by Josh Dillon last updated June 19, 2023
This notebook parses and summarizes the output of the file_calibration
notebook to produce a report on per-antenna malfunctions on a daily basis.
Quick links:
import numpy as np
import pandas as pd
import glob
import os
import matplotlib.pyplot as plt
from hera_cal import io, utils
from hera_qm import ant_class
from uvtools.plot import plot_antpos, plot_antclass
%matplotlib inline
from IPython.display import display, HTML
# Parse settings from environment
ANT_CLASS_FOLDER = os.environ.get("ANT_CLASS_FOLDER", "./")
SUM_FILE = os.environ.get("SUM_FILE", None)
# ANT_CLASS_FOLDER = '/lustre/aoc/projects/hera/h6c-analysis/IDR2/2459866'
# SUM_FILE = '/lustre/aoc/projects/hera/h6c-analysis/IDR2/2459866/zen.2459866.25292.sum.uvh5'
OC_SKIP_OUTRIGGERS = os.environ.get("OC_SKIP_OUTRIGGERS", "TRUE").upper() == "TRUE"
for param in ['ANT_CLASS_FOLDER', 'SUM_FILE', 'OC_SKIP_OUTRIGGERS']:
print(f"{param} = '{eval(param)}'")
ANT_CLASS_FOLDER = '/mnt/sn1/2460166' SUM_FILE = '/mnt/sn1/2460166/zen.2460166.46128.sum.uvh5' OC_SKIP_OUTRIGGERS = 'True'
if SUM_FILE is not None:
from astropy.time import Time, TimeDelta
utc = Time(float(SUM_FILE.split('zen.')[-1].split('.sum.uvh5')[0]), format='jd').datetime
print(f'Date: {utc.month}-{utc.day}-{utc.year}')
Date: 8-9-2023
# set thresholds for fraction of the day
overall_thresh = .1
all_zero_thresh = .1
eo_zeros_thresh = .1
xengine_diff_thresh = .1
cross_pol_thresh = .5
bad_fem_thresh = .1
high_power_thresh = .1
low_power_thresh = .1
low_corr_thresh = .1
bad_shape_thresh = .5
excess_rfi_thresh = .1
chisq_thresh = .25
# Load csvs
csv_files = sorted(glob.glob(os.path.join(ANT_CLASS_FOLDER, '*.ant_class.csv')))
jds = [float(f.split('/')[-1].split('zen.')[-1].split('.sum')[0]) for f in csv_files]
tables = [pd.read_csv(f).dropna(axis=0, how='all') for f in csv_files]
table_cols = tables[0].columns[1::2]
class_cols = tables[0].columns[2::2]
print(f'Found {len(csv_files)} csv files starting with {csv_files[0]}')
Found 360 csv files starting with /mnt/sn1/2460166/zen.2460166.42101.sum.ant_class.csv
# parse ant_strings
ap_strs = np.array(tables[0]['Antenna'])
ants = sorted(set(int(a[:-1]) for a in ap_strs))
translator = ''.maketrans('e', 'n') | ''.maketrans('n', 'e')
# get node numbers
node_dict = {ant: 'Unknown' for ant in ants}
try:
from hera_mc import cm_hookup
hookup = cm_hookup.get_hookup('default')
for ant_name in hookup:
ant = int("".join(filter(str.isdigit, ant_name)))
if ant in node_dict:
if hookup[ant_name].get_part_from_type('node')['E<ground'] is not None:
node_dict[ant] = int(hookup[ant_name].get_part_from_type('node')['E<ground'][1:])
except:
pass
nodes = sorted(set(node_dict.values()))
def classification_array(col):
class_array = np.vstack([t[col] for t in tables])
class_array[class_array == 'good'] = 1.7
class_array[class_array == 'suspect'] = 1
class_array[class_array == 'bad'] = 0
return class_array.astype(float)
if SUM_FILE is not None:
hd = io.HERADataFastReader(SUM_FILE)
ap_tuples = [(int(ap[:-1]), {'e': 'Jee', 'n': 'Jnn'}[ap[-1]]) for ap in ap_strs]
