtimesort = np.argsort(foldedtimes)
foldfluxes = flux[foldtimesort]
plt.subplot2grid((8,16), (3,0),colspan=2)
plt.scatter(foldedtimes, flux, s=2)
plt.plot(np.sort(foldedtimes), scipy.ndimage.filters.median_filter(foldfluxes, 40), lw=2, color='r', label=f'P={period:.2f} days, dur={dur:.2f} hrs')
plt.xlabel('Phase')
plt.ylabel('Flux')
plt.xlim(-0.5, 0.5)
plt.ylim(-0.0025, 0.0025)
plt.legend(loc=0)
fig = plt.gcf()
fig.patch.set_facecolor('white')
fig.suptitle(f'{ticid}', fontsize=14)
fig.set_size_inches(12, 10)
if save_data:
np.savetxt(outdir+'/timeseries/'+str(ticid)+'.dat.ts', np.transpose([time, flux]), fmt='%.8f', delimiter=' ')
np.savetxt(outdir+'/fft/'+str(ticid)+'.dat.ts.fft', np.transpose([freq, fts]), fmt='%.8f', delimiter=' ')
with open(os.path.join(outdir,"transit_stats.txt"), "a+") as file:
file.write(f"{ticid} {depth} {depth_snr} {period} {t0} {dur}\n")
"""
---------------
TRANSIT VETTING
---------------
"""
tpf = get_cutout(ticid, cutout_size=11)
ica_lcs = find_ica_components(tpf)
fig = plt.subplot2grid((8,16),(0,8),colspan=4,rowspan=4)
fig.patch.set_facecolor('white')
tpf.plot(ax=fig, title='', show_colorbar=False)
add_gaia_figure_elements(tpf, fig)
fig = plt.subplot2grid((8,16),(2,8),colspan=4,rowspan=2)
lc.fold(2*period, t0+period/2).scatter(ax=fig, c='k', label='Odd Transit')
lc.fold(2*period, t0+period/2).bin(3).plot(ax=fig, c='C1', lw=2)
plt.xlim(-.5, 0)
rms = np.std(lc.flux)
plt.ylim(-3*rms, rms)
fig = plt.subplot2grid((8,16),(3,8),colspan=4,rowspan=2)
lc.fold(2*period, t0+period/2).scatter(ax=fig, c='k', label='Even Transit')
lc.fold(2*period, t0+period/2).bin(3).plot(ax=fig, c='C1', lw=2)
plt.xlim(0, .5)
plt.ylim(-3*rms, rms)
fig = plt.subplot2grid((8,16),(0,12),colspan=4,rowspan=4)
for i,ilc in enumerate(ica_lcs):
scale = 1
plt.plot(ilc + i*scale)
plt.xlim(0, len(ica_lcs[0]))
plt.ylim(-scale, len(ica_lcs)*scale)
"""
STARRY MODEL
------------
"""
from .utils import _fit
x, y, yerr = lc.time, lc.flux, lc.flux_err
model, static_lc = _fit(x, y, yerr, target_list=target_list)
model_lc = lk.LightCurve(time=x, flux=static_lc)
with model:
period = model.map_soln['period'][0]
t0 = model.map_soln['t0'][0]
r_pl = model.map_soln['r_pl'] * 9.96
a = model.map_soln['a'][0]
b = model.map_soln['b'][0]
try:
r_star = target_list[target_list['ID'] == ticid]['rad'].values[0]
except:
r_star = 10.
fig = plt.subplot2grid((8,16),(4,0),colspan=4,rowspan=2)
'''
Plot unfolded transit
---------------------
'''
lc.scatter(c='k', label='Corrected Flux')
lc.bin(binsize=7).plot(c='b', lw=1.5, alpha=.75, label='binned')
model_lc.plot(c='r', lw=2, label='Transit Model')
plt.ylim([-.002, .002])
plt.xlim([lc.time[0], lc.time[-1]])
fig = plt.subplot2grid((8,16),(6,0),colspan=4,rowspan=2)
'''
Plot folded transit
-------------------
'''
lc.fold(period, t0).scatter(c='k', label=rf'$P={period:.3f}, t0={t0:.3f}, '
'R_p={r_pl:.3f} R_J, b={b:.3f}')
lc.fold(period, t0).bin(binsize=7).plot(c='b', alpha=.75, lw=2)
model_lc.fold(period, t0).plot(c='r', lw=2)
plt.xlim([-0.5, .5])
plt.ylim([-.002, .002])
def make_ica_plot(tic, tpf=None):
"""
"""
if tpf is None:
tpf = lk.search_tesscut(f'TIC {tic}').download(cutout_size=11)
raw_lc = tpf.to_lightcurve(aperture_mask='all')
##Perform ICA
n_components = 20
X = np.ascontiguousarray(np.nan_to_num(tpf.flux), np.float64)
X_flat = X.reshape(len(tpf.flux), -1) #turns three dimensional into two dimensional
f1 = np.reshape(X_flat, (len(X), -1))
X_pix = f1 / np.nansum(X_flat, axis=-1)[:, None]
ica = FastICA(n_components=n_components) #define n_components
S_ = ica.fit_transform(X_pix)
A_ = ica.mixing_ #combine x_flat to get x
a = np.dot(S_.T, S_)
a[np.diag_indices_from(a)] += 1e-5
b = np.dot(S_.T, raw_lc.flux)
w = np.linalg.solve(a, b)
comp_lcs = []
blss = []
max_powers = []
for i,s in enumerate(S_.T):
component_lc = s * w[i]
comp_lcs.append(component_lc)
# plt.plot(component_lc + i*1e5)
model = BoxLeastSquares(tpf.time, component_lc)
results = model.autopower(0.16, minimum_period=.5, maximum_period=24.)
