def get_frequency_grid(times,
samplesperpeak=5,
nyquistfactor=5,
minfreq=None,
maxfreq=None,
returnf0dfnf=False):
'''This calculates a frequency grid for the period finding functions in this
module.
Based on the autofrequency function in astropy.stats.lombscargle.
http://docs.astropy.org/en/stable/_modules/astropy/stats/lombscargle/core.html#LombScargle.autofrequency
'''
baseline = times.max() - times.min()
nsamples = times.size
df = 1. / baseline / samplesperpeak
if minfreq is not None:
f0 = minfreq
else:
f0 = 0.5 * df
if maxfreq is not None:
Nf = int(npceil((maxfreq - f0) / df))
else:
Nf = int(0.5 * samplesperpeak * nyquistfactor * nsamples)
if returnf0dfnf:
return f0, df, Nf, f0 + df * nparange(Nf)
else:
return f0 + df * nparange(Nf)
def _autocorr_func2(mags, lag, maglen, magmed, magstd):
'''
This is an alternative function to calculate the autocorrelation.
mags MUST be an array with no nans.
lag is the current lag to calculate the autocorr for. MUST be less than the
total number of observations in mags (maglen).
maglen, magmed, magstd are provided by auto_correlation below.
This version is from (first definition):
https://en.wikipedia.org/wiki/Correlogram#Estimation_of_autocorrelations
'''
lagindex = nparange(0, maglen - lag)
products = (mags[lagindex] - magmed) * (mags[lagindex + lag] - magmed)
autocovarfunc = npsum(products) / lagindex.size
varfunc = npsum(
(mags[lagindex] - magmed) * (mags[lagindex] - magmed)) / mags.size
acorr = autocovarfunc / varfunc
return acorr
def wma(close, length=None, asc=None, offset=None, **kwargs):
"""Indicator: Weighted Moving Average (WMA)"""
# Validate Arguments
close = verify_series(close)
length = int(length) if length and length > 0 else 10
min_periods = int(kwargs["min_periods"]) if "min_periods" in kwargs and kwargs["min_periods"] is not None else length
asc = asc if asc else True
offset = get_offset(offset)
# Calculate Result
total_weight = 0.5 * length * (length + 1)
weights_ = Series(nparange(1, length + 1))
weights = weights_ if asc else weights_[::-1]
def linear(w):
def _compute(x):
return npdot(x, w) / total_weight
return _compute
close_ = close.rolling(length, min_periods=length)
wma = close_.apply(linear(weights), raw=True)
# Offset
if offset != 0:
wma = wma.shift(offset)
# Name & Category
wma.name = f"WMA_{length}"
wma.category = "overlap"
return wma
def make_data(n=None, i=None, p=None):
from random import randint
from numpy import log, random as nprandom, arange as nparange, exp as npexp
n = n or randint(10,100)
i = i or randint(1,100)
p = p or randint(1,50) / 100
xx = nparange(1, n + 1)
yy_clean = npexp(xx * p) * i
yy = yy_clean + nprandom.normal(0, log(yy_clean).round() + (yy_clean//10), size=n)
return (xx,yy,yy_clean, n,i,p)
def primes_below(n: int) -> ndarray:
"""
Computes all the primes strictly below the given integer.
:param n: the upper bound of the primes to be computed.
:return: an array containing all the primes strictly below n.
"""
assert isinstance(
n, int), f"n is supposed to be an integer but {n} was given."
primes = nparange(2, n)
for i in range(2, n):
primes[(primes % i == 0) * (primes > i)] = 0
return primes[primes > 0]
def _autocorr_func2(mags, lag, maglen, magmed, magstd):
'''
This is an alternative function to calculate the autocorrelation.
This version is from (first definition):
https://en.wikipedia.org/wiki/Correlogram#Estimation_of_autocorrelations
Parameters
----------
mags : np.array
This is the magnitudes array. MUST NOT have any nans.
lag : float
The specific lag value to calculate the auto-correlation for. This MUST
be less than total number of observations in `mags`.
maglen : int
The number of elements in the `mags` array.
magmed : float
The median of the `mags` array.
magstd : float
The standard deviation of the `mags` array.
Returns
-------
float
The auto-correlation at this specific `lag` value.
'''
lagindex = nparange(0,maglen-lag)
products = (mags[lagindex] - magmed) * (mags[lagindex+lag] - magmed)
autocovarfunc = npsum(products)/lagindex.size
varfunc = npsum(
(mags[lagindex] - magmed)*(mags[lagindex] - magmed)
)/mags.size
acorr = autocovarfunc/varfunc
return acorr
def _autocorr_func1(mags, lag, maglen, magmed, magstd):
'''Calculates the autocorr of mag series for specific lag.
mags MUST be an array with no nans.
lag is the current lag to calculate the autocorr for. MUST be less than the
total number of observations in mags (maglen).
maglen, magmed, magstd are provided by auto_correlation below.
