data.py stays the reader (METRIC_RE now also captures the file date, same matches); common.py holds columns, steps, noise, sensor list, runs, file names. Duplicated run grouping, pose gaps, step bucketing, --table/--outside parsing removed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
184 lines
9.9 KiB
Python
184 lines
9.9 KiB
Python
"""Several stations on one timeline: enclosure temperature, camera pose, corr of the targets, rejections, gaps.
|
|
|
|
Usage: .venv/bin/python tools/scripts/stations.py data/BREITHORN data/MICHIGAN data/NEBRASKA
|
|
[--columns temperature,cam_tilt,cam_rotation,cam_scale,tgt_corr_x,tgt_corr_y] [--step 1h] [--stat median|min|max]
|
|
[--table T1/T2|no] [--start ...] [--end ...] [--out FOLDER]
|
|
|
|
For each station (one station folder each), over the window --start/--end:
|
|
- possible columns: temperature (median of the sensor_*_deg_c components, as in metrics.py), cam_pan, cam_tilt,
|
|
cam_rotation, cam_scale, cam_sigma0 (raw camera pose), tgt_corr_x, tgt_corr_y (median over the targets of
|
|
corr minus each target's own level, accepted measurements, as in metrics.py), rej_targets, rej_refs (number of
|
|
rejected targets, of rejected references: the largest over the measurement times of the step);
|
|
- prints, per station, the period of the measurements, the cadence (median step) and the number of times; then the **gaps**:
|
|
the runs of steps of --step without a measurement or without temperature, with the stations where they are missing (a gap shared by
|
|
several stations is on a single line); then the table, one line per step (start of the step, UTC; --stat of the
|
|
values of the step; "-": no value), one column per station and per column, tab-separated
|
|
(--table T1/T2: only between T1 and T2, "no": not at all; the rest covers the whole window); then, for
|
|
each column and each pair of stations, the correlation r of the values and that of the steps (difference from one value to
|
|
the next, over the steps where both stations have a value: a common movement shows on the steps, a common
|
|
trend on the values), with the number of steps;
|
|
- one PNG "stations": one panel per column, one line per station (raw temperature; the other columns minus
|
|
their median over the window, so that they overlap), broken over a gap; measurement gaps shaded below the axis, one band
|
|
per station.
|
|
Never an identifier from metrics/ (SIM_CCID, ip*): only the temperatures are read there. Gives values, not a verdict.
|
|
"""
|
|
import argparse
|
|
import os
|
|
import statistics
|
|
import sys
|
|
|
|
import matplotlib
|
|
|
|
matplotlib.use("Agg")
|
|
import matplotlib.dates as mdates # noqa: E402
|
|
import matplotlib.pyplot as plt # noqa: E402
|
|
|
|
from common import STATS, bound, cut, duration, group, targets, window_filter # noqa: E402
|
|
from data import POSE, filter_window, is_reference, iso, load, load_camera, load_temperature, parse_time, rejected # noqa: E402
|
|
|
|
COLUMNS = ("temperature",) + tuple("cam_" + c for c in POSE) + ("tgt_corr_x", "tgt_corr_y", "rej_targets", "rej_refs")
|
|
|
|
|
|
def read(folder, start, end):
|
|
"""Station folder -> ({column: [{'t', 'v'}]}, [measurement times])."""
