def search_extended_timing_solutions(timing_files, timestamp):
# Load the timing correction
nfiles = len(timing_files)
tstart = np.zeros(nfiles, dtype=np.float32)
tstop = np.zeros(nfiles, dtype=np.float32)
all_tcorr = []
for ff, filename in enumerate(timing_files):
kwargs = {}
with h5py.File(filename, 'r') as handler:
for key in ['tau', 'avg_phase', 'noise_source', 'time']:
kwargs[key] = handler[key][:]
tcorr = timing.TimingCorrection(**kwargs)
all_tcorr.append(tcorr)
tstart[ff] = tcorr.time[0]
tstop[ff] = tcorr.time[-1]
# Map timestamp to a timing correction object
imatch = np.flatnonzero((timestamp >= tstart) & (timestamp <= tstop))
if imatch.size > 1:
ValueError("Timing corrections overlap!")
elif imatch.size < 1:
ValueError("No timing correction for transit on %s (CSD %d)" %
(ephemeris.unix_to_datetime(timestamp).strftime("%Y-%m-%d"),
ephemeris.unix_to_csd(timestamp)))
return all_tcorr[imatch[0]]
def _flags_mask(self, index_map_ra):
if self._cache_flags:
flag_time_spans = get_flags_cached(self.flags,
self._cache_reset_time)
else:
flag_time_spans = get_flags(
self.flags,
csd_to_unix(self.lsd.lsd),
csd_to_unix(self.lsd.lsd + 1),
)
csd_arr = self.lsd.lsd + index_map_ra / 360.0
flag_mask = np.zeros_like(csd_arr, dtype=np.bool)
for type_, ca, cb in flag_time_spans:
flag_mask[(csd_arr > unix_to_csd(ca))
& (csd_arr < unix_to_csd(cb))] = True
return flag_mask[:, np.newaxis]
def csds_in_range(start, end, step=1):
"""Get the CSDs within a time range.
The start and end parameters must either be strings of the form "CSD\d+"
(i.e. CSD followed by an int), which specifies an exact CSD start, or a
form that `ephemeris.ensure_unix` understands.
Parameters
----------
start : str or parseable to datetime
Start of interval.
end : str or parseable to datetime
End of interval. If `None` use now. Note that for CSD intervals the
end is *inclusive* (unlike a `range`).
Returns
-------
csds : list of ints
"""
if end is None:
end = datetime.datetime.utcnow()
if start.startswith("CSD"):
start_csd = int(start[3:])
else:
start_csd = ephemeris.unix_to_csd(ephemeris.ensure_unix(start))
start_csd = math.floor(start_csd)
if end.startswith("CSD"):
end_csd = int(end[3:])
else:
end_csd = ephemeris.unix_to_csd(ephemeris.ensure_unix(end))
end_csd = math.ceil(end_csd)
csds = [day for day in range(start_csd, end_csd + 1, step)]
return csds
def from_date(cls, date: datetime.date):
unix = time.mktime(date.timetuple())
lsd = int(unix_to_csd(unix))
day = cls(lsd, date)
return day
def offline_point_source_calibration(file_list,
source,
inputmap=None,
start=None,
stop=None,
physical_freq=None,
tcorr=None,
logging_params=DEFAULT_LOGGING,
**kwargs):
# Load config
config = DEFAULTS.deepcopy()
config.merge(NameSpace(kwargs))
# Setup logging
log.setup_logging(logging_params)
mlog = log.get_logger(__name__)
mlog.info("ephemeris file: %s" % ephemeris.__file__)
# Set the model to use
fitter_function = utils.fit_point_source_transit
model_function = utils.model_point_source_transit
farg = inspect.getargspec(fitter_function)
defaults = {
key: val
for key, val in zip(farg.args[-len(farg.defaults):], farg.defaults)
}
poly_deg_amp = kwargs.get('poly_deg_amp', defaults['poly_deg_amp'])
poly_deg_phi = kwargs.get('poly_deg_phi', defaults['poly_deg_phi'])
poly_type = kwargs.get('poly_type', defaults['poly_type'])
param_name = ([
'%s_poly_amp_coeff%d' % (poly_type, cc)
for cc in range(poly_deg_amp + 1)
] + [
'%s_poly_phi_coeff%d' % (poly_type, cc)
for cc in range(poly_deg_phi + 1)
])
model_kwargs = [('poly_deg_amp', poly_deg_amp),
('poly_deg_phi', poly_deg_phi), ('poly_type', poly_type)]
model_name = '.'.join(
[getattr(model_function, key) for key in ['__module__', '__name__']])
tval = {}
# Set where to evaluate gain
ha_eval_str = ['raw_transit']
if config.multi_sample:
ha_eval_str += ['transit', 'peak']
ha_eval = [0.0, None]
fitslc = slice(1, 3)
ind_eval = ha_eval_str.index(config.evaluate_gain_at)
# Determine dimensions
direction = ['amp', 'phi']
nparam = len(param_name)
ngain = len(ha_eval_str)
ndir = len(direction)
# Determine frequencies
data = andata.CorrData.from_acq_h5(file_list,
datasets=(),
start=start,
stop=stop)
freq = data.freq
if physical_freq is not None:
index_freq = np.array(
[np.argmin(np.abs(ff - freq)) for ff in physical_freq])
freq_sel = utils.convert_to_slice(index_freq)
freq = freq[index_freq]
else:
index_freq = np.arange(freq.size)
freq_sel = None
nfreq = freq.size
# Compute flux of source
inv_rt_flux_density = tools.invert_no_zero(
np.sqrt(FluxCatalog[source].predict_flux(freq)))
# Read in the eigenvaluess for all frequencies
data = andata.CorrData.from_acq_h5(file_list,
datasets=['erms', 'eval'],
freq_sel=freq_sel,
start=start,
stop=stop)
# Determine source coordinates
this_csd = np.floor(ephemeris.unix_to_csd(np.median(data.time)))
timestamp0 = ephemeris.transit_times(FluxCatalog[source].skyfield,
ephemeris.csd_to_unix(this_csd))[0]
src_ra, src_dec = ephemeris.object_coords(FluxCatalog[source].skyfield,
date=timestamp0,
deg=True)
ra = ephemeris.lsa(data.time)
ha = ra - src_ra
ha = ha - (ha > 180.0) * 360.0 + (ha < -180.0) * 360.0
ha = np.radians(ha)
itrans = np.argmin(np.abs(ha))
window = 0.75 * np.max(np.abs(ha))
off_source = np.abs(ha) > window
mlog.info("CSD %d" % this_csd)
mlog.info("Hour angle at transit (%d of %d): %0.2f deg " %
(itrans, len(ha), np.degrees(ha[itrans])))
mlog.info("Hour angle off source: %0.2f deg" %
np.median(np.abs(np.degrees(ha[off_source]))))
src_dec = np.radians(src_dec)
lat = np.radians(ephemeris.CHIMELATITUDE)
# Determine division of frequencies
ninput = data.ninput
ntime = data.ntime
nblock_freq = int(np.ceil(nfreq / float(config.nfreq_per_block)))
# Determine bad inputs
eps = 10.0 * np.finfo(data['erms'].dtype).eps
good_freq = np.flatnonzero(np.all(data['erms'][:] > eps, axis=-1))
ind_sub_freq = good_freq[slice(0, good_freq.size,
max(int(good_freq.size / 10), 1))]
tmp_data = andata.CorrData.from_acq_h5(file_list,
datasets=['evec'],
freq_sel=ind_sub_freq,
start=start,
stop=stop)
eps = 10.0 * np.finfo(tmp_data['evec'].dtype).eps
bad_input = np.flatnonzero(
np.all(np.abs(tmp_data['evec'][:, 0]) < eps, axis=(0, 2)))
input_axis = tmp_data.input.copy()
del tmp_data
# Query layout database for correlator inputs
if inputmap is None:
inputmap = tools.get_correlator_inputs(
datetime.datetime.utcfromtimestamp(data.time[itrans]),
correlator='chime')
inputmap = tools.reorder_correlator_inputs(input_axis, inputmap)
tools.change_chime_location(rotation=config.telescope_rotation)
# Determine x and y pol index
xfeeds = np.array([
idf for idf, inp in enumerate(inputmap)
if (idf not in bad_input) and tools.is_array_x(inp)
])
yfeeds = np.array([
idf for idf, inp in enumerate(inputmap)
if (idf not in bad_input) and tools.is_array_y(inp)
])
nfeed = xfeeds.size + yfeeds.size
pol = [yfeeds, xfeeds]
polstr = ['Y', 'X']
npol = len(pol)
neigen = min(max(npol, config.neigen), data['eval'].shape[1])
phase_ref = config.phase_reference_index
phase_ref_by_pol = [
pol[pp].tolist().index(phase_ref[pp]) for pp in range(npol)
]
# Calculate dynamic range
eval0_off_source = np.median(data['eval'][:, 0, off_source], axis=-1)
dyn = data['eval'][:, 1, :] * tools.invert_no_zero(
eval0_off_source[:, np.newaxis])
# Determine frequencies to mask
not_rfi = np.ones((nfreq, 1), dtype=np.bool)