This version of the function taken from:
doi:10.1088/0004-637X/735/2/68 (Kim et al. 2011)
'''
lagindex = nparange(1, maglen - lag)
products = (mags[lagindex] - magmed) * (mags[lagindex + lag] - magmed)
acorr = (1.0 / ((maglen - lag) * magstd)) * npsum(products)
return acorr
def _autocorr_func1(mags, lag, maglen, magmed, magstd):
'''Calculates the autocorr of mag series for specific lag.
This version of the function is taken from: Kim et al. (`2011
<https://dx.doi.org/10.1088/0004-637X/735/2/68>`_)
Parameters
----------
mags : np.array
This is the magnitudes array. MUST NOT have any nans.
lag : float
The specific lag value to calculate the auto-correlation for. This MUST
be less than total number of observations in `mags`.
maglen : int
The number of elements in the `mags` array.
magmed : float
The median of the `mags` array.
magstd : float
The standard deviation of the `mags` array.
Returns
-------
float
The auto-correlation at this specific `lag` value.
'''
lagindex = nparange(1, maglen - lag)
products = (mags[lagindex] - magmed) * (mags[lagindex + lag] - magmed)
acorr = (1.0 / ((maglen - lag) * magstd)) * npsum(products)
return acorr
def macf_period_find(
times,
mags,
errs,
fillgaps=0.0,
filterwindow=11,
forcetimebin=None,
maxlags=None,
maxacfpeaks=10,
smoothacf=21, # set for Kepler-type LCs, see details below
smoothfunc=_smooth_acf_savgol,
smoothfunckwargs=None,
magsarefluxes=False,
sigclip=3.0,
verbose=True,
periodepsilon=0.1, # doesn't do anything, for consistent external API
nworkers=None, # doesn't do anything, for consistent external API
startp=None, # doesn't do anything, for consistent external API
endp=None, # doesn't do anything, for consistent external API
autofreq=None, # doesn't do anything, for consistent external API
stepsize=None, # doesn't do anything, for consistent external API
):
'''This finds periods using the McQuillan+ (2013a, 2014) ACF method.
The kwargs from `periodepsilon` to `stepsize` don't do anything but are used
to present a consistent API for all periodbase period-finders to an outside
driver (e.g. the one in the checkplotserver).
Parameters
----------
times,mags,errs : np.array
The input magnitude/flux time-series to run the period-finding for.
fillgaps : 'noiselevel' or float
This sets what to use to fill in gaps in the time series. If this is
'noiselevel', will smooth the light curve using a point window size of
`filterwindow` (this should be an odd integer), subtract the smoothed LC
from the actual LC and estimate the RMS. This RMS will be used to fill
in the gaps. Other useful values here are 0.0, and npnan.
filterwindow : int
The light curve's smoothing filter window size to use if
`fillgaps='noiselevel`'.
forcetimebin : None or float
This is used to force a particular cadence in the light curve other than
the automatically determined cadence. This effectively rebins the light
curve to this cadence. This should be in the same time units as `times`.
maxlags : None or int
This is the maximum number of lags to calculate. If None, will calculate
all lags.
maxacfpeaks : int
This is the maximum number of ACF peaks to use when finding the highest
peak and obtaining a fit period.
smoothacf : int
This is the number of points to use as the window size when smoothing
the ACF with the `smoothfunc`. This should be an odd integer value. If
this is None, will not smooth the ACF, but this will probably lead to
finding spurious peaks in a generally noisy ACF.
For Kepler, a value between 21 and 51 seems to work fine. For ground
based data, much larger values may be necessary: between 1001 and 2001
seem to work best for the HAT surveys. This is dependent on cadence, RMS
of the light curve, the periods of the objects you're looking for, and
finally, any correlated noise in the light curve. Make a plot of the
smoothed/unsmoothed ACF vs. lag using the result dict of this function
and the `plot_acf_results` function above to see the identified ACF
peaks and what kind of smoothing might be needed.
The value of `smoothacf` will also be used to figure out the interval to
use when searching for local peaks in the ACF: this interval is 1/2 of
the `smoothacf` value.
smoothfunc : Python function
This is the function that will be used to smooth the ACF. This should
take at least one kwarg: 'windowsize'. Other kwargs can be passed in
using a dict provided in `smoothfunckwargs`. By default, this uses a
Savitsky-Golay filter, a Gaussian filter is also provided but not
used. Another good option would be an actual low-pass filter (generated
using scipy.signal?) to remove all high frequency noise from the ACF.
smoothfunckwargs : dict or None
The dict of optional kwargs to pass in to the `smoothfunc`.
magsarefluxes : bool
If your input measurements in `mags` are actually fluxes instead of
mags, set this is True.
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.
verbose : bool
If True, will indicate progress and report errors.
Returns
-------
dict
Returns a dict with results. dict['bestperiod'] is the estimated best
period and dict['fitperiodrms'] is its estimated error. Other
interesting things in the output include:
- dict['acfresults']: all results from calculating the ACF. in
particular, the unsmoothed ACF might be of interest:
dict['acfresults']['acf'] and dict['acfresults']['lags'].
