Calibration Smoothing¶
by Josh Dillon, last updated March 29, 2023
This notebook runs calibration smoothing to the gains coming out of file_calibration notebook. It removes any flags founds on by that notebook and replaces them with flags generated from full_day_rfi and full_day_antenna_flagging. It also plots the results for a couple of antennas.
Here's a set of links to skip to particular figures and tables:
• Figure 1: Full-Day Gain Amplitudes Before and After smooth_cal¶
• Figure 2: Full-Day Gain Phases Before and After smooth_cal¶
• Figure 3: Full-Day $\chi^2$ / DoF Waterfall from Redundant-Baseline Calibration¶
• Figure 4: Average $\chi^2$ per Antenna vs. Time and Frequency¶
In [1]:
import time
tstart = time.time()
In [2]:
import os
os.environ['HDF5_USE_FILE_LOCKING'] = 'FALSE'
import h5py
import hdf5plugin # REQUIRED to have the compression plugins available
import numpy as np
import glob
import copy
import warnings
import matplotlib
import matplotlib.pyplot as plt
from hera_cal import io, utils, smooth_cal
from hera_qm.time_series_metrics import true_stretches
%matplotlib inline
from IPython.display import display, HTML
Parse inputs¶
In [3]:
# get files
SUM_FILE = os.environ.get("SUM_FILE", None)
# SUM_FILE = '/users/jsdillon/lustre/H6C/abscal/2459853/zen.2459853.25518.sum.uvh5'
SUM_SUFFIX = os.environ.get("SUM_SUFFIX", 'sum.uvh5')
CAL_SUFFIX = os.environ.get("CAL_SUFFIX", 'sum.omni.calfits')
SMOOTH_CAL_SUFFIX = os.environ.get("SMOOTH_CAL_SUFFIX", 'sum.smooth.calfits')
ANT_FLAG_SUFFIX = os.environ.get("ANT_FLAG_SUFFIX", 'sum.antenna_flags.h5')
RFI_FLAG_SUFFIX = os.environ.get("RFI_FLAG_SUFFIX", 'sum.flag_waterfall.h5')
FREQ_SMOOTHING_SCALE = float(os.environ.get("FREQ_SMOOTHING_SCALE", 10.0)) # MHz
TIME_SMOOTHING_SCALE = float(os.environ.get("TIME_SMOOTHING_SCALE", 6e5)) # seconds
EIGENVAL_CUTOFF = float(os.environ.get("EIGENVAL_CUTOFF", 1e-12))
for setting in ['SUM_FILE', 'SUM_SUFFIX', 'CAL_SUFFIX', 'SMOOTH_CAL_SUFFIX', 'ANT_FLAG_SUFFIX',
'RFI_FLAG_SUFFIX', 'FREQ_SMOOTHING_SCALE', 'TIME_SMOOTHING_SCALE', 'EIGENVAL_CUTOFF']:
print(f'{setting} = {eval(setting)}')
SUM_FILE = /mnt/sn1/2460327/zen.2460327.25433.sum.uvh5 SUM_SUFFIX = sum.uvh5 CAL_SUFFIX = sum.omni.calfits SMOOTH_CAL_SUFFIX = sum.smooth.calfits ANT_FLAG_SUFFIX = sum.antenna_flags.h5 RFI_FLAG_SUFFIX = sum.flag_waterfall.h5 FREQ_SMOOTHING_SCALE = 10.0 TIME_SMOOTHING_SCALE = 600000.0 EIGENVAL_CUTOFF = 1e-12
Load files¶
In [4]:
sum_glob = '.'.join(SUM_FILE.split('.')[:-3]) + '.*.' + SUM_SUFFIX
cal_files_glob = sum_glob.replace(SUM_SUFFIX, CAL_SUFFIX)
cal_files = sorted(glob.glob(cal_files_glob))
print(f'Found {len(cal_files)} *.{CAL_SUFFIX} files starting with {cal_files[0]}.')
Found 1759 *.sum.omni.calfits files starting with /mnt/sn1/2460327/zen.2460327.25433.sum.omni.calfits.