# model = transitleastsquares(tpf.time, component_lc)
# results = model.power()
period, power = results.period, results.power
blss.append([period, power])
# print(results.depth_snr[np.argmax(power)])
if (np.std(component_lc) > 1e4) or (np.abs(period[np.argmax(power)] - 14) < 2) or (results.depth[np.argmax(power)]/np.median(component_lc) < 0):
power = [0]
max_powers.append(np.max(power))
# plt.ylim(-1e5, 10e5)
best_pers = blss[np.argmax(max_powers)][0]
best_powers = blss[np.argmax(max_powers)][1]
period = best_pers[np.argmax(best_powers)]
transit_lc = lk.LightCurve(time=tpf.time, flux=comp_lcs[np.argmax(max_powers)])
fig, ax = plt.subplots(2, 3, figsize=(10, 7))
fig.suptitle(f'TIC {tic}')
for i,c in enumerate(comp_lcs):
ax[0,0].plot(tpf.time, c + i*1e5)
ax[0,0].set_ylim(-1e5, n_components*1e5)
ax[0,0].set_xlim(tpf.time[0], tpf.time[-1])
ax[0,0].set_xlabel('Time')
ax[0,0].set_ylabel('Flux')
ax[0,0].yaxis.set_major_formatter(mtick.FormatStrFormatter('%.e'))
ax[0,0].set_title('ICA Components')
transit_lc.plot(ax=ax[0,1])
ax[0,1].set_xlim(tpf.time[0], tpf.time[-1])
ax[0,1].yaxis.set_major_formatter(mtick.FormatStrFormatter('%.e'))
ax[0,1].set_title('ICA comp with max BLS power')
transit_lc.remove_outliers(9).fold(period).scatter(ax=ax[0,2], c='k', label=f'Period={period:.2f}')
transit_lc.remove_outliers(9).fold(period).bin(7).plot(ax=ax[0,2], c='r', lw=2, C='C1', label='Binned')
ax[0,2].set_ylim(-5*np.std(transit_lc.flux), 2*np.std(transit_lc.flux))
ax[0,2].set_xlim(-.5,.5)
ax[0,2].set_title('Folded ICA Transit Component')
A_useful = A_.reshape(11,11,n_components).T #reshape from 2d to 3d
weighted_comp = A_useful[np.argmax(max_powers)].T * w[np.argmax(max_powers)]
ax[1,0].imshow(weighted_comp, origin='lower')
ax[1,1].imshow(tpf.flux[200], origin='lower')
im = ax[1,2].imshow(weighted_comp / tpf.flux[200], origin='lower')
ax[1,0].set_title('Weighted Transit Component')
ax[1,1].set_title('TPF')
ax[1,2].set_title('Model / Flux')
plt.colorbar(im)
fig.tight_layout(rect=[0, 0.03, 1, 0.95])
fig.patch.set_facecolor('white')
fig.set_size_inches(10, 7)
return fig
def bls_parallel_pfind(
times,
mags,
errs,
magsarefluxes=False,
startp=0.1, # by default, search from 0.1 d to...
endp=100.0, # ... 100.0 d -- don't search full timebase
stepsize=1.0e-4,
mintransitduration=0.01, # minimum transit length in phase
maxtransitduration=0.4, # maximum transit length in phase
ndurations=100,
autofreq=True, # figure out f0, nf, and df automatically
blsobjective='likelihood',
blsmethod='fast',
blsoversample=5,
blsmintransits=3,
blsfreqfactor=10.0,
nbestpeaks=5,
periodepsilon=0.1, # 0.1
sigclip=10.0,
endp_timebase_check=True,
verbose=True,
nworkers=None,
):
'''Runs the Box Least Squares Fitting Search for transit-shaped signals.
Breaks up the full frequency space into chunks and passes them to parallel
BLS workers.
Based on the version of BLS in Astropy 3.1:
`astropy.stats.BoxLeastSquares`. If you don't have Astropy 3.1, this module
will fail to import. Note that by default, this implementation of
`bls_parallel_pfind` doesn't use the `.autoperiod()` function from
`BoxLeastSquares` but uses the same auto frequency-grid generation as the
functions in `periodbase.kbls`. If you want to use Astropy's implementation,
set the value of `autofreq` kwarg to 'astropy'. The generated period array
will then be broken up into chunks and sent to the individual workers.
NOTE: the combined BLS spectrum produced by this function is not identical
to that produced by running BLS in one shot for the entire frequency
space. There are differences on the order of 1.0e-3 or so in the respective
peak values, but peaks appear at the same frequencies for both methods. This
is likely due to different aliasing caused by smaller chunks of the
frequency space used by the parallel workers in this function. When in
doubt, confirm results for this parallel implementation by comparing to
those from the serial implementation above.
In particular, when you want to get reliable estimates of the SNR, transit
depth, duration, etc. that Astropy's BLS gives you, rerun `bls_serial_pfind`
with `startp`, and `endp` close to the best period you want to characterize
the transit at. The dict returned from that function contains a `blsmodel`
key, which is the generated model from Astropy's BLS. Use the
`.compute_stats()` method to calculate the required stats.
Parameters
----------
times,mags,errs : np.array
The magnitude/flux time-series to search for transits.
magsarefluxes : bool
If the input measurement values in `mags` and `errs` are in fluxes, set
this to True.
startp,endp : float
The minimum and maximum periods to consider for the transit search.
stepsize : float
The step-size in frequency to use when constructing a frequency grid for
the period search.
mintransitduration,maxtransitduration : float
The minimum and maximum transitdurations (in units of phase) to consider
for the transit search.
ndurations : int
The number of transit durations to use in the period-search.
autofreq : bool or str
If this is True, the values of `stepsize` and `nphasebins` will be
ignored, and these, along with a frequency-grid, will be determined
based on the following relations::
nphasebins = int(ceil(2.0/mintransitduration))
if nphasebins > 3000:
nphasebins = 3000
stepsize = 0.25*mintransitduration/(times.max()-times.min())
minfreq = 1.0/endp
maxfreq = 1.0/startp
nfreq = int(ceil((maxfreq - minfreq)/stepsize))
If this is False, you must set `startp`, `endp`, and `stepsize` as
appropriate.
