Keep spans with unknown inputs out of Model Error

Reproduced: a window unknown for a whole 15-minute span was replayed as
closed and scored as a Model Error sample (MAE 0.76 °C on one sample).

- A zone's replay is complete only if every step's model inputs were
  observed: window openings (and a confirmed recovery), the wind, direction
  and other zones' windows that an open window's terms use, and, for the
  extended layer, electrical heat and neighbours, whose own replay must be
  complete too.
- Incomplete spans are counted, not scored; the base model's error on them
  is kept separately (it needs only the relay and outdoor temperature).
  Spans that could not be replayed (uncertain radiator lag, no reading at
  the end) are counted as skipped. Model Error sensors show incomplete,
  skipped and incomplete_base_model_mae; stored data gains an "excluded"
  section and older data loads unchanged.
- Window inputs no longer stand in for unknown values: the facing term is
  unknown while a window is open and the wind direction is not, and the
  cross-ventilation input is unknown while another zone's window is. With
  every window closed, opening terms are 0 and need no weather input.
  Learning refuses such samples; forecasts still assume calm air.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

custom_components/heating_mpc/evaluation.py

@@ -34,7 +34,7 @@ from math import isfinite, sqrt
 from typing import Any
 
 from .physics import Learner
-from .windows import ventilation_vector_for_prediction
+from .windows import ventilation_known, ventilation_vector_for_prediction
 from .zone_model import feature_vector
 
 HORIZONS = (15, 30, 60, 120)  # minutes
@@ -97,19 +97,50 @@ def snapshot_delta(snapshot: dict[str, Any], temp: float, inputs: dict[str, Any]
     return main
 
 
-def replay_zones(origin: dict[str, Any], path: list[dict[str, Any]]) -> dict[str, float]:
-    """All zones advanced together with the origin's models and the actual inputs."""
+def inputs_complete(snapshot: dict[str, Any], temp: float, inputs: dict[str, Any],
+                    incomplete: set[str]) -> bool:
+    """Whether a step of a zone's model used only observed inputs.
+
+    Not when a window state, or a weather input an open window's terms need, was
+    unknown; nor when the extended layer is in use and its electrical heat or a
+    neighbour is unknown, or that neighbour's own replay is already incomplete.
+    The replay itself still falls back as forecasts do; the result is just not a
+    measurement of the model.
+    """
+    vent_features = snapshot["ventilation"][0] if snapshot.get("ventilation") else ()
+    if not ventilation_known(vent_features, inputs.get("ventilation")):
+        return False
+    if snapshot["uses_extended"] and snapshot["extended"]:
+        features = snapshot["extended"][0]
+        if feature_vector(features, temp, inputs) is None:
+            return False
+        if any(f.startswith("couple:") and f.split(":", 1)[1] in incomplete for f in features):
+            return False
+    return True
+
+
+def replay_zones(origin: dict[str, Any], path: list[dict[str, Any]]) -> tuple[dict[str, float], set[str]]:
+    """All zones advanced together with the origin's models and the actual inputs.
+
+    Returns the replayed temperatures and the zones whose replay needed an input
+    that was not observed at some step (see inputs_complete).
+    """
     state = dict(origin["temps"])
+    incomplete: set[str] = set()
     for before, poll in zip(path, path[1:]):
         seconds = (poll["time"] - before["time"]).total_seconds()
         new = {}
+        unknown = set(incomplete)
         for zone, temp in state.items():
             actual = poll["inputs"].get(zone, {})
             inputs = {"outside": origin["outside"], "lag": poll["lag"], "temps": state,
                       "internal": actual.get("internal"), "ventilation": actual.get("ventilation")}
-            new[zone] = temp + snapshot_delta(origin["models"][zone], temp, inputs) * seconds / STEP_SECONDS
-        state = new
-    return state
+            snapshot = origin["models"][zone]
+            if not inputs_complete(snapshot, temp, inputs, incomplete):
+                unknown.add(zone)
+            new[zone] = temp + snapshot_delta(snapshot, temp, inputs) * seconds / STEP_SECONDS
+        state, incomplete = new, unknown
+    return state, incomplete
 