In [5]:
rfi_flag_files_glob = sum_glob.replace(SUM_SUFFIX, RFI_FLAG_SUFFIX)
rfi_flag_files = sorted(glob.glob(rfi_flag_files_glob))
print(f'Found {len(rfi_flag_files)} *.{RFI_FLAG_SUFFIX} files starting with {rfi_flag_files[0]}.')
Found 1759 *.sum.flag_waterfall.h5 files starting with /mnt/sn1/2460327/zen.2460327.25433.sum.flag_waterfall.h5.
In [6]:
ant_flag_files_glob = sum_glob.replace(SUM_SUFFIX, ANT_FLAG_SUFFIX)
ant_flag_files = sorted(glob.glob(ant_flag_files_glob))
print(f'Found {len(ant_flag_files)} *.{ANT_FLAG_SUFFIX} files starting with {ant_flag_files[0]}.')
Found 1759 *.sum.antenna_flags.h5 files starting with /mnt/sn1/2460327/zen.2460327.25433.sum.antenna_flags.h5.
In [7]:
cs = smooth_cal.CalibrationSmoother(cal_files, flag_file_list=(ant_flag_files + rfi_flag_files), ignore_calflags=True,
pick_refant=True, propagate_refant_flags=True, load_chisq=True, load_cspa=True)
for pol in cs.refant:
print(f'Reference antenna {cs.refant[pol][0]} selected for {pol}.')
Mean of empty slice
Reference antenna 129 selected for Jee. Reference antenna 204 selected for Jnn.
In [8]:
# duplicate a small number of abscal gains for plotting
antnums = set([ant[0] for ant in cs.ants])
flags_per_antnum = [np.sum(cs.flag_grids[ant, 'Jnn']) + np.sum(cs.flag_grids[ant, 'Jee']) for ant in antnums]
refant_nums = [ant[0] for ant in cs.refant.values()]
candidate_ants = [ant for ant, nflags in zip(antnums, flags_per_antnum) if (ant not in refant_nums) and (nflags <= np.percentile(flags_per_antnum, 25))
and not np.all(cs.flag_grids[ant, 'Jee']) and not np.all(cs.flag_grids[ant, 'Jnn'])]
ants_to_plot = [func(candidate_ants) for func in (np.min, np.max)]
abscal_gains = {(ant, pol): np.array(cs.gain_grids[(ant, pol)]) for ant in ants_to_plot for pol in ['Jee', 'Jnn']}
Perform smoothing¶
In [9]:
cs.time_freq_2D_filter(freq_scale=FREQ_SMOOTHING_SCALE, time_scale=TIME_SMOOTHING_SCALE, eigenval_cutoff=EIGENVAL_CUTOFF,
method='DPSS', fit_method='lu_solve', fix_phase_flips=True, flag_phase_flip_ints=True)
WARNING:jax._src.lib.xla_bridge:No GPU/TPU found, falling back to CPU. (Set TF_CPP_MIN_LOG_LEVEL=0 and rerun for more info.)
103 phase-flipped integrations detected on antenna (135, 'Jnn') between 2460327.636294527 and 2460327.647703035. 103 phase-flipped integrations detected on antenna (117, 'Jnn') between 2460327.636294527 and 2460327.647703035. 103 phase-flipped integrations detected on antenna (116, 'Jnn') between 2460327.636294527 and 2460327.647703035. 103 phase-flipped integrations detected on antenna (137, 'Jnn') between 2460327.636294527 and 2460327.647703035. 103 phase-flipped integrations detected on antenna (81, 'Jnn') between 2460327.636294527 and 2460327.647703035. 1212 phase-flipped integrations detected on antenna (144, 'Jnn') between 2460327.5122549664 and 2460327.647703035.