- dict['lags'] and dict['acf'] contain the ACF after smoothing was
applied.
- dict['periods'] and dict['lspvals'] can be used to construct a
pseudo-periodogram.
- dict['naivebestperiod'] is obtained by multiplying the lag at the
highest ACF peak with the cadence. This is usually close to the fit
period (dict['fitbestperiod']), which is calculated by doing a fit to
the lags vs. peak index relation as in McQuillan+ 2014.
'''
# get the ACF
acfres = autocorr_magseries(times,
mags,
errs,
maxlags=maxlags,
fillgaps=fillgaps,
forcetimebin=forcetimebin,
sigclip=sigclip,
magsarefluxes=magsarefluxes,
filterwindow=filterwindow,
verbose=verbose)
xlags = acfres['lags']
# smooth the ACF if requested
if smoothacf and isinstance(smoothacf, int) and smoothacf > 0:
if smoothfunckwargs is None:
sfkwargs = {'windowsize': smoothacf}
else:
sfkwargs = smoothfunckwargs.copy()
sfkwargs.update({'windowsize': smoothacf})
xacf = smoothfunc(acfres['acf'], **sfkwargs)
else:
xacf = acfres['acf']
# get the relative peak heights and fit best lag
peakres = _get_acf_peakheights(xlags,
xacf,
npeaks=maxacfpeaks,
searchinterval=int(smoothacf / 2))
# this is the best period's best ACF peak height
bestlspval = peakres['bestpeakheight']
try:
# get the fit best lag from a linear fit to the peak index vs time(peak
# lag) function as in McQillian+ (2014)
fity = npconcatenate(([
0.0, peakres['bestlag']
], peakres['relpeaklags'][peakres['relpeaklags'] > peakres['bestlag']]
))
fity = fity * acfres['cadence']
fitx = nparange(fity.size)
fitcoeffs, fitcovar = nppolyfit(fitx, fity, 1, cov=True)
# fit best period is the gradient of fit
fitbestperiod = fitcoeffs[0]
bestperiodrms = npsqrt(fitcovar[0, 0]) # from the covariance matrix
except Exception as e:
LOGWARNING('linear fit to time at each peak lag '
'value vs. peak number failed, '
'naively calculated ACF period may not be accurate')
fitcoeffs = nparray([npnan, npnan])
fitcovar = nparray([[npnan, npnan], [npnan, npnan]])
fitbestperiod = npnan
bestperiodrms = npnan
raise
# calculate the naive best period using delta_tau = lag * cadence
naivebestperiod = peakres['bestlag'] * acfres['cadence']
if fitbestperiod < naivebestperiod:
LOGWARNING('fit bestperiod = %.5f may be an alias, '
'naively calculated bestperiod is = %.5f' %
(fitbestperiod, naivebestperiod))
if npisfinite(fitbestperiod):
bestperiod = fitbestperiod
else:
bestperiod = naivebestperiod
return {
'bestperiod':
bestperiod,
'bestlspval':
bestlspval,
'nbestpeaks':
maxacfpeaks,
# for compliance with the common pfmethod API
'nbestperiods':
npconcatenate([[fitbestperiod], peakres['relpeaklags'][1:maxacfpeaks] *
acfres['cadence']]),
'nbestlspvals':
peakres['maxacfs'][:maxacfpeaks],
'lspvals':
xacf,
'periods':
xlags * acfres['cadence'],
'acf':
xacf,
'lags':
xlags,
'method':
'acf',
'naivebestperiod':
naivebestperiod,
'fitbestperiod':
fitbestperiod,
'fitperiodrms':
bestperiodrms,
'periodfitcoeffs':
fitcoeffs,
'periodfitcovar':
fitcovar,
'kwargs': {
'maxlags': maxlags,
'maxacfpeaks': maxacfpeaks,
'fillgaps': fillgaps,
'filterwindow': filterwindow,
'smoothacf': smoothacf,
'smoothfunckwargs': sfkwargs,
'magsarefluxes': magsarefluxes,
'sigclip': sigclip
},
'acfresults':
acfres,
'acfpeaks':
peakres
}
def aov_theta(times, mags, errs, frequency,
binsize=0.05, minbin=9):
'''Calculates the Schwarzenberg-Czerny AoV statistic at a test frequency.
Parameters
----------
times,mags,errs : np.array
The input time-series and associated errors.
frequency : float
The test frequency to calculate the theta statistic at.
binsize : float
The phase bin size to use.
minbin : int
The minimum number of items in a phase bin to consider in the
calculation of the statistic.
Returns
-------
theta_aov : float
The value of the AoV statistic at the specified `frequency`.
