diff --git a/.beads/issues.jsonl b/.beads/issues.jsonl index e7e2d79..38c3a5e 100644 --- a/.beads/issues.jsonl +++ b/.beads/issues.jsonl @@ -9,13 +9,13 @@ {"id":"homemaker-py-ccw","title":"Scaled topology search on native fitness","description":"DESIGN.md §7 Phase 3 closing step. Once native fitness passes corpus parity, re-run the Phase-2 memetic search at real scale (population/generations comparable to urb-evolve) on the native objective. This is the first point where the §1 scaling question gets a real answer.","acceptance_criteria":"Full-scale run on programme-house beats both urb-evolve and the small-scale Phase-2 result; larger programme attempted","status":"open","priority":2,"issue_type":"feature","owner":"bruno@postle.net","created_at":"2026-06-11T23:38:59Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:38:59Z","dependencies":[{"issue_id":"homemaker-py-ccw","depends_on_id":"homemaker-py-uxz","type":"blocks","created_at":"2026-06-12T00:39:44Z","created_by":"Bruno Postle","metadata":"{}"},{"issue_id":"homemaker-py-ccw","depends_on_id":"homemaker-py-way","type":"blocks","created_at":"2026-06-12T00:39:45Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":2,"dependent_count":1,"comment_count":0} {"id":"homemaker-py-way","title":"Benchmark: memetic loop vs urb-evolve at equal oracle-call budget (Phase 2 gate)","description":"DESIGN.md §7 Phase 2 gate. Compare against urb-evolve from the same seeds/programmes at equal oracle-evaluation budget — NOT generations (urb-evolve has diversity injection/culling baked in, so generations are not comparable). Go/no-go: memetic loop must beat equal-budget urb-evolve. Scaling up waits for native fitness.","acceptance_criteria":"Best-fitness and failure-count comparison at \u003e=2 budgets, \u003e=3 seeds; go/no-go decision recorded in DESIGN.md","status":"open","priority":2,"issue_type":"task","owner":"bruno@postle.net","created_at":"2026-06-11T23:37:28Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:37:28Z","dependencies":[{"issue_id":"homemaker-py-way","depends_on_id":"homemaker-py-b39","type":"blocks","created_at":"2026-06-12T00:39:39Z","created_by":"Bruno Postle","metadata":"{}"},{"issue_id":"homemaker-py-way","depends_on_id":"homemaker-py-gp2","type":"blocks","created_at":"2026-06-12T08:27:45Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":2,"dependent_count":1,"comment_count":0} {"id":"homemaker-py-b39","title":"Memetic search driver, small-scale (budgets in oracle evaluations)","description":"DESIGN.md §5, §7 Phase 2, §4.6 arithmetic. Memetic EA/SA over topology genomes wrapping the geometry inner loop (warm-started per §5.6); score = best full fitness over the inner loop. Explicitly small-scale on the batched oracle: tens of topologies, budget accounted in oracle evaluations, not generations. Population evaluation batched into single oracle calls.","acceptance_criteria":"End-to-end run on programme-house completes within a stated oracle-call budget and logs evaluations; produces valid .dom output","status":"open","priority":2,"issue_type":"feature","owner":"bruno@postle.net","created_at":"2026-06-11T23:37:27Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:37:27Z","dependencies":[{"issue_id":"homemaker-py-b39","depends_on_id":"homemaker-py-1p0","type":"blocks","created_at":"2026-06-12T00:39:37Z","created_by":"Bruno Postle","metadata":"{}"},{"issue_id":"homemaker-py-b39","depends_on_id":"homemaker-py-nyb","type":"blocks","created_at":"2026-06-12T00:39:38Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":2,"dependent_count":1,"comment_count":0} -{"id":"homemaker-py-nyb","title":"High-locality topology operators (mutation + subtree crossover)","description":"DESIGN.md §5, §7 Phase 2, §8.4. Mutation moves: divide/undivide leaf, swap children, rotate cut, retype leaf, per-floor delta edits, storey add/delete (cf. Urb