In [26]:
classification_plot('Antenna Class')
by Josh Dillon last updated October 17, 2022
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
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)
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/sn1/2459871' SUM_FILE = '/mnt/sn1/2459871/zen.2459871.25287.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: 10-18-2022
# set thresholds for fraction of the day
overall_thresh = .1
all_zero_thresh = .1
eo_zeros_thresh = .1
cross_pol_thresh = .1
bad_fem_thresh = .1
high_power_thresh = .1
low_power_thresh = .1
low_corr_thresh = .1
bad_slope_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) 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 1862 csv files starting with /mnt/sn1/2459871/zen.2459871.25287.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 print_issue_summary(bad_ant_strs, title, notes=''):
'''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>'))
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)}')
# 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'
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'
# 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]
# find FEM power issues
fem_bad_conditions = (bad_powers & bad_slopes & bad_rfi) | (suspect_powers & bad_slopes & bad_rfi) | (bad_powers & suspect_slopes & bad_rfi)
fem_off_strs = ap_strs[np.mean(fem_bad_conditions & (all_powers < median_power) & (all_slopes > median_slope), axis=0) > bad_fem_thresh]
# 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_slopes, axis=0) > bad_slope_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 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(all_zeros_strs) | set(high_power_strs) | set(fem_off_strs) | set(eo_zeros_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.'),
(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.'),
(high_power_strs, 'High Power', 'These antennas have high median power.'),
(low_power_strs, 'Other Low Power Issues', 'These antennas have low power, but are not all-zeros and not FEM off.'),
(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 Bandpasses, But Not Bad Power',
'These antennas have unusual bandpass slopes, but are not all-zeros, high power, low power, or FEM off.'),
(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.'),
(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) flagged for {tp[1]}.')
def print_all_issue_summaries():
for tp in to_print:
print_issue_summary(*tp)
print_high_level_summary()
50 antpols (on 30 antennas) flagged for Low Correlation, But Not Low Power. 41 antpols (on 31 antennas) flagged for Likely FEM Power Issue. 40 antpols (on 24 antennas) flagged for Redcal chi^2. 23 antpols (on 19 antennas) flagged for Excess RFI. 21 antpols (on 17 antennas) flagged for Bad Bandpasses, But Not Bad Power. 18 antpols (on 9 antennas) flagged for All-Zeros. 12 antpols (on 8 antennas) flagged for High Power. 6 antpols (on 6 antennas) flagged for Other Low Power Issues. 0 antpols (on 0 antennas) flagged for Excess Zeros in Either Even or Odd Spectra. 0 antpols (on 0 antennas) flagged for Cross-Polarized.
print_all_issue_summaries()
Node 13: Antpols (6 total): 140e, 140n, 141e, 141n, 142e, 142n Whole Ants (3 total): 140, 141, 142 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 16: Antpols (6 total): 152e, 152n, 153e, 153n, 154e, 154n Whole Ants (3 total): 152, 153, 154 Single Pols (0 total):
Node 1: Antpols (2 total): 27e, 27n Whole Ants (1 total): 27 Single Pols (0 total): Node 3: Antpols (2 total): 51e, 68n Whole Ants (0 total): Single Pols (2 total): 51e, 68n Node 4: Antpols (3 total): 54e, 54n, 55n Whole Ants (1 total): 54 Single Pols (1 total): 55n Node 5: Antpols (11 total): 43e, 46n, 58e, 58n, 60e, 60n, 73e, 73n, 74e, 74n, 75n Whole Ants (4 total): 73, 58, 60, 74 Single Pols (3 total): 43e, 46n, 75n Node 7: Antpols (2 total): 117e, 117n Whole Ants (1 total): 117 Single Pols (0 total): Node 8: Antpols (5 total): 84n, 102n, 103e, 103n, 120n Whole Ants (1 total): 103 Single Pols (3 total): 84n, 102n, 120n Node 9: Antpols (1 total): 108e Whole Ants (0 total): Single Pols (1 total): 108e Node 10: Antpols (3 total): 109n, 110n, 111n Whole Ants (0 total): Single Pols (3 total): 109n, 110n, 111n Node 12: Antpols (5 total): 135n, 155e, 156e, 179e, 179n Whole Ants (1 total): 179 Single Pols (3 total): 135n, 155e, 156e Node 13: Antpols (1 total): 180n Whole Ants (0 total): Single Pols (1 total): 180n Node 14: Antpols (1 total): 184n Whole Ants (0 total): Single Pols (1 total): 184n Node 15: Antpols (3 total): 150e, 170e, 190n Whole Ants (0 total): Single Pols (3 total): 150e, 170e, 190n Node 18: Antpols (2 total): 203e, 203n Whole Ants (1 total): 203 Single Pols (0 total):