'''
period = 1.0/frequency
fold_time = times[0]
phased = phase_magseries(times,
mags,
period,
fold_time,
wrap=False,
sort=True)
phases = phased['phase']
pmags = phased['mags']
bins = nparange(0.0, 1.0, binsize)
ndets = phases.size
binnedphaseinds = npdigitize(phases, bins)
bin_s1_tops = []
bin_s2_tops = []
binndets = []
goodbins = 0
all_xbar = npmedian(pmags)
for x in npunique(binnedphaseinds):
thisbin_inds = binnedphaseinds == x
thisbin_mags = pmags[thisbin_inds]
if thisbin_mags.size > minbin:
thisbin_ndet = thisbin_mags.size
thisbin_xbar = npmedian(thisbin_mags)
# get s1
thisbin_s1_top = (
thisbin_ndet *
(thisbin_xbar - all_xbar) *
(thisbin_xbar - all_xbar)
)
# get s2
thisbin_s2_top = npsum((thisbin_mags - all_xbar) *
(thisbin_mags - all_xbar))
bin_s1_tops.append(thisbin_s1_top)
bin_s2_tops.append(thisbin_s2_top)
binndets.append(thisbin_ndet)
goodbins = goodbins + 1
# turn the quantities into arrays
bin_s1_tops = nparray(bin_s1_tops)
bin_s2_tops = nparray(bin_s2_tops)
binndets = nparray(binndets)
# calculate s1 first
s1 = npsum(bin_s1_tops)/(goodbins - 1.0)
# then calculate s2
s2 = npsum(bin_s2_tops)/(ndets - goodbins)
theta_aov = s1/s2
return theta_aov
def analytic_false_alarm_probability(lspinfo,
times,
conservative_nfreq_eff=True,
peakvals=None,
inplace=True):
'''This returns the analytic false alarm probabilities for periodogram
peak values.
FIXME: this doesn't actually work. Fix later.
The calculation follows that on page 3 of Zechmeister & Kurster (2009)::
FAP = 1 − [1 − Prob(z > z0)]**M
where::
M is the number of independent frequencies
Prob(z > z0) is the probability of peak with value > z0
z0 is the peak value we're evaluating
For AoV and AoV-harmonic, the Prob(z > z0) is described by the F
distribution, according to:
- Schwarzenberg-Czerny (1997;
https://ui.adsabs.harvard.edu/#abs/1997ApJ...489..941S)
This is given by::
F( (B-1), (N-B); theta_aov )
Where::
N = number of observations
B = number of phase bins
This translates to a scipy.stats call to the F distribution CDF::
x = theta_aov_best
prob_exceeds_val = scipy.stats.f.cdf(x, (B-1.0), (N-B))
Which we can then plug into the false alarm prob eqn above with the
calculation of M.
Parameters
----------
lspinfo : dict
The dict returned by the
:py:func:`~astrobase.periodbase.spdm.aov_periodfind` function.
times : np.array
The times for which the periodogram result in ``lspinfo`` was
calculated.
conservative_nfreq_eff : bool
If True, will follow the prescription given in Schwarzenberg-Czerny
(2003):
http://adsabs.harvard.edu/abs/2003ASPC..292..383S
and estimate the effective number of independent frequences M_eff as::
min(N_obs, N_freq, DELTA_f/delta_f)
peakvals : sequence or None
The peak values for which to evaluate the false-alarm probability. If
None, will calculate this for each of the peak values in the
``nbestpeaks`` key of the ``lspinfo`` dict.
inplace : bool
If True, puts the results of the FAP calculation into the ``lspinfo``
dict as a list available as ``lspinfo['falsealarmprob']``.
Returns
-------
list
The calculated false alarm probabilities for each of the peak values in
``peakvals``.
'''
from scipy.stats import f
frequencies = 1.0/lspinfo['periods']
M = independent_freq_count(frequencies,
times,
conservative=conservative_nfreq_eff)
if peakvals is None:
peakvals = lspinfo['nbestlspvals']
nphasebins = nparange(0.0, 1.0, lspinfo['kwargs']['phasebinsize']).size
ndet = times.size
false_alarm_probs = []
for peakval in peakvals:
prob_xval = peakval
prob_exceeds_val = f.cdf(prob_xval,
nphasebins - 1.0,
ndet - nphasebins)
false_alarm_probs.append(1.0 - (1.0 - prob_exceeds_val)**M)
if inplace:
lspinfo['falsealarmprob'] = false_alarm_probs
return false_alarm_probs
def aov_periodfind(times,
mags,
errs,
magsarefluxes=False,
startp=None,
endp=None,
stepsize=1.0e-4,
autofreq=True,
normalize=True,
phasebinsize=0.05,
mindetperbin=9,
nbestpeaks=5,
periodepsilon=0.1,
sigclip=10.0,
nworkers=None,
verbose=True):
'''This runs a parallelized Analysis-of-Variance (AoV) period search.
NOTE: `normalize = True` here as recommended by Schwarzenberg-Czerny 1996,
i.e. mags will be normalized to zero and rescaled so their variance = 1.0.