If this is str == 'astropy', will use the
`astropy.stats.BoxLeastSquares.autoperiod()` function to calculate the
frequency grid instead of the kbls method.
blsobjective : {'likelihood','snr'}
Sets the type of objective to optimize in the `BoxLeastSquares.power()`
function.
blsmethod : {'fast','slow'}
Sets the type of method to use in the `BoxLeastSquares.power()`
function.
blsoversample : {'likelihood','snr'}
Sets the `oversample` kwarg for the `BoxLeastSquares.power()` function.
blsmintransits : int
Sets the `min_n_transits` kwarg for the `BoxLeastSquares.autoperiod()`
function.
blsfreqfactor : float
Sets the `frequency_factor` kwarg for the `BoxLeastSquares.autoperiod()`
function.
periodepsilon : float
The fractional difference between successive values of 'best' periods
when sorting by periodogram power to consider them as separate periods
(as opposed to part of the same periodogram peak). This is used to avoid
broad peaks in the periodogram and make sure the 'best' periods returned
are all actually independent.
nbestpeaks : int
The number of 'best' peaks to return from the periodogram results,
starting from the global maximum of the periodogram peak values.
sigclip : float or int or sequence of two floats/ints or None
If a single float or int, a symmetric sigma-clip will be performed using
the number provided as the sigma-multiplier to cut out from the input
time-series.
If a list of two ints/floats is provided, the function will perform an
'asymmetric' sigma-clip. The first element in this list is the sigma
value to use for fainter flux/mag values; the second element in this
list is the sigma value to use for brighter flux/mag values. For
example, `sigclip=[10., 3.]`, will sigclip out greater than 10-sigma
dimmings and greater than 3-sigma brightenings. Here the meaning of
"dimming" and "brightening" is set by *physics* (not the magnitude
system), which is why the `magsarefluxes` kwarg must be correctly set.
If `sigclip` is None, no sigma-clipping will be performed, and the
time-series (with non-finite elems removed) will be passed through to
the output.
endp_timebase_check : bool
If True, will check if the ``endp`` value is larger than the time-base
of the observations. If it is, will change the ``endp`` value such that
it is half of the time-base. If False, will allow an ``endp`` larger
than the time-base of the observations.
verbose : bool
If this is True, will indicate progress and details about the frequency
grid used for the period search.
nworkers : int or None
The number of parallel workers to launch for period-search. If None,
nworkers = NCPUS.
Returns
-------
dict
This function returns a dict, referred to as an `lspinfo` dict in other
astrobase functions that operate on periodogram results. This is a
standardized format across all astrobase period-finders, and is of the
form below::
{'bestperiod': the best period value in the periodogram,
'bestlspval': the periodogram peak associated with the best period,
'nbestpeaks': the input value of nbestpeaks,
'nbestlspvals': nbestpeaks-size list of best period peak values,
'nbestperiods': nbestpeaks-size list of best periods,
'lspvals': the full array of periodogram powers,
'frequencies': the full array of frequencies considered,
'periods': the full array of periods considered,
'durations': the array of durations used to run BLS,
'blsresult': Astropy BLS result object (BoxLeastSquaresResult),
'blsmodel': Astropy BLS BoxLeastSquares object used for work,
'stepsize': the actual stepsize used,
'nfreq': the actual nfreq used,
'durations': the durations array used,
'mintransitduration': the input mintransitduration,
'maxtransitduration': the input maxtransitdurations,
'method':'bls' -> the name of the period-finder method,
'kwargs':{ dict of all of the input kwargs for record-keeping}}
'''
# get rid of nans first and sigclip
stimes, smags, serrs = sigclip_magseries(times,
mags,
errs,
magsarefluxes=magsarefluxes,
sigclip=sigclip)
# make sure there are enough points to calculate a spectrum
if len(stimes) > 9 and len(smags) > 9 and len(serrs) > 9:
# if we're setting up everything automatically
if isinstance(autofreq, bool) and autofreq:
# use heuristic to figure out best timestep
stepsize = 0.25 * mintransitduration / (stimes.max() -
stimes.min())
# now figure out the frequencies to use
minfreq = 1.0 / endp
maxfreq = 1.0 / startp
nfreq = int(npceil((maxfreq - minfreq) / stepsize))
# say what we're using
if verbose:
LOGINFO('min P: %s, max P: %s, nfreq: %s, '
'minfreq: %s, maxfreq: %s' %
(startp, endp, nfreq, minfreq, maxfreq))
LOGINFO('autofreq = True: using AUTOMATIC values for '
'freq stepsize: %s, ndurations: %s, '
'min transit duration: %s, max transit duration: %s' %
(stepsize, ndurations, mintransitduration,
maxtransitduration))
use_autoperiod = False
elif isinstance(autofreq, bool) and not autofreq:
minfreq = 1.0 / endp
maxfreq = 1.0 / startp
nfreq = int(npceil((maxfreq - minfreq) / stepsize))
# say what we're using
if verbose:
LOGINFO('min P: %s, max P: %s, nfreq: %s, '
'minfreq: %s, maxfreq: %s' %
(startp, endp, nfreq, minfreq, maxfreq))
LOGINFO('autofreq = False: using PROVIDED values for '
'freq stepsize: %s, ndurations: %s, '
'min transit duration: %s, max transit duration: %s' %
(stepsize, ndurations, mintransitduration,
maxtransitduration))
use_autoperiod = False
elif isinstance(autofreq, str) and autofreq == 'astropy':
use_autoperiod = True
minfreq = 1.0 / endp
maxfreq = 1.0 / startp
else:
LOGERROR("unknown autofreq kwarg encountered. can't continue...")