if config.mask_rfi is not None:
for frng in config.mask_rfi:
not_rfi[:, 0] &= ((freq < frng[0]) | (freq > frng[1]))
mlog.info("%0.1f percent of frequencies available after masking RFI." %
(100.0 * np.sum(not_rfi, dtype=np.float32) / float(nfreq), ))
#dyn_flg = utils.contiguous_flag(dyn > config.dyn_rng_threshold, centre=itrans)
if source in config.dyn_rng_threshold:
dyn_rng_threshold = config.dyn_rng_threshold[source]
else:
dyn_rng_threshold = config.dyn_rng_threshold.default
mlog.info("Dynamic range threshold set to %0.1f." % dyn_rng_threshold)
dyn_flg = dyn > dyn_rng_threshold
# Calculate fit flag
fit_flag = np.zeros((nfreq, npol, ntime), dtype=np.bool)
for pp in range(npol):
mlog.info("Dynamic Range Nsample, Pol %d: %s" % (pp, ','.join([
"%d" % xx for xx in np.percentile(np.sum(dyn_flg, axis=-1),
[25, 50, 75, 100])
])))
if config.nsigma1 is None:
fit_flag[:, pp, :] = dyn_flg & not_rfi
else:
fit_window = config.nsigma1 * np.radians(
utils.get_window(freq, pol=polstr[pp], dec=src_dec, deg=True))
win_flg = np.abs(ha)[np.newaxis, :] <= fit_window[:, np.newaxis]
fit_flag[:, pp, :] = (dyn_flg & win_flg & not_rfi)
# Calculate base error
base_err = data['erms'][:, np.newaxis, :]
# Check for sign flips
ref_resp = andata.CorrData.from_acq_h5(file_list,
datasets=['evec'],
input_sel=config.eigen_reference,
freq_sel=freq_sel,
start=start,
stop=stop)['evec'][:, 0:neigen,
0, :]
sign0 = 1.0 - 2.0 * (ref_resp.real < 0.0)
# Check that we have the correct reference feed
if np.any(np.abs(ref_resp.imag) > 0.0):
ValueError("Reference feed %d is incorrect." % config.eigen_reference)
del ref_resp
# Save index_map
results = {}
results['model'] = model_name
results['param'] = param_name
results['freq'] = data.index_map['freq'][:]
results['input'] = input_axis
results['eval'] = ha_eval_str
results['dir'] = direction
for key, val in model_kwargs:
results[key] = val
# Initialize numpy arrays to hold results
if config.return_response:
results['response'] = np.zeros((nfreq, ninput, ntime),
dtype=np.complex64)
results['response_err'] = np.zeros((nfreq, ninput, ntime),
dtype=np.float32)
results['fit_flag'] = fit_flag
results['ha_axis'] = ha
results['ra'] = ra
else:
results['gain_eval'] = np.zeros((nfreq, ninput, ngain),
dtype=np.complex64)
results['weight_eval'] = np.zeros((nfreq, ninput, ngain),
dtype=np.float32)
results['frac_gain_err'] = np.zeros((nfreq, ninput, ngain, ndir),
dtype=np.float32)
results['parameter'] = np.zeros((nfreq, ninput, nparam),
dtype=np.float32)
results['parameter_err'] = np.zeros((nfreq, ninput, nparam),
dtype=np.float32)
results['index_eval'] = np.full((nfreq, ninput), -1, dtype=np.int8)
results['gain'] = np.zeros((nfreq, ninput), dtype=np.complex64)
results['weight'] = np.zeros((nfreq, ninput), dtype=np.float32)
results['ndof'] = np.zeros((nfreq, ninput, ndir), dtype=np.float32)
results['chisq'] = np.zeros((nfreq, ninput, ndir), dtype=np.float32)
results['timing'] = np.zeros((nfreq, ninput), dtype=np.complex64)
# Initialize metric like variables
results['runtime'] = np.zeros((nblock_freq, 2), dtype=np.float64)
# Compute distances
dist = tools.get_feed_positions(inputmap)
for pp, feeds in enumerate(pol):
dist[feeds, :] -= dist[phase_ref[pp], np.newaxis, :]
# Loop over frequency blocks
for gg in range(nblock_freq):
mlog.info("Frequency block %d of %d." % (gg, nblock_freq))
fstart = gg * config.nfreq_per_block
fstop = min((gg + 1) * config.nfreq_per_block, nfreq)
findex = np.arange(fstart, fstop)
ngroup = findex.size
freq_sel = utils.convert_to_slice(index_freq[findex])
timeit_start_gg = time.time()
#
if config.return_response:
gstart = start
gstop = stop
tslc = slice(0, ntime)
else:
good_times = np.flatnonzero(np.any(fit_flag[findex], axis=(0, 1)))
if good_times.size == 0:
continue
gstart = int(np.min(good_times))
gstop = int(np.max(good_times)) + 1
tslc = slice(gstart, gstop)
gstart += start
gstop += start
hag = ha[tslc]
itrans = np.argmin(np.abs(hag))
# Load eigenvectors.
nudata = andata.CorrData.from_acq_h5(
file_list,
datasets=['evec', 'vis', 'flags/vis_weight'],
apply_gain=False,
freq_sel=freq_sel,
start=gstart,
stop=gstop)
# Save time to load data
results['runtime'][gg, 0] = time.time() - timeit_start_gg
timeit_start_gg = time.time()
mlog.info("Time to load (per frequency): %0.3f sec" %
(results['runtime'][gg, 0] / ngroup, ))
# Loop over polarizations
for pp, feeds in enumerate(pol):
# Get timing correction
if tcorr is not None:
tgain = tcorr.get_gain(nudata.freq, nudata.input[feeds],
nudata.time)
tgain *= tgain[:, phase_ref_by_pol[pp], np.newaxis, :].conj()
tgain_transit = tgain[:, :, itrans].copy()
tgain *= tgain_transit[:, :, np.newaxis].conj()
# Create the polarization masking vector
P = np.zeros((1, ninput, 1), dtype=np.float64)
P[:, feeds, :] = 1.0
# Loop over frequencies
for gff, ff in enumerate(findex):
flg = fit_flag[ff, pp, tslc]
if (2 * int(np.sum(flg))) < (nparam +
1) and not config.return_response:
continue
# Normalize by eigenvalue and correct for pi phase flips in process.
resp = (nudata['evec'][gff, 0:neigen, :, :] *
np.sqrt(data['eval'][ff, 0:neigen, np.newaxis, tslc]) *
sign0[ff, :, np.newaxis, tslc])
# Rotate to single-pol response
# Move time to first axis for the matrix multiplication
invL = tools.invert_no_zero(
np.rollaxis(data['eval'][ff, 0:neigen, np.newaxis, tslc],
-1, 0))
UT = np.rollaxis(resp, -1, 0)
U = np.swapaxes(UT, -1, -2)
mu, vp = np.linalg.eigh(np.matmul(UT.conj(), P * U))
rsign0 = (1.0 - 2.0 * (vp[:, 0, np.newaxis, :].real < 0.0))
resp = mu[:, np.newaxis, :] * np.matmul(U, rsign0 * vp * invL)
# Extract feeds of this pol
# Transpose so that time is back to last axis
resp = resp[:, feeds, -1].T
# Compute error on response
dataflg = ((nudata.weight[gff, feeds, :] > 0.0)
& np.isfinite(nudata.weight[gff, feeds, :])).astype(
np.float32)
resp_err = dataflg * base_err[ff, :, tslc] * np.sqrt(
nudata.vis[gff, feeds, :].real) * tools.invert_no_zero(
np.sqrt(mu[np.newaxis, :, -1]))
# Reference to specific input
resp *= np.exp(
-1.0J *
np.angle(resp[phase_ref_by_pol[pp], np.newaxis, :]))
# Apply timing correction
if tcorr is not None:
resp *= tgain[gff]
results['timing'][ff, feeds] = tgain_transit[gff]
# Fringestop
lmbda = scipy.constants.c * 1e-6 / nudata.freq[gff]
resp *= tools.fringestop_phase(
hag[np.newaxis, :], lat, src_dec,
dist[feeds, 0, np.newaxis] / lmbda,
dist[feeds, 1, np.newaxis] / lmbda)
# Normalize by source flux
resp *= inv_rt_flux_density[ff]
resp_err *= inv_rt_flux_density[ff]
# If requested, reference phase to the median value
if config.med_phase_ref:
phi0 = np.angle(resp[:, itrans, np.newaxis])
resp *= np.exp(-1.0J * phi0)
resp *= np.exp(
-1.0J *
np.median(np.angle(resp), axis=0, keepdims=True))
resp *= np.exp(1.0J * phi0)
# Check if return_response flag was set by user
if not config.return_response:
if config.multi_sample:
moving_window = config.nsigma2 and config.nsigma2 * np.radians(
utils.get_window(nudata.freq[gff],
pol=polstr[pp],
dec=src_dec,
deg=True))
# Loop over inputs
for pii, ii in enumerate(feeds):
is_good = flg & (np.abs(resp[pii, :]) >
0.0) & (resp_err[pii, :] > 0.0)
# Set the intial gains based on raw response at transit
if is_good[itrans]:
results['gain_eval'][ff, ii,
0] = tools.invert_no_zero(
resp[pii, itrans])
results['frac_gain_err'][ff, ii, 0, :] = (
resp_err[pii, itrans] * tools.invert_no_zero(