bad_bools = np.mean(classification_array('Antenna Class') == 0, axis=0) > overall_thresh
bad_aps = [ap_tuples[i] for i in np.arange(len(ap_tuples))[bad_bools]]
suspect_bools = np.mean(classification_array('Antenna Class') == 1, axis=0) > overall_thresh
suspect_aps = [ap_tuples[i] for i in np.arange(len(ap_tuples))[suspect_bools] if ap_tuples[i] not in bad_aps]
good_aps = [ap for ap in ap_tuples if ap not in bad_aps and ap not in suspect_aps]
overall_class = ant_class.AntennaClassification(bad=bad_aps, suspect=suspect_aps, good=good_aps)
autos, _, _ = hd.read(bls=[bl for bl in hd.bls if utils.split_bl(bl)[0] == utils.split_bl(bl)[1]], read_flags=False, read_nsamples=False)
avg_unflagged_auto = {pol: np.mean([autos[bl] for bl in autos if bl[2] == pol and overall_class[utils.split_bl(bl)[0]] != 'bad'], axis=(0, 1)) for pol in ['ee', 'nn']}
def print_issue_summary(bad_ant_strs, title, notes='', plot=False):
'''Print report for list of bad antenna polarizations strings'''
unique_bad_antnums = [int(ap[:-1]) for ap in bad_ant_strs]
display(HTML(f'<h2>{title}: ({len(bad_ant_strs)} antpols across {len(set([ba[:-1] for ba in bad_ant_strs]))} antennas)</h2>'))
if len(notes) > 0:
display(HTML(f'<h4>{notes}</h4>'))
if len(bad_ant_strs) > 0:
print(f'All Bad Antpols: {", ".join(bad_ant_strs)}\n')
for node in nodes:
if np.any([node == node_dict[a] for a in unique_bad_antnums]):
aps = [ap for ap in bad_ant_strs if node_dict[int(ap[:-1])] == node]
whole_ants = [str(wa) for wa in set([int(ap[:-1]) for ap in aps if ap.translate(translator) in bad_ant_strs])]
single_pols = [ap for ap in aps if ap.translate(translator) not in bad_ant_strs]
print(f'Node {node}:')
print(f'\tAntpols ({len(aps)} total): {", ".join(aps)}')
print(f'\tWhole Ants ({len(whole_ants)} total): {", ".join(whole_ants)}')
print(f'\tSingle Pols ({len(single_pols)} total): {", ".join(single_pols)}')
if plot and SUM_FILE is not None:
fig, axes = plt.subplots(1, 2, figsize=(12,4), dpi=70, sharey=True, gridspec_kw={'wspace': 0})
for ax, pol in zip(axes, ['ee', 'nn']):
ax.semilogy(autos.freqs / 1e6, avg_unflagged_auto[pol], 'k--', label='Average\nUnflagged\nAuto')
for ap in aps:
ant = int(ap[:-1]), utils.comply_pol(ap[-1])
auto_bl = utils.join_bl(ant, ant)
if auto_bl[2] == pol:
ax.semilogy(autos.freqs / 1e6, np.mean(autos[auto_bl], axis=0), label=ap)
ax.legend()
ax.set_xlim([40, 299])
ax.set_title(f'{title} on Node {node} ({pol}-antennas)')
ax.set_xlabel('Frequency (MHz)')
axes[0].set_ylabel('Single File Raw Autocorrelation')
plt.tight_layout()
plt.show()
# precompute various helpful quantities
all_slopes = np.vstack([t['Autocorr Slope'] for t in tables])
median_slope = np.median(all_slopes)
bad_slopes = np.vstack([t['Autocorr Slope Class'] for t in tables]) == 'bad'
suspect_slopes = np.vstack([t['Autocorr Slope Class'] for t in tables]) == 'suspect'
bad_shapes = np.vstack([t['Autocorr Shape Class'] for t in tables]) == 'bad'
suspect_shapes = np.vstack([t['Autocorr Shape Class'] for t in tables]) == 'suspect'
all_powers = np.vstack([t['Autocorr Power'] for t in tables])
