diff --git a/scripts/common.py b/scripts/common.py new file mode 100644 index 0000000..fe0be56 --- /dev/null +++ b/scripts/common.py @@ -0,0 +1,47 @@ +"""Helpers shared by the detectors.""" +import statistics +from datetime import timedelta + +from data import iso + + +def episode(start, end, kind, label, text, sensors, ignore, **extra): + return {"start": iso(start), "end": iso(end), "kind": kind, "label": label, "text": text, "ignore": ignore, + "sensors": sorted(sensors), **extra} + + +def runs(times, gap): + """Sorted times -> [[t, ...]]: runs of times at most gap apart.""" + out = [] + for t in times: + if out and t - out[-1][-1] <= gap: + out[-1].append(t) + else: + out.append([t]) + return out + + +def noise(v): + """Median step of a series, from one value to the next.""" + return statistics.median(abs(y - x) for x, y in zip(v, v[1:])) if len(v) > 1 else 0 + + +def level(v): + """-> (median, MAD) of the values.""" + med = statistics.median(v) + return med, statistics.median(abs(x - med) for x in v) or 1e-9 + + +def cadence(measurements): + """Cycle of the measurements: the median gap between two instants, at least an hour divided by the median number of + instants per clock hour (a station measuring in bursts, three measurements a minute apart every 15 min: 15 min).""" + ts = sorted({m["t"].replace(second=0, microsecond=0) for ms in measurements.values() for m in ms}) + per_hour = {} + for t in ts: + per_hour[t.replace(minute=0)] = per_hour.get(t.replace(minute=0), 0) + 1 + gap = statistics.median(b - a for a, b in zip(ts, ts[1:])) if len(ts) > 1 else timedelta(hours=1) + return max(gap, timedelta(hours=1) / statistics.median(per_hour.values())) + + +def targets(n): + return "one target" if n == 1 else f"{n} targets" diff --git a/scripts/visibility.py b/scripts/visibility.py index ff7054c..ee44489 100644 --- a/scripts/visibility.py +++ b/scripts/visibility.py @@ -1,110 +1,40 @@ -"""Detector of the Visibility family (the families document): the camera sees less well, the image is faint or blurred -(error_value), or it trembles (heat shimmer, end of file). The same error_value computation also finds objects in front -of a few targets (Brief obstruction, Target obscured): episodes() returns them with the Obstruction family, which -detect() leaves to obstruction.py. +"""Visibility family: the camera sees the targets less well (error_value), or the air trembles (heat shimmer). The same +error_value also finds objects in front of a few targets: Obstruction family (Brief obstruction, Target obscured). -Method: -1. "High" measurement: error_value > median + K_MAD MAD of the sensor over the export, and > FACTOR × median, or - rejected (> error_threshold) and > REJECT_FACTOR × median: a sensor at a usual level of 0.6 never doubles, and - FLORIDA (batch 01) showed its fogs as Target obscured. -2. Brief obstruction: an instant where at least BRIEF_MIN sensors are high, SALIENCE times more than at the neighbouring - instants (train, vehicle), with no reference (global_ref) among them: a one-step peak touching the references is not - an obstacle in front of targets (peak of the whole image, NORDEND on 01.09 11:15, batch 01); it is not shown. Unless - at least BRIEF_MIN targets are rejected at this instant and neither at the instant before nor after: something - passing in front of them, a reference touched as well (wf-improve session Displacement, mod. 1, S5: trains of - NIEDERHORN, 12 and 13 targets rejected). - Also, something passing in front of one or two targets, or a single reference: at an instant, fewer than BRIEF_MIN - sensors rejected at more than FACTOR times their median (without K_MAD: by day, heat shimmer inflates the MAD), at - most one