 
 class ForecastEvaluator:
@@ -121,6 +152,9 @@ class ForecastEvaluator:
         # UTC day -> horizon -> room -> [count, sum error, sum |error|, sum |persistence error|,
         #   sum |base model error|, sum error^2, count with squares (0 for 0.3/0.4 data)]
         self._days: dict[str, dict[str, dict[str, list[float]]]] = {}
+        # UTC day -> horizon -> room -> [incomplete spans, skipped spans, sum |base model error|
+        #   over the incomplete ones]. Neither kind enters the statistics above.
+        self._excluded: dict[str, dict[str, dict[str, list[float]]]] = {}
 
     def reset_window(self) -> None:
         """Inputs were missing: no forecast may be scored across this poll."""
@@ -147,6 +181,11 @@ class ForecastEvaluator:
         self._score()
         self._prune(time)
 
+    def _exclude(self, day: str, horizon: int, room: str, kind: int, base_error: float = 0.0) -> None:
+        bucket = self._excluded.setdefault(day, {}).setdefault(str(horizon), {}).setdefault(room, [0, 0, 0.0])
+        bucket[kind] += 1
+        bucket[2] += abs(base_error)
+
     def _score(self) -> None:
         history = list(self._history)
         latest = history[-1]
@@ -156,19 +195,27 @@ class ForecastEvaluator:
             if len(history) < steps + 1:
                 continue
             path = history[-(steps + 1):]
+            origin = path[0]
             # The actual heat input must be known along the way.
             if any(poll["lag_uncertainty"] > self._max_lag_uncertainty for poll in path[1:]):
+                for room in origin["temps"]:
+                    self._exclude(day, horizon, room, SKIPPED)
                 continue
-            origin = path[0]
             inputs = [(poll["lag"], (poll["time"] - before["time"]).total_seconds())
                       for before, poll in zip(path, path[1:])]
-            full = replay_zones(origin, path)
-            for room, actual in latest["temps"].items():
-                start, theta = origin["temps"].get(room), origin["theta"].get(room)
-                if start is None or theta is None:
+            full, incomplete = replay_zones(origin, path)
+            for room, start in origin["temps"].items():
+                actual, theta = latest["temps"].get(room), origin["theta"].get(room)
+                if actual is None or theta is None:
+                    self._exclude(day, horizon, room, SKIPPED)  # no reading at the end
                     continue
                 error = full[room] - actual
                 base_error = replay(start, origin["outside"], theta, inputs) - actual
+                if room in incomplete:
+                    # The base model needs only the relay and outdoor temperature: its
+                    # error is still a measurement, kept apart from the main figures.
+                    self._exclude(day, horizon, room, INCOMPLETE, base_error)
+                    continue
                 bucket = self._days.setdefault(day, {}).setdefault(str(horizon), {}).setdefault(
                     room, [0, 0.0, 0.0, 0.0, 0.0, 0.0, 0])
                 bucket[0] += 1
@@ -181,8 +228,9 @@ class ForecastEvaluator:
 
     def _prune(self, time: datetime) -> None:
         oldest = (time.date() - timedelta(days=WINDOW_DAYS - 1)).isoformat()
-        for day in [day for day in self._days if day < oldest]:
-            del self._days[day]
+        for store in (self._days, self._excluded):
+            for day in [day for day in store if day < oldest]:
+                del store[day]
 
     def summary(self, rooms: list[str]) -> dict[int, dict[str, Any]]:
         """Error statistics per horizon, overall and per configured room."""
@@ -196,15 +244,27 @@ class ForecastEvaluator:
                         for i, value in enumerate(values):
                             totals[i] += value
             overall = [sum(values[i] for values in per_room.values()) for i in range(7)]
-            result[horizon] = {**_stats(overall, horizon, len(per_room)),
-                               "rooms": {room: _stats(values, horizon) for room, values in per_room.items()}}
+            excluded: dict[str, list[float]] = {}
+            for day in self._excluded.values():
+                for room, values in day.get(str(horizon), {}).items():
+                    if room in rooms:
+                        totals = excluded.setdefault(room, [0, 0, 0.0])
+                        for i, value in enumerate(values):
+                            totals[i] += value
+            all_excluded = [sum(values[i] for values in excluded.values()) for i in range(3)]
+            result[horizon] = {**_stats(overall, horizon, len(per_room)), **_excluded_stats(all_excluded),
+                               "rooms": {room: {**_stats(per_room.get(room, [0, 0.0, 0.0, 0.0, 0.0, 0.0, 0]),
+                                                         horizon),
+                                                **_excluded_stats(excluded.get(room, [0, 0, 0.0]))}
+                                         for room in rooms if room in per_room or room in excluded}}
         return result
 
     def forget(self, room: str) -> None:
         """Drop a zone's statistics, for example when its temperature is measured differently."""
-        for by_horizon in self._days.values():
-            for by_room in by_horizon.values():
-                by_room.pop(room, None)
+        for store in (self._days, self._excluded):
+            for by_horizon in store.values():
+                for by_room in by_horizon.values():
+                    by_room.pop(room, None)
         for poll in self._history:
             poll["temps"].pop(room, None)
 