median_power = np.median(all_powers)
bad_powers = np.vstack([t['Autocorr Power Class'] for t in tables]) == 'bad'
suspect_powers = np.vstack([t['Autocorr Power Class'] for t in tables]) == 'suspect'
bad_rfi = np.vstack([t['RFI in Autos Class'] for t in tables]) == 'bad'
suspect_rfi = np.vstack([t['RFI in Autos Class'] for t in tables]) == 'suspect'
# find all zeros
all_zeros_strs = ap_strs[np.mean(np.vstack([t['Dead? Class'] for t in tables]) == 'bad', axis=0) > all_zero_thresh]
# find even/odd zeros
eo_zeros_strs = ap_strs[np.mean(np.vstack([t['Even/Odd Zeros Class'] for t in tables]) == 'bad', axis=0) > eo_zeros_thresh]
eo_zeros_strs = [ap for ap in eo_zeros_strs if ap not in all_zeros_strs]
# find cross-polarized antennas
cross_pol_strs = ap_strs[np.mean(np.vstack([t['Cross-Polarized Class'] for t in tables]) == 'bad', axis=0) > cross_pol_thresh]
cross_pol_strs = [ap for ap in cross_pol_strs if ap not in all_zeros_strs]
# find FEM power issues: must be low power, high slope, and bad or suspect in power, slope, rfi, and shape
fem_off_prod = (bad_powers + .5 * suspect_powers) * (bad_slopes + .5 * suspect_slopes)
fem_off_prod *= (bad_rfi + .5 * suspect_rfi) * (bad_shapes + .5 * suspect_shapes)
fem_off_strs = ap_strs[np.mean(fem_off_prod * (all_powers < median_power) * (all_slopes > median_slope), axis=0) > .1]
# find high power issues
high_power_strs = ap_strs[np.mean(bad_powers & (all_powers > median_power), axis=0) > high_power_thresh]
# find other low power issues
low_power_strs = ap_strs[np.mean(bad_powers & (all_powers < median_power), axis=0) > low_power_thresh]
low_power_strs = [ap for ap in low_power_strs if ap not in all_zeros_strs and ap not in fem_off_strs]
# find low correlation (but not low power)
low_corr_strs = ap_strs[np.mean(np.vstack([t['Low Correlation Class'] for t in tables]) == 'bad', axis=0) > low_corr_thresh]
low_corr_strs = [ap for ap in low_corr_strs if ap not in (set(low_power_strs) | set(all_zeros_strs) | set(fem_off_strs))]
# find bad bandpasses
bad_bandpass_strs = ap_strs[np.mean(bad_shapes, axis=0) > bad_shape_thresh]
bad_bandpass_strs = [ap for ap in bad_bandpass_strs if ap not in (set(low_power_strs) | set(all_zeros_strs) | set(high_power_strs) | set(fem_off_strs))]
# find antennas with excess RFI
excess_rfi_strs = ap_strs[np.mean(np.vstack([t['RFI in Autos Class'] for t in tables]) == 'bad', axis=0) > excess_rfi_thresh]
excess_rfi_strs = [ap for ap in excess_rfi_strs if ap not in (set(low_power_strs) | set(all_zeros_strs) | set(fem_off_strs) |
set(bad_bandpass_strs) | set(high_power_strs))]
# find bad x-engine diffs
xengine_diff_strs = ap_strs[np.mean(np.vstack([t['Bad Diff X-Engines Class'] for t in tables]) == 'bad', axis=0) > xengine_diff_thresh]
xengine_diff_strs = [ap for ap in xengine_diff_strs if ap not in (set(bad_bandpass_strs) | set(low_power_strs) | set(excess_rfi_strs) | set(low_corr_strs) |
set(all_zeros_strs) | set(high_power_strs) | set(fem_off_strs) | set(eo_zeros_strs))]
# find antennas with high redcal chi^2
chisq_strs = ap_strs[np.mean(np.vstack([t['Redcal chi^2 Class'] for t in tables]) == 'bad', axis=0) > chisq_thresh]