Plot results¶
In [10]:
lst_grid = utils.JD2LST(cs.time_grid) * 12 / np.pi
lst_grid[lst_grid > lst_grid[-1]] -= 24
In [11]:
def amplitude_plot(ant_to_plot):
with warnings.catch_warnings():
warnings.simplefilter("ignore")
# Pick vmax to not saturate 90% of the abscal gains
vmax = np.max([np.percentile(np.abs(cs.gain_grids[ant_to_plot, pol][~cs.flag_grids[ant_to_plot, pol]]), 99) for pol in ['Jee', 'Jnn']])
display(HTML(f'<h2>Antenna {ant_to_plot} Amplitude Waterfalls</h2>'))
# Plot abscal gain amplitude waterfalls for a single antenna
fig, axes = plt.subplots(4, 2, figsize=(14,14), gridspec_kw={'height_ratios': [1, 1, .4, .4]})
for ax, pol in zip(axes[0], ['Jee', 'Jnn']):
ant = (ant_to_plot, pol)
extent=[cs.freqs[0]/1e6, cs.freqs[-1]/1e6, lst_grid[-1], lst_grid[0]]
im = ax.imshow(np.where(cs.flag_grids[ant], np.nan, np.abs(cs.gain_grids[ant])), aspect='auto', cmap='inferno',
interpolation='nearest', vmin=0, vmax=vmax, extent=extent)
ax.set_title(f'Smoothcal Gain Amplitude of Antenna {ant[0]}: {pol[-1]}-polarized' )
ax.set_xlabel('Frequency (MHz)')
ax.set_ylabel('LST (Hours)')
ax.set_xlim([cs.freqs[0]/1e6, cs.freqs[-1]/1e6])
ax.set_yticklabels(ax.get_yticks() % 24)
plt.colorbar(im, ax=ax, orientation='horizontal', pad=.15)
# Now flagged plot abscal waterfall
for ax, pol in zip(axes[1], ['Jee', 'Jnn']):
ant = (ant_to_plot, pol)
extent=[cs.freqs[0]/1e6, cs.freqs[-1]/1e6, lst_grid[-1], lst_grid[0]]
im = ax.imshow(np.where(cs.flag_grids[ant], np.nan, np.abs(abscal_gains[ant])), aspect='auto', cmap='inferno',
interpolation='nearest', vmin=0, vmax=vmax, extent=extent)
ax.set_title(f'Abscal Gain Amplitude of Antenna {ant[0]}: {pol[-1]}-polarized' )
ax.set_xlabel('Frequency (MHz)')
ax.set_ylabel('LST (Hours)')
ax.set_xlim([cs.freqs[0]/1e6, cs.freqs[-1]/1e6])
ax.set_yticklabels(ax.get_yticks() % 24)
plt.colorbar(im, ax=ax, orientation='horizontal', pad=.15)
# Now plot mean gain spectra
for ax, pol in zip(axes[2], ['Jee', 'Jnn']):
ant = (ant_to_plot, pol)
nflags_spectrum = np.sum(cs.flag_grids[ant], axis=0)
to_plot = nflags_spectrum <= np.percentile(nflags_spectrum, 75)
ax.plot(cs.freqs[to_plot] / 1e6, np.nanmean(np.where(cs.flag_grids[ant], np.nan, np.abs(abscal_gains[ant])), axis=0)[to_plot], 'r.', label='Abscal')
ax.plot(cs.freqs[to_plot] / 1e6, np.nanmean(np.where(cs.flag_grids[ant], np.nan, np.abs(cs.gain_grids[ant])), axis=0)[to_plot], 'k.', ms=2, label='Smoothed')
ax.set_ylim([0, vmax])
ax.set_xlim([cs.freqs[0]/1e6, cs.freqs[-1]/1e6])
ax.set_xlabel('Frequency (MHz)')
ax.set_ylabel('|g| (unitless)')
ax.set_title(f'Mean Infrequently-Flagged Gain Amplitude of Antenna {ant[0]}: {pol[-1]}-polarized')
ax.legend(loc='upper left')
# Now plot mean gain time series
for ax, pol in zip(axes[3], ['Jee', 'Jnn']):
ant = (ant_to_plot, pol)
nflags_series = np.sum(cs.flag_grids[ant], axis=1)
to_plot = nflags_series <= np.percentile(nflags_series, 75)