return None
# check the minimum frequency
if ((minfreq < (1.0 / (stimes.max() - stimes.min())))
and endp_timebase_check):
LOGWARNING('the requested max P = %.3f is larger than '
'the time base of the observations = %.3f, '
' will make minfreq = 2 x 1/timebase' %
(endp, stimes.max() - stimes.min()))
minfreq = 2.0 / (stimes.max() - stimes.min())
LOGWARNING('new minfreq: %s, maxfreq: %s' % (minfreq, maxfreq))
#############################
## NOW RUN BLS IN PARALLEL ##
#############################
# fix number of CPUs if needed
if not nworkers or nworkers > NCPUS:
nworkers = NCPUS
if verbose:
LOGINFO('using %s workers...' % nworkers)
# check if autoperiod is True and get the correct period-grid
if use_autoperiod:
# astropy's BLS requires durations in units of time
durations = nplinspace(mintransitduration * startp,
maxtransitduration * startp, ndurations)
# set up the correct units for the BLS model
if magsarefluxes:
blsmodel = BoxLeastSquares(stimes * u.day,
smags * u.dimensionless_unscaled,
dy=serrs * u.dimensionless_unscaled)
else:
blsmodel = BoxLeastSquares(stimes * u.day,
smags * u.mag,
dy=serrs * u.mag)
periods = nparray(
blsmodel.autoperiod(durations * u.day,
minimum_period=startp,
maximum_period=endp,
minimum_n_transit=blsmintransits,
frequency_factor=blsfreqfactor))
frequencies = 1.0 / periods
nfreq = frequencies.size
if verbose:
LOGINFO("autofreq = 'astropy', used .autoperiod() with "
"minimum_n_transit = %s, freq_factor = %s "
"to generate the frequency grid" %
(blsmintransits, blsfreqfactor))
LOGINFO('stepsize = %s, nfreq = %s, minfreq = %.5f, '
'maxfreq = %.5f, ndurations = %s' %
(abs(frequencies[1] - frequencies[0]), nfreq, 1.0 /
periods.max(), 1.0 / periods.min(), durations.size))
del blsmodel
del durations
# otherwise, use kbls method
else:
frequencies = minfreq + nparange(nfreq) * stepsize
# break up the tasks into chunks
csrem = int(fmod(nfreq, nworkers))
csint = int(float(nfreq / nworkers))
chunk_minfreqs, chunk_nfreqs = [], []
for x in range(nworkers):
this_minfreqs = frequencies[x * csint]
# handle usual nfreqs
if x < (nworkers - 1):
this_nfreqs = frequencies[x * csint:x * csint + csint].size
else:
this_nfreqs = frequencies[x * csint:x * csint + csint +
csrem].size
chunk_minfreqs.append(this_minfreqs)
chunk_nfreqs.append(this_nfreqs)
# populate the tasks list
#
# task[0] = times
# task[1] = mags
# task[2] = errs
# task[3] = magsarefluxes
# task[4] = minfreq
# task[5] = nfreq
# task[6] = stepsize
# task[7] = nphasebins
# task[8] = mintransitduration
# task[9] = maxtransitduration
# task[10] = blsobjective
# task[11] = blsmethod
# task[12] = blsoversample
# populate the tasks list
tasks = [(stimes, smags, serrs, magsarefluxes, chunk_minf, chunk_nf,
stepsize, ndurations, mintransitduration, maxtransitduration,
blsobjective, blsmethod, blsoversample)
for (chunk_minf,
chunk_nf) in zip(chunk_minfreqs, chunk_nfreqs)]
if verbose:
for ind, task in enumerate(tasks):
LOGINFO('worker %s: minfreq = %.6f, nfreqs = %s' %
(ind + 1, task[4], task[5]))
LOGINFO('running...')
# return tasks
# start the pool
pool = Pool(nworkers)
results = pool.map(_parallel_bls_worker, tasks)
pool.close()
pool.join()
del pool
# now concatenate the output lsp arrays
lsp = npconcatenate([x['power'] for x in results])
periods = 1.0 / frequencies
# find the nbestpeaks for the periodogram: 1. sort the lsp array
# by highest value first 2. go down the values until we find
# five values that are separated by at least periodepsilon in
# period
# make sure to get only the finite peaks in the periodogram
# this is needed because BLS may produce infs for some peaks
finitepeakind = npisfinite(lsp)
finlsp = lsp[finitepeakind]
finperiods = periods[finitepeakind]
# make sure that finlsp has finite values before we work on it
try:
bestperiodind = npargmax(finlsp)
except ValueError:
LOGERROR('no finite periodogram values '
'for this mag series, skipping...')