@@ -213,11 +273,20 @@ class ForecastEvaluator:
         return {"days": {day: {horizon: {room: [v[0], *(round(x, 6) for x in v[1:6]), v[6]]
                                          for room, v in by_room.items()}
                                for horizon, by_room in by_horizon.items()}
-                         for day, by_horizon in self._days.items()}}
+                         for day, by_horizon in self._days.items()},
+                "excluded": {day: {horizon: {room: [v[0], v[1], round(v[2], 6)] for room, v in by_room.items()}
+                                   for horizon, by_room in by_horizon.items()}
+                             for day, by_horizon in self._excluded.items()}}
 
     def load(self, data: Any) -> None:
         """Restore stored statistics, keeping only well-formed entries."""
-        self._days = {}
+        self._days, self._excluded = {}, {}
+        excluded = data.get("excluded") if isinstance(data, dict) else None
+        for day, horizon, room, values in _entries(excluded):
+            if (isinstance(values, list) and len(values) == 3 and all(type(v) is int and v >= 0 for v in values[:2])
+                    and type(values[2]) in (int, float) and isfinite(values[2]) and values[2] >= 0):
+                self._excluded.setdefault(day, {}).setdefault(horizon, {})[room] = [
+                    values[0], values[1], float(values[2])]
         days = data.get("days") if isinstance(data, dict) else None
         if not isinstance(days, dict):
             return
@@ -243,6 +312,30 @@ class ForecastEvaluator:
                             *squares]
 
 
+INCOMPLETE, SKIPPED = 0, 1  # columns of the excluded-span counts
+
+
+def _entries(days: Any):
+    """(day, horizon, zone, values) of stored per-day statistics with a valid shape."""
+    if not isinstance(days, dict):
+        return
+    horizons = {str(horizon) for horizon in HORIZONS}
+    for day, by_horizon in days.items():
+        if not _valid_day(day) or not isinstance(by_horizon, dict):
+            continue
+        for horizon, by_zone in by_horizon.items():
+            if horizon in horizons and isinstance(by_zone, dict):
+                for zone, values in by_zone.items():
+                    if isinstance(zone, str):
+                        yield day, horizon, zone, values
+
+
+def _excluded_stats(values: list[float]) -> dict[str, Any]:
+    incomplete, skipped, base = values
+    return {"incomplete": int(incomplete), "skipped": int(skipped),
+            "incomplete_base_model_mae": round(base / incomplete, 3) if incomplete else None}
+
+
 def _valid_bucket(room: Any, values: Any) -> bool:
     if not isinstance(room, str) or not isinstance(values, list) or len(values) not in (4, 5, 7):
         return False

custom_components/heating_mpc/sensor.py

@@ -180,6 +180,11 @@ class MPCForecastError(CoordinatorEntity, SensorEntity):
             "skill": accuracy.get("skill"),
             "base_model_mae": accuracy.get("base_model_mae"),
             "improvement_vs_base": accuracy.get("improvement_vs_base"),
+            # Spans left out of the figures above: an input the model needed was unknown
+            # (the base model's error on them is still measured), or no replay was possible.
+            "incomplete": accuracy.get("incomplete", 0),
+            "incomplete_base_model_mae": accuracy.get("incomplete_base_model_mae"),
+            "skipped": accuracy.get("skipped", 0),
             # Per zone, by name.
             "zones": {self.coordinator.zones[key].name if key in self.coordinator.zones else key: stats
                       for key, stats in accuracy.get("rooms", {}).items()},

custom_components/heating_mpc/windows.py

@@ -150,17 +150,22 @@ def ventilation_vector(features: Iterable[str], temp: float, outside: float,
                        inputs: Mapping[str, Any]) -> list[float] | None:
     """Ventilation feature values for one zone and step; None if an input is unknown.
 