chisq_strs = [ap for ap in chisq_strs if ap not in (set(bad_bandpass_strs) | set(low_power_strs) | set(excess_rfi_strs) | set(low_corr_strs) |
set(all_zeros_strs) | set(high_power_strs) | set(fem_off_strs) | set(eo_zeros_strs) | set(xengine_diff_strs))]
if OC_SKIP_OUTRIGGERS:
chisq_strs = [ap for ap in chisq_strs if int(ap[:-1]) < 320]
# collect all results
to_print = [(all_zeros_strs, 'All-Zeros', 'These antennas have visibilities that are more than half zeros.'),
(eo_zeros_strs, 'Excess Zeros in Either Even or Odd Spectra',
'These antennas are showing evidence of packet loss or X-engine failure.', True),
(xengine_diff_strs, 'Excess Power in X-Engine Diffs',
'These antennas are showing evidence of mis-written packets in either the evens or the odds.', True),
(cross_pol_strs, 'Cross-Polarized', 'These antennas have their east and north cables swapped.'),
(fem_off_strs, 'Likely FEM Power Issue', 'These antennas have low power, anomolously high slopes, and extra channels identified as RFI.', True),
(high_power_strs, 'High Power', 'These antennas have high median power.', True),
(low_power_strs, 'Other Low Power Issues', 'These antennas have low power, but are not all-zeros and not FEM off.', True),
(low_corr_strs, 'Low Correlation, But Not Low Power', 'These antennas are low correlation, but their autocorrelation power levels look OK.'),
(bad_bandpass_strs, 'Bad Bandpass Shapes, But Not Bad Power',
'These antennas have unusual bandpass shapes, but are not all-zeros, high power, low power, or FEM off.', True),
(excess_rfi_strs, 'Excess RFI', 'These antennas have excess strucutre (identified as possible RFI) in their bandpassed relative to the ' + \
'median antenna, but not low or high power or a bad bandpass.', True),
(chisq_strs, 'Redcal chi^2', 'These antennas have been idenfied as not redundantly calibrating well, even after passing the above checks.')]
def print_high_level_summary():
for tp in sorted(to_print, key=lambda x: len(x[0]), reverse=True):
print(f'{len(tp[0])} antpols (on {len(set([ap[:-1] for ap in tp[0]]))} antennas) frequently flagged for {tp[1]}.')
def print_all_issue_summaries():
for tp in to_print:
print_issue_summary(*tp)
print_high_level_summary()
96 antpols (on 48 antennas) frequently flagged for All-Zeros. 36 antpols (on 29 antennas) frequently flagged for Likely FEM Power Issue. 20 antpols (on 14 antennas) frequently flagged for High Power. 15 antpols (on 14 antennas) frequently flagged for Bad Bandpass Shapes, But Not Bad Power. 13 antpols (on 12 antennas) frequently flagged for Low Correlation, But Not Low Power. 12 antpols (on 11 antennas) frequently flagged for Excess RFI. 5 antpols (on 4 antennas) frequently flagged for Other Low Power Issues. 4 antpols (on 4 antennas) frequently flagged for Excess Power in X-Engine Diffs. 1 antpols (on 1 antennas) frequently flagged for Redcal chi^2. 0 antpols (on 0 antennas) frequently flagged for Excess Zeros in Either Even or Odd Spectra. 0 antpols (on 0 antennas) frequently flagged for Cross-Polarized.