Mutate.pm — but geometry sliding belongs to the inner loop, not the operator set). Crossover: area-matched subtree exchange (a subtree = a contiguous region, so crossover is meaningful — Crossover.pm). Operators must be high-locality: small genome change =\u003e small phenotype change, so warm-started inner loops stay cheap.","acceptance_criteria":"Each operator produces valid genomes (oracle scores them without error); locality measured (mean fitness/geometry perturbation per operator)","status":"open","priority":2,"issue_type":"feature","owner":"bruno@postle.net","created_at":"2026-06-11T23:37:27Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:37:27Z","dependencies":[{"issue_id":"homemaker-py-nyb","depends_on_id":"homemaker-py-k2g","type":"blocks","created_at":"2026-06-12T00:39:36Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":1,"dependent_count":1,"comment_count":0} -{"id":"homemaker-py-k2g","title":"Topology genome: base-floor tree + per-floor deltas + type assignment","description":"DESIGN.md §5.2, §7 Phase 2. Genome = base-floor slicing topology (primary) + per-leaf type assignment + per-floor divide/undivide deltas (Below-inheritance as regulariser; cut owned by lowest storey where its path is divided — §10). Must round-trip to/from dom.py Node trees so the oracle and inner loop consume it directly. Includes storey count and per-floor type overrides.","acceptance_criteria":"Genome \u003c-\u003e .dom round-trip on all 35 corpus files preserves fitness; multi-storey wall stacking preserved","status":"in_progress","priority":2,"issue_type":"feature","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-06-11T23:37:26Z","created_by":"Bruno Postle","updated_at":"2026-06-12T10:55:21Z","started_at":"2026-06-12T10:55:21Z","dependency_count":0,"dependent_count":1,"comment_count":0} +{"id":"homemaker-py-nyb","title":"High-locality topology operators (mutation + subtree crossover)","description":"DESIGN.md §5, §7 Phase 2, §8.4. Mutation moves: divide/undivide leaf, swap children, rotate cut, retype leaf, per-floor delta edits, storey add/delete (cf. Urb Mutate.pm — but geometry sliding belongs to the inner loop, not the operator set). Crossover: area-matched subtree exchange (a subtree = a contiguous region, so crossover is meaningful — Crossover.pm). Operators must be high-locality: small genome change =\u003e small phenotype change, so warm-started inner loops stay cheap.","acceptance_criteria":"Each operator produces valid genomes (oracle scores them without error); locality measured (mean fitness/geometry perturbation per operator)","status":"in_progress","priority":2,"issue_type":"feature","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-06-11T23:37:27Z","created_by":"Bruno Postle","updated_at":"2026-06-12T12:54:23Z","started_at":"2026-06-12T12:54:23Z","dependencies":[{"issue_id":"homemaker-py-nyb","depends_on_id":"homemaker-py-k2g","type":"blocks","created_at":"2026-06-12T00:39:36Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":1,"dependent_count":1,"comment_count":0} +{"id":"homemaker-py-k2g","title":"Topology genome: base-floor tree + per-floor deltas + type assignment","description":"DESIGN.md §5.2, §7 Phase 2. Genome = base-floor slicing topology (primary) + per-leaf type assignment + per-floor divide/undivide deltas (Below-inheritance as regulariser; cut owned by lowest storey where its path is divided — §10). Must round-trip to/from dom.py Node trees so the oracle and inner loop consume it directly. Includes storey count and per-floor type overrides.","acceptance_criteria":"Genome \u003c-\u003e .dom round-trip on all 35 corpus files preserves fitness; multi-storey wall stacking preserved","status":"closed","priority":2,"issue_type":"feature","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-06-11T23:37:26Z","created_by":"Bruno Postle","updated_at":"2026-06-12T12:52:34Z","started_at":"2026-06-12T10:55:21Z","closed_at":"2026-06-12T12:52:34Z","close_reason":"genome.py encode/decode lands. 