Parameters
----------
times,mags,errs : np.array
The mag/flux time-series with associated measurement errors to run the
period-finding on.
magsarefluxes : bool
If the input measurement values in `mags` and `errs` are in fluxes, set
this to True.
startp,endp : float or None
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.
autofreq : bool
If this is True, the value of `stepsize` will be ignored and the
:py:func:`astrobase.periodbase.get_frequency_grid` function will be used
to generate a frequency grid based on `startp`, and `endp`. If these are
None as well, `startp` will be set to 0.1 and `endp` will be set to
`times.max() - times.min()`.
normalize : bool
This sets if the input time-series is normalized to 0.0 and rescaled
such that its variance = 1.0. This is the recommended procedure by
Schwarzenberg-Czerny 1996.
phasebinsize : float
The bin size in phase to use when calculating the AoV theta statistic at
a test frequency.
mindetperbin : int
The minimum number of elements in a phase bin to consider it valid when
calculating the AoV theta statistic at a test frequency.
nbestpeaks : int
The number of 'best' peaks to return from the periodogram results,
starting from the global maximum of the periodogram peak values.
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.
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.
nworkers : int
The number of parallel workers to use when calculating the periodogram.
verbose : bool
If this is True, will indicate progress and details about the frequency
grid used for the period search.
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,
'periods': the full array of periods considered,
'method':'aov' -> 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:
# get the frequencies to use
if startp:
endf = 1.0/startp
else:
# default start period is 0.1 day
endf = 1.0/0.1
if endp:
startf = 1.0/endp
else:
# default end period is length of time series
startf = 1.0/(stimes.max() - stimes.min())
# if we're not using autofreq, then use the provided frequencies
if not autofreq:
frequencies = nparange(startf, endf, stepsize)
if verbose:
LOGINFO(
'using %s frequency points, start P = %.3f, end P = %.3f' %
(frequencies.size, 1.0/endf, 1.0/startf)
)
else:
# this gets an automatic grid of frequencies to use
frequencies = get_frequency_grid(stimes,
minfreq=startf,
maxfreq=endf)
if verbose:
LOGINFO(
'using autofreq with %s frequency points, '
'start P = %.3f, end P = %.3f' %
(frequencies.size,
1.0/frequencies.max(),
1.0/frequencies.min())
)
# map to parallel workers
if (not nworkers) or (nworkers > NCPUS):
nworkers = NCPUS
if verbose:
LOGINFO('using %s workers...' % nworkers)
pool = Pool(nworkers)
# renormalize the working mags to zero and scale them so that the
# variance = 1 for use with our LSP functions
if normalize:
nmags = (smags - npmedian(smags))/npstd(smags)
else:
nmags = smags
tasks = [(stimes, nmags, serrs, x, phasebinsize, mindetperbin)
for x in frequencies]
lsp = pool.map(_aov_worker, tasks)
pool.close()
pool.join()
del pool
lsp = nparray(lsp)
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 filter out non-finite values
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,
'nbestlspvals':None,
'nbestperiods':None,
'lspvals':None,
'periods':None,
'method':'aov',
'kwargs':{'startp':startp,
'endp':endp,
'stepsize':stepsize,
'normalize':normalize,
'phasebinsize':phasebinsize,
'mindetperbin':mindetperbin,
'autofreq':autofreq,
'periodepsilon':periodepsilon,
'nbestpeaks':nbestpeaks,
'sigclip':sigclip}}
sortedlspind = npargsort(finlsp)[::-1]
sortedlspperiods = finperiods[sortedlspind]
sortedlspvals = finlsp[sortedlspind]
# now get the nbestpeaks
nbestperiods, nbestlspvals, peakcount = (
[finperiods[bestperiodind]],
[finlsp[bestperiodind]],
1
)
prevperiod = sortedlspperiods[0]
# find the best nbestpeaks in the lsp and their periods
for period, lspval in zip(sortedlspperiods, sortedlspvals):
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)
peakcount = peakcount + 1
prevperiod = period
return {'bestperiod':finperiods[bestperiodind],
'bestlspval':finlsp[bestperiodind],
'nbestpeaks':nbestpeaks,
'nbestlspvals':nbestlspvals,
'nbestperiods':nbestperiods,
'lspvals':lsp,
'periods':periods,
'method':'aov',
'kwargs':{'startp':startp,
'endp':endp,
'stepsize':stepsize,
'normalize':normalize,
'phasebinsize':phasebinsize,
'mindetperbin':mindetperbin,
'autofreq':autofreq,
'periodepsilon':periodepsilon,
'nbestpeaks':nbestpeaks,
'sigclip':sigclip}}
else:
LOGERROR('no good detections for these times and mags, skipping...')
return {'bestperiod':npnan,
'bestlspval':npnan,
'nbestpeaks':nbestpeaks,
'nbestlspvals':None,
'nbestperiods':None,
'lspvals':None,
'periods':None,
'method':'aov',
'kwargs':{'startp':startp,
'endp':endp,
'stepsize':stepsize,
'normalize':normalize,
'phasebinsize':phasebinsize,
'mindetperbin':mindetperbin,
'autofreq':autofreq,
'periodepsilon':periodepsilon,
'nbestpeaks':nbestpeaks,
'sigclip':sigclip}}
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=0.8, # maximum transit length in phase
nphasebins=200,
autofreq=True, # figure out f0, nf, and df automatically
nbestpeaks=5,
periodepsilon=0.1, # 0.1
nworkers=None,
sigclip=10.0,
verbose=True):
'''Runs the Box Least Squares Fitting Search for transit-shaped signals.