print_all_issue_summaries()
All Bad Antpols: 43e, 43n, 44e, 44n, 47e, 47n, 58e, 58n, 59e, 59n, 60e, 60n, 61e, 61n, 74e, 74n, 77e, 77n, 115e, 115n, 131e, 131n, 133e, 133n, 143e, 143n, 144e, 144n, 145e, 145n, 146e, 146n, 147e, 147n, 148e, 148n, 149e, 149n, 163e, 163n, 164e, 164n, 165e, 165n, 166e, 166n, 184e, 184n, 185e, 185n, 186e, 186n, 187e, 187n, 200e, 200n, 201e, 201n, 202e, 202n, 204e, 204n, 205e, 205n, 206e, 206n, 207e, 207n, 220e, 220n, 221e, 221n, 222e, 222n, 223e, 223n, 224e, 224n, 225e, 225n, 226e, 226n, 237e, 237n, 238e, 238n, 239e, 239n, 240e, 240n, 241e, 241n, 242e, 242n, 243e, 243n Node 5: Antpols (12 total): 43e, 43n, 44e, 44n, 58e, 58n, 59e, 59n, 60e, 60n, 74e, 74n Whole Ants (6 total): 74, 43, 44, 58, 59, 60 Single Pols (0 total): Node 6: Antpols (6 total): 47e, 47n, 61e, 61n, 77e, 77n Whole Ants (3 total): 77, 61, 47 Single Pols (0 total): Node 11: Antpols (6 total): 115e, 115n, 131e, 131n, 133e, 133n Whole Ants (3 total): 115, 131, 133 Single Pols (0 total): Node 14: Antpols (24 total): 143e, 143n, 144e, 144n, 145e, 145n, 146e, 146n, 163e, 163n, 164e, 164n, 165e, 165n, 166e, 166n, 184e, 184n, 185e, 185n, 186e, 186n, 187e, 187n Whole Ants (12 total): 163, 164, 165, 166, 143, 144, 145, 146, 184, 185, 186, 187 Single Pols (0 total): Node 15: Antpols (6 total): 147e, 147n, 148e, 148n, 149e, 149n Whole Ants (3 total): 147, 148, 149 Single Pols (0 total): Node 18: Antpols (18 total): 200e, 200n, 201e, 201n, 202e, 202n, 220e, 220n, 221e, 221n, 222e, 222n, 237e, 237n, 238e, 238n, 239e, 239n Whole Ants (9 total): 200, 201, 202, 237, 238, 239, 220, 221, 222 Single Pols (0 total): Node 19: Antpols (24 total): 204e, 204n, 205e, 205n, 206e, 206n, 207e, 207n, 223e, 223n, 224e, 224n, 225e, 225n, 226e, 226n, 240e, 240n, 241e, 241n, 242e, 242n, 243e, 243n Whole Ants (12 total): 224, 225, 226, 204, 205, 206, 207, 240, 241, 242, 243, 223 Single Pols (0 total):
All Bad Antpols: 109e, 140e, 262n, 336n Node 10: Antpols (1 total): 109e Whole Ants (0 total): Single Pols (1 total): 109e
Node 13: Antpols (1 total): 140e Whole Ants (0 total): Single Pols (1 total): 140e
Node 20: Antpols (1 total): 262n Whole Ants (0 total): Single Pols (1 total): 262n
Node 21: Antpols (1 total): 336n Whole Ants (0 total): Single Pols (1 total): 336n
All Bad Antpols: 27e, 28n, 29e, 29n, 34e, 55e, 88n, 89n, 90n, 91n, 92e, 92n, 93n, 94n, 106e, 106n, 107n, 108e, 108n, 109n, 124e, 124n, 125e, 125n, 126n, 141e, 153e, 174n, 182n, 183n, 211n, 213n, 214e, 246n, 329e, 329n Node 1: Antpols (4 total): 27e, 28n, 29e, 29n Whole Ants (1 total): 29 Single Pols (2 total): 27e, 28n
Node 4: Antpols (1 total): 55e Whole Ants (0 total): Single Pols (1 total): 55e
Node 6: Antpols (1 total): 34e Whole Ants (0 total): Single Pols (1 total): 34e
Node 9: Antpols (14 total): 88n, 89n, 90n, 91n, 106e, 106n, 107n, 108e, 108n, 124e, 124n, 125e, 125n, 126n Whole Ants (4 total): 124, 106, 108, 125 Single Pols (6 total): 88n, 89n, 90n, 91n, 107n, 126n