35/35 oracle fitness parity after round-trip (flag-on); genome fixed-point + owned-projection tests. Dead-field discovery: corpus upper storeys carry drifted dead divisions (97) and rotations (187) — canonicalised by decode, validated fitness-neutral.","dependency_count":0,"dependent_count":1,"comment_count":0} {"id":"homemaker-py-d0s","title":"Experiment: inner-loop optimiser bake-off at equal oracle budgets","description":"DESIGN.md §7 Phase 1, §8.3. DOF is only ~rooms-1 (6–7 on corpus). Compare Nelder-Mead vs CMA-ES vs batched multi-start pattern search at equal oracle-call budgets, measuring fitness gained per oracle call and wall-clock (batch-friendliness matters — §4.6). Measure, don't commit blind.","acceptance_criteria":"Table of fitness-per-budget across \u003e=3 candidates; one optimiser chosen and recorded in DESIGN.md","status":"open","priority":2,"issue_type":"task","owner":"bruno@postle.net","created_at":"2026-06-11T23:36:59Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:36:59Z","dependencies":[{"issue_id":"homemaker-py-d0s","depends_on_id":"homemaker-py-1p0","type":"blocks","created_at":"2026-06-12T00:39:35Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":1,"dependent_count":0,"comment_count":0} {"id":"homemaker-py-can","title":"Programme width defaults: t3 contradiction (impossible width_inside default)","description":"DESIGN.md §8.2, confirmed in source. t3 (3 m2 WC) has no width spec so inherits width_inside [4.0, 1.0] (Fitness/Base.pm:60) — geometrically impossible; designs 'pass' only by failing size instead. Fix AFTER faithful-port validation (port-faithfully-first policy, §8.1): a sane width default scaled to area (e.g. sqrt(area/proportion)) or per-room widths in patterns.config. Applies to native fitness; optionally upstream to Urb.","acceptance_criteria":"No programme space has a default width incompatible with its target area; corpus re-scored and effect documented","status":"open","priority":3,"issue_type":"bug","owner":"bruno@postle.net","created_at":"2026-06-11T23:39:01Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:39:01Z","dependencies":[{"issue_id":"homemaker-py-can","depends_on_id":"homemaker-py-uxz","type":"blocks","created_at":"2026-06-12T00:39:47Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":1,"dependent_count":0,"comment_count":0} {"id":"homemaker-py-yg5","title":"Penalty reshaping: replace 0.5^n while preserving inner-loop protection","description":"DESIGN.md §4.7, §5.4, §7 Phase 4, §8.5. The 0.5^n cliff gives the outer search no gradient and rewards flag-count over geometry, but it also PROTECTS the inner loop from trading into new failures (§4.5). One fitness shape cannot naively be both soft outside and cliff-protected inside. Candidates: cliff-inside-inner-loop only, lexicographic (failure count first, score second), additive/soft, multi-objective Pareto. Must preserve the missing-space failure hierarchy (worse to drop a room than to have a poor one). Measure landscape + search outcomes; this helps Urb today too.","acceptance_criteria":"Chosen scheme documented with measurements: search improves while inner loop still never trades into new failures","status":"open","priority":3,"issue_type":"feature","owner":"bruno@postle.net","created_at":"2026-06-11T23:39:00Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:39:00Z","dependencies":[{"issue_id":"homemaker-py-yg5","depends_on_id":"homemaker-py-uxz","type":"blocks","created_at":"2026-06-12T00:39:46Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":1,"dependent_count":0,"comment_count":0} {"id":"homemaker-py-9gp","title":"Canonical slicing encoding (normalized Polish expression) + shape feasibility","description":"DESIGN.md §5.5, §7 Phase 5. Representation upgrade once core lands: normalized Polish expression / skewed slicing tree (Wong–Liu) for redundancy-free, high-locality topology moves (M1/M2/M3); bottom-up shape-feasibility checks to prune infeasible topologies before the inner loop. Goal: scale to larger programmes. Excluded representations stay excluded (§2): no sequence-pair/B*-tree (non-slicing).","acceptance_criteria":"Encoding round-trips with the genome; M1/M2/M3 moves implemented; measured search improvement on a larger-than-house programme","status":"open","priority":4,"issue_type":"feature","owner":"bruno@postle.net","created_at":"2026-06-11T23:39:02Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:39:02Z","dependencies":[{"issue_id":"homemaker-py-9gp","depends_on_id":"homemaker-py-ccw","type":"blocks","created_at":"2026-06-12T00:39:48Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":1,"dependent_count":0,"comment_count":0} {"id":"homemaker-py-2g5","title":"Rebuild occlusion/daylight/sun subsystem in Python (post-Phase-5, after optimisation fully native)","description":"DESIGN.md §6 port scope — a whole subsystem, not a term. quality_daylight (Leaf.pm:281-296) needs Urb::Misc::Sun + Urb::Field::Occlusion (+CIESky); quality_uncrinkliness also takes the occlusion object. Indoor spaces return 1 for daylight; cost is outdoor spaces + crinkliness. Port Sun_horizontal (262980-minute normalisation) and the occlusion wall set from Dom-\u003eWalls.","acceptance_criteria":"Daylight and crinkliness factors match Perl (float tolerance) across the corpus, including multi-storey cases","notes":"Re-scoped 2026-06-12: occlusion disabled in the Urb oracle instead of ported (see homemaker-py-gp2). Native fitness ships with simple crinkliness (illumination factor = 1, in homemaker-py-gnw). This issue is now the eventual Python occlusion rebuild, only after optimisation works entirely in Python. Restores outdoor-daylight and shaded-wall selection pressure.","status":"open","priority":4,"issue_type":"feature","owner":"bruno@postle.net","created_at":"2026-06-11T23:38:25Z","created_by":"Bruno Postle","updated_at":"2026-06-12T07:27:48Z","dependency_count":0,"dependent_count":0,"comment_count":0} -{"_type":"memory","key":"urb-oracle-nondeterminism-urb-fitness-pl-output-varies","value":"Urb oracle nondeterminism: urb-fitness.pl output varies run-to-run from Perl hash-order randomisation — .fails line ORDER shuffles (compare sorted, use oracle.Score.fail_lines) and the score float can flip by ~1 ULP (compare with math.isclose rel_tol=1e-12, never ==). Not a batching artifact; affects single runs too. Matters for the Phase 3 native-fitness parity gate (homemaker-py-uxz)."} {"_type":"memory","key":"strategy-decision-2026-06-12-bruno-occlusion-daylight","value":"Strategy decision 2026-06-12 (Bruno): occlusion/daylight is ORTHOGONAL to building a scalable optimiser. Disable it in Urb (env flag, homemaker-py-gp2) rather than port it; native fitness uses simple crinkliness (illumination factor = 1); rebuild occlusion in Python only after optimisation is fully native (homemaker-py-2g5, now P4). Consequence: all scores change when the flag flips — re-baseline corpus/.score, DESIGN \\$4.5 gains, gate bars at one clean boundary AFTER homemaker-py-1p0 closes; Phase-2 urb-evolve benchmark must run with the same flag."} {"_type":"memory","key":"user-preference-bruno-this-is-a-fedora-system","value":"User preference (Bruno): this is a Fedora system — NEVER install Python packages via pip without asking first; always ask whether to install the rpm via dnf (e.g. python3-cma) before considering pip. Applies to any dependency additions."