reference, none of them rejected at the instant before or after, and fewer than BRIEF_MIN high sensors - (wf-improve session Obstruction, mod. 1, S3: vehicles, passers-by, insects in front of one or two targets of - WILDSTRUBEL, NIEDERHORN, LENZSPITZE; a reference hidden by a truck at JUNGFRAU, BREITHORN). -3. Poor visibility: runs of at least RUN_MIN high measurements per sensor, joined across sensors (at least 2), reduced - to the instants where at least FRAC of the episode's peak is high. -4. Target obscured: a target (not a global_ref) rejected (> error_threshold) and above K_TARGET MAD, at least TARGET_MIN - times less than TARGET_GAP apart, mostly outside the episodes of 2 and 3 (leaves, snow, glare on a target). The gap - is at least two measurement steps, and two rejections are enough when TARGET_MIN steps do not fit in TARGET_GAP - (wf-improve session Obstruction, mod. 1, S6: at one measurement every 4 h, vehicles parked at night in front of COLI22, - COLI24, POUI22 of BREITHORN make only two or three rejections). All episodes: ignore = True. -5. Level of a Poor visibility (validated 2026-10-24), measurement by measurement: "none" (nothing is seen) when at least - HALF of the usually seen targets (under their threshold at least half the time) are rejected, "reduced" (average - data) otherwise; one episode per period of the same level, with the level field. -6. Bounds of a Poor visibility (WILDSTRUBEL, batch 01): from the first to the last measurement where a target is - rejected (> error_threshold), and no episode without a rejected target. On a road in full sun, the daytime - error_value (×1.5 to ×3, heat shimmer) made reduced visibility last for hours without any rejection; references do - not count: R3 is above its threshold almost all day. -7. Poor visibility or object (boundary "Visibility or Obstruction" of the families document; BREITHORN, batch 01): a - nuisance touching at most FEW targets, and no reference, is not diffuse: it is an object in front of them (a parked - vehicle), a "Target obscured" episode of its whole duration, without a level. -8. Diffuse nuisance, with or without rejections (wf-improve session Visibility, mod. 1, S2): at each instant, the median, - over the sensors, of the error_value in MAD above each one's median; at least RUN_MIN instants in a row at K_DIFFUSE - or more make a Poor visibility "reduced". A diffuse nuisance entirely within heat shimmer is the heat shimmer, and - within a Poor visibility of point 3, that one (the same instants twice, two events: wf-improve, batch 2026-11-05, S2): - no episode (otherwise it absorbed the jump back of the day before, WILDSTRUBEL on 04.10). Finds the drops of - visibility of the whole scene without rejection at JUNGFRAU, FLORIDA, NORDEND; at 2, nights labelled thermal at - JUNGFRAU; at 3, half the gain. - -A simpler version (share of targets rejected above their threshold, without comparing each sensor with its own level) -was tried on 2026-10-24 and dropped: worse on five data sets out of six (git history of Support-Agent, -detectors/archive/visibilite_simple.py). +1. High measurement: error_value above the median of its sensor + K_MAD MAD and above FACTOR times that median. +2. Brief obstruction (one instant): at least BRIEF_MIN sensors high, SALIENCE times more than at each neighbouring instant + (a train, a vehicle); or fewer than BRIEF_MIN sensors, at most one reference, rejected at FACTOR times their median + and not at the neighbouring instants (something passing in front of one or two targets). +3. Poor visibility: runs of at least RUN_MIN high measurements of a sensor (steps of at most GAP_STEPS), outside the brief + instants, overlapping on at least two