-    `inputs`: opening, facing (sum of opening x cos), other_opening, recovery,
-    t_ref (pre-ventilation temperature), wind, gust.
+    `inputs`: opening, facing (sum of opening x cos; None when the wind direction is
+    unknown), other_opening (None when another zone's windows are unknown),
+    recovery, t_ref (pre-ventilation temperature), wind, gust. With every window
+    closed the opening terms are 0 whatever the weather, so only the opening and,
+    while recovering, the reference temperature must be known.
     """
     difference = outside - temp
+    opening = inputs.get("opening")
+    if opening is None:
+        return None
     values = []
     for name in features:
-        opening = inputs.get("opening")
-        if opening is None:
-            return None
         if name == "vent_natural":
             values.append(opening * difference)
+        elif name in ("vent_wind", "vent_wind_dir", "vent_gust", "vent_cross") and opening == 0:
+            values.append(0.0)
         elif name in ("vent_wind", "vent_wind_dir", "vent_gust"):
             wind = inputs.get("wind")
             if wind is None:
@@ -178,7 +183,10 @@ def ventilation_vector(features: Iterable[str], temp: float, outside: float,
                     return None
                 values.append(opening * max(0.0, gust - wind) * difference)
         elif name == "vent_cross":
-            values.append(opening * (inputs.get("other_opening") or 0.0) * difference)
+            other = inputs.get("other_opening")
+            if other is None:
+                return None
+            values.append(opening * other * difference)
         elif name == "recovery":
             recovery = inputs.get("recovery") or 0.0
             t_ref = inputs.get("t_ref")
@@ -203,10 +211,22 @@ def ventilation_vector_for_prediction(features: Iterable[str], temp: float, outs
     if x is None and inputs.get("opening") is not None:
         x = ventilation_vector(features, temp, outside, {
             **inputs, "wind": inputs.get("wind") or 0.0, "gust": inputs.get("gust") or inputs.get("wind") or 0.0,
-            "facing": inputs.get("facing") or 0.0})
+            "facing": inputs.get("facing") or 0.0, "other_opening": inputs.get("other_opening") or 0.0})
     return x
 
 
+def ventilation_known(features: Iterable[str], inputs: Mapping[str, Any] | None) -> bool:
+    """True when a zone's ventilation term follows from observed inputs alone.
+
+    False while a window state is unknown or a recovery's start is unconfirmed,
+    or while a window is open and a term it activates lacks its weather input.
+    Zones without windows (`inputs` None or empty) need nothing.
+    """
+    if not inputs:
+        return True
+    return ventilation_vector(list(features), 0.0, 0.0, inputs) is not None
+
+
 def _iso(timestamp: float) -> str:
     return datetime.fromtimestamp(timestamp, timezone.utc).isoformat(timespec="seconds")
 
@@ -266,7 +286,7 @@ class VentilationTracker:
             zone = zones.setdefault(window.zone, {
                 "opening": 0.0, "facing_unit": 0.0, "known": True, "open_now": False, "possibly_open": False,
                 "open_windows": [], "last_close": None, "close_confirmed": True, "first_open": None,
-                "open_confirmed": True, "unknown_windows": []})
+                "open_confirmed": True, "unknown_windows": [], "facing_known": True})
             if fraction is None:
                 zone["known"] = False
             else:
@@ -274,6 +294,8 @@ class VentilationTracker:
                 zone["facing_unit"] += window.opening * fraction * (
                     facing_cos(weather["wind_direction"], window.azimuth)
                     if weather.get("wind_direction") is not None else 0.0)
+                if fraction > 0 and weather.get("wind_direction") is None:
+                    zone["facing_known"] = False
             if is_open is None:
                 if memory["unknown_since"] is None:
                     memory["unknown_since"] = memory["seen"] if memory["seen"] is not None else now
@@ -382,7 +404,8 @@ class VentilationTracker:
             recovery = 0.0
         zone.update(recovery=recovery, t_ref=self._t_ref.get(key),
                     recovery_confirmed=self._recovery_confirmed.get(key, True),
-                    other_opening=sum(z["opening"] for k, z in zones.items() if k != key and z["known"]))
+                    other_opening=sum(z["opening"] for k, z in zones.items() if k != key and z["known"]),
+                    others_known=all(z["known"] for k, z in zones.items() if k != key))
         # Learning of the closed-window model is unsafe while anything ventilation-related goes on.
         zone["affected"] = (not zone["known"]) or zone["opening"] > 0 or ventilating or recovery > 0
 