return {
'bestperiod': npnan,
'bestlspval': npnan,
'nbestpeaks': nbestpeaks,
'nbestinds': None,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'durations': None,
'method': 'bls',
'blsresult': None,
'blsmodel': None,
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'ndurations': ndurations,
'blsobjective': blsobjective,
'blsmethod': blsmethod,
'blsoversample': blsoversample,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip,
'magsarefluxes': magsarefluxes
}
}
sortedlspind = npargsort(finlsp)[::-1]
sortedlspperiods = finperiods[sortedlspind]
sortedlspvals = finlsp[sortedlspind]
# now get the nbestpeaks
nbestperiods, nbestlspvals, nbestinds, peakcount = ([
finperiods[bestperiodind]
], [finlsp[bestperiodind]], [bestperiodind], 1)
prevperiod = sortedlspperiods[0]
# find the best nbestpeaks in the lsp and their periods
for period, lspval, ind in zip(sortedlspperiods, sortedlspvals,
sortedlspind):
if peakcount == nbestpeaks:
break
perioddiff = abs(period - prevperiod)
bestperiodsdiff = [abs(period - x) for x in nbestperiods]
# this ensures that this period is different from the last
# period and from all the other existing best periods by
# periodepsilon to make sure we jump to an entire different
# peak in the periodogram
if (perioddiff > (periodepsilon * prevperiod)
and all(x > (periodepsilon * period)
for x in bestperiodsdiff)):
nbestperiods.append(period)
nbestlspvals.append(lspval)
nbestinds.append(ind)
peakcount = peakcount + 1
prevperiod = period
# generate the return dict
resultdict = {
'bestperiod': finperiods[bestperiodind],
'bestlspval': finlsp[bestperiodind],
'nbestpeaks': nbestpeaks,
'nbestinds': nbestinds,
'nbestlspvals': nbestlspvals,
'nbestperiods': nbestperiods,
'lspvals': lsp,
'frequencies': frequencies,
'periods': periods,
'durations': [x['durations'] for x in results],
'blsresult': [x['blsresult'] for x in results],
'blsmodel': [x['blsmodel'] for x in results],
'stepsize': stepsize,
'nfreq': nfreq,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'ndurations': ndurations,
'blsobjective': blsobjective,
'blsmethod': blsmethod,
'blsoversample': blsoversample,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip,
'magsarefluxes': magsarefluxes
}
}
return resultdict
else:
LOGERROR('no good detections for these times and mags, skipping...')
return {
'bestperiod': npnan,
'bestlspval': npnan,
'nbestinds': None,
'nbestpeaks': nbestpeaks,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'durations': None,
'blsresult': None,
'blsmodel': None,
'stepsize': stepsize,
'nfreq': None,
'nphasebins': None,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'ndurations': ndurations,
'blsobjective': blsobjective,
'blsmethod': blsmethod,
'blsoversample': blsoversample,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip,
'magsarefluxes': magsarefluxes
}
}
def bls_serial_pfind(
times,
mags,
errs,
magsarefluxes=False,
startp=0.1, # search from 0.1 d to...
endp=100.0, # ... 100.0 d -- don't search full timebase
stepsize=5.0e-4,
mintransitduration=0.01, # minimum transit length in phase
maxtransitduration=0.4, # maximum transit length in phase
ndurations=100,
autofreq=True, # figure out f0, nf, and df automatically
blsobjective='likelihood',
blsmethod='fast',
blsoversample=10,
blsmintransits=3,
blsfreqfactor=10.0,
periodepsilon=0.1,
nbestpeaks=5,
sigclip=10.0,
endp_timebase_check=True,
verbose=True,
raiseonfail=False):
'''Runs the Box Least Squares Fitting Search for transit-shaped signals.
Based on the version of BLS in Astropy 3.1:
`astropy.stats.BoxLeastSquares`. If you don't have Astropy 3.1, this module
will fail to import. Note that by default, this implementation of
`bls_serial_pfind` doesn't use the `.autoperiod()` function from
`BoxLeastSquares` but uses the same auto frequency-grid generation as the
functions in `periodbase.kbls`. If you want to use Astropy's implementation,
set the value of `autofreq` kwarg to 'astropy'.
The dict returned from this function contains a `blsmodel` key, which is the
generated model from Astropy's BLS. Use the `.compute_stats()` method to
calculate the required stats like SNR, depth, duration, etc.
Parameters
----------
times,mags,errs : np.array
The magnitude/flux time-series to search for transits.
magsarefluxes : bool
If the input measurement values in `mags` and `errs` are in fluxes, set
this to True.
startp,endp : float
The minimum and maximum periods to consider for the transit search.
stepsize : float
The step-size in frequency to use when constructing a frequency grid for
the period search.
mintransitduration,maxtransitduration : float
The minimum and maximum transitdurations (in units of phase) to consider
for the transit search.
ndurations : int
The number of transit durations to use in the period-search.
autofreq : bool or str
If this is True, the values of `stepsize` and `nphasebins` will be
ignored, and these, along with a frequency-grid, will be determined
based on the following relations::
nphasebins = int(ceil(2.0/mintransitduration))
if nphasebins > 3000:
nphasebins = 3000
stepsize = 0.25*mintransitduration/(times.max()-times.min())
minfreq = 1.0/endp
maxfreq = 1.0/startp
nfreq = int(ceil((maxfreq - minfreq)/stepsize))
If this is False, you must set `startp`, `endp`, and `stepsize` as
appropriate.
If this is str == 'astropy', will use the
`astropy.stats.BoxLeastSquares.autoperiod()` function to calculate the
frequency grid instead of the kbls method.
blsobjective : {'likelihood','snr'}
Sets the type of objective to optimize in the `BoxLeastSquares.power()`
function.
blsmethod : {'fast','slow'}
Sets the type of method to use in the `BoxLeastSquares.power()`
function.
blsoversample : {'likelihood','snr'}
Sets the `oversample` kwarg for the `BoxLeastSquares.power()` function.
blsmintransits : int
Sets the `min_n_transits` kwarg for the `BoxLeastSquares.autoperiod()`
function.
blsfreqfactor : float
Sets the `frequency_factor` kwarg for the `BoxLeastSquares.autperiod()`
function.
periodepsilon : float
The fractional difference between successive values of 'best' periods
when sorting by periodogram power to consider them as separate periods
(as opposed to part of the same periodogram peak). This is used to avoid
broad peaks in the periodogram and make sure the 'best' periods returned
are all actually independent.
nbestpeaks : int
The number of 'best' peaks to return from the periodogram results,
starting from the global maximum of the periodogram peak values.
sigclip : float or int or sequence of two floats/ints or None
If a single float or int, a symmetric sigma-clip will be performed using
the number provided as the sigma-multiplier to cut out from the input
time-series.