sensors. Level of each instant: "none" (greyed) when at least HALF of the + usually seen targets are rejected, "reduced" otherwise; one episode per period of the same level. +4. Diffuse nuisance: at least RUN_MIN instants in a row where the median over the sensors of the error_value, in MAD + above each one's median, reaches K_DIFFUSE: Poor visibility "reduced", unless within heat shimmer or another Poor + visibility. +5. Target obscured: a target rejected above K_TARGET MAD at least TARGET_MIN times, less than TARGET_GAP apart, mostly + outside the episodes above (leaves, snow, glare on one target). +Heat shimmer: end of file. """ import statistics from datetime import timedelta -from data import iso +from common import cadence, episode, level, runs, targets +from data import is_reference -K_MAD = 10 # tuned on E-001 (fog: 11 to 57 MAD) and E-005 (rain, trains: 10 to 70 MAD) -FACTOR = 2 # drops sensors with a near-zero MAD (E-004: PWD_REF10 ×1.6 at 14 MAD, E-005) -RUN_MIN = 3 # high measurements in a row for poor visibility (E-001, E-005 rain) -BRIEF_MIN = 3 # tuned on E-005 (trains: 5 to 17 sensors; the one with 2 targets is missed) -K_TARGET = 5 # tuned on E-005 (leaves: 6 to 25 MAD, rejected) -TARGET_MIN = 3 # repeated rejections of a target -FRAC = 0.15 # cuts the tails of PR09 + CTR01 (NORDEND October) without cutting the cobweb (E-002) -GAP_STEPS = 2.5 # steps tolerated between two high measurements of the same run (a missing step, clock to the second) -BREAK = timedelta(hours=2) # lull separating two episodes (NORDEND October, night of 13 to 14.10) -SALIENCE = 3 # a train stands out at least 3 times above the neighbouring instants (E-005: 5 to 17 against 0 to 2; - # the cobweb of E-002 varies from 2 to 9 from one step to the next) -TARGET_GAP = timedelta(hours=6) # tuned on E-005 (leaves: 7 rejections in 12 h, up to 5 h apart) -REJECT_FACTOR = 1.2 # a rejection at 10 MAD also counts (FLORIDA, batch 01: levels of 0.6, ×2 out of reach); drops C24 - # of E-009 (level 0.68 just under the threshold 0.7, rejected at ×1.04) -HALF = 0.5 # "nothing is seen"; tuned on NORDEND (09.10 23:00: 68 % rejected) and E-005 (rain: 24 to 33 %) -K_DIFFUSE = 2.5 # diffuse nuisance (8); wf-improve session Visibility, mod. 1, S2 -FEW = 3 # Poor visibility on at most 3 targets, no reference: an object, Target obscured (7); BREITHORN, - # batch 01 (vehicles parked in front of 2 or 3 targets out of 12) +K_MAD = 10 # E-001 (fog: 11 to 57 MAD), E-005 (rain, trains: 10 to 70 MAD) +FACTOR = 2 # drops the sensors with a near-zero MAD (E-004, E-005) +RUN_MIN = 3 # E-001, rain of E-005 +GAP_STEPS = 2.5 # steps tolerated inside a run (a missing step, timestamp jitter) +BRIEF_MIN = 3 # trains of E-005: 5 to 17 sensors +SALIENCE = 3 # a train stands out (E-005: 5 to 17 against 0 to 2); the cobweb of E-002 varies from 2 to 9 +HALF = 0.5 # "nothing is seen": NORDEND 09.10 23:00 (68 % rejected) against the rain of E-005 (24 to 33 %) +K_DIFFUSE = 2.5 # wf-improve Visibility, mod. 1, S2 (JUNGFRAU, FLORIDA, NORDEND: the whole scene less clear) +K_TARGET = 5 # leaves of E-005: 6 to 25 MAD, rejected +TARGET_MIN = 3 +TARGET_GAP = timedelta(hours=6) # leaves of E-005: 7 rejections in 12 h, up to 5 h apart - -def _step(measurements): - ts = sorted({m["t"] for v in measurements.values() for m in v}) - return statistics.median(b - a for a, b in zip(ts, ts[1:])) - - -def _group(points, gap): - """[(t, sensor)] sorted by t -> groups [(start, end, {sensors}, [t])] whose points are ≤ gap from each other.""" - groups = [] - for t, s in points: - if groups and t - groups[-1][1] <= gap: - g = groups[-1] - groups[-1] = (g[0], t, g[2] | {s}, g[3] + [t]) - else: - groups.append((t, t, {s}, [t])) - return