@@ -396,8 +419,10 @@ class VentilationTracker:
         if zone is None:
             return None
         known = zone["known"] and (zone["recovery"] == 0 or zone["recovery_confirmed"])
-        return {"opening": zone["opening"] if known else None, "facing": zone["facing_unit"],
-                "other_opening": zone["other_opening"], "recovery": zone["recovery"],
+        return {"opening": zone["opening"] if known else None,
+                "facing": zone["facing_unit"] if zone["facing_known"] else None,
+                "other_opening": zone["other_opening"] if zone["others_known"] else None,
+                "recovery": zone["recovery"],
                 "t_ref": zone["t_ref"], "wind": weather.get("wind"), "gust": weather.get("wind_gust"),
                 "affected": zone["affected"], "known": known,
                 "unknown_windows": list(zone["unknown_windows"])}

tests/ha/test_lifecycle.py

@@ -302,6 +302,7 @@ async def test_forecast_error_sensors_score_scheduled_polls(hass, entry, inputs,
     assert state.attributes["mae"] == accuracy["mae"] > 0
     assert state.attributes["quality"] == "insufficient"
     assert state.attributes["samples"] == 1
+    assert (state.attributes["incomplete"], state.attributes["skipped"]) == (0, 0)
     assert state.attributes["zones"]["room"]["samples"] == 1  # by zone name
     assert state.attributes["unit_of_measurement"] == "°C"
     assert state.attributes["friendly_name"] == "Heating MPC Model Error 15 min"

tests/test_evaluation.py

@@ -116,15 +116,22 @@ class EvaluationTests(unittest.TestCase):
             day: {'45': {'sensor.room': [1, 0.0, 0.1, 0.1]},
                   '15': {'sensor.a': [1, 0.0, -0.1, 0.1], 'sensor.b': [True, 0, 0, 0],
                          'sensor.c': [1, float('nan'), 0, 0], 'sensor.d': [2, 0.1, 0.2, 0.4],
-                         'sensor.e': [2, 0.1, 0.2, 0.4, 0.3], 'sensor.f': [2, 0.1, 0.2, 0.4, -1]}}}})
+                         'sensor.e': [2, 0.1, 0.2, 0.4, 0.3], 'sensor.f': [2, 0.1, 0.2, 0.4, -1]}}},
+            'excluded': {day: {'15': {'sensor.d': [1, 2, 0.3], 'sensor.x': [1, -2, 0.3], 'sensor.y': [1, 2]},
+                               '45': {'sensor.d': [1, 2, 0.3]}}}})
         # A 0.3 bucket has no base-model column; its model was the base model then.
         # Neither 0.3 nor 0.4 buckets have squared errors: they do not count for RMSE.
+        # 0.4 data has no excluded-span counts.
         self.assertEqual(restored.as_dict(), {'days': {day: {'15': {
-            'sensor.d': [2, 0.1, 0.2, 0.4, 0.2, 0.0, 0], 'sensor.e': [2, 0.1, 0.2, 0.4, 0.3, 0.0, 0]}}}})
+            'sensor.d': [2, 0.1, 0.2, 0.4, 0.2, 0.0, 0], 'sensor.e': [2, 0.1, 0.2, 0.4, 0.3, 0.0, 0]}}},
+            'excluded': {day: {'15': {'sensor.d': [1, 2, 0.3]}}}})
         self.assertIsNone(restored.summary(['sensor.d'])[15]['rmse'])
+        self.assertEqual({k: restored.summary(['sensor.d'])[15][k] for k in ('incomplete', 'skipped',
+                                                                             'incomplete_base_model_mae')},
+                         {'incomplete': 1, 'skipped': 2, 'incomplete_base_model_mae': 0.3})
         for garbage in (None, [], {'days': []}):
             restored.load(garbage)
-            self.assertEqual(restored.as_dict(), {'days': {}})
+            self.assertEqual(restored.as_dict(), {'days': {}, 'excluded': {}})
 