} +{"_type":"memory","key":"urb-oracle-nondeterminism-urb-fitness-pl-output-varies","value":"Urb oracle nondeterminism: urb-fitness.pl output varies run-to-run from Perl hash-order randomisation — .fails line ORDER shuffles (compare sorted, use oracle.Score.fail_lines) and the score float can flip by ~1 ULP (compare with math.isclose rel_tol=1e-12, never ==). Not a batching artifact; affects single runs too. Matters for the Phase 3 native-fitness parity gate (homemaker-py-uxz)."} diff --git a/experiments/operator_locality.py b/experiments/operator_locality.py new file mode 100644 index 0000000..d1c61f8 --- /dev/null +++ b/experiments/operator_locality.py @@ -0,0 +1,103 @@ +#!/usr/bin/env python3 +"""Operator validity + locality measurement (homemaker-py-nyb acceptance). + +For each operator: apply 5 seeded instances per corpus design, score every +child through the oracle (validity = scores without error), and report +locality as (a) mean relative fitness perturbation and (b) mean geometry +perturbation — the fraction of leaf rooms whose (type, footprint) changed. +High-locality operators keep both small, so warm-started inner loops stay +cheap (DESIGN.md §5). + +Run under the go-forward fitness: + URB_NO_OCCLUSION=1 python3 experiments/operator_locality.py +""" + +from __future__ import annotations + +import shutil +import sys +import tempfile +from collections import Counter +from pathlib import Path + +import numpy as np + +sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src")) +from homemaker import dom, genome, geometry, operators, oracle, programme # noqa: E402 + +URB = Path("/home/bruno/src/urb") +CORPUS = URB / "examples" / "programme-house" +FILES = ["2f45907abd9accac2a124d311732f749.dom", "candidate-002.dom", + "c964435454c459f86c3ed9a5a7621132.dom"] +SEEDS = range(5) + + +def leaf_signature(root: dom.Node) -> Counter: + sig = Counter() + for li, lvl in enumerate(dom.levels(root)): + for leaf in lvl.leaves(): + corners = tuple(tuple(round(c, 6) for c in geometry.coordinate(leaf, i)) + for i in range(4)) + sig[(li, leaf.type, corners)] += 1 + return sig + + +def geometry_perturbation(parent_sig: Counter, child: dom.Node) -> float: + child_sig = leaf_signature(child) + common = sum((parent_sig & child_sig).values()) + return 1.0 - common / max(parent_sig.total(), child_sig.total()) + + +def main() -> int: + types = sorted(programme.load_programme(str(CORPUS / "patterns.config"))) + ["c", "o"] + roots = {f: genome.decode(genome.encode(dom.load(str(CORPUS / f)))) for f in FILES} + + with tempfile.TemporaryDirectory(prefix="op_locality_") as tmp: + scratch = Path(tmp) + shutil.copy(CORPUS / "patterns.config", scratch) + + parents = {} + paths = [] + for f, root in roots.items(): + p = scratch / f + dom.dump(root, str(p)) + paths.append(p) + for f, s in zip(roots, oracle.score_batch(paths, URB)): + parents[f] = s + + jobs: list[tuple[str, str, dom.Node]] = [] # (op, desc, child) + for f, root in roots.items(): + for name, op in operators.MUTATIONS.items(): + for seed in SEEDS: + child, desc = op(root, np.random.default_rng(seed), types) + jobs.append((name, f, child)) + for seed in SEEDS: + ca, cb, _ = operators.crossover(roots[FILES[0]], roots[FILES[1]], + np.random.default_rng(seed)) + jobs.append(("crossover", FILES[0], ca)) + jobs.append(("crossover", FILES[1], cb)) + + paths = [] + for i, (_, _, child) in enumerate(jobs): + p = scratch / f"child_{i:03d}.dom" + dom.dump(child, str(p)) + paths.append(p) + scores = oracle.score_batch(paths, URB) # raises if any child is invalid + + sigs = {f: leaf_signature(root) for f, root in roots.items()} + stats: dict[str, list[tuple[float, float]]] = {} + for (name, f, child), s in zip(jobs, scores): + df = abs(s.fitness - parents[f].fitness) / parents[f].fitness + dg = geometry_perturbation(sigs[f], child) + stats.setdefault(name, []).append((df, dg)) + + print(f"{'operator':14s} {'n':>3s} {'mean |dF|/F':>12s} {'mean geom-pert':>15s}") + for name in sorted(stats): + dfs, dgs = zip(*stats[name]) + print(f"{name:14s} {len(dfs):3d} {np.mean(dfs):12.3f} {np.mean(dgs):15.3f}") + print(f"\nall {len(jobs)} children scored by the oracle without error") + return 0 + + +if __name__ == "__main__": + sys.exit(main()) diff --git a/src/homemaker/dom.py b/src/homemaker/dom.py index 5e477d7..6533427 100644 --- a/src/homemaker/dom.py +++ b/src/homemaker/dom.py @@ -126,9 +126,9 @@ def _link(root: Node) -> None: below_root = lvls[i - 1] def _set(n: Node, below_root: Node = below_root) -> None: - b = below_root.by_id(n.id) - if b is not None: - n.below = b + # always assign: re-linking a structurally mutated tree must CLEAR + # below-links whose path no longer exists on the storey below + n.below = below_root.by_id(n.id) if n.divided: _set(n.left) _set(n.right) diff --git a/src/homemaker/operators.py b/src/homemaker/operators.py new file mode 100644 index 0000000..6253791 --- /dev/null +++ b/src/homemaker/operators.py @@ -0,0 +1,194 @@ +"""High-locality topology operators: mutation + subtree crossover. + +Operators edit a *decoded* Node tree (the canonical phenotype) and re-link it; +``genome.encode`` then re-derives the genome, which makes every operator +total: dangling per-storey deltas after an undivide below, or storey +misalignment after crossover, are absorbed by encode's parallel walk (cuts +that stop existing below simply become owned above). Geometry moves (Urb's +``slide``, floor heights) are deliberately absent — the inner loop owns all +continuous DOF (DESIGN.md §5), and the warm-vs-cold result (homemaker-py-8cs) +makes Lamarckian re-optimisation after every topology move mandatory anyway. + +Each ``mutate_*`` helper applies one random instance to a deep copy and +returns ``(child_root, descriptor)``; ``crossover`` returns two children. +Candidate selection respects ownership: cuts are swappable/rotatable only +where they are live (below is None / below undivided — the free-branch +criterion), so operators never edit dead fields. +""" + +from __future__ import annotations + +import copy + +import numpy as np + +from . import dom + + +def _finalise(root: dom.Node) -> dom.Node: + from . import geometry + + dom._link(root) + geometry.clear_cache() + return root + + +def _level_nodes(lvl: dom.Node) -> list[dom.Node]: + out = [lvl] + if lvl.divided: + out += _level_nodes(lvl.left) + _level_nodes(lvl.right) + return out + + +def _pick(rng: np.random.Generator, items: list): + return items[int(rng.integers(len(items)))] + + +def _owned_branches(root: dom.Node) -> list[tuple[int, dom.Node]]: + """(level_index, node) for every divided node whose cut is live here.""" + out = [] + for li, lvl in enumerate(dom.levels(root)): + for n in _level_nodes(lvl): + if n.divided and (n.below is None or not n.below.divided): + out.append((li, n)) + return out + + +def _leaves(root: dom.Node) -> list[tuple[int, dom.Node]]: + return [(li, leaf) for li, lvl in enumerate(dom.levels(root)) for leaf in lvl.leaves()] + + +# --------------------------------------------------------------------------- # +# Mutations +# --------------------------------------------------------------------------- # +def mutate_divide(root: dom.Node, rng: np.random.Generator, + types: list[str]) -> tuple[dom.Node, str]: + child = copy.deepcopy(root) + li, leaf = _pick(rng, _leaves(child)) + leaf.division = [0.5, 0.5] + leaf.rotation = int(rng.integers(4)) + leaf.left = dom.Node(type=leaf.type) + leaf.right = dom.Node(type=str(_pick(rng, types))) + leaf.type = None + return _finalise(child), f"divide {li}/{leaf.id or 'root'}" + + +def mutate_undivide(root: dom.Node, rng: np.random.Generator, + types: list[str]) -> tuple[dom.Node, str]: + child = copy.deepcopy(root) + cands = [(li, n) for li, n in _owned_branches(child) + if not n.left.divided and not n.right.divided] + if not cands: + return _finalise(child), "undivide noop" + li, n = _pick(rng, cands) + keep = [t