|
|
by_sensor = load(folder)
|
|
series = {"temperature": filter_window([{"t": t, "v": v} for t, v in load_temperature(folder)], start, end)}
|
|
for p in filter_window(load_camera(folder), start, end):
|
|
for c in POSE:
|
|
if p[c] is not None:
|
|
series.setdefault("cam_" + c, []).append({"t": p["t"], "v": p[c]})
|
|
for c in ("corr_x", "corr_y"):
|
|
series["tgt_" + c] = targets(by_sensor, c, start, end)
|
|
rej = {} # t -> [rejected targets, rejected references]
|
|
for s, ms in by_sensor.items():
|
|
ref = is_reference(ms)
|
|
for m in filter_window(ms, start, end):
|
|
n = rej.setdefault(m["t"], [0, 0])
|
|
n[ref] += rejected(m)
|
|
series["rej_targets"] = [{"t": t, "v": float(n[0])} for t, n in sorted(rej.items())]
|
|
series["rej_refs"] = [{"t": t, "v": float(n[1])} for t, n in sorted(rej.items())]
|
|
return series, sorted(rej)
|
|
|
|
|
|
def correlation(a, b):
|
|
try:
|
|
return f"{statistics.correlation(a, b):+.2f}"
|
|
except (statistics.StatisticsError, ValueError):
|
|
return "-"
|
|
|
|
|
|
def main():
|
|
a = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
|
|
a.add_argument("folders", nargs="+", help="station folders, at least two")
|
|
a.add_argument("--columns", default="temperature,cam_tilt,cam_rotation,cam_scale,tgt_corr_x,tgt_corr_y")
|
|
a.add_argument("--step", default="1h", type=duration)
|
|
a.add_argument("--stat", default="median", choices=STATS)
|
|
a.add_argument("--table", default="", metavar="T1/T2|no", help="table printed only between T1 and T2 (\"no\": not at all)")
|
|
a.add_argument("--start", type=parse_time)
|
|
a.add_argument("--end", type=parse_time)
|
|
a.add_argument("--out", default=os.path.join("out", "diagnostic"), help="folder of the PNG")
|
|
o = a.parse_args()
|
|
columns = o.columns.split(",")
|
|
if missing := [c for c in columns if c not in COLUMNS]:
|
|
sys.exit(f"Unknown columns: {', '.join(missing)}. Known: {', '.join(COLUMNS)}.")
|
|
in_table = window_filter(o.table)
|
|
|
|
names = [os.path.basename(os.path.normpath(d)) for d in o.folders]
|
|
by_station, measured = {}, {}
|
|
for n, d in zip(names, o.folders):
|
|
by_station[n], measured[n] = read(d, o.start, o.end)
|
|
times = [p["t"] for s in by_station.values() for c in s.values() for p in c]
|
|
if not times:
|
|
sys.exit("No value in the requested window.")
|
|
t0 = (o.start or min(times)).replace(minute=0, second=0, microsecond=0)
|
|
t1 = o.end or max(times)
|
|
grid = [t0 + i * o.step for i in range(int((t1 - t0) / o.step) + 1)]
|
|
cell = lambda t: t0 + ((t - t0) // o.step) * o.step # noqa: E731
|
|
|
|
print("Stations:")
|
|
for n in names:
|
|
ts = measured[n]
|
|
if not ts:
|
|
print(f" {n}: no measurement in the window")
|
|
continue
|
|
cad = statistics.median(b - a_ for a_, b in zip(ts, ts[1:])) if len(ts) > 1 else None
|
|
print(f" {n}: measurements {iso(ts[0])} → {iso(ts[-1])}, {len(ts)} times, cadence {round(cad.total_seconds() / 60) if cad else '-'} min; "
|
|
+ ", ".join(f"{c} {len(by_station[n].get(c, []))}" for c in columns))
|
|
|
|
# gaps: steps without a measurement, without temperature, and the stations concerned
|
|
with_meas = {n: {cell(t) for t in measured[n]} for n in names}
|
|
with_temp = {n: {cell(p["t"]) for p in by_station[n]["temperature"]} for n in names}
|
|
print(f"\nGaps (steps of {int(o.step.total_seconds() // 60)} min without a measurement or without temperature), with the stations where they are missing:")
|
|
keys = {}
|
|