ax.plot(lst_grid[to_plot], np.nanmean(np.where(cs.flag_grids[ant], np.nan, np.abs(abscal_gains[ant])), axis=1)[to_plot], 'r.', label='Abscal')
ax.plot(lst_grid[to_plot], np.nanmean(np.where(cs.flag_grids[ant], np.nan, np.abs(cs.gain_grids[ant])), axis=1)[to_plot], 'k.', ms=2, label='Smoothed')
ax.set_ylim([0, vmax])
ax.set_xlabel('LST (hours)')
ax.set_ylabel('|g| (unitless)')
ax.set_title(f'Mean Infrequently-Flagged Gain Amplitude of Antenna {ant[0]}: {pol[-1]}-polarized')
ax.set_xticklabels(ax.get_xticks() % 24)
ax.legend(loc='upper left')
plt.tight_layout()
plt.show()
In [12]:
def phase_plot(ant_to_plot):
with warnings.catch_warnings():
warnings.simplefilter("ignore")
display(HTML(f'<h2>Antenna {ant_to_plot} Phase Waterfalls</h2>'))
fig, axes = plt.subplots(4, 2, figsize=(14,14), gridspec_kw={'height_ratios': [1, 1, .4, .4]})
# Plot phase waterfalls for a single antenna
for ax, pol in zip(axes[0], ['Jee', 'Jnn']):
ant = (ant_to_plot, pol)
extent=[cs.freqs[0]/1e6, cs.freqs[-1]/1e6, lst_grid[-1], lst_grid[0]]
im = ax.imshow(np.where(cs.flag_grids[ant], np.nan, np.angle(cs.gain_grids[ant])), aspect='auto', cmap='inferno',
interpolation='nearest', vmin=-np.pi, vmax=np.pi, extent=extent)
ax.set_title(f'Smoothcal Gain Phase of Ant {ant[0]} / Ant {cs.refant[pol][0]}: {pol[-1]}-polarized')
ax.set_xlabel('Frequency (MHz)')
ax.set_ylabel('LST (Hours)')
ax.set_xlim([cs.freqs[0]/1e6, cs.freqs[-1]/1e6])
ax.set_yticklabels(ax.get_yticks() % 24)
plt.colorbar(im, ax=ax, orientation='horizontal', pad=.15)
# Now plot abscal phase waterfall
for ax, pol in zip(axes[1], ['Jee', 'Jnn']):
ant = (ant_to_plot, pol)
extent=[cs.freqs[0]/1e6, cs.freqs[-1]/1e6, lst_grid[-1], lst_grid[0]]
im = ax.imshow(np.where(cs.flag_grids[ant], np.nan, np.angle(abscal_gains[ant])), aspect='auto', cmap='inferno',
interpolation='nearest', vmin=-np.pi, vmax=np.pi, extent=extent)
ax.set_title(f'Abscal Gain Phase of Ant {ant[0]} / Ant {cs.refant[pol][0]}: {pol[-1]}-polarized')
ax.set_xlabel('Frequency (MHz)')
ax.set_ylabel('LST (Hours)')
ax.set_xlim([cs.freqs[0]/1e6, cs.freqs[-1]/1e6])
ax.set_yticklabels(ax.get_yticks() % 24)
plt.colorbar(im, ax=ax, orientation='horizontal', pad=.15)
# Now plot median gain spectra
for ax, pol in zip(axes[2], ['Jee', 'Jnn']):
ant = (ant_to_plot, pol)
nflags_spectrum = np.sum(cs.flag_grids[ant], axis=0)
to_plot = nflags_spectrum <= np.percentile(nflags_spectrum, 75)
ax.plot(cs.freqs[to_plot] / 1e6, np.nanmedian(np.where(cs.flag_grids[ant], np.nan, np.angle(abscal_gains[ant])), axis=0)[to_plot], 'r.', label='Abscal')
ax.plot(cs.freqs[to_plot] / 1e6, np.nanmedian(np.where(cs.flag_grids[ant], np.nan, np.angle(cs.gain_grids[ant])), axis=0)[to_plot], 'k.', ms=2, label='Smoothed')
ax.set_ylim([-np.pi, np.pi])
ax.set_xlim([cs.freqs[0]/1e6, cs.freqs[-1]/1e6])
ax.set_xlabel('Frequency (MHz)')
ax.set_ylabel(f'Phase of g$_{{{ant[0]}}}$ / g$_{{{cs.refant[pol][0]}}}$')
ax.set_title(f'Median Infrequently-Flagged Gain Phase of Ant {ant[0]} / Ant {cs.refant[pol][0]}: {pol[-1]}-polarized')