Node 13: Antpols (1 total): 182n Whole Ants (0 total): Single Pols (1 total): 182n Node 16: Antpols (2 total): 192n, 193e Whole Ants (0 total): Single Pols (2 total): 192n, 193e Node 18: Antpols (9 total): 201e, 201n, 219e, 219n, 220e, 220n, 222e, 222n, 239n Whole Ants (4 total): 201, 219, 220, 222 Single Pols (1 total): 239n
Node 8: Antpols (1 total): 104n Whole Ants (0 total): Single Pols (1 total): 104n Node 13: Antpols (1 total): 183e Whole Ants (0 total): Single Pols (1 total): 183e Node 14: Antpols (4 total): 143e, 166n, 184e, 185e Whole Ants (0 total): Single Pols (4 total): 143e, 166n, 184e, 185e
Node 1: Antpols (1 total): 28n Whole Ants (0 total): Single Pols (1 total): 28n Node 3: Antpols (1 total): 320n Whole Ants (0 total): Single Pols (1 total): 320n Node 6: Antpols (3 total): 34e, 47e, 63n Whole Ants (0 total): Single Pols (3 total): 34e, 47e, 63n Node 9: Antpols (23 total): 88e, 88n, 89e, 89n, 90e, 90n, 91e, 91n, 105e, 105n, 106e, 106n, 107e, 107n, 108n, 124e, 124n, 125e, 125n, 126e, 126n, 325e, 325n Whole Ants (11 total): 325, 105, 106, 107, 88, 89, 90, 91, 124, 125, 126 Single Pols (1 total): 108n Node 10: Antpols (1 total): 92n Whole Ants (0 total): Single Pols (1 total): 92n Node 14: Antpols (17 total): 143n, 144e, 144n, 145e, 145n, 163e, 163n, 164e, 164n, 165e, 165n, 166e, 185n, 186e, 186n, 187e, 187n Whole Ants (7 total): 163, 164, 165, 144, 145, 186, 187 Single Pols (3 total): 143n, 166e, 185n Node 16: Antpols (2 total): 173e, 173n Whole Ants (1 total): 173 Single Pols (0 total): Node 18: Antpols (2 total): 200e, 200n Whole Ants (1 total): 200 Single Pols (0 total):
Node 1: Antpols (2 total): 28e, 28n Whole Ants (1 total): 28 Single Pols (0 total): Node 2: Antpols (2 total): 32n, 323e Whole Ants (0 total): Single Pols (2 total): 32n, 323e Node 3: Antpols (1 total): 50n Whole Ants (0 total): Single Pols (1 total): 50n Node 4: Antpols (1 total): 57e Whole Ants (0 total): Single Pols (1 total): 57e Node 5: Antpols (1 total): 59n Whole Ants (0 total): Single Pols (1 total): 59n Node 6: Antpols (4 total): 22e, 77e, 77n, 78e Whole Ants (1 total): 77 Single Pols (2 total): 22e, 78e Node 10: Antpols (2 total): 92e, 92n Whole Ants (1 total): 92 Single Pols (0 total): Node 13: Antpols (1 total): 161n Whole Ants (0 total): Single Pols (1 total): 161n Node 14: Antpols (2 total): 165e, 166e Whole Ants (0 total): Single Pols (2 total): 165e, 166e Node 15: Antpols (3 total): 167e, 167n, 190e Whole Ants (1 total): 167 Single Pols (1 total): 190e Node 16: Antpols (1 total): 151e Whole Ants (0 total): Single Pols (1 total): 151e Node 18: Antpols (1 total): 200n Whole Ants (0 total): Single Pols (1 total): 200n
Node 1: Antpols (3 total): 4e, 18e, 18n Whole Ants (1 total): 18 Single Pols (1 total): 4e Node 2: Antpols (2 total): 10e, 33n Whole Ants (0 total): Single Pols (2 total): 10e, 33n Node 3: Antpols (2 total): 51n, 320n Whole Ants (0 total): Single Pols (2 total): 51n, 320n Node 5: Antpols (2 total): 44e, 44n Whole Ants (1 total): 44 Single Pols (0 total): Node 6: Antpols (3 total): 34e, 47e, 63n Whole Ants (0 total): Single Pols (3 total): 34e, 47e, 63n Node 7: Antpols (4 total): 98n, 99e, 99n, 119n Whole Ants (1 total): 99 Single Pols (2 total): 98n, 119n Node 12: Antpols (3 total): 158n, 329e, 333e Whole Ants (0 total): Single Pols (3 total): 158n, 329e, 333e Node 13: Antpols (1 total): 182e Whole Ants (0 total): Single Pols (1 total): 182e Node 16: Antpols (2 total): 173e, 173n Whole Ants (1 total): 173 Single Pols (0 total): Node 18: Antpols (1 total): 200e Whole Ants (0 total): Single Pols (1 total): 200e