for k in grid:
|
|
m = tuple(n for n in names if k not in with_meas[n])
|
|
t = tuple(n for n in names if k not in with_temp[n])
|
|
if m or t:
|
|
keys.setdefault((m, t), []).append(k)
|
|
lines = [(g[0], g[-1], len(g), m, t) for (m, t), ks in keys.items() for g in group(ks, lambda a, b: b - a == o.step)]
|
|
for d, f, nb, m, t in sorted(lines):
|
|
print(f" {iso(d)} → {iso(f)} ({nb} steps): no measurement {','.join(m) or '-'}; no temperature {','.join(t) or '-'}")
|
|
if not lines:
|
|
print(" (none)")
|
|
|
|
stat = STATS[o.stat]
|
|
table = {} # (station, column) -> {step: value}
|
|
for n in names:
|
|
for c in columns:
|
|
cells = {}
|
|
for p in by_station[n].get(c, []):
|
|
cells.setdefault(cell(p["t"]), []).append(p["v"])
|
|
table[n, c] = {k: stat(v) for k, v in cells.items()}
|
|
header = [f"{n}:{c}" for n in names for c in columns]
|
|
print(f"\n{o.stat} per step of {int(o.step.total_seconds() // 60)} min (start of the step, UTC); \"-\": no value"
|
|
+ (f" (table: {o.table})" if o.table else "") + ":")
|
|
if o.table != "no":
|
|
print("\t".join(["time"] + header))
|
|
for k in grid:
|
|
if in_table(k):
|
|
v = [table[n, c].get(k) for n in names for c in columns]
|
|
if any(x is not None for x in v):
|
|
print("\t".join([iso(k)] + ["-" if x is None else f"{x:.6g}" for x in v]))
|
|
|
|
print("\nCorrelation between stations, r of the values, then r of the steps from one value to the next (n: steps where both have a value):")
|
|
for c in columns:
|
|
for i, s1 in enumerate(names):
|
|
for s2 in names[i + 1:]:
|
|
ks = sorted(set(table[s1, c]) & set(table[s2, c]))
|
|
v1, v2 = [table[s1, c][k] for k in ks], [table[s2, c][k] for k in ks]
|
|
d1, d2 = [b - a_ for a_, b in zip(v1, v1[1:])], [b - a_ for a_, b in zip(v2, v2[1:])]
|
|
print(f" {c:12} {s1}-{s2}: r values {correlation(v1, v2)}, r steps {correlation(d1, d2)} (n = {len(ks)})")
|
|
|
|
fig, axes = plt.subplots(len(columns) + 1, 1, sharex=True, figsize=(14, 2.4 * (len(columns) + 1)), squeeze=False,
|
|
layout="constrained", gridspec_kw={"height_ratios": [3] * len(columns) + [0.3 * len(names)]})
|
|
for ax, c in zip(axes[:-1, 0], columns):
|
|
for i, n in enumerate(names):
|
|
s = by_station[n].get(c, [])
|
|
if not s:
|
|
continue
|
|
med = 0 if c == "temperature" else statistics.median(p["v"] for p in s)
|
|
ts, vs = cut([{"t": p["t"], "v": p["v"] - med} for p in s])
|
|
ax.plot(ts, vs, ".-", ms=2, lw=0.8, color=f"C{i % 10}", label=n)
|
|
ax.set_ylabel(c if c == "temperature" else f"{c}\nminus its median", fontsize=8)
|
|
ax.grid(alpha=0.3)
|
|
ax.legend(loc="upper left", bbox_to_anchor=(1.0, 1.0), fontsize=8)
|
|
ax = axes[-1, 0]
|
|
for i, n in enumerate(names):
|
|
for k in grid:
|
|
if k not in with_meas[n]:
|
|
ax.axvspan(k, k + o.step, ymin=i / len(names), ymax=(i + 1) / len(names), color=f"C{i % 10}", lw=0)
|
|
ax.set_yticks([(i + 0.5) / len(names) for i in range(len(names))], names, fontsize=7)
|
|
ax.set_ylim(0, 1)
|
|
ax.set_ylabel("no measurement", fontsize=8)
|
|
ax.set_xlim(grid[0], grid[-1] + o.step)
|
|
ax.xaxis.set_major_formatter(mdates.DateFormatter("%d/%m\n%H:%MZ"))
|
|
fig.suptitle(f"{', '.join(names)}: same timeline (UTC times)")
|
|
os.makedirs(o.out, exist_ok=True)
|
|
path = os.path.join(o.out, f"{'-'.join(names)}_stations_{bound(o.start, 'start')}_{bound(o.end, 'end')}.png")
|
|
fig.savefig(path, dpi=100, bbox_inches="tight")
|
|
print(f"\n{path}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|