Based on eebls.f from Kovacs et al. 2002 and python-bls from Foreman-Mackey
et al. 2015. Breaks up the full frequency space into chunks and passes them
to parallel BLS 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.
'''
# 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 autofreq:
# figure out the best number of phasebins to use
nphasebins = int(np.ceil(2.0 / mintransitduration))
# 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(np.ceil((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, nphasebins: %s, '
'min transit duration: %s, max transit duration: %s' %
(stepsize, nphasebins, mintransitduration,
maxtransitduration))
else:
minfreq = 1.0 / endp
maxfreq = 1.0 / startp
nfreq = int(np.ceil((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, nphasebins: %s, '
'min transit duration: %s, max transit duration: %s' %
(stepsize, nphasebins, mintransitduration,
maxtransitduration))
# check the minimum frequency
if minfreq < (1.0 / (stimes.max() - stimes.min())):
minfreq = 2.0 / (stimes.max() - stimes.min())
if verbose:
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()))
LOGINFO('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)
# break up the tasks into chunks
frequencies = minfreq + nparange(nfreq) * stepsize
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)
# chunk_minfreqs = [frequencies[x*chunksize] for x in range(nworkers)]
# chunk_nfreqs = [frequencies[x*chunksize:x*chunksize+chunksize].size
# for x in range(nworkers)]
# populate the tasks list
tasks = [(stimes, smags, chunk_minf, chunk_nf, stepsize, nphasebins,
mintransitduration, maxtransitduration)
for (chunk_nf,
chunk_minf) in zip(chunk_minfreqs, chunk_nfreqs)]
if verbose:
for ind, task in enumerate(tasks):
LOGINFO('worker %s: minfreq = %.6f, nfreqs = %s' %
(ind + 1, task[3], task[2]))
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 = np.concatenate([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,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'nphasebins': nphasebins,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip
}
}
sortedlspind = np.argsort(finlsp)[::-1]
sortedlspperiods = finperiods[sortedlspind]
sortedlspvals = finlsp[sortedlspind]
prevbestlspval = sortedlspvals[0]
# now get the nbestpeaks
nbestperiods, nbestlspvals, peakcount = ([finperiods[bestperiodind]],
[finlsp[bestperiodind]], 1)
prevperiod = sortedlspperiods[0]
# find the best nbestpeaks in the lsp and their periods
for period, lspval in zip(sortedlspperiods, sortedlspvals):
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 * prevperiod)
for x in bestperiodsdiff)):
nbestperiods.append(period)
nbestlspvals.append(lspval)
peakcount = peakcount + 1
prevperiod = period
# generate the return dict
resultdict = {
'bestperiod': finperiods[bestperiodind],
'bestlspval': finlsp[bestperiodind],
'nbestpeaks': nbestpeaks,
'nbestlspvals': nbestlspvals,
'nbestperiods': nbestperiods,
'lspvals': lsp,
'frequencies': frequencies,
'periods': periods,
'blsresult': results,
'stepsize': stepsize,
'nfreq': nfreq,
'nphasebins': nphasebins,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'nphasebins': nphasebins,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip
}
}
return resultdict
else:
LOGERROR('no good detections for these times and mags, skipping...')
return {
'bestperiod': npnan,
'bestlspval': npnan,
'nbestpeaks': nbestpeaks,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'blsresult': None,
'stepsize': stepsize,
'nfreq': None,
'nphasebins': None,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'nphasebins': nphasebins,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip
}
}
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=0.8, # maximum transit length in phase
nphasebins=200,
autofreq=True, # figure out f0, nf, and df automatically
periodepsilon=0.1,
nbestpeaks=5,
sigclip=10.0,
verbose=True):
'''Runs the Box Least Squares Fitting Search for transit-shaped signals.
Based on eebls.f from Kovacs et al. 2002 and python-bls from Foreman-Mackey
et al. 2015. This is the serial version (which is good enough in most cases
because BLS in Fortran is fairly fast). If nfreq > 5e5, this will take a
while.