groups - - -def _group_intervals(intervals, gap): - """[(start, end, sensor)] sorted -> [(start, end, {sensors})] of the intervals that overlap (within gap).""" - out = [] - for a, b, s in intervals: - if out and a - out[-1][1] <= gap: - out[-1] = (out[-1][0], max(out[-1][1], b), out[-1][2] | {s}) - else: - out.append((a, b, {s})) - return out - - -def _episode(start, end, label, text, sensors, level=None): - e = {"start": iso(start), "end": iso(end), "kind": "Visibility" if label == "Poor visibility" else "Obstruction", - "label": label, "text": text, - "ignore": level != "reduced", "sensors": sorted(sensors)} # reduced visibility: average data, not greyed - return {**e, "level": level} if level else e +BRIEF = "Something passed in front of {} for a single measurement. Ignore this point on the curves." +OBSCURED = "{} was hidden several times while the targets around it stayed clear. Ignore its curve in this period." def _levels(measurements, instants): @@ -118,220 +48,132 @@ def _levels(measurements, instants): for t in instants} -def episodes(measurements): - """All error_value episodes: Visibility (Poor visibility), Obstruction (Brief obstruction, Target obscured).""" - step = _step(measurements) - gap = GAP_STEPS * step - refs = {s for s, v in measurements.items() if v[0]["pattern_type"] == "global_ref"} - instants = sorted({m["t"] for v in measurements.values() for m in v}) - high, rejections = {}, {} # sensor -> [t] - refused = set() # instants where a target (not a global_ref) is above its threshold - rejected_targets = {} # t -> {targets above their threshold} - strong, refusals = {}, {} # t -> {sensors rejected at more than FACTOR times their median}, {sensors rejected} - for s, v in measurements.items(): - e = [m["error_value"] for m in v if m["error_value"] is not None] - if len(e) < 10: - continue - med = statistics.median(e) - mad = statistics.median(abs(x - med) for x in e) or 1e-9 - for m in v: - x = m["error_value"] - if x is None: - continue - rejected = m["error_threshold"] and x > m["error_threshold"] - if rejected and s not in refs: - refused.add(m["t"]) - rejected_targets.setdefault(m["t"], set()).add(s) - if x > med + K_MAD * mad and (x > FACTOR * med or rejected and x > REJECT_FACTOR * med): - high.setdefault(s, []).append(m["t"]) - if rejected: - refusals.setdefault(m["t"], set()).add(s) - if x > FACTOR * med: - strong.setdefault(m["t"], set()).add(s) - if s not in refs and rejected and x > med + K_TARGET * mad: - rejections.setdefault(s, []).append(m["t"]) - by_t = {} # t -> {high sensors} - for s, ts in high.items(): - for t in ts: - by_t.setdefault(t, set()).add(s) - n = lambda t: len(by_t.get(t, ())) # noqa: E731 - out = [] - - # 2. Brief obstruction: an instant where many sensors are high, at least SALIENCE times more than the neighbours. - briefs = set() - for i, t in enumerate(instants): - neighbours = [n(instants[j]) for j in (i - 1, i + 1) if 0 <= j < len(instants)] - if n(t) >= BRIEF_MIN and n(t) >= SALIENCE * max(neighbours): - briefs.add(t) - only = rejected_targets.get(t, set()).difference(*(rejected_targets.get(instants[j], set()) for j in (i - 1, i + 1) - if 0 <= j < len(instants))) - if by_t[t] & refs and len(only) < BRIEF_MIN: # references touched without targets rejected at this instant - continue # alone: not an obstacle in front of targets, the whole image - out.append(_episode(t, t, "Brief obstruction", f"{n(t)} points were poorly seen for a single measurement, then came " - "back: probably a train, a vehicle or an animal passing; ignore this point on the curves.", by_t[t])) - elif 0 < len(f := strong.get(t, set())) < BRIEF_MIN and n(t) < BRIEF_MIN and len(f & refs) <= 1 and not f & set().union( - *(refusals.get(instants[j], set()) for j in (i - 1, i + 1) if 0 <= j < len(instants))): - # one or two targets, or a reference, rejected at this single measurement, at FACTOR times their median - out.append(_episode(t, t, "Brief obstruction", f"{len(f)} point{'s were' if len(f) > 1 else ' was'} poorly seen " - "for a single measurement, then came back: probably something passing; ignore this point on the " - "curves.", f)) - - # 3. Poor visibility: long runs per sensor (without the brief instants), joined across sensors, then reduced to the - # instants where at least FRAC of the episode's peak is high (cuts the tails of one or two sensors and the long - # lulls, more than BREAK). - runs = [] - for s, ts in high.items(): - pts = [(t, s) for t in ts if t not in briefs] - runs += [(a, b, s) for a, b, _, l in _group(pts, gap) if len(l) >= RUN_MIN] - zones = [z for z in _group_intervals(sorted(runs), gap) if len(z[2]) >= 2] - kept = [] - for a, b, _ in zones: - inside = [t for t in instants if a <= t <= b and t not in briefs] - peak = max(n(t) for t in inside) - pts = [(t, s) for t in inside if n(t) >= max(1, FRAC * peak) for s in by_t[t]] - kept += [(d, f, cs) for d, f, cs, l in _group(pts, max(gap, BREAK)) if len(cs) >= 2 and len(set(l)) >= RUN_MIN] - # Bounds: from the first to the last rejected target; without a rejection, no episode (6). - kept = [(r[0], r[-1], cs) for a, b, cs in kept if (r := [t for t in instants if a <= t <= b and t in refused])] - level = _levels(measurements, instants) - for a, b, cs in kept: # one episode per period of the same level (5); the text comes from categories.py - if len(cs) <= FEW and not cs & refs: # an object in front of a few targets, not a diffuse nuisance (7) - out.append(_episode(a, b, "Target obscured", "", cs)) - continue - seg = [] - for t in [t for t in instants if a <= t <= b] + [None]: - if seg and (t is None or level[t] != level[seg[0]]): - who = cs & set().union(*(by_t.get(u, set()) for u in seg)) or cs - out.append(_episode(seg[0], seg[-1], "Poor visibility", "", who, level[seg[0]])) - seg = [] - if t is not None: - seg.append(t) - inside_any = lambda t: t in briefs or any(a <= t <= b for a, b, _ in kept) # noqa: E731 - - # 4. Target obscured: a target rejected again and again, mostly outside the episodes above. - targets = [] - for s, ts in rejections.items(): - for a, b, _, l in _group([(t, s) for t in ts], max(TARGET_GAP, 2 * step)): - if len(l) >= (TARGET_MIN if TARGET_MIN * step <= TARGET_GAP else 2) and sum(map(inside_any, l)) * 2 < len(l): - targets.append((a, b, s)) - for a, b, cs in _group_intervals(sorted(targets), timedelta(0)): - who, it, its = ("One target was", "it", "its") if len(cs) == 1 else (f"{len(cs)} targets were", "them", "their") - out.append(_episode(a, b, "Target obscured", f"{who} repeatedly lost while the targets around stayed clear: probably " - f"something in front of {it} (leaves, snow) or glare; {its} displacements in this period are unreliable.", cs)) - return sorted(out, key=lambda e: e["start"]) - - -def diffuse(measurements): - """Diffuse nuisance (8): the runs of at least RUN_MIN instants where the median, over the sensors, of the error_value - in MAD above each one's median reaches K_DIFFUSE, with or without rejections -> Poor visibility "reduced".""" - z = {} # t -> {sensor: gap in MAD} - for s, v in measurements.items(): - e = [m["error_value"] for m in v if m["error_value"] is not None] - if len(e) < 10: - continue - med = statistics.median(e) - mad = statistics.median(abs(x - med) for x in e) or 1e-9 - for m in v: - if m["error_value"] is not None: - z.setdefault(m["t"], {})[s] = (m["error_value"] - med) / mad - highs = [(t, None) for t in sorted(z) if