np.abs(resp[pii, itrans])))
results['weight_eval'][ff, ii, 0] = 0.5 * (
np.abs(resp[pii, itrans])**2 *
tools.invert_no_zero(resp_err[pii, itrans]))**2
results['index_eval'][ff, ii] = 0
results['gain'][ff,
ii] = results['gain_eval'][ff, ii,
0]
results['weight'][ff,
ii] = results['weight_eval'][ff,
ii,
0]
# Exit if not performing multi time sample fit
if not config.multi_sample:
continue
if (2 * int(np.sum(is_good))) < (nparam + 1):
continue
try:
param, param_err, gain, gain_err, ndof, chisq, tval = fitter_function(
hag[is_good],
resp[pii, is_good],
resp_err[pii, is_good],
ha_eval,
window=moving_window,
tval=tval,
**config.fit)
except Exception as rex:
if config.verbose:
mlog.info(
"Frequency %0.2f, Feed %d failed with error: %s"
% (nudata.freq[gff], ii, rex))
continue
# Check for nan
wfit = (np.abs(gain) *
tools.invert_no_zero(np.abs(gain_err)))**2
if np.any(~np.isfinite(np.abs(gain))) or np.any(
~np.isfinite(wfit)):
continue
# Save to results using the convention that you should *multiply* the visibilites by the gains
results['gain_eval'][
ff, ii, fitslc] = tools.invert_no_zero(gain)
results['frac_gain_err'][ff, ii, fitslc,
0] = gain_err.real
results['frac_gain_err'][ff, ii, fitslc,
1] = gain_err.imag
results['weight_eval'][ff, ii, fitslc] = wfit
results['parameter'][ff, ii, :] = param
results['parameter_err'][ff, ii, :] = param_err
results['ndof'][ff, ii, :] = ndof
results['chisq'][ff, ii, :] = chisq
# Check if the fit was succesful and update the gain evaluation index appropriately
if np.all((chisq / ndof.astype(np.float32)
) <= config.chisq_per_dof_threshold):
results['index_eval'][ff, ii] = ind_eval
results['gain'][ff, ii] = results['gain_eval'][
ff, ii, ind_eval]
results['weight'][ff, ii] = results['weight_eval'][
ff, ii, ind_eval]
else:
# Return response only (do not fit model)
results['response'][ff, feeds, :] = resp
results['response_err'][ff, feeds, :] = resp_err
# Save time to fit data
results['runtime'][gg, 1] = time.time() - timeit_start_gg
mlog.info("Time to fit (per frequency): %0.3f sec" %
(results['runtime'][gg, 1] / ngroup, ))
# Clean up
del nudata
gc.collect()
# Print total run time
mlog.info("TOTAL TIME TO LOAD: %0.3f min" %
(np.sum(results['runtime'][:, 0]) / 60.0, ))
mlog.info("TOTAL TIME TO FIT: %0.3f min" %
(np.sum(results['runtime'][:, 1]) / 60.0, ))
# Set the best estimate of the gain
if not config.return_response:
flag = results['index_eval'] >= 0
gain = results['gain']
# Compute amplitude
amp = np.abs(gain)
# Hard cutoffs on the amplitude
med_amp = np.median(amp[flag])
min_amp = med_amp * config.min_amp_scale_factor
max_amp = med_amp * config.max_amp_scale_factor
flag &= ((amp >= min_amp) & (amp <= max_amp))
# Flag outliers in amplitude for each frequency
for pp, feeds in enumerate(pol):
med_amp_by_pol = np.zeros(nfreq, dtype=np.float32)
sig_amp_by_pol = np.zeros(nfreq, dtype=np.float32)
for ff in range(nfreq):
this_flag = flag[ff, feeds]
if np.any(this_flag):
med, slow, shigh = utils.estimate_directional_scale(
amp[ff, feeds[this_flag]])
lower = med - config.nsigma_outlier * slow
upper = med + config.nsigma_outlier * shigh
flag[ff, feeds] &= ((amp[ff, feeds] >= lower) &
(amp[ff, feeds] <= upper))
med_amp_by_pol[ff] = med
sig_amp_by_pol[ff] = 0.5 * (shigh - slow) / np.sqrt(
np.sum(this_flag, dtype=np.float32))
if config.nsigma_med_outlier:
med_flag = med_amp_by_pol > 0.0
not_outlier = flag_outliers(med_amp_by_pol,
med_flag,
window=config.window_med_outlier,
nsigma=config.nsigma_med_outlier)
flag[:, feeds] &= not_outlier[:, np.newaxis]
mlog.info("Pol %s: %d frequencies are outliers." %
(polstr[pp],
np.sum(~not_outlier & med_flag, dtype=np.int)))
# Determine bad frequencies
flag_freq = (np.sum(flag, axis=1, dtype=np.float32) /
float(ninput)) > config.threshold_good_freq
good_freq = np.flatnonzero(flag_freq)
# Determine bad inputs
fraction_good = np.sum(flag[good_freq, :], axis=0,
dtype=np.float32) / float(good_freq.size)
flag_input = fraction_good > config.threshold_good_input
# Finalize flag
flag &= (flag_freq[:, np.newaxis] & flag_input[np.newaxis, :])
# Interpolate gains
interp_gain, interp_weight = interpolate_gain(
freq,
gain,
results['weight'],
flag=flag,
length_scale=config.interpolation_length_scale,
mlog=mlog)
# Save gains to object
results['flag'] = flag
results['gain'] = interp_gain
results['weight'] = interp_weight
# Return results
return results
def process(self, sstream):
"""Calculate the mean(median) over the sidereal day.
Parameters
----------
sstream : andata.CorrData or containers.SiderealStream
Timestream or sidereal stream.
Returns
-------
mustream : same as sstream
Sidereal stream containing only the mean(median) value.
"""
from .flagging import daytime_flag, transit_flag
# Make sure we are distributed over frequency
sstream.redistribute("freq")
# Extract lsd
lsd = sstream.attrs[
"lsd"] if "lsd" in sstream.attrs else sstream.attrs["csd"]
lsd_list = lsd if hasattr(lsd, "__iter__") else [lsd]
# Calculate the right ascension, method differs depending on input container
if "ra" in sstream.index_map:
ra = sstream.ra
timestamp = {
dd: ephemeris.csd_to_unix(dd + ra / 360.0)
for dd in lsd_list
}
flag_quiet = np.ones(ra.size, dtype=np.bool)
elif "time" in sstream.index_map:
ra = ephemeris.lsa(sstream.time)
timestamp = {lsd: sstream.time}
flag_quiet = np.fix(ephemeris.unix_to_csd(sstream.time)) == lsd
else:
raise RuntimeError("Format of `sstream` argument is unknown.")
# If requested, determine "quiet" region of sky.
# In the case of a SiderealStack, there will be multiple LSDs and the
# mask will be the logical AND of the mask from each individual LSDs.
if self.mask_day:
for dd, time_dd in timestamp.items():
# Mask daytime data
flag_quiet &= ~daytime_flag(time_dd)
if self.mask_sources:
for dd, time_dd in timestamp.items():
# Mask data near bright source transits
for body in self.body:
flag_quiet &= ~transit_flag(
body, time_dd, nsigma=self.nsigma)
if self.mask_ra:
# Only use data within user specified ranges of RA
mask_ra = np.zeros(ra.size, dtype=np.bool)
for ra_range in self.mask_ra:
self.log.info("Using data between RA = [%0.2f, %0.2f] deg" %
tuple(ra_range))
mask_ra |= (ra >= ra_range[0]) & (ra <= ra_range[1])
flag_quiet &= mask_ra
# Create output container
newra = np.mean(ra[flag_quiet], keepdims=True)
mustream = containers.SiderealStream(
ra=newra,
axes_from=sstream,
attrs_from=sstream,
distributed=True,
comm=sstream.comm,
)
mustream.redistribute("freq")
mustream.attrs["statistic"] = self._name_of_statistic
# Dereference visibilities
all_vis = sstream.vis[:].view(np.ndarray)
mu_vis = mustream.vis[:].view(np.ndarray)
# Combine the visibility weights with the quiet flag
all_weight = sstream.weight[:].view(np.ndarray) * flag_quiet.astype(
np.float32)
if not self.inverse_variance:
all_weight = (all_weight > 0.0).astype(np.float32)
# Only include freqs/baselines where enough data is actually present
frac_present = all_weight.sum(axis=-1) / flag_quiet.sum(axis=-1)
all_weight *= (frac_present > self.missing_threshold)[..., np.newaxis]
num_freq_missing_local = int(
(frac_present < self.missing_threshold).all(axis=1).sum())
num_freq_missing = self.comm.allreduce(num_freq_missing_local,
op=MPI.SUM)
self.log.info(
"Cannot estimate a sidereal mean for "
f"{100.0 * num_freq_missing / len(mustream.freq):.2f}% of all frequencies."