ax.legend(loc='upper left')
# # Now plot median gain time series
for ax, pol in zip(axes[3], ['Jee', 'Jnn']):
ant = (ant_to_plot, pol)
nflags_series = np.sum(cs.flag_grids[ant], axis=1)
to_plot = nflags_series <= np.percentile(nflags_series, 75)
ax.plot(lst_grid[to_plot], np.nanmean(np.where(cs.flag_grids[ant], np.nan, np.angle(abscal_gains[ant])), axis=1)[to_plot], 'r.', label='Abscal')
ax.plot(lst_grid[to_plot], np.nanmean(np.where(cs.flag_grids[ant], np.nan, np.angle(cs.gain_grids[ant])), axis=1)[to_plot], 'k.', ms=2, label='Smoothed')
ax.set_ylim([-np.pi, np.pi])
ax.set_xlabel('LST (hours)')
ax.set_ylabel(f'Phase of g$_{{{ant[0]}}}$ / g$_{{{cs.refant[pol][0]}}}$')
ax.set_title(f'Mean Infrequently-Flagged Gain Phase of Ant {ant[0]} / Ant {cs.refant[pol][0]}: {pol[-1]}-polarized')
ax.set_xticklabels(ax.get_xticks() % 24)
ax.legend(loc='upper left')
plt.tight_layout()
plt.show()
Figure 1: Full-Day Gain Amplitudes Before and After smooth_cal¶
Here we plot abscal and smooth_cal gain amplitudes for both of the sample antennas. We also show means across time/frequency, excluding frequencies/times that are frequently flagged.
In [13]:
for ant_to_plot in ants_to_plot:
amplitude_plot(ant_to_plot)
Antenna 36 Amplitude Waterfalls
Antenna 282 Amplitude Waterfalls
Figure 2: Full-Day Gain Phases Before and After smooth_cal¶
Here we plot abscal and smooth_cal phases relative to each polarization's reference antenna for both of the sample antennas. We also show medians across time/frequency, excluding frequencies/times that are frequently flagged.
In [14]:
for ant_to_plot in ants_to_plot:
phase_plot(ant_to_plot)
Antenna 36 Phase Waterfalls
Antenna 282 Phase Waterfalls
Examine $\chi^2$¶
In [15]:
def chisq_plot():
fig, axes = plt.subplots(1, 2, figsize=(14, 10), sharex=True, sharey=True)
extent = [cs.freqs[0]/1e6, cs.freqs[-1]/1e6, lst_grid[-1], lst_grid[0]]
for ax, pol in zip(axes, ['Jee', 'Jnn']):
im = ax.imshow(np.where(cs.flag_grids[cs.refant[pol]], np.nan, cs.chisq_grids[pol]), vmin=1, vmax=5,
aspect='auto', cmap='turbo', interpolation='none', extent=extent)
ax.set_yticklabels(ax.get_yticks() % 24)
ax.set_title(f'{pol[1:]}-Polarized $\\chi^2$ / DoF')
ax.set_xlabel('Frequency (MHz)')
axes[0].set_ylabel('LST (hours)')
plt.tight_layout()
fig.colorbar(im, ax=axes, pad=.07, label='$\\chi^2$ / DoF', orientation='horizontal', extend='both', aspect=50)
Figure 3: Full-Day $\chi^2$ / DoF Waterfall from Redundant-Baseline Calibration¶
Here we plot $\chi^2$ per degree of freedom from redundant-baseline calibration for both polarizations separately. While this plot is a little out of place, as it was not produced by this notebook, it is a convenient place where all the necessary components are readily available. If the array were perfectly redundant and any non-redundancies in the calibrated visibilities were explicable by thermal noise alone, this waterfall should be all 1.