'''
# 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 autofreq:
# figure out the best number of phasebins to use
nphasebins = int(np.ceil(2.0 / mintransitduration))
# 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(np.ceil((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, nphasebins: %s, '
'min transit duration: %s, max transit duration: %s' %
(stepsize, nphasebins, mintransitduration,
maxtransitduration))
else:
minfreq = 1.0 / endp
maxfreq = 1.0 / startp
nfreq = int(np.ceil((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, nphasebins: %s, '
'min transit duration: %s, max transit duration: %s' %
(stepsize, nphasebins, mintransitduration,
maxtransitduration))
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 '
'periodbase.bls_parallel_pfind function instead')
if minfreq < (1.0 / (stimes.max() - stimes.min())):
if verbose:
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())
if verbose:
LOGINFO('new minfreq: %s, maxfreq: %s' % (minfreq, maxfreq))
# run BLS
try:
blsresult = _bls_runner(stimes, smags, nfreq, minfreq, stepsize,
nphasebins, mintransitduration,
maxtransitduration)
# find the peaks in the BLS. this uses wavelet transforms to
# smooth the spectrum and find peaks. a similar thing would be
# to do a convolution with a gaussian kernel or a tophat
# function, calculate d/dx(result), then get indices where this
# is zero
# blspeakinds = find_peaks_cwt(blsresults['power'],
# nparray([2.0,3.0,4.0,5.0]))
frequencies = minfreq + nparange(nfreq) * stepsize
periods = 1.0 / frequencies
lsp = 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,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'nphasebins': nphasebins,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip
}
}
sortedlspind = np.argsort(finlsp)[::-1]
sortedlspperiods = finperiods[sortedlspind]
sortedlspvals = finlsp[sortedlspind]
prevbestlspval = sortedlspvals[0]
# now get the nbestpeaks
nbestperiods, nbestlspvals, peakcount = ([
finperiods[bestperiodind]
], [finlsp[bestperiodind]], 1)
prevperiod = sortedlspperiods[0]
# find the best nbestpeaks in the lsp and their periods
for period, lspval in zip(sortedlspperiods, sortedlspvals):
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 * prevperiod)
for x in bestperiodsdiff)):
nbestperiods.append(period)
nbestlspvals.append(lspval)
peakcount = peakcount + 1
prevperiod = period
# generate the return dict
resultdict = {
'bestperiod': finperiods[bestperiodind],
'bestlspval': finlsp[bestperiodind],
'nbestpeaks': nbestpeaks,
'nbestlspvals': nbestlspvals,
'nbestperiods': nbestperiods,
'lspvals': lsp,
'frequencies': frequencies,
'periods': periods,
'blsresult': blsresult,
'stepsize': stepsize,
'nfreq': nfreq,
'nphasebins': nphasebins,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'nphasebins': nphasebins,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip
}
}
return resultdict
except Exception as e:
LOGEXCEPTION('BLS failed!')
return {
'bestperiod': npnan,
'bestlspval': npnan,
'nbestpeaks': nbestpeaks,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'stepsize': stepsize,
'nfreq': nfreq,
'nphasebins': nphasebins,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'nphasebins': nphasebins,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip
}
}
else:
LOGERROR('no good detections for these times and mags, skipping...')
return {
'bestperiod': npnan,
'bestlspval': npnan,
'nbestpeaks': nbestpeaks,
'nbestlspvals': None,
'nbestperiods': None,
'lspvals': None,
'periods': None,
'stepsize': stepsize,
'nfreq': None,
'nphasebins': None,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'method': 'bls',
'kwargs': {
'startp': startp,
'endp': endp,
'stepsize': stepsize,
'mintransitduration': mintransitduration,
'maxtransitduration': maxtransitduration,
'nphasebins': nphasebins,
'autofreq': autofreq,
'periodepsilon': periodepsilon,
'nbestpeaks': nbestpeaks,
'sigclip': sigclip
}
}
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 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 _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 autocorr_magseries(times,
mags,
errs,
maxlags=1000,
func=_autocorr_func3,
fillgaps=0.0,
forcetimebin=None,
sigclip=3.0,
magsarefluxes=False,
filterwindow=11,
verbose=True):
'''This calculates the ACF of a light curve.
This will pre-process the light curve to fill in all the gaps and normalize
everything to zero. If fillgaps == 'noiselevel', fills the gaps with the
noise level obtained via the procedure above. If fillgaps == 'nan', fills
the gaps with np.nan.
'''
# get the gap-filled timeseries
interpolated = fill_magseries_gaps(times,
mags,
errs,
fillgaps=fillgaps,
forcetimebin=forcetimebin,
sigclip=sigclip,
magsarefluxes=magsarefluxes,
filterwindow=filterwindow,
verbose=verbose)
if not interpolated:
LOGERROR('failed to interpolate light curve to minimum cadence!')
return None
itimes, imags, ierrs = (interpolated['itimes'], interpolated['imags'],
interpolated['ierrs'])
# calculate the lags up to maxlags
if maxlags:
lags = nparange(0, maxlags)
else:
lags = nparange(itimes.size)
series_stdev = 1.483 * npmedian(npabs(imags))
if func != _autocorr_func3:
# get the autocorrelation as a function of the lag of the mag series
autocorr = nparray(
[func(imags, x, imags.size, 0.0, series_stdev) for x in lags])
# this doesn't need a lags array
else:
autocorr = _autocorr_func3(imags, lags[0], imags.size, 0.0,
series_stdev)
interpolated.update({
'minitime': itimes.min(),
'lags': lags,
'acf': autocorr
})
return interpolated
def autocorr_magseries(times,
mags,
errs,
maxlags=1000,
func=_autocorr_func3,
fillgaps=0.0,
filterwindow=11,
forcetimebin=None,
sigclip=3.0,
magsarefluxes=False,
verbose=True):
'''This calculates the ACF of a light curve.