)
# Save the total number of nonzero samples as the weight dataset of the output
# container
mustream.weight[:] = np.sum(all_weight, axis=-1, keepdims=True)
# If requested, compute median (requires loop over frequencies and baselines)
if self.median:
mu_vis[..., 0].real = weighted_median(all_vis.real.copy(),
all_weight)
mu_vis[..., 0].imag = weighted_median(all_vis.imag.copy(),
all_weight)
# Where all the weights are zero explicitly set the median to zero
missing = ~(all_weight.any(axis=-1))
mu_vis[missing, 0] = 0.0
else:
# Otherwise calculate the mean
mu_vis[:] = np.sum(all_weight * all_vis, axis=-1, keepdims=True)
mu_vis[:] *= tools.invert_no_zero(mustream.weight[:])
# Return sidereal stream containing the mean value
return mustream
def view(self):
if self.lsd is None:
return panel.pane.Markdown("No data selected.")
try:
if self.intercylinder_only:
name = "ringmap_intercyl"
else:
name = "ringmap"
container = self.data.load_file(self.revision, self.lsd, name)
except DataError as err:
return panel.pane.Markdown(
f"Error: {str(err)}. Please report this problem."
)
# Index map for ra (x-axis)
index_map_ra = container.index_map["ra"]
axis_name_ra = "RA [degrees]"
# Index map for sin(ZA)/sin(theta) (y-axis)
index_map_el = container.index_map["el"]
axis_name_el = "sin(\u03B8)"
# Apply data selections
sel_beam = np.where(container.index_map["beam"] == self.beam)[0]
sel_freq = np.where(
[f[0] for f in container.index_map["freq"]] == self.frequency
)[0]
if self.polarization == self.mean_pol_text:
sel_pol = np.where(
(container.index_map["pol"] == "XX")
| (container.index_map["pol"] == "YY")
)[0]
rmap = np.squeeze(container.map[sel_beam, sel_pol, sel_freq])
rmap = np.nanmean(rmap, axis=0)
else:
sel_pol = np.where(container.index_map["pol"] == self.polarization)[0]
rmap = np.squeeze(container.map[sel_beam, sel_pol, sel_freq])
if self.flag_mask:
rmap = np.where(self._flags_mask(container.index_map["ra"]), np.nan, rmap)
if self.weight_mask:
try:
rms = np.squeeze(container.rms[sel_pol, sel_freq])
except IndexError:
logger.error(
f"rms dataset of ringmap file for rev {self.revision} lsd "
f"{self.lsd} is missing [{sel_pol}, {sel_freq}] (polarization, "
f"frequency). rms has shape {container.rms.shape}"
)
self.weight_mask = False
else:
rmap = np.where(self._weights_mask(rms), np.nan, rmap)
# Set flagged data to nan
rmap = np.where(rmap == 0, np.nan, rmap)
if self.crosstalk_removal:
# The mean of an all-nan slice (masked?) is nan. We don't need a warning about that.
with warnings.catch_warnings():
warnings.filterwarnings("ignore", r"All-NaN slice encountered")
rmap -= np.nanmedian(rmap, axis=0)
if self.template_subtraction:
try:
rm_stack = self.data.load_file_from_path(
self._stack_path, ccontainers.RingMap
)
except DataError as err:
return panel.pane.Markdown(
f"Error: {str(err)}. Please report this problem."
)
# The stack file has all polarizations, so we can't reuse sel_pol
if self.polarization == self.mean_pol_text:
stack_sel_pol = np.where(
(rm_stack.index_map["pol"] == "XX")
| (rm_stack.index_map["pol"] == "YY")
)[0]
else:
stack_sel_pol = np.where(
rm_stack.index_map["pol"] == self.polarization
)[0]
try:
rm_stack = np.squeeze(rm_stack.map[sel_beam, stack_sel_pol, sel_freq])
except IndexError as err:
logger.error(
f"map dataset of ringmap stack file "
f"is missing [{sel_beam}, {stack_sel_pol}, {sel_freq}] (beam, polarization, "
f"frequency). map has shape {rm_stack.map.shape}:\n{err}"
)
self.template_subtraction = False
else:
if self.polarization == self.mean_pol_text:
rm_stack = np.nanmean(rm_stack, axis=0)
# FIXME: this is a hack. remove when rinmap stack file fixed.
rmap -= rm_stack.reshape(rm_stack.shape[0], -1, 2).mean(axis=-1)
if self.transpose:
rmap = rmap.T
index_x = index_map_ra
index_y = index_map_el
axis_names = [axis_name_ra, axis_name_el]
xlim, ylim = self.ylim, self.xlim
else:
index_x = index_map_el
index_y = index_map_ra
axis_names = [axis_name_el, axis_name_ra]
xlim, ylim = self.xlim, self.ylim
img = hv.Image(
(index_x, index_y, rmap),
datatype=["image", "grid"],
kdims=axis_names,
).opts(
clim=self.colormap_range,
logz=self.logarithmic_colorscale,
cmap=process_cmap("inferno", provider="matplotlib"),
colorbar=True,
xlim=xlim,
ylim=ylim,
)
if self.serverside_rendering is not None:
# set colormap
cmap_inferno = copy.copy(matplotlib_cm.get_cmap("inferno"))
cmap_inferno.set_under("black")
cmap_inferno.set_bad("lightgray")
# Set z-axis normalization (other possible values are 'eq_hist', 'cbrt').
if self.logarithmic_colorscale:
normalization = "log"
else:
normalization = "linear"
# datashade/rasterize the image
img = self.serverside_rendering(
img,
cmap=cmap_inferno,
precompute=True,
x_range=xlim,
y_range=ylim,
normalization=normalization,
)
if self.mark_moon:
# Put a ring around the location of the moon if it transits on this day
eph = skyfield_wrapper.ephemeris
# Start and end times of the CSD
st = csd_to_unix(self.lsd.lsd)
et = csd_to_unix(self.lsd.lsd + 1)
moon_time, moon_dec = chime.transit_times(
eph["moon"], st, et, return_dec=True
)
if len(moon_time):
lunar_transit = unix_to_csd(moon_time[0])
lunar_dec = moon_dec[0]
lunar_ra = (lunar_transit % 1) * 360.0
lunar_za = np.sin(np.radians(lunar_dec - 49.0))
if self.transpose:
img *= hv.Ellipse(lunar_ra, lunar_za, (5.5, 0.15))
else:
img *= hv.Ellipse(lunar_za, lunar_ra, (0.04, 21))
if self.mark_day_time:
# Calculate the sun rise/set times on this sidereal day
# Start and end times of the CSD
start_time = csd_to_unix(self.lsd.lsd)
end_time = csd_to_unix(self.lsd.lsd + 1)
times, rises = chime.rise_set_times(
skyfield_wrapper.ephemeris["sun"],
start_time,
end_time,
diameter=-10,
)
sun_rise = 0
sun_set = 0
for t, r in zip(times, rises):
if r:
sun_rise = (unix_to_csd(t) % 1) * 360
else:
sun_set = (unix_to_csd(t) % 1) * 360
# Highlight the day time data
opts = {
"color": "grey",
"alpha": 0.5,
"line_width": 1,
"line_color": "black",
"line_dash": "dashed",
}
if self.transpose:
if sun_rise < sun_set:
img *= hv.VSpan(sun_rise, sun_set).opts(**opts)
else:
img *= hv.VSpan(self.ylim[0], sun_set).opts(**opts)
img *= hv.VSpan(sun_rise, self.ylim[1]).opts(**opts)
else:
if sun_rise < sun_set:
img *= hv.HSpan(sun_rise, sun_set).opts(**opts)
else:
img *= hv.HSpan(self.ylim[0], sun_set).opts(**opts)
img *= hv.HSpan(sun_rise, self.ylim[1]).opts(**opts)
img.opts(
# Fix height, but make width responsive
height=self.height,
responsive=True,
shared_axes=True,
bgcolor="lightgray",
)
return panel.Row(img, width_policy="max")
def main(config_file=None, logging_params=DEFAULT_LOGGING):
# Load config
config = DEFAULTS.deepcopy()
if config_file is not None:
config.merge(NameSpace(load_yaml_config(config_file)))
# Setup logging
log.setup_logging(logging_params)
logger = log.get_logger(__name__)
## Load data for flagging
# Load fpga restarts
time_fpga_restart = []
if config.fpga_restart_file is not None:
with open(config.fpga_restart_file, 'r') as handler:
for line in handler:
time_fpga_restart.append(
ephemeris.datetime_to_unix(
ephemeris.timestr_to_datetime(line.split('_')[0])))
time_fpga_restart = np.array(time_fpga_restart)
# Load housekeeping flag
if config.housekeeping_file is not None:
ftemp = TempData.from_acq_h5(config.housekeeping_file,
datasets=["time_flag"])
else:
ftemp = None
# Load jump data
if config.jump_file is not None:
with h5py.File(config.jump_file, 'r') as handler:
jump_time = handler["time"][:]
jump_size = handler["jump_size"][:]
else:
jump_time = None
jump_size = None
# Load rain data
if config.rain_file is not None:
with h5py.File(config.rain_file, 'r') as handler:
rain_ranges = handler["time_range_conservative"][:]
else:
rain_ranges = []
# Load data flags
data_flags = {}
if config.data_flags:
finder.connect_database()
flag_types = finder.DataFlagType.select()
possible_data_flags = []
for ft in flag_types:
possible_data_flags.append(ft.name)
if ft.name in config.data_flags:
new_data_flags = finder.DataFlag.select().where(
finder.DataFlag.type == ft)
data_flags[ft.name] = list(new_data_flags)
# Set desired range of time
start_time = (ephemeris.datetime_to_unix(
datetime.datetime(
*config.start_date)) if config.start_date is not None else None)
end_time = (ephemeris.datetime_to_unix(datetime.datetime(
*config.end_date)) if config.end_date is not None else None)
## Find gain files
files = {}
for src in config.sources:
files[src] = sorted(
glob.glob(
os.path.join(config.directory, src.lower(),
"%s_%s_lsd_*.h5" % (
config.prefix,
src.lower(),
))))
csd = {}
for src in config.sources:
csd[src] = np.array(
[int(os.path.splitext(ff)[0][-4:]) for ff in files[src]])
for src in config.sources:
logger.info("%s: %d files" % (src, len(csd[src])))
## Remove files that occur during flag
csd_flag = {}
for src in config.sources:
body = ephemeris.source_dictionary[src]
csd_flag[src] = np.ones(csd[src].size, dtype=np.bool)
for ii, cc in enumerate(csd[src][:]):
ttrans = ephemeris.transit_times(body,
ephemeris.csd_to_unix(cc))[0]
if (start_time is not None) and (ttrans < start_time):
csd_flag[src][ii] = False
continue
if (end_time is not None) and (ttrans > end_time):
csd_flag[src][ii] = False
continue
# If requested, remove daytime transits
if not config.include_daytime.get(
src, config.include_daytime.default) and daytime_flag(
ttrans)[0]:
logger.info("%s CSD %d: daytime transit" % (src, cc))
csd_flag[src][ii] = False
continue
# Remove transits during HKP drop out
if ftemp is not None:
itemp = np.flatnonzero(
(ftemp.time[:] >= (ttrans - config.transit_window))
& (ftemp.time[:] <= (ttrans + config.transit_window)))
tempflg = ftemp['time_flag'][itemp]
if (tempflg.size == 0) or ((np.sum(tempflg, dtype=np.float32) /
float(tempflg.size)) < 0.50):
logger.info("%s CSD %d: no housekeeping" % (src, cc))
csd_flag[src][ii] = False
continue
# Remove transits near jumps
if jump_time is not None:
njump = np.sum((jump_size > config.min_jump_size)
& (jump_time > (ttrans - config.jump_window))
& (jump_time < ttrans))
if njump > config.max_njump:
logger.info("%s CSD %d: %d jumps before" %
(src, cc, njump))
csd_flag[src][ii] = False
continue
# Remove transits near rain
for rng in rain_ranges:
if (((ttrans - config.transit_window) <= rng[1])
and ((ttrans + config.transit_window) >= rng[0])):
logger.info("%s CSD %d: during rain" % (src, cc))
csd_flag[src][ii] = False
break
# Remove transits during data flag
for name, flag_list in data_flags.items():
if csd_flag[src][ii]:
for flg in flag_list:
if (((ttrans - config.transit_window) <=
flg.finish_time)
and ((ttrans + config.transit_window) >=
flg.start_time)):
logger.info("%s CSD %d: %s flag" %
(src, cc, name))
csd_flag[src][ii] = False
break
# Print number of files left after flagging
for src in config.sources:
logger.info("%s: %d files (after flagging)" %
(src, np.sum(csd_flag[src])))
## Construct pair wise differences
npair = len(config.diff_pair)
shift = [nd * 24.0 * 3600.0 for nd in config.nday_shift]
calmap = []
calpair = []
for (tsrc, csrc), sh in zip(config.diff_pair, shift):
body_test = ephemeris.source_dictionary[tsrc]
body_cal = ephemeris.source_dictionary[csrc]
for ii, cc in enumerate(csd[tsrc]):
if csd_flag[tsrc][ii]:
test_transit = ephemeris.transit_times(
body_test, ephemeris.csd_to_unix(cc))[0]
cal_transit = ephemeris.transit_times(body_cal,
test_transit + sh)[0]
cal_csd = int(np.fix(ephemeris.unix_to_csd(cal_transit)))
ttrans = np.sort([test_transit, cal_transit])
if cal_csd in csd[csrc]:
jj = list(csd[csrc]).index(cal_csd)
if csd_flag[csrc][jj] and not np.any(
(time_fpga_restart >= ttrans[0])
& (time_fpga_restart <= ttrans[1])):
calmap.append([ii, jj])
calpair.append([tsrc, csrc])
calmap = np.array(calmap)
calpair = np.array(calpair)
ntransit = calmap.shape[0]
logger.info("%d total transit pairs" % ntransit)
for ii in range(ntransit):
t1 = ephemeris.transit_times(
ephemeris.source_dictionary[calpair[ii, 0]],
ephemeris.csd_to_unix(csd[calpair[ii, 0]][calmap[ii, 0]]))[0]
t2 = ephemeris.transit_times(
ephemeris.source_dictionary[calpair[ii, 1]],
ephemeris.csd_to_unix(csd[calpair[ii, 1]][calmap[ii, 1]]))[0]
logger.info("%s (%d) - %s (%d): %0.1f hr" %
(calpair[ii, 0], csd_flag[calpair[ii, 0]][calmap[ii, 0]],
calpair[ii, 1], csd_flag[calpair[ii, 1]][calmap[ii, 1]],
(t1 - t2) / 3600.0))
# Determine unique diff pairs
diff_name = np.array(['%s/%s' % tuple(cp) for cp in calpair])
uniq_diff, lbl_diff, cnt_diff = np.unique(diff_name,
return_inverse=True,
return_counts=True)
ndiff = uniq_diff.size
for ud, udcnt in zip(uniq_diff, cnt_diff):
logger.info("%s: %d transit pairs" % (ud, udcnt))
## Load gains
inputmap = tools.get_correlator_inputs(datetime.datetime.utcnow(),
correlator='chime')
ninput = len(inputmap)
nfreq = 1024
# Set up gain arrays
gain = np.zeros((2, nfreq, ninput, ntransit), dtype=np.complex64)
weight = np.zeros((2, nfreq, ninput, ntransit), dtype=np.float32)
input_sort = np.zeros((2, ninput, ntransit), dtype=np.int)
kcsd = np.zeros((2, ntransit), dtype=np.float32)
timestamp = np.zeros((2, ntransit), dtype=np.float64)
is_daytime = np.zeros((2, ntransit), dtype=np.bool)
for tt in range(ntransit):
for kk, (src, ind) in enumerate(zip(calpair[tt], calmap[tt])):
body = ephemeris.source_dictionary[src]
filename = files[src][ind]
logger.info("%s: %s" % (src, filename))
temp = containers.StaticGainData.from_file(filename)
freq = temp.freq[:]
inputs = temp.input[:]
isort = reorder_inputs(inputmap, inputs)
inputs = inputs[isort]
gain[kk, :, :, tt] = temp.gain[:, isort]
weight[kk, :, :, tt] = temp.weight[:, isort]
input_sort[kk, :, tt] = isort
kcsd[kk, tt] = temp.attrs['lsd']
timestamp[kk, tt] = ephemeris.transit_times(
body, ephemeris.csd_to_unix(kcsd[kk, tt]))[0]
is_daytime[kk, tt] = daytime_flag(timestamp[kk, tt])[0]
if np.any(isort != np.arange(isort.size)):
logger.info("Input ordering has changed: %s" %
ephemeris.unix_to_datetime(
timestamp[kk, tt]).strftime("%Y-%m-%d"))
logger.info("")
inputs = np.array([(inp.id, inp.input_sn) for inp in inputmap],
dtype=[('chan_id', 'u2'), ('correlator_input', 'S32')])
## Load input flags
inpflg = np.ones((2, ninput, ntransit), dtype=np.bool)
min_flag_time = np.min(timestamp) - 7.0 * 24.0 * 60.0 * 60.0
max_flag_time = np.max(timestamp) + 7.0 * 24.0 * 60.0 * 60.0
flaginput_files = sorted(
glob.glob(
os.path.join(config.flaginput_dir, "*" + config.flaginput_suffix,
"*.h5")))
if flaginput_files:
logger.info("Found %d flaginput files." % len(flaginput_files))
tmp = andata.FlagInputData.from_acq_h5(flaginput_files, datasets=())
start, stop = [
int(yy) for yy in np.percentile(
np.flatnonzero((tmp.time[:] >= min_flag_time)
& (tmp.time[:] <= max_flag_time)), [0, 100])
]
cont = andata.FlagInputData.from_acq_h5(flaginput_files,
start=start,
stop=stop,
datasets=['flag'])
for kk in range(2):
inpflg[kk, :, :] = cont.resample('flag',
timestamp[kk],
transpose=True)
logger.info("Flaginput time offsets in minutes (pair %d):" % kk)
logger.info(
str(
np.fix((cont.time[cont.search_update_time(timestamp[kk])] -