If a list of two ints/floats is provided, the function will perform an
'asymmetric' sigma-clip. The first element in this list is the sigma
value to use for fainter flux/mag values; the second element in this
list is the sigma value to use for brighter flux/mag values. For
example, `sigclip=[10., 3.]`, will sigclip out greater than 10-sigma
dimmings and greater than 3-sigma brightenings. Here the meaning of
"dimming" and "brightening" is set by *physics* (not the magnitude
system), which is why the `magsarefluxes` kwarg must be correctly set.
If `sigclip` is None, no sigma-clipping will be performed, and the
time-series (with non-finite elems removed) will be passed through to
the output.
endp_timebase_check : bool
If True, will check if the ``endp`` value is larger than the time-base
of the observations. If it is, will change the ``endp`` value such that
it is half of the time-base. If False, will allow an ``endp`` larger
than the time-base of the observations.
verbose : bool
If this is True, will indicate progress and details about the frequency
grid used for the period search.
raiseonfail : bool
If True, raises an exception if something goes wrong. Otherwise, returns
None.
Returns
-------
dict
This function returns a dict, referred to as an `lspinfo` dict in other
astrobase functions that operate on periodogram results. This is a
standardized format across all astrobase period-finders, and is of the
form below::
{'bestperiod': the best period value in the periodogram,
'bestlspval': the periodogram peak associated with the best period,
'nbestpeaks': the input value of nbestpeaks,
'nbestlspvals': nbestpeaks-size list of best period peak values,
'nbestperiods': nbestpeaks-size list of best periods,
'lspvals': the full array of periodogram powers,
'frequencies': the full array of frequencies considered,
'periods': the full array of periods considered,
'durations': the array of durations used to run BLS,
'blsresult': Astropy BLS result object (BoxLeastSquaresResult),
'blsmodel': Astropy BLS BoxLeastSquares object used for work,
'stepsize': the actual stepsize used,
'nfreq': the actual nfreq used,
'durations': the durations array used,
'mintransitduration': the input mintransitduration,
'maxtransitduration': the input maxtransitdurations,
'method':'bls' -> the name of the period-finder method,
'kwargs':{ dict of all of the input kwargs for record-keeping}}
'''
# get rid of nans first and sigclip
stimes, smags, serrs = sigclip_magseries(times,
mags,
errs,
magsarefluxes=magsarefluxes,
sigclip=sigclip)
# make sure there are enough points to calculate a spectrum
if len(stimes) > 9 and len(smags) > 9 and len(serrs) > 9:
# if we're setting up everything automatically
if isinstance(autofreq, bool) and autofreq:
# use heuristic to figure out best timestep
stepsize = 0.25 * mintransitduration / (stimes.max() -
stimes.min())
# now figure out the frequencies to use
minfreq = 1.0 / endp
maxfreq = 1.0 / startp
nfreq = int(npceil((maxfreq - minfreq) / stepsize))
# say what we're using
if verbose:
LOGINFO('min P: %s, max P: %s, nfreq: %s, '
'minfreq: %s, maxfreq: %s' %
(startp, endp, nfreq, minfreq, maxfreq))
LOGINFO('autofreq = True: using AUTOMATIC values for '
'freq stepsize: %s, ndurations: %s, '
'min transit duration: %s, max transit duration: %s' %
(stepsize, ndurations, mintransitduration,
maxtransitduration))
use_autoperiod = False
elif isinstance(autofreq, bool) and not autofreq:
minfreq = 1.0 / endp
maxfreq = 1.0 / startp
nfreq = int(npceil((maxfreq - minfreq) / stepsize))
# say what we're using
if verbose:
LOGINFO('min P: %s, max P: %s, nfreq: %s, '
'minfreq: %s, maxfreq: %s' %
(startp, endp, nfreq, minfreq, maxfreq))
LOGINFO('autofreq = False: using PROVIDED values for '
'freq stepsize: %s, ndurations: %s, '
'min transit duration: %s, max transit duration: %s' %
(stepsize, ndurations, mintransitduration,
maxtransitduration))
use_autoperiod = False
elif isinstance(autofreq, str) and autofreq == 'astropy':
use_autoperiod = True
minfreq = 1.0 / endp
maxfreq = 1.0 / startp
else:
LOGERROR("unknown autofreq kwarg encountered. can't continue...")