statistics.median(z[t].values()) >= K_DIFFUSE] - return [_episode(a, b, "Poor visibility", "", {s for t in l for s, x in z[t].items() if x >= K_DIFFUSE}, "reduced") - for a, b, _, l in _group(highs, GAP_STEPS * _step(measurements)) if len(l) >= RUN_MIN] +def _poor(start, end, sensors, level, refs): + refs = ", including the reference targets" if set(sensors) & refs else "" + text = (f"The camera could not see {targets(len(sensors))} clearly{refs}. The curves in this period are not " + "reliable: ignore them." if level == "none" else f"The camera saw {targets(len(sensors))} less clearly than " + f"usual{refs}. The data in this period are less precise: use them with care.") + return episode(start, end, "Visibility", "Poor visibility", text, sensors, level == "none", level=level) def detect(measurements): - shimmer = heat_shimmer(measurements) # a diffuse nuisance during heat shimmer is the heat shimmer (8) - eps = episodes(measurements) - poor = [e for e in eps if e["kind"] == "Visibility"] # a diffuse nuisance within one of them is it - return eps + shimmer + [e for e in diffuse(measurements) - if not any(t["start"] <= e["start"] and e["end"] <= t["end"] for t in shimmer + poor)] + gap = GAP_STEPS * cadence(measurements) + refs = {s for s, v in measurements.items() if is_reference(v)} + instants = sorted({m["t"] for v in measurements.values() for m in v}) + z = {} # t -> {sensor: error_value in MAD above the sensor's median} + high, strong, rejected, repeated = {}, {}, {}, {} # t -> {sensors}; repeated: target -> [t] + for s, v in measurements.items(): + e = [m["error_value"] for m in v if m["error_value"] is not None] + if len(e) < 10: + continue + med, mad = level(e) + for m in v: + t, x = m["t"], m["error_value"] + if x is None: + continue + z.setdefault(t, {})[s] = (x - med) / mad + if x > med + K_MAD * mad and x > FACTOR * med: + high.setdefault(t, set()).add(s) + if m["error_threshold"] and x > m["error_threshold"]: + rejected.setdefault(t, set()).add(s) + if x > FACTOR * med: + strong.setdefault(t, set()).add(s) + if s not in refs and x > med + K_TARGET * mad: + repeated.setdefault(s, []).append(t) + n = lambda t: len(high.get(t, ())) # noqa: E731 + out, briefs = [], set() + + for i, t in enumerate(instants): # 2. Brief obstruction + around = [instants[j] for j in (i - 1, i + 1) if 0 <= j < len(instants)] + few = strong.get(t, set()) + if n(t) >= BRIEF_MIN and n(t) >= SALIENCE * max(map(n, around), default=0): + briefs.add(t) + few = high[t] + elif not (few and len(few) < BRIEF_MIN and n(t) < BRIEF_MIN and len(few & refs) <= 1 + and not few & set().union(*(rejected.get(u, set()) for u in around))): + continue + out.append(episode(t, t, "Obstruction", "Brief obstruction", BRIEF.format(targets(len(few))), few, True)) + + spans = [] # 3. Poor visibility: runs of each sensor, then the overlapping runs of at least two sensors + for s in {s for t in high for s in high[t]}: + spans += [(r[0], r[-1], s) for r in runs([t for t in instants if s in high.get(t, ()) and t not in briefs], gap) + if len(r) >= RUN_MIN] + zones = [] + for a, b, s in sorted(spans): + if zones and a - zones[-1][1] <= gap: + zones[-1] = (zones[-1][0], max(zones[-1][1], b), zones[-1][2] | {s}) + else: + zones.append((a, b, {s})) + zones = [zone for zone in zones if len(zone[2]) >= 2] + lv = _levels(measurements, instants) + for a, b, cs in zones: + inside = [t for t in instants if a <= t <= b] + for k, t in enumerate(inside): + seg = [t] if k == 0 or lv[t] != lv[inside[k - 1]] else seg + [t] + if k == len(inside) - 1 or lv[inside[k + 1]] != lv[t]: + out.append(_poor(seg[0], seg[-1], cs & set().union(*(high.get(u, set()) for u in seg)) or cs, lv[t], refs)) + + shimmer = heat_shimmer(measurements) # 