for t in (n.left.type, n.right.type) if t and not t.startswith(("c", "o", "s"))] + n.type = keep[0] if keep else (n.left.type or str(_pick(rng, types))) + n.division = None + n.left = n.right = None + return _finalise(child), f"undivide {li}/{n.id or 'root'}" + + +def mutate_retype(root: dom.Node, rng: np.random.Generator, + types: list[str]) -> tuple[dom.Node, str]: + child = copy.deepcopy(root) + li, leaf = _pick(rng, _leaves(child)) + leaf.type = str(_pick(rng, [t for t in types if t != leaf.type] or types)) + return _finalise(child), f"retype {li}/{leaf.id or 'root'}->{leaf.type}" + + +def mutate_swap(root: dom.Node, rng: np.random.Generator, + types: list[str]) -> tuple[dom.Node, str]: + child = copy.deepcopy(root) + li, n = _pick(rng, _owned_branches(child)) + n.left, n.right = n.right, n.left + return _finalise(child), f"swap {li}/{n.id or 'root'}" + + +def mutate_rotate(root: dom.Node, rng: np.random.Generator, + types: list[str]) -> tuple[dom.Node, str]: + # re-orient a live cut; live rotation = node without a below link (base + # storey or inside an upper-storey divide delta) + child = copy.deepcopy(root) + cands = [(li, n) for li, n in _owned_branches(child) if n.below is None] + if not cands: + return _finalise(child), "rotate noop" + li, n = _pick(rng, cands) + n.rotation = (n.rotation + int(rng.integers(1, 4))) % 4 + return _finalise(child), f"rotate {li}/{n.id or 'root'}" + + +def mutate_level_add(root: dom.Node, rng: np.random.Generator, + types: list[str]) -> tuple[dom.Node, str]: + from . import genome as _g + + child = copy.deepcopy(root) + top = dom.levels(child)[-1] + dup = _g._copy_storey(top) + dup.height = top.height + top.above = dup + return _finalise(child), f"level_add ({len(dom.levels(child))} storeys)" + + +def mutate_level_delete(root: dom.Node, rng: np.random.Generator, + types: list[str]) -> tuple[dom.Node, str]: + child = copy.deepcopy(root) + lvls = dom.levels(child) + if len(lvls) < 2: + return _finalise(child), "level_delete noop" + lvls[-2].above = None + return _finalise(child), f"level_delete ({len(lvls) - 1} storeys)" + + +MUTATIONS = { + "divide": mutate_divide, + "undivide": mutate_undivide, + "retype": mutate_retype, + "swap": mutate_swap, + "rotate": mutate_rotate, + "level_add": mutate_level_add, + "level_delete": mutate_level_delete, +} + + +def mutate(root: dom.Node, rng: np.random.Generator, types: list[str], + weights: dict[str, float] | None = None) -> tuple[dom.Node, str]: + """Apply one random mutation drawn from MUTATIONS.""" + names = sorted(MUTATIONS) + p = np.array([(weights or {}).get(n, 1.0) for n in names], dtype=float) + name = rng.choice(names, p=p / p.sum()) + return MUTATIONS[name](root, rng, types) + + +# --------------------------------------------------------------------------- # +# Crossover +# --------------------------------------------------------------------------- # +def _graft(dst: dom.Node, src: dom.Node) -> None: + """Replace dst's subtree content with a copy of src's (cf. Urb Crossover).""" + sub = copy.deepcopy(src) + dst.type = sub.type + dst.rotation = sub.rotation + dst.division = sub.division + dst.left, dst.right = sub.left, sub.right + + +def crossover(a: dom.Node, b: dom.Node, + rng: np.random.Generator) -> tuple[dom.Node, dom.Node, str]: + """Area-matched base-storey subtree exchange (Urb Crossover.pm style): + pick a random subtree of A's base storey, find the area-closest third of + B's base subtrees, exchange. A subtree is a contiguous region, so this + recombines whole neighbourhoods; storeys above re-anchor via encode.""" + from . import geometry + + ca, cb = copy.deepcopy(a), copy.deepcopy(b) + _finalise(ca) + _finalise(cb) + base_a, base_b = dom.levels(ca)[0], dom.levels(cb)[0] + na = _pick(rng, _level_nodes(base_a)) + by_area = sorted(_level_nodes(base_b), + key=lambda n: abs(geometry.area(n) - geometry.area(na))) + nb = by_area[int(rng.integers(max(1, len(by_area) // 3)))] + tmp = copy.deepcopy(na) + _graft(na, nb) + _graft(nb, tmp) + desc = f"crossover {na.id or 'root'}<->{nb.id or 'root'}" + return _finalise(ca), _finalise(cb), desc diff --git a/tests/test_operators.py b/tests/test_operators.py new file mode 100644 index 0000000..07074bd --- /dev/null +++ b/tests/test_operators.py @@ -0,0 +1,93 @@ +"""Operator tests (oracle-free): every child is a valid, canonical genome.""" + +from pathlib import Path + +import numpy as np +import pytest + +from homemaker import dom, genome, operators + +CORPUS = Path("/home/bruno/src/urb/examples/programme-house") +FILES = ["2f45907abd9accac2a124d311732f749.dom", "candidate-002.dom", + "c964435454c459f86c3ed9a5a7621132.dom"] +TYPES = ["k1", "l1", "b1", "b2", "t1", "c", "o"] + +pytestmark = pytest.mark.skipif(not CORPUS.is_dir(), reason="Urb corpus not available") + + +def canonical(root: dom.Node) -> None: + """Child must encode to a genome that decode/encode holds fixed.""" + g1 = genome.encode(root) + g2 = genome.encode(genome.decode(g1)) + assert g2 == g1 + + +@pytest.mark.parametrize("name", sorted(operators.MUTATIONS)) +def test_mutations_yield_canonical_genomes(name): + op = operators.MUTATIONS[name] + for f in FILES: + root = genome.decode(genome.encode(dom.load(str(CORPUS / f)))) + for seed in range(5): + child, desc = op(root, np.random.default_rng(seed), TYPES) + assert desc.startswith(name.split("_")[0]) or "noop" in desc + canonical(child) + # the parent must never be mutated in place + canonical(root) + + +def test_divide_grows_and_undivide_shrinks(): + root = genome.decode(genome.encode(dom.load(str(CORPUS / FILES[0])))) + n_leaves = sum(len(lvl.leaves()) for lvl in dom.levels(root)) + child, _ = operators.mutate_divide(root, np.random.default_rng(0), TYPES) + assert sum(len(lvl.leaves()) for lvl in dom.levels(child)) == n_leaves + 1 + child, desc = operators.mutate_undivide(root, np.random.default_rng(0), TYPES) + if "noop" not in desc: + assert sum(len(lvl.leaves()) for lvl in dom.levels(child)) < n_leaves + + +def test_level_add_delete(): + root = genome.decode(genome.encode(dom.load(str(CORPUS / FILES[0])))) + n = len(dom.levels(root)) + up, _ = operators.mutate_level_add(root, np.random.default_rng(0), TYPES) + assert len(dom.levels(up)) == n + 1 + canonical(up) + down, _ = operators.mutate_level_delete(root, np.random.default_rng(0), TYPES) + assert len(dom.levels(down)) == n - 1 + + +def test_relink_clears_stale_below_after_base_undivide(): + # regression: dom._link must clear below-links whose path vanished, or + # geometry on the mutated tree dereferences orphaned nodes + from homemaker import geometry + + root = genome.decode(genome.encode(dom.load(str(CORPUS / FILES[0])))) + # force an undivide on the BASE storey specifically + base = dom.levels(root)[0] + cands = [n for li, n in operators._owned_branches(root) + if li == 0 and not n.left.divided and not n.right.divided] + assert cands, "corpus design has no base leaf-pair branch" + import copy as _copy + + child = _copy.deepcopy(root) + target = dom.levels(child)[0].by_id(cands[0].id) + target.division = None + target.left = target.right = None + target.type = "l1" + dom._link(child) + geometry.clear_cache() + for lvl in dom.levels(child): + for leaf in lvl.leaves(): + for i in range(4): + geometry.coordinate(leaf, i) # must not raise + canonical(child) + assert base.by_id(cands[0].id) is not None # parent untouched + + +def test_crossover_yields_canonical_pair(): + a = genome.decode(genome.encode(dom.load(str(CORPUS / FILES[0])))) + b = genome.decode(genome.encode(dom.load(str(CORPUS / FILES[1])))) + for seed in range(5): + ca, cb, desc = operators.crossover(a, b, np.random.default_rng(seed)) + assert desc.startswith("crossover") + canonical(ca) + canonical(cb)