return None
# check the minimum frequency
if ((minfreq < (1.0 / (stimes.max() - stimes.min())))
and endp_timebase_check):
LOGWARNING('the requested max P = %.3f is larger than '
'the time base of the observations = %.3f, '
' will make minfreq = 2 x 1/timebase' %
(endp, stimes.max() - stimes.min()))
minfreq = 2.0 / (stimes.max() - stimes.min())
LOGWARNING('new minfreq: %s, maxfreq: %s' % (minfreq, maxfreq))
# run BLS
try:
# astropy's BLS requires durations in units of time
durations = nplinspace(mintransitduration * startp,
maxtransitduration * startp, ndurations)
# set up the correct units for the BLS model
if magsarefluxes:
blsmodel = BoxLeastSquares(stimes * u.day,
smags * u.dimensionless_unscaled,
dy=serrs * u.dimensionless_unscaled)
else:
blsmodel = BoxLeastSquares(stimes * u.day,
smags * u.mag,
dy=serrs * u.mag)
# use autoperiod if requested
if use_autoperiod:
periods = nparray(
blsmodel.autoperiod(durations,
minimum_period=startp,
maximum_period=endp,
minimum_n_transit=blsmintransits,
frequency_factor=blsfreqfactor))
nfreq = periods.size
if verbose:
LOGINFO("autofreq = 'astropy', used .autoperiod() with "
"minimum_n_transit = %s, freq_factor = %s "
"to generate the frequency grid" %
(blsmintransits, blsfreqfactor))
LOGINFO(
'stepsize = %.5f, nfreq = %s, minfreq = %.5f, '
'maxfreq = %.5f, ndurations = %s' %
(abs(1.0 / periods[1] - 1.0 / periods[0]), nfreq, 1.0 /
periods.max(), 1.0 / periods.min(), durations.size))
# otherwise, use kbls method
else:
frequencies = minfreq + nparange(nfreq) * stepsize
periods = 1.0 / frequencies
if nfreq > 5.0e5:
if verbose:
LOGWARNING('more than 5.0e5 frequencies to go through; '
'this will take a while. '
'you might want to use the '
'abls.bls_parallel_pfind function instead')
# run the periodogram
blsresult = blsmodel.power(periods * u.day,
durations * u.day,
objective=blsobjective,
method=blsmethod,
oversample=blsoversample)
# get the peak values
lsp = nparray(blsresult.power)
# find the nbestpeaks for the periodogram: 1. sort the lsp array
# by highest value first 2. go down the values until we find
# five values that are separated by at least periodepsilon in
# period
# make sure to get only the finite peaks in the periodogram
# this is needed because BLS may produce infs for some peaks
finitepeakind = npisfinite(lsp)
finlsp = lsp[finitepeakind]
finperiods = periods[finitepeakind]
# make sure that finlsp has finite values before we work on it
try:
bestperiodind = npargmax(finlsp)
except ValueError:
LOGERROR('no finite periodogram values '
'for this mag series, skipping...')
return {
'bestperiod': npnan,
'bestlspval': npnan,
'nbestpeaks': nbestpeaks,
'nbestinds': None,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'durations': None,
'method': 'bls',
'blsresult': None,
'blsmodel': None,
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'ndurations': ndurations,
'blsobjective': blsobjective,
'blsmethod': blsmethod,
'blsoversample': blsoversample,
'blsntransits': blsmintransits,
'blsfreqfactor': blsfreqfactor,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip,
'magsarefluxes': magsarefluxes
}
}
sortedlspind = npargsort(finlsp)[::-1]
sortedlspperiods = finperiods[sortedlspind]
sortedlspvals = finlsp[sortedlspind]
# now get the nbestpeaks
nbestperiods, nbestlspvals, nbestinds, peakcount = ([
finperiods[bestperiodind]
], [finlsp[bestperiodind]], [bestperiodind], 1)
prevperiod = sortedlspperiods[0]
# find the best nbestpeaks in the lsp and their periods
for period, lspval, ind in zip(sortedlspperiods, sortedlspvals,
sortedlspind):
if peakcount == nbestpeaks:
break
perioddiff = abs(period - prevperiod)
bestperiodsdiff = [abs(period - x) for x in nbestperiods]
# print('prevperiod = %s, thisperiod = %s, '
# 'perioddiff = %s, peakcount = %s' %
# (prevperiod, period, perioddiff, peakcount))
# this ensures that this period is different from the last
# period and from all the other existing best periods by
# periodepsilon to make sure we jump to an entire different
# peak in the periodogram
if (perioddiff > (periodepsilon * prevperiod)
and all(x > (periodepsilon * period)
for x in bestperiodsdiff)):
nbestperiods.append(period)
nbestlspvals.append(lspval)
nbestinds.append(ind)
peakcount = peakcount + 1
prevperiod = period
# generate the return dict
resultdict = {
'bestperiod': finperiods[bestperiodind],
'bestlspval': finlsp[bestperiodind],
'nbestpeaks': nbestpeaks,
'nbestinds': nbestinds,
'nbestlspvals': nbestlspvals,
'nbestperiods': nbestperiods,
'lspvals': lsp,
'frequencies': frequencies,
'periods': periods,
'durations': durations,
'blsresult': blsresult,
'blsmodel': blsmodel,
'stepsize': stepsize,
'nfreq': nfreq,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'ndurations': ndurations,
'blsobjective': blsobjective,
'blsmethod': blsmethod,
'blsoversample': blsoversample,
'blsntransits': blsmintransits,
'blsfreqfactor': blsfreqfactor,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip,
'magsarefluxes': magsarefluxes
}
}
return resultdict
except Exception as e:
LOGEXCEPTION('BLS failed!')
if raiseonfail:
raise
return {
'bestperiod': npnan,
'bestlspval': npnan,
'nbestinds': None,
'nbestpeaks': nbestpeaks,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'durations': None,
'blsresult': None,
'blsmodel': None,
'stepsize': stepsize,
'nfreq': nfreq,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'ndurations': ndurations,
'blsobjective': blsobjective,
'blsmethod': blsmethod,
'blsoversample': blsoversample,
'blsntransits': blsmintransits,
'blsfreqfactor': blsfreqfactor,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip,
'magsarefluxes': magsarefluxes
}
}
else:
LOGERROR('no good detections for these times and mags, skipping...')
return {
'bestperiod': npnan,
'bestlspval': npnan,
'nbestinds': None,
'nbestpeaks': nbestpeaks,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'durations': None,
'blsresult': None,
'blsmodel': None,
'stepsize': stepsize,
'nfreq': None,
'nphasebins': None,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'ndurations': ndurations,
'blsobjective': blsobjective,
'blsmethod': blsmethod,
'blsoversample': blsoversample,
'blsntransits': blsmintransits,
'blsfreqfactor': blsfreqfactor,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip,
'magsarefluxes': magsarefluxes
}
}
def find_and_mask_transits(time,
flux,
flux_err,
periods,
durations,
nplanets=1):
"""
Iteratively find and mask transits in the flattened light curve.
Args:
time (array): The time array.
flux (array): The flux array. You'll get the best results
if this is flattened.
flux_err (array): The array of flux uncertainties.
periods (array): The array of periods to search over for BLS.