 
 T0 = START.timestamp()
@@ -206,3 +213,89 @@ class OperationalForecastTests(unittest.TestCase):
 
 if __name__ == '__main__':
     unittest.main()
+
+
+BASE = (0.004, 0.12, 0.0005)
+
+
+def ventilated(observed, actual=None, wind=4.0, features=('vent_natural',), zones=('r',), internal=None,
+               extended=None, lag_uncertain_at=(), missing_end_at=()):
+    """Zones cooled by real ventilation; `observed[k]` is what the window sensor said
+    for the interval ending at poll k (None: unknown). Returns the summary at 15 min."""
+    actual = actual if actual is not None else [1.0 if o is None else o for o in observed]
+    snapshot = {'base': BASE, 'uses_extended': extended is not None, 'extended': extended,
+                'ventilation': (list(features), (0.02,) * len(features))}
+    evaluator, temps = ev.ForecastEvaluator(0.1), {zone: 20.0 for zone in zones}
+    for k, seen in enumerate(observed):
+        if k:
+            temps = {zone: t + 0.004 * (5 - t) + 0.12 * 0.5 + 0.0005
+                     + 0.02 * actual[k] * (5 - t) * (1 + (wind or 0) * ('vent_wind' in features))
+                     for zone, t in temps.items()}
+        vent = {'opening': seen, 'facing': 0.0, 'other_opening': 0.0, 'recovery': 0.0, 't_ref': None,
+                'wind': wind}
+        readings = {z: t for z, t in temps.items() if not (k in missing_end_at and z == zones[0])}
+        evaluator.observe(START + timedelta(seconds=300 * k), readings, 5.0, 0.5,
+                          0.5 if k in lag_uncertain_at else 0.0, {z: BASE for z in zones},
+                          models={z: snapshot for z in zones},
+                          inputs={z: {'internal': internal, 'ventilation': vent if z == zones[0] else
+                                      {**vent, 'opening': actual[k]}} for z in zones})
+    return evaluator.summary(list(zones))[15]
+
+
+class IncompleteInputTests(unittest.TestCase):
+    """Unknown ventilation or extended inputs never become Model Error samples."""
+
+    def test_window_unknown_for_the_whole_span_is_incomplete(self):
+        stats = ventilated([0.0, None, None, None])
+        self.assertEqual((stats['samples'], stats['mae'], stats['incomplete']), (0, None, 1))
+        # The base model needs no window input: its error is still kept, apart.
+        self.assertGreater(stats['incomplete_base_model_mae'], 0.1)
+
+    def test_window_unknown_halfway_or_recovering_during_the_span(self):
+        self.assertEqual(ventilated([0.0, 1.0, None, 1.0])['incomplete'], 1)   # unavailable halfway
+        stats = ventilated([0.0, None, 1.0, 1.0, 1.0, 1.0, 1.0])            # back after one poll
+        # Spans ending at polls 3-6: only the first contains the unknown interval.
+        self.assertEqual((stats['incomplete'], stats['samples']), (1, 3))
+        self.assertAlmostEqual(stats['mae'], 0, places=6)                   # the known spans are exact
+
+    def test_one_zone_unknown_leaves_the_other_zone_scored(self):
+        stats = ventilated([0.0, None, None, None], zones=('a', 'b'))
+        self.assertEqual((stats['rooms']['a']['incomplete'], stats['rooms']['a']['samples']), (1, 0))
+        self.assertEqual((stats['rooms']['b']['incomplete'], stats['rooms']['b']['samples']), (0, 1))
+
+    def test_missing_wind_matters_only_while_a_window_is_open(self):
+        features = ('vent_natural', 'vent_wind')
+        open_span = ventilated([0.0, 1.0, 1.0, 1.0], wind=None, features=features)
+        closed_span = ventilated([0.0, 0.0, 0.0, 0.0], wind=None, features=features)
+        self.assertEqual((open_span['incomplete'], open_span['samples']), (1, 0))
+        self.assertEqual((closed_span['incomplete'], closed_span['samples']), (0, 1))
+        self.assertEqual(ventilated([0.0, 1.0, 1.0, 1.0], features=features)['samples'], 1)
+
+    def test_unknown_electrical_heat_makes_the_extended_replay_incomplete(self):
+        extended = (['loss', 'heat', 'bias', 'internal'], BASE + (0.15,))
+        stats = ventilated([0.0] * 4, extended=extended, internal=None)
+        self.assertEqual((stats['incomplete'], stats['samples']), (1, 0))
+        self.assertIsNotNone(stats['incomplete_base_model_mae'])
+        self.assertEqual(ventilated([0.0] * 4, extended=extended, internal=0.0)['samples'], 1)
+
+    def test_a_neighbour_with_unknown_inputs_spoils_a_coupled_zone(self):
+        coupled = {'base': BASE, 'uses_extended': True, 'ventilation': None,
+                   'extended': (['loss', 'heat', 'bias', 'couple:a'], BASE + (0.01,))}
+        plain = {'base': BASE, 'uses_extended': False, 'extended': None,
+                 'ventilation': (['vent_natural'], (0.02,))}
+        origin = {'temps': {'a': 20.0, 'b': 20.0}, 'outside': 5.0, 'models': {'a': plain, 'b': coupled}}
+        path = [origin] + [{'time': START + timedelta(seconds=300 * k), 'lag': 0.5,
+                            'inputs': {'a': {'ventilation': {'opening': None}}, 'b': {}}} for k in range(4)]
+        origin['time'] = START - timedelta(seconds=300)
+        _, incomplete = ev.replay_zones(origin, path)
+        self.assertEqual(incomplete, {'a', 'b'})
+        path = [origin] + [{**poll, 'inputs': {'a': {'ventilation': {'opening': 0.0}}, 'b': {}}} for poll in path[1:]]
+        self.assertEqual(ev.replay_zones(origin, path)[1], set())
+
+    def test_skipped_spans_are_counted_and_samples_stay_correct(self):
+        stats = ventilated([0.0] * 9, lag_uncertain_at=(4,))
+        # Spans ending at 3..8: those crossing poll 4 (ending 4, 5, 6) are skipped.
+        self.assertEqual((stats['samples'], stats['skipped'], stats['incomplete']), (3, 3, 0))
+        stats = ventilated([0.0] * 5, missing_end_at=(4,), zones=('a', 'b'))
+        self.assertEqual((stats['rooms']['a']['samples'], stats['rooms']['a']['skipped']), (1, 1))
+        self.assertEqual(stats['rooms']['b']['samples'], 2)