timestamp[kk]) / 60.0).astype(np.int)))
# Sort flags so they are in same order
for tt in range(ntransit):
for kk in range(2):
inpflg[kk, :, tt] = inpflg[kk, input_sort[kk, :, tt], tt]
# Do not apply input flag to phase reference
for ii in config.index_phase_ref:
inpflg[:, ii, :] = True
## Flag out gains with high uncertainty and frequencies with large fraction of data flagged
frac_err = tools.invert_no_zero(np.sqrt(weight) * np.abs(gain))
flag = np.all((weight > 0.0) & (np.abs(gain) > 0.0) &
(frac_err < config.max_uncertainty),
axis=0)
freq_flag = ((np.sum(flag, axis=(1, 2), dtype=np.float32) /
float(np.prod(flag.shape[1:]))) > config.freq_threshold)
if config.apply_rfi_mask:
freq_flag &= np.logical_not(rfi.frequency_mask(freq))
flag = flag & freq_flag[:, np.newaxis, np.newaxis]
good_freq = np.flatnonzero(freq_flag)
logger.info("Number good frequencies %d" % good_freq.size)
## Generate flags with more conservative cuts on frequency
c_flag = flag & np.all(frac_err < config.conservative.max_uncertainty,
axis=0)
c_freq_flag = ((np.sum(c_flag, axis=(1, 2), dtype=np.float32) /
float(np.prod(c_flag.shape[1:]))) >
config.conservative.freq_threshold)
if config.conservative.apply_rfi_mask:
c_freq_flag &= np.logical_not(rfi.frequency_mask(freq))
c_flag = c_flag & c_freq_flag[:, np.newaxis, np.newaxis]
c_good_freq = np.flatnonzero(c_freq_flag)
logger.info("Number good frequencies (conservative thresholds) %d" %
c_good_freq.size)
## Apply input flags
flag &= np.all(inpflg[:, np.newaxis, :, :], axis=0)
## Update flags based on beam flag
if config.beam_flag_file is not None:
dbeam = andata.BaseData.from_acq_h5(config.beam_flag_file)
db_csd = np.floor(ephemeris.unix_to_csd(dbeam.index_map['time'][:]))
for ii, name in enumerate(config.beam_flag_datasets):
logger.info("Applying %s beam flag." % name)
if not ii:
db_flag = dbeam.flags[name][:]
else:
db_flag &= dbeam.flags[name][:]
cnt = 0
for ii, dbc in enumerate(db_csd):
this_csd = np.flatnonzero(np.any(kcsd == dbc, axis=0))
if this_csd.size > 0:
logger.info("Beam flag for %d matches %s." %
(dbc, str(kcsd[:, this_csd])))
flag[:, :, this_csd] &= db_flag[np.newaxis, :, ii, np.newaxis]
cnt += 1
logger.info("Applied %0.1f percent of the beam flags" %
(100.0 * cnt / float(db_csd.size), ))
## Flag inputs with large amount of missing data
input_frac_flagged = (
np.sum(flag[good_freq, :, :], axis=(0, 2), dtype=np.float32) /
float(good_freq.size * ntransit))
input_flag = input_frac_flagged > config.input_threshold
for ii in config.index_phase_ref:
logger.info("Phase reference %d has %0.3f fraction of data flagged." %
(ii, input_frac_flagged[ii]))
input_flag[ii] = True
good_input = np.flatnonzero(input_flag)
flag = flag & input_flag[np.newaxis, :, np.newaxis]
logger.info("Number good inputs %d" % good_input.size)
## Calibrate
gaincal = gain[0] * tools.invert_no_zero(gain[1])
frac_err_cal = np.sqrt(frac_err[0]**2 + frac_err[1]**2)
count = np.sum(flag, axis=-1, dtype=np.int)
stat_flag = count > config.min_num_transit
## Calculate phase
amp = np.abs(gaincal)
phi = np.angle(gaincal)
## Calculate polarisation groups
pol_dict = {'E': 'X', 'S': 'Y'}
cyl_dict = {2: 'A', 3: 'B', 4: 'C', 5: 'D'}
if config.group_by_cyl:
group_id = [
(inp.pol,
inp.cyl) if tools.is_chime(inp) and (ii in good_input) else None
for ii, inp in enumerate(inputmap)
]
else:
group_id = [
inp.pol if tools.is_chime(inp) and (ii in good_input) else None
for ii, inp in enumerate(inputmap)
]
ugroup_id = sorted([uidd for uidd in set(group_id) if uidd is not None])
ngroup = len(ugroup_id)
group_list_noref = [
np.array([
gg for gg, gid in enumerate(group_id)
if (gid == ugid) and gg not in config.index_phase_ref
]) for ugid in ugroup_id
]
group_list = [
np.array([gg for gg, gid in enumerate(group_id) if gid == ugid])
for ugid in ugroup_id
]
if config.group_by_cyl:
group_str = [
"%s-%s" % (pol_dict[pol], cyl_dict[cyl]) for pol, cyl in ugroup_id
]
else:
group_str = [pol_dict[pol] for pol in ugroup_id]
index_phase_ref = []
for gstr, igroup in zip(group_str, group_list):
candidate = [ii for ii in config.index_phase_ref if ii in igroup]
if len(candidate) != 1:
index_phase_ref.append(None)
else:
index_phase_ref.append(candidate[0])
logger.info(
"Phase reference: %s" %
', '.join(['%s = %s' % tpl
for tpl in zip(group_str, index_phase_ref)]))
## Apply thermal correction to amplitude
if config.amp_thermal.enabled:
logger.info("Applying thermal correction.")
# Load the temperatures
tdata = TempData.from_acq_h5(config.amp_thermal.filename)
index = tdata.search_sensors(config.amp_thermal.sensor)[0]
temp = tdata.datasets[config.amp_thermal.field][index]
temp_func = scipy.interpolate.interp1d(tdata.time, temp,
**config.amp_thermal.interp)
itemp = temp_func(timestamp)
dtemp = itemp[0] - itemp[1]
flag_func = scipy.interpolate.interp1d(
tdata.time, tdata.datasets['flag'][index].astype(np.float32),
**config.amp_thermal.interp)
dtemp_flag = np.all(flag_func(timestamp) == 1.0, axis=0)
flag &= dtemp_flag[np.newaxis, np.newaxis, :]
for gstr, igroup in zip(group_str, group_list):
pstr = gstr[0]
thermal_coeff = np.polyval(config.amp_thermal.coeff[pstr], freq)
gthermal = 1.0 + thermal_coeff[:, np.newaxis, np.newaxis] * dtemp[
np.newaxis, np.newaxis, :]
amp[:, igroup, :] *= tools.invert_no_zero(gthermal)
## Compute common mode
if config.subtract_common_mode_before:
logger.info("Calculating common mode amplitude and phase.")
cmn_amp, flag_cmn_amp = compute_common_mode(amp,
flag,
group_list_noref,
median=False)
cmn_phi, flag_cmn_phi = compute_common_mode(phi,
flag,
group_list_noref,
median=False)
# Subtract common mode (from phase only)
logger.info("Subtracting common mode phase.")
group_flag = np.zeros((ngroup, ninput), dtype=np.bool)
for gg, igroup in enumerate(group_list):
group_flag[gg, igroup] = True
phi[:,
igroup, :] = phi[:, igroup, :] - cmn_phi[:, gg, np.newaxis, :]
for iref in index_phase_ref:
if (iref is not None) and (iref in igroup):
flag[:, iref, :] = flag_cmn_phi[:, gg, :]
## If requested, determine and subtract a delay template
if config.fit_delay_before:
logger.info("Fitting delay template.")
omega = timing.FREQ_TO_OMEGA * freq
tau, tau_flag, _ = construct_delay_template(
omega,
phi,
c_flag & flag,
min_num_freq_for_delay_fit=config.min_num_freq_for_delay_fit)
# Compute residuals
logger.info("Subtracting delay template.")
phi = phi - tau[np.newaxis, :, :] * omega[:, np.newaxis, np.newaxis]
## Normalize by median over time
logger.info("Calculating median amplitude and phase.")
med_amp = np.zeros((nfreq, ninput, ndiff), dtype=amp.dtype)
med_phi = np.zeros((nfreq, ninput, ndiff), dtype=phi.dtype)
count_by_diff = np.zeros((nfreq, ninput, ndiff), dtype=np.int)
stat_flag_by_diff = np.zeros((nfreq, ninput, ndiff), dtype=np.bool)
def weighted_mean(yy, ww, axis=-1):
return np.sum(ww * yy, axis=axis) * tools.invert_no_zero(
np.sum(ww, axis=axis))
for dd in range(ndiff):
this_diff = np.flatnonzero(lbl_diff == dd)
this_flag = flag[:, :, this_diff]
this_amp = amp[:, :, this_diff]
this_amp_err = this_amp * frac_err_cal[:, :,
this_diff] * this_flag.astype(
np.float32)
this_phi = phi[:, :, this_diff]
this_phi_err = frac_err_cal[:, :, this_diff] * this_flag.astype(
np.float32)
count_by_diff[:, :, dd] = np.sum(this_flag, axis=-1, dtype=np.int)
stat_flag_by_diff[:, :,
dd] = count_by_diff[:, :,
dd] > config.min_num_transit
if config.weighted_mean == 2:
logger.info("Calculating inverse variance weighted mean.")