For example, periods = np.linspace(0.5, 20, 10)
durations (array): The array of durations to search over for BLS.
For example, durations = np.linspace(0.05, 0.2, 10)
nplanets (Optional[int]): The number of planets you'd like to search for.
This function will interatively find and remove nplanets. Default is 1.
Returns:
transit_masks (list): a list of masks that correspond to the in
transit points of each light curve. To mask out transits do
time[~transit_masks[index]], etc.
"""
cum_transit = np.ones(len(time), dtype=bool)
_time, _flux, _flux_err = time * 1, flux * 1, flux_err * 1
t0s, durs, porbs = [np.zeros(nplanets) for i in range(3)]
transit_masks = []
for i in range(nplanets):
bls = BoxLeastSquares(t=_time, y=_flux, dy=_flux_err)
bls.power(periods, durations)
print("periods")
periods = bls.autoperiod(durations,
minimum_n_transit=3,
frequency_factor=5.0)
print("results")
results = bls.autopower(durations, frequency_factor=5.0)
# Find the period of the peak
print("find_period")
period = results.period[np.argmax(results.power)]
print("extract")
# Extract the parameters of the best-fit model
index = np.argmax(results.power)
porbs[i] = results.period[index]
t0s[i] = results.transit_time[index]
durs[i] = results.duration[index]
# # Plot the periodogram
# fig, ax = plt.subplots(1, 1, figsize=(10, 5))
# ax.plot(results.period, results.power, "k", lw=0.5)
# ax.set_xlim(results.period.min(), results.period.max())
# ax.set_xlabel("period [days]")
# ax.set_ylabel("log likelihood")
# # Highlight the harmonics of the peak period
# ax.axvline(period, alpha=0.4, lw=4)
# for n in range(2, 10):
# ax.axvline(n*period, alpha=0.4, lw=1, linestyle="dashed")
# ax.axvline(period / n, alpha=0.4, lw=1, linestyle="dashed")
# plt.show()
# plt.plot(_time, _flux, ".")
# plt.xlim(1355, 1360)
print("mask")
in_transit = bls.transit_mask(_time, porbs[i], 2 * durs[i], t0s[i])
transit_masks.append(in_transit)
_time, _flux, _flux_err = _time[~in_transit], _flux[~in_transit], \
_flux_err[~in_transit]
return transit_masks, t0s, durs, porbs
def validate_transit(self, ticid=None, lc=None, rprs=0.02):
"""Take a closer look at potential transit signals."""
from .plotting import create_starry_model
if ticid is not None:
lc = self.from_eleanor(ticid)[1]
lc = self._clean_data(lc)
elif lc is None:
lc = self.lc
model = BoxLeastSquares(lc.time, lc.flux)
results = model.autopower(0.16)
period = results.period[np.argmax(results.power)]
t0 = results.transit_time[np.argmax(results.power)]
if rprs is None:
depth = results.depth[np.argmax(results.power)]
rprs = depth**2
# create the model
model_flux = create_starry_model(
lc.time, period=period, t0=t0, rprs=rprs) - 1
model_lc = lk.LightCurve(time=lc.time, flux=model_flux)
fig, ax = plt.subplots(3, 1, figsize=(12, 14))
fig.patch.set_facecolor('white')
'''
Plot unfolded transit
---------------------
'''
lc.scatter(ax=ax[0], c='k', label='Corrected Flux')
model_lc.plot(ax=ax[0], c='r', lw=2, label='Transit Model')
ax[0].set_ylim([-.002, .002])
ax[0].set_xlim([lc.time[0], lc.time[-1]])
'''
Plot folded transit
-------------------
'''
lc.fold(period, t0).scatter(ax=ax[1],
c='k',
label=f'P={period:.3f}, t0={t0}')
lc.fold(period, t0).bin(binsize=7).plot(ax=ax[1],
c='b',
label='binned',
lw=2)
model_lc.fold(period, t0).plot(ax=ax[1],
c='r',
lw=2,
label="transit Model")
ax[1].set_xlim([-0.5, .5])
ax[1].set_ylim([-.002, .002])
'''
Zoom folded transit
-------------------
'''
lc.fold(period, t0).scatter(ax=ax[2],
c='k',
label=f'folded at {period:.3f} days')
lc.fold(period, t0).bin(binsize=7).plot(ax=ax[2],
c='b',
label='binned',
lw=2)
model_lc.fold(period, t0).plot(ax=ax[2],
c='r',
lw=2,
label="transit Model")
ax[2].set_xlim([-0.1, .1])
ax[2].set_ylim([-.002, .002])
ax[0].set_title(f'{ticid}', fontsize=14)
plt.show()
#Full lightcurve
plot = figure(plot_height=200,
plot_width=1000,
title='Curva de luz',
x_range=[np.nanmin(t), np.nanmax(t)])
plot.xaxis.axis_label = 'Tiempo (dias)'
plot.yaxis.axis_label = 'Flujo'
plot.circle('t', 'f', source=src, size=1)
#plot.line('t', 'trn', source=ndata, line_width=1, color='lime')
#BLS
print('Calculando período...')
durations = np.linspace(0.05, 0.2, 60)
model = BLS(t, f)
result = model.autopower(durations, frequency_factor=2.0)
idx = np.argmax(result.power)
per = result.period[idx] if args.period is None else args.period
pgram = figure(width=1000,
height=200,
x_range=[0, 20],
title='Periodograma (BLS)')
pgram.xaxis.axis_label = 'Periodo'
pgram.yaxis.axis_label = 'Potencia'
freqs = 1 / np.arange(1 / 30., 1 / 30. + 50000 * 1e-4, 1e-4)
#blsda = ColumnDataSource(data=dict(per=freqs, pow=blsre[0]))
#pgram.line('per', 'pow', source=blsda)
print('Done!')