tests/test_windows.py

@@ -392,3 +392,26 @@ class StartupAndRestartTests(unittest.TestCase):
         self.assertFalse(tracker.changed)               # nothing new
         self.poll(tracker, 'unavailable')
         self.assertTrue(tracker.changed)
+
+
+class StrictInputTests(unittest.TestCase):
+    """Weather inputs of an open window are required, never assumed, outside forecasts."""
+
+    def test_unknown_direction_or_other_zone_while_open(self):
+        windows = wm.build_windows([(window('a'), None), (window('c', zone='living'), None)], ['bed', 'living'])
+        tracker = wm.VentilationTracker(windows)
+        calm = {**WEATHER, 'wind_direction': None}
+        for t, a, c in ((300.0, 'off', 'off'), (600.0, 'on', 'unavailable'), (900.0, 'on', 'unavailable')):
+            tracker.update(t, {'a': (a, 450.0), 'c': (c, 450.0)}, {'bed': 20.0, 'living': 21.0}, calm)
+        bed = tracker.zone_inputs('bed', calm)
+        self.assertEqual((bed['opening'], bed['facing'], bed['other_opening']), (1.0, None, None))
+        features = ['vent_natural', 'vent_wind', 'vent_wind_dir', 'vent_cross']
+        self.assertFalse(wm.ventilation_known(features, bed))
+        self.assertTrue(wm.ventilation_known(['vent_natural', 'vent_wind'], bed))
+        self.assertIsNone(wm.ventilation_vector(features, 20.0, 2.0, bed))           # learning refuses
+        self.assertIsNotNone(wm.ventilation_vector_for_prediction(features, 20.0, 2.0, bed))
+        # Closed, every opening term is 0 whatever the weather: nothing is missing.
+        closed = {**bed, 'opening': 0.0, 'facing': 0.0, 'wind': None, 'other_opening': None}
+        self.assertEqual(wm.ventilation_vector(features, 20.0, 2.0, closed), [0.0, 0.0, 0.0, 0.0])
+        self.assertTrue(wm.ventilation_known(features, closed))
+        self.assertTrue(wm.ventilation_known(features, None))                        # no windows