4. diffuse nuisance + hosts = shimmer + [e for e in out if e["kind"] == "Visibility"] + for r in runs([t for t in sorted(z) if statistics.median(z[t].values()) >= K_DIFFUSE], gap): + e = _poor(r[0], r[-1], {s for t in r for s, x in z[t].items() if x >= K_DIFFUSE}, "reduced", refs) + if len(r) >= RUN_MIN and not any(h["start"] <= e["start"] and e["end"] <= h["end"] for h in hosts): + out.append(e) + + seen = lambda t: t in briefs or any(a <= t <= b for a, b, _ in zones) # noqa: E731 + for s, ts in repeated.items(): # 5. Target obscured + for r in runs(ts, TARGET_GAP): + if len(r) >= TARGET_MIN and 2 * sum(map(seen, r)) < len(r): + out.append(episode(r[0], r[-1], "Obstruction", "Target obscured", OBSCURED.format(s), [s], True)) + return out + shimmer -# --- Heat shimmer ---------------------------------------------------------------------------------------------------- -# Atmospheric turbulence (fast noise on the corrected displacements). Method: -# 1. Per sensor and per hour H, on the measurements of [H − 1 h, H + 2 h): agitation = median of |Δcorr_x| + |Δcorr_y| -# between successive measurements (robust to one-step jumps), and median of the error_value. -# 2. Each is divided by the sensor's calm: the lower quartile of its hourly values over the export (often the night). -# 3. Turbulent hour: at least SHARE of the sensors at ≥ RATIO times their calm agitation, and median error_value of the -# sensors at ≥ RATIO_ERR times the calm (warm air blurs the spots: E-003). -# 4. Neighbouring hours merged (a one-hour hole tolerated), episode of at least MIN_DURATION, dropped if more than -# REJECT_MAX of the measurements are rejected beyond their sensor's habit (its share of rejections over the export): -# it is then poor visibility, another rule. A target that is always rejected (Target issue) does not count (wf-improve -# session Visibility, mod. 1, S1: WILDSTRUBEL, R3 rejected all day, the days of heat shimmer were dropped). -# Greyed if the median agitation ≥ STRONG. -RATIO = 1.5 # tuned on E-003 (WILDSTRUBEL: by day, corr ×1.7 to ×3 the night) -SHARE = 0.5 # share of the sensors agitated at the same time -RATIO_ERR = 1.5 # tuned on E-003 (error_value ×1.7 to ×3.2 the night; ≈ ×1 at noon elsewhere) -REJECT_MAX = 0.15 # E-003 ≤ 7 %; cobweb (E-002) and rain (E-005) ≥ 18 %; rejections beyond the habit since wf-improve - # session Visibility, mod. 1, S1 (WILDSTRUBEL: 4 to 14 %, against 9 to 22 % raw) -STRONG = 2.0 # E-003 (×2.3 to ×2.6) is strong; an episode between ×1.5 and ×2 stays visible -MIN_DURATION = timedelta(hours=3) # E-003 lasts 10-11 h; drops the morning of the real movement of E-004 (2 h), which - # the classification drops too, whatever the duration +# --- Heat shimmer: fast noise of the corrected displacements in warm air. +# 1. Per sensor and per hour H, over [H - 1 h, H + 2 h): agitation, the median of |Δcorr_x| + |Δcorr_y| between successive +# measurements, and the median error_value; each divided by its calm (lower quartile of the sensor's hourly values). +# 2. Turbulent hour: at least SHARE of the sensors agitated at RATIO times their calm, and median error_value at RATIO. +# 3. Turbulent hours at most 2 h apart make an episode, dropped if more than REJECT_MAX of its measurements are rejected +# beyond each sensor's habit (its share of rejections over the export): that is poor visibility. Greyed if the median +# agitation reaches STRONG. +RATIO = 1.5 # E-003 (WILDSTRUBEL: by day, corr ×1.7 to ×3 the night, error_value ×1.7 to ×3.2) +SHARE = 0.5 +REJECT_MAX = 0.15 # E-003 ≤ 7 %; cobweb (E-002) and rain (E-005) ≥ 18 %; beyond the habit: wf-improve Visibility, mod. 1, S1 +STRONG = 2.0 # E-003 (×2.3 to ×2.6) HOUR = timedelta(hours=1) - - -def _hour(t): - return t.replace(minute=0, second=0, microsecond=0) +SHIMMER = "Warm air made the readings shake ({:.1f}× noisier than in calm hours). The small fast wiggles are not movement." def _ratios(points): - """[(t, value)] -> {hour H: median over [H − 1 h, H + 2 h) / lower quartile of these medians}.""" + """[(t, value)] -> {hour H: median over [H - 1 h, H + 2 h) / lower quartile of these medians}.""" by = {} for t, v in points: for k in (-1, 0, 1): - by.setdefault(_hour(t) + k * HOUR, []).append(v) + by.setdefault(t.replace(minute=0, second=0, microsecond=0) + k * HOUR, []).append(v) med = {h: statistics.median(v) for h, v in by.items() if len(v) >= 3} - if len(med) < 8: - return {} - calm = statistics.quantiles(med.values(), n=4)[0] + calm = statistics.quantiles(med.values(), n=4)[0] if len(med) >= 8 else 0 return {h: v / calm for h, v in med.items()} if calm > 0 else {} -def hours(measurements): - """-> {hour: {sensor: (agitation / calm, error_value / calm)}}.""" - out = {} +def heat_shimmer(measurements): + hours = {} # hour -> {sensor: (agitation / calm, error_value / calm)} for s, ms in measurements.items(): ag = _ratios([(b["t"], abs(b["corr_x"] - a["corr_x"]) + abs(b["corr_y"] - a["corr_y"])) for a, b in zip(ms, ms[1:]) if a["corr_x"] is not None and b["corr_x"] is not None]) er = _ratios([(m["t"], m["error_value"]) for m in ms if m["error_value"] is not None]) - for h, r in ag.items(): - if h in er: - out.setdefault(h, {})[s] = (r, er[h]) - return out - - -def _turbulent(r): - return (sum(a >= RATIO for a, _ in r.values()) >= SHARE * len(r) - and statistics.median(e for _, e in r.values()) >= RATIO_ERR) - - -def heat_shimmer(measurements): - H = hours(measurements) - blocks = [] - for h in sorted(h for h, r in H.items() if _turbulent(r)): - if blocks and h - blocks[-1][-1] <= 2 * HOUR: - blocks[-1].append(h) - else: - blocks.append([h]) - habit = {s: sum(m["corr_x"] is None for m in ms) / len(ms) for s, ms in measurements.items()} # usual rejections - episodes = [] - for b in blocks: + for h in ag.keys() & er.keys(): + hours.setdefault(h, {})[s] = (ag[h], er[h]) + turbulent = [h for h, r in sorted(hours.items()) if sum(a >= RATIO for a, _ in r.values()) >= SHARE * len(r) + and statistics.median(e for _, e in r.values()) >= RATIO] + habit = {s: sum(m["corr_x"] is None for m in ms) / len(ms) for s, ms in measurements.items()} + out = [] + for b in runs(turbulent, 2 * HOUR): start, end = b[0], b[-1] + HOUR by = {s: [m for m in ms if start <= m["t"] < end] for s, ms in measurements.items()} new = sum(max(0, sum(m["corr_x"] is None for m in d) - habit[s] * len(d)) for s, d in by.items()) - if end - start < MIN_DURATION or new > REJECT_MAX * sum(map(len, by.values())): + if new > REJECT_MAX * sum(map(len, by.values())): continue - by_sensor = {} - for h in b: - for s, (a, _) in H[h].items(): - by_sensor.setdefault(s, []).append(a) - agit = {s: statistics.median(v) for s, v in by_sensor.items()} + agit = {s: statistics.median(hours[h][s][0] for h in b if s in hours[h]) for s in {s for h in b for s in hours[h]}} strength = statistics.median(agit.values()) - episodes.append({ - "start": iso(start), "end": iso(end), "kind": "Visibility", - "label": "Heat shimmer", - "text": f"Readings were about {strength:.1f}× noisier than in calm hours because of heat shimmer " - "(warm air trembling in the line of sight); the small fast wiggles are not movement.", - "ignore": strength >= STRONG, - "sensors": sorted(s for s, v in agit.items() if v >= RATIO), - }) - return episodes + out.append(episode(start, end, "Visibility", "Heat shimmer", SHIMMER.format(strength), + [s for s, v in agit.items() if v >= RATIO], strength >= STRONG)) + return out