Node 2: Antpols (1 total): 32e Whole Ants (0 total): Single Pols (1 total): 32e Node 5: Antpols (1 total): 59e Whole Ants (0 total): Single Pols (1 total): 59e Node 6: Antpols (1 total): 22n Whole Ants (0 total): Single Pols (1 total): 22n Node 9: Antpols (21 total): 88e, 88n, 89e, 89n, 90e, 90n, 91e, 91n, 105e, 105n, 106e, 106n, 107e, 107n, 108n, 124e, 124n, 125e, 125n, 126e, 126n Whole Ants (10 total): 105, 106, 107, 88, 89, 90, 91, 124, 125, 126 Single Pols (1 total): 108n Node 14: Antpols (15 total): 143n, 144e, 144n, 145e, 145n, 163e, 163n, 164e, 164n, 165n, 185n, 186e, 186n, 187e, 187n Whole Ants (6 total): 163, 164, 144, 145, 186, 187 Single Pols (3 total): 143n, 165n, 185n Node 15: Antpols (1 total): 169n Whole Ants (0 total): Single Pols (1 total): 169n
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)
def classification_plot(col):
class_array = classification_array(col)
plt.figure(figsize=(12, len(ants) / 10), dpi=100)
plt.imshow(class_array.T, aspect='auto', interpolation='none', cmap='RdYlGn', vmin=0, vmax=2,
extent=[jds[0] - np.floor(jds[0]), jds[-1] - np.floor(jds[0]), len(ants), 0])
plt.xlabel(f'JD - {int(jds[0])}')
plt.yticks(ticks=np.arange(.5, len(ants)+.5), labels=[ant for ant in ants], fontsize=6)
plt.ylabel('Antenna Number (East First, Then North)')
plt.gca().tick_params(right=True, top=True, labelright=True, labeltop=True)
plt.tight_layout()
plt.title(f'{col}: Green is "good", Yellow is "suspect", Red is "bad"')
This "big green board" shows the overall (i.e. after redundant calibration) classification of antennas on a per-file basis. This is useful for looking at time-dependent effects across the array. While only antenna numbers are labeled, both polarizations are shown, first East then North going down, above and below the antenna's tick mark.
classification_plot('Antenna Class')
# compute flag fractions for all classifiers and antennas
frac_flagged = []
for col in class_cols[1:]:
class_array = np.vstack([t[col] for t in tables])
class_array[class_array == 'good'] = False
class_array[class_array == 'suspect'] = False
class_array[class_array == 'bad'] = True
frac_flagged.append(np.sum(class_array, axis=0))
def plot_flag_frac_all_classifiers():
ticks = []
for i, col in enumerate(list(class_cols[1:])):
ticks.append(f'{col} ({np.nanmean(np.array(frac_flagged).astype(float)[i]) / len(csv_files):.2%})')
plt.figure(figsize=(8, len(ants) / 10), dpi=100)
plt.imshow(np.array(frac_flagged).astype(float).T, aspect='auto', interpolation='none', cmap='viridis')
plt.xticks(ticks=np.arange(len(list(class_cols[1:]))), labels=ticks, rotation=-45, ha='left')
plt.yticks(ticks=np.arange(.5, len(ap_strs)+.5, 2), labels=[ant for ant in ants], fontsize=6)
plt.ylabel('Antenna Number (East First, Then North)')
plt.gca().tick_params(right=True, labelright=True,)
ax2 = plt.gca().twiny()
ax2.set_xticks(ticks=np.arange(len(list(class_cols[1:]))), labels=ticks, rotation=45, ha='left')
plt.colorbar(ax=plt.gca(), label=f'Number of Files Flagged Out of {len(csv_files)}', aspect=50)
plt.tight_layout()
This plot shows the fraction of files flagged for each reason for each antenna. It's useful for seeing which problems are transitory and which ones are more common. Note that not all flags are independent and in particular redcal chi^2 takes an OR of other classifications as an input. Also note that only antenna numbers are labeled, both polarizations are shown, first East then North going down, above and below the antenna's tick mark.
plot_flag_frac_all_classifiers()
if SUM_FILE is not None:
hd = io.HERAData(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)
def array_class_plot():
fig, axes = plt.subplots(1, 2, figsize=(14, 6), dpi=100, gridspec_kw={'width_ratios': [2, 1]})
plot_antclass(hd.antpos, overall_class, ax=axes[0], ants=[ant for ant in hd.data_ants if ant < 320], legend=False,
title=f'HERA Core: Overall Flagging Based on {overall_thresh:.1%} Daily Threshold')
plot_antclass(hd.antpos, overall_class, ax=axes[1], ants=[ant for ant in hd.data_ants if ant >= 320], radius=50, title='Outriggers')
Overall classification of antenna-polarizations shown on the array layout. If any antenna is marked bad for any reason more than the threshold (default 10%), it is marked bad here. Likewise, if any antenna is marked suspect for more than 10% of the night (but not bad), it's suspect here.
if SUM_FILE is not None: array_class_plot()