med_amp[:, :,
dd] = weighted_mean(this_amp,
tools.invert_no_zero(this_amp_err**2),
axis=-1)
med_phi[:, :,
dd] = weighted_mean(this_phi,
tools.invert_no_zero(this_phi_err**2),
axis=-1)
elif config.weighted_mean == 1:
logger.info("Calculating uniform weighted mean.")
med_amp[:, :, dd] = weighted_mean(this_amp,
this_flag.astype(np.float32),
axis=-1)
med_phi[:, :, dd] = weighted_mean(this_phi,
this_flag.astype(np.float32),
axis=-1)
else:
logger.info("Calculating median value.")
for ff in range(nfreq):
for ii in range(ninput):
if np.any(this_flag[ff, ii, :]):
med_amp[ff, ii, dd] = wq.median(
this_amp[ff, ii, :],
this_flag[ff, ii, :].astype(np.float32))
med_phi[ff, ii, dd] = wq.median(
this_phi[ff, ii, :],
this_flag[ff, ii, :].astype(np.float32))
damp = np.zeros_like(amp)
dphi = np.zeros_like(phi)
for dd in range(ndiff):
this_diff = np.flatnonzero(lbl_diff == dd)
damp[:, :, this_diff] = amp[:, :, this_diff] * tools.invert_no_zero(
med_amp[:, :, dd, np.newaxis]) - 1.0
dphi[:, :,
this_diff] = phi[:, :, this_diff] - med_phi[:, :, dd, np.newaxis]
# Compute common mode
if not config.subtract_common_mode_before:
logger.info("Calculating common mode amplitude and phase.")
cmn_amp, flag_cmn_amp = compute_common_mode(damp,
flag,
group_list_noref,
median=True)
cmn_phi, flag_cmn_phi = compute_common_mode(dphi,
flag,
group_list_noref,
median=True)
# Subtract common mode (from phase only)
logger.info("Subtracting common mode phase.")
group_flag = np.zeros((ngroup, ninput), dtype=np.bool)
for gg, igroup in enumerate(group_list):
group_flag[gg, igroup] = True
dphi[:, igroup, :] = dphi[:, igroup, :] - cmn_phi[:, gg,
np.newaxis, :]
for iref in index_phase_ref:
if (iref is not None) and (iref in igroup):
flag[:, iref, :] = flag_cmn_phi[:, gg, :]
## Compute RMS
logger.info("Calculating RMS of amplitude and phase.")
mad_amp = np.zeros((nfreq, ninput), dtype=amp.dtype)
std_amp = np.zeros((nfreq, ninput), dtype=amp.dtype)
mad_phi = np.zeros((nfreq, ninput), dtype=phi.dtype)
std_phi = np.zeros((nfreq, ninput), dtype=phi.dtype)
mad_amp_by_diff = np.zeros((nfreq, ninput, ndiff), dtype=amp.dtype)
std_amp_by_diff = np.zeros((nfreq, ninput, ndiff), dtype=amp.dtype)
mad_phi_by_diff = np.zeros((nfreq, ninput, ndiff), dtype=phi.dtype)
std_phi_by_diff = np.zeros((nfreq, ninput, ndiff), dtype=phi.dtype)
for ff in range(nfreq):
for ii in range(ninput):
this_flag = flag[ff, ii, :]
if np.any(this_flag):
std_amp[ff, ii] = np.std(damp[ff, ii, this_flag])
std_phi[ff, ii] = np.std(dphi[ff, ii, this_flag])
mad_amp[ff, ii] = 1.48625 * wq.median(
np.abs(damp[ff, ii, :]), this_flag.astype(np.float32))
mad_phi[ff, ii] = 1.48625 * wq.median(
np.abs(dphi[ff, ii, :]), this_flag.astype(np.float32))
for dd in range(ndiff):
this_diff = this_flag & (lbl_diff == dd)
if np.any(this_diff):
std_amp_by_diff[ff, ii, dd] = np.std(damp[ff, ii,
this_diff])
std_phi_by_diff[ff, ii, dd] = np.std(dphi[ff, ii,
this_diff])
mad_amp_by_diff[ff, ii, dd] = 1.48625 * wq.median(
np.abs(damp[ff, ii, :]),
this_diff.astype(np.float32))
mad_phi_by_diff[ff, ii, dd] = 1.48625 * wq.median(
np.abs(dphi[ff, ii, :]),
this_diff.astype(np.float32))
## Construct delay template
if not config.fit_delay_before:
logger.info("Fitting delay template.")
omega = timing.FREQ_TO_OMEGA * freq
tau, tau_flag, _ = construct_delay_template(
omega,
dphi,
c_flag & flag,
min_num_freq_for_delay_fit=config.min_num_freq_for_delay_fit)
# Compute residuals
logger.info("Subtracting delay template from phase.")
resid = (dphi - tau[np.newaxis, :, :] *
omega[:, np.newaxis, np.newaxis]) * flag.astype(np.float32)
else:
resid = dphi
tau_count = np.sum(tau_flag, axis=-1, dtype=np.int)
tau_stat_flag = tau_count > config.min_num_transit
tau_count_by_diff = np.zeros((ninput, ndiff), dtype=np.int)
tau_stat_flag_by_diff = np.zeros((ninput, ndiff), dtype=np.bool)
for dd in range(ndiff):
this_diff = np.flatnonzero(lbl_diff == dd)
tau_count_by_diff[:, dd] = np.sum(tau_flag[:, this_diff],
axis=-1,
dtype=np.int)
tau_stat_flag_by_diff[:,
dd] = tau_count_by_diff[:,
dd] > config.min_num_transit
## Calculate statistics of residuals
std_resid = np.zeros((nfreq, ninput), dtype=phi.dtype)
mad_resid = np.zeros((nfreq, ninput), dtype=phi.dtype)
std_resid_by_diff = np.zeros((nfreq, ninput, ndiff), dtype=phi.dtype)
mad_resid_by_diff = np.zeros((nfreq, ninput, ndiff), dtype=phi.dtype)
for ff in range(nfreq):
for ii in range(ninput):
this_flag = flag[ff, ii, :]
if np.any(this_flag):
std_resid[ff, ii] = np.std(resid[ff, ii, this_flag])
mad_resid[ff, ii] = 1.48625 * wq.median(
np.abs(resid[ff, ii, :]), this_flag.astype(np.float32))
for dd in range(ndiff):
this_diff = this_flag & (lbl_diff == dd)
if np.any(this_diff):
std_resid_by_diff[ff, ii,
dd] = np.std(resid[ff, ii,
this_diff])
mad_resid_by_diff[ff, ii, dd] = 1.48625 * wq.median(
np.abs(resid[ff, ii, :]),
this_diff.astype(np.float32))
## Calculate statistics of delay template
mad_tau = np.zeros((ninput, ), dtype=phi.dtype)
std_tau = np.zeros((ninput, ), dtype=phi.dtype)
mad_tau_by_diff = np.zeros((ninput, ndiff), dtype=phi.dtype)
std_tau_by_diff = np.zeros((ninput, ndiff), dtype=phi.dtype)
for ii in range(ninput):
this_flag = tau_flag[ii]
if np.any(this_flag):
std_tau[ii] = np.std(tau[ii, this_flag])
mad_tau[ii] = 1.48625 * wq.median(np.abs(tau[ii]),
this_flag.astype(np.float32))
for dd in range(ndiff):
this_diff = this_flag & (lbl_diff == dd)
if np.any(this_diff):
std_tau_by_diff[ii, dd] = np.std(tau[ii, this_diff])
mad_tau_by_diff[ii, dd] = 1.48625 * wq.median(
np.abs(tau[ii]), this_diff.astype(np.float32))
## Define output
res = {
"timestamp": {
"data": timestamp,
"axis": ["div", "time"]
},
"is_daytime": {
"data": is_daytime,
"axis": ["div", "time"]
},
"csd": {
"data": kcsd,
"axis": ["div", "time"]
},
"pair_map": {
"data": lbl_diff,
"axis": ["time"]
},
"pair_count": {
"data": cnt_diff,
"axis": ["pair"]
},
"gain": {
"data": gaincal,
"axis": ["freq", "input", "time"]
},
"frac_err": {
"data": frac_err_cal,
"axis": ["freq", "input", "time"]
},
"flags/gain": {
"data": flag,
"axis": ["freq", "input", "time"],
"flag": True
},
"flags/gain_conservative": {
"data": c_flag,
"axis": ["freq", "input", "time"],
"flag": True
},
"flags/count": {
"data": count,
"axis": ["freq", "input"],
"flag": True
},
"flags/stat": {
"data": stat_flag,
"axis": ["freq", "input"],
"flag": True
},
"flags/count_by_pair": {
"data": count_by_diff,
"axis": ["freq", "input", "pair"],
"flag": True
},
"flags/stat_by_pair": {
"data": stat_flag_by_diff,
"axis": ["freq", "input", "pair"],
"flag": True
},
"med_amp": {
"data": med_amp,
"axis": ["freq", "input", "pair"]
},
"med_phi": {
"data": med_phi,
"axis": ["freq", "input", "pair"]
},
"flags/group_flag": {
"data": group_flag,
"axis": ["group", "input"],
"flag": True
},
"cmn_amp": {
"data": cmn_amp,
"axis": ["freq", "group", "time"]
},
"cmn_phi": {
"data": cmn_phi,
"axis": ["freq", "group", "time"]
},
"amp": {
"data": damp,
"axis": ["freq", "input", "time"]
},
"phi": {