In [16]:
chisq_plot()
FixedFormatter should only be used together with FixedLocator
In [17]:
avg_cspa_vs_time = {ant: np.nanmean(np.where(cs.flag_grids[ant], np.nan, cs.cspa_grids[ant]), axis=1) for ant in cs.ants}
avg_cspa_vs_freq = {ant: np.nanmean(np.where(cs.flag_grids[ant], np.nan, cs.cspa_grids[ant]), axis=0) for ant in cs.ants}
Mean of empty slice Mean of empty slice
In [18]:
def cspa_vs_time_plot():
fig, axes = plt.subplots(2, 1, figsize=(14, 8), sharex=True, sharey=True, gridspec_kw={'hspace': 0})
for ax, pol in zip(axes, ['Jee', 'Jnn']):
detail_cutoff = np.percentile([np.nanmean(m) for ant, m in avg_cspa_vs_time.items()
if ant[1] == pol and np.isfinite(np.nanmean(m))], 95)
for ant in avg_cspa_vs_time:
if ant[1] == pol and not np.all(cs.flag_grids[ant]):
if np.nanmean(avg_cspa_vs_time[ant]) > detail_cutoff:
ax.plot(lst_grid, avg_cspa_vs_time[ant], label=ant, zorder=100)
else:
ax.plot(lst_grid, avg_cspa_vs_time[ant], c='grey', alpha=.2, lw=.5)
ax.legend(title=f'{pol[1:]}-Polarized', ncol=2)
ax.set_ylabel('Mean Unflagged $\\chi^2$ per Antenna')
ax.set_xlabel('LST (hours)')
ax.set_xticklabels(ax.get_xticks() % 24)
plt.ylim([1, 5.4])
plt.tight_layout()
In [19]:
def cspa_vs_freq_plot():
fig, axes = plt.subplots(2, 1, figsize=(14, 6), sharex=True, sharey=True, gridspec_kw={'hspace': 0})
for ax, pol in zip(axes, ['Jee', 'Jnn']):
detail_cutoff = np.percentile([np.nanmean(m) for ant, m in avg_cspa_vs_freq.items()
if ant[1] == pol and np.isfinite(np.nanmean(m))], 95)
for ant in avg_cspa_vs_freq:
if ant[1] == pol and not np.all(cs.flag_grids[ant]):
if np.nanmean(avg_cspa_vs_freq[ant]) > detail_cutoff:
ax.plot(cs.freqs / 1e6, avg_cspa_vs_freq[ant], label=ant, zorder=100)
else:
ax.plot(cs.freqs / 1e6, avg_cspa_vs_freq[ant], c='grey', alpha=.2, lw=.5)
ax.legend(title=f'{pol[1:]}-Polarized', ncol=2)
ax.set_ylabel('Mean Unflagged $\\chi^2$ per Antenna')
ax.set_xlabel('Frequency (MHz)')
plt.ylim([1, 5.4])
plt.tight_layout()
Figure 4: Average $\chi^2$ per Antenna vs. Time and Frequency¶
Here we plot $\chi^2$ per antenna from redundant-baseline calibration, separating polarizations and averaging the unflagged pixels in the waterfalls over frequency or time. The worst 5% of antennas are shown in color and highlighted in the legends, the rest are shown in grey.
In [20]:
cspa_vs_time_plot()
cspa_vs_freq_plot()
Mean of empty slice FixedFormatter should only be used together with FixedLocator
Save Results¶
In [21]:
add_to_history = 'Produced by calibration_smoothing notebook with the following environment:\n' + '=' * 65 + '\n' + os.popen('conda env export').read() + '=' * 65
In [22]:
cs.write_smoothed_cal(output_replace=(CAL_SUFFIX, SMOOTH_CAL_SUFFIX), add_to_history=add_to_history, clobber=True)
Mean of empty slice
Metadata¶
In [23]:
for repo in ['hera_cal', 'hera_qm', 'hera_filters', 'hera_notebook_templates', 'pyuvdata']:
exec(f'from {repo} import __version__')
print(f'{repo}: {__version__}')
hera_cal: 3.4.2.dev11+ga9e1297 hera_qm: 2.1.3.dev5+g3e71720 hera_filters: 0.1.0 hera_notebook_templates: 0.1.dev486+gfb8560a pyuvdata: 2.4.0
In [24]:
print(f'Finished execution in {(time.time() - tstart) / 60:.2f} minutes.')
Finished execution in 24.82 minutes.