This will pre-process the light curve to fill in all the gaps and normalize
everything to zero. If `fillgaps = 'noiselevel'`, fills the gaps with the
noise level obtained via the procedure above. If `fillgaps = 'nan'`, fills
the gaps with `np.nan`.
Parameters
----------
times,mags,errs : np.array
The measurement time-series and associated errors.
maxlags : int
The maximum number of lags to calculate.
func : Python function
This is a function to calculate the lags.
fillgaps : 'noiselevel' or float
This sets what to use to fill in gaps in the time series. If this is
'noiselevel', will smooth the light curve using a point window size of
`filterwindow` (this should be an odd integer), subtract the smoothed LC
from the actual LC and estimate the RMS. This RMS will be used to fill
in the gaps. Other useful values here are 0.0, and npnan.
filterwindow : int
The light curve's smoothing filter window size to use if
`fillgaps='noiselevel`'.
forcetimebin : None or float
This is used to force a particular cadence in the light curve other than
the automatically determined cadence. This effectively rebins the light
curve to this cadence. This should be in the same time units as `times`.
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.
magsarefluxes : bool
If your input measurements in `mags` are actually fluxes instead of
mags, set this is True.
verbose : bool
If True, will indicate progress and report errors.
Returns
-------
dict
A dict of the following form is returned::
{'itimes': the interpolated time values after gap-filling,
'imags': the interpolated mag/flux values after gap-filling,
'ierrs': the interpolated mag/flux values after gap-filling,
'cadence': the cadence of the output mag/flux time-series,
'minitime': the minimum value of the interpolated times array,
'lags': the lags used to calculate the auto-correlation function,
'acf': the value of the ACF at each lag used}
'''
# get the gap-filled timeseries
interpolated = fill_magseries_gaps(times,
mags,
errs,
fillgaps=fillgaps,
forcetimebin=forcetimebin,
sigclip=sigclip,
magsarefluxes=magsarefluxes,
filterwindow=filterwindow,
verbose=verbose)
if not interpolated:
print('failed to interpolate light curve to minimum cadence!')
return None
itimes, imags = interpolated['itimes'], interpolated['imags'],
# calculate the lags up to maxlags
if maxlags:
lags = nparange(0, maxlags)
else:
lags = nparange(itimes.size)
series_stdev = 1.483 * npmedian(npabs(imags))
if func != _autocorr_func3:
# get the autocorrelation as a function of the lag of the mag series
autocorr = nparray(
[func(imags, x, imags.size, 0.0, series_stdev) for x in lags])
# this doesn't need a lags array
else:
autocorr = _autocorr_func3(imags, lags[0], imags.size, 0.0,
series_stdev)
# return only the maximum number of lags
if maxlags is not None:
autocorr = autocorr[:maxlags]
interpolated.update({
'minitime': itimes.min(),
'lags': lags,
'acf': autocorr
})
return interpolated
def stellingwerf_pdm_theta(times,
mags,
errs,
frequency,
binsize=0.05,
minbin=9):
'''
This calculates the Stellingwerf PDM theta value at a test frequency.
Parameters
----------
times,mags,errs : np.array
The input time-series and associated errors.
frequency : float
The test frequency to calculate the theta statistic at.
binsize : float
The phase bin size to use.
minbin : int
The minimum number of items in a phase bin to consider in the
calculation of the statistic.
Returns
-------
theta_pdm : float
The value of the theta statistic at the specified `frequency`.
'''
period = 1.0 / frequency
fold_time = times[0]
phased = phase_magseries(times,
mags,
period,
fold_time,
wrap=False,
sort=True)
phases = phased['phase']
pmags = phased['mags']
bins = nparange(0.0, 1.0, binsize)
binnedphaseinds = npdigitize(phases, bins)
binvariances = []
binndets = []
goodbins = 0
for x in npunique(binnedphaseinds):
thisbin_inds = binnedphaseinds == x
thisbin_mags = pmags[thisbin_inds]
if thisbin_mags.size > minbin:
thisbin_variance = npvar(thisbin_mags, ddof=1)
binvariances.append(thisbin_variance)
binndets.append(thisbin_mags.size)
goodbins = goodbins + 1
# now calculate theta
binvariances = nparray(binvariances)
binndets = nparray(binndets)
theta_top = npsum(binvariances *
(binndets - 1)) / (npsum(binndets) - goodbins)
theta_bot = npvar(pmags, ddof=1)
theta = theta_top / theta_bot
return theta