"data": dphi,
"axis": ["freq", "input", "time"]
},
"std_amp": {
"data": std_amp,
"axis": ["freq", "input"]
},
"std_amp_by_pair": {
"data": std_amp_by_diff,
"axis": ["freq", "input", "pair"]
},
"mad_amp": {
"data": mad_amp,
"axis": ["freq", "input"]
},
"mad_amp_by_pair": {
"data": mad_amp_by_diff,
"axis": ["freq", "input", "pair"]
},
"std_phi": {
"data": std_phi,
"axis": ["freq", "input"]
},
"std_phi_by_pair": {
"data": std_phi_by_diff,
"axis": ["freq", "input", "pair"]
},
"mad_phi": {
"data": mad_phi,
"axis": ["freq", "input"]
},
"mad_phi_by_pair": {
"data": mad_phi_by_diff,
"axis": ["freq", "input", "pair"]
},
"tau": {
"data": tau,
"axis": ["input", "time"]
},
"flags/tau": {
"data": tau_flag,
"axis": ["input", "time"],
"flag": True
},
"flags/tau_count": {
"data": tau_count,
"axis": ["input"],
"flag": True
},
"flags/tau_stat": {
"data": tau_stat_flag,
"axis": ["input"],
"flag": True
},
"flags/tau_count_by_pair": {
"data": tau_count_by_diff,
"axis": ["input", "pair"],
"flag": True
},
"flags/tau_stat_by_pair": {
"data": tau_stat_flag_by_diff,
"axis": ["input", "pair"],
"flag": True
},
"std_tau": {
"data": std_tau,
"axis": ["input"]
},
"std_tau_by_pair": {
"data": std_tau_by_diff,
"axis": ["input", "pair"]
},
"mad_tau": {
"data": mad_tau,
"axis": ["input"]
},
"mad_tau_by_pair": {
"data": mad_tau_by_diff,
"axis": ["input", "pair"]
},
"resid_phi": {
"data": resid,
"axis": ["freq", "input", "time"]
},
"std_resid_phi": {
"data": std_resid,
"axis": ["freq", "input"]
},
"std_resid_phi_by_pair": {
"data": std_resid_by_diff,
"axis": ["freq", "input", "pair"]
},
"mad_resid_phi": {
"data": mad_resid,
"axis": ["freq", "input"]
},
"mad_resid_phi_by_pair": {
"data": mad_resid_by_diff,
"axis": ["freq", "input", "pair"]
},
}
## Create the output container
logger.info("Creating StabilityData container.")
data = StabilityData()
data.create_index_map(
"div", np.array(["numerator", "denominator"], dtype=np.string_))
data.create_index_map("pair", np.array(uniq_diff, dtype=np.string_))
data.create_index_map("group", np.array(group_str, dtype=np.string_))
data.create_index_map("freq", freq)
data.create_index_map("input", inputs)
data.create_index_map("time", timestamp[0, :])
logger.info("Writing datsets to container.")
for name, dct in res.iteritems():
is_flag = dct.get('flag', False)
if is_flag:
dset = data.create_flag(name.split('/')[-1], data=dct['data'])
else:
dset = data.create_dataset(name, data=dct['data'])
dset.attrs['axis'] = np.array(dct['axis'], dtype=np.string_)
data.attrs['phase_ref'] = np.array(
[iref for iref in index_phase_ref if iref is not None])
# Determine the output filename and save results
start_time, end_time = ephemeris.unix_to_datetime(
np.percentile(timestamp, [0, 100]))
tfmt = "%Y%m%d"
night_str = 'night_' if not np.any(is_daytime) else ''
output_file = os.path.join(
config.output_dir, "%s_%s_%sraw_stability_data.h5" %
(start_time.strftime(tfmt), end_time.strftime(tfmt), night_str))
logger.info("Saving results to %s." % output_file)
data.save(output_file)
def view(self):
if self.lsd is None:
return panel.pane.Markdown("No data selected.")
try:
sens_container = self.data.load_file(self.revision, self.lsd,
"sensitivity")
except DataError as err:
return panel.pane.Markdown(
f"Error: {str(err)}. Please report this problem.")
# Index map for ra (x-axis)
sens_csd = csd(sens_container.time)
index_map_ra = (sens_csd - self.lsd.lsd) * 360
axis_name_ra = "RA [degrees]"
# Index map for frequency (y-axis)
index_map_f = np.linspace(800.0, 400.0, 1024, endpoint=False)
axis_name_f = "Frequency [MHz]"
# Apply data selections
if self.polarization == self.mean_pol_text:
sel_pol = np.where((sens_container.index_map["pol"] == "XX")
| (sens_container.index_map["pol"] == "YY"))[0]
sens = np.squeeze(sens_container.measured[:, sel_pol])
sens = np.squeeze(np.nanmean(sens, axis=1))
else:
sel_pol = np.where(
sens_container.index_map["pol"] == self.polarization)[0]
sens = np.squeeze(sens_container.measured[:, sel_pol])
if self.flag_mask:
sens = np.where(self._flags_mask(index_map_ra).T, np.nan, sens)
# Set flagged data to nan
sens = np.where(sens == 0, np.nan, sens)
if self.mask_rfi:
try:
rfi_container = self.data.load_file(self.revision, self.lsd,
"rfi")
except DataError as err:
return panel.pane.Markdown(
f"Error: {str(err)}. Please report this problem.")
rfi = np.squeeze(rfi_container.mask[:])
# calculate percentage masked to print later
rfi_percentage = round(np.count_nonzero(rfi) / rfi.size * 100)
sens *= np.where(rfi, np.nan, 1)
if self.divide_by_estimate:
estimate = np.squeeze(sens_container.radiometer[:, sel_pol])
if self.polarization == self.mean_pol_text:
estimate = np.squeeze(np.nanmean(estimate, axis=1))
estimate = np.where(estimate == 0, np.nan, estimate)
sens = sens / estimate
if self.transpose:
sens = sens.T
index_x = index_map_f
index_y = index_map_ra
axis_names = [axis_name_f, axis_name_ra]
xlim, ylim = self.ylim, self.xlim
else:
index_x = index_map_ra
index_y = index_map_f
axis_names = [axis_name_ra, axis_name_f]
xlim, ylim = self.xlim, self.ylim
image_opts = {
"clim": self.colormap_range,
"logz": self.logarithmic_colorscale,
"cmap": process_cmap("viridis", provider="matplotlib"),
"colorbar": True,
"xticks": [0, 60, 120, 180, 240, 300, 360],
}
if self.mask_rfi:
image_opts["title"] = f"RFI mask: {rfi_percentage}%"
overlay_opts = {
"xlim": xlim,
"ylim": ylim,
}
# Fill in missing data
img = hv_image_with_gaps(index_x,
index_y,
sens,
opts=image_opts,
kdims=axis_names).opts(**overlay_opts)
if self.serverside_rendering is not None:
# set colormap
cmap_inferno = copy.copy(matplotlib_cm.get_cmap("viridis"))
# Set z-axis normalization (other possible values are 'eq_hist', 'cbrt').
if self.logarithmic_colorscale:
normalization = "log"
else:
normalization = "linear"
# datashade/rasterize the image
img = self.serverside_rendering(
img,
cmap=cmap_inferno,
precompute=True,
x_range=xlim,
y_range=ylim,
normalization=normalization,
# TODO: set xticks like above
)
if self.mark_day_time:
# Calculate the sun rise/set times on this sidereal day
# Start and end times of the CSD
start_time = csd_to_unix(self.lsd.lsd)
end_time = csd_to_unix(self.lsd.lsd + 1)
times, rises = chime.rise_set_times(
skyfield_wrapper.ephemeris["sun"],
start_time,
end_time,
diameter=-10,
)
sun_rise = 0
sun_set = 0
for t, r in zip(times, rises):
if r:
sun_rise = (unix_to_csd(t) % 1) * 360
else:
sun_set = (unix_to_csd(t) % 1) * 360
# Highlight the day time data
opts = {
"color": "grey",
"alpha": 0.5,
"line_width": 1,
"line_color": "black",
"line_dash": "dashed",
}
span = hv.HSpan if self.transpose else hv.VSpan
if sun_rise < sun_set:
img *= span(sun_rise, sun_set).opts(**opts)
else:
img *= span(self.xlim[0], sun_set).opts(**opts)
img *= span(sun_rise, self.xlim[-1]).opts(**opts)
img.opts(
# Fix height, but make width responsive
height=self.height,
responsive=True,
bgcolor="lightgray",
shared_axes=True,
)
return panel.Row(img, width_policy="max")