da7cde3ef9
CI / Lint (ruff check) (push) Successful in 27s
CI / Format (ruff format) (push) Successful in 28s
CI / Sync project version with tag (push) Has been skipped
CI / Lint (ruff check) (pull_request) Successful in 36s
CI / Type check (ty) (push) Successful in 39s
CI / Format (ruff format) (pull_request) Successful in 30s
CI / Sync project version with tag (pull_request) Has been skipped
CI / Type check (ty) (pull_request) Successful in 30s
CI / Tests (pull_request) Successful in 2m50s
CI / Tests (push) Successful in 2m58s
Works through docs/v0.3.0-followups.md item by item, closing the gap between the design doc and the shipped v0.3.0-stage2-autoregressive code: 1. validate.py: 7-tuple batch unpacking, sample_stage1/sample_stage2 dispatch, stage-2 particle-type-class marginal. 2. Stage-prefixed --stage1-*/--stage2-* CLI flags for train/new-run. 3. Thread stage2_model.k_max through loader/transforms/dataset/pipeline/ train instead of the hardcoded K_MAX constant. 4. Mixed conditioning.particle.type / conditioning.material.type support end-to-end (data pipeline + dwarf warm-cache). 5. conditioning.share_stages = true: one shared ConditionEncoder instance across both stages. 6. stage2_model.generator = "ddpm" formally deferred into design doc §11.2 (was silently unimplemented). 7. giant predict/rollout: implement conditioning.*.type = "onehot" via the checkpoint's saved pdg_topn_map/mat_topn_map. 8. network.py's checkpoint-path model_config migration now fails loudly on non-zero legacy expert_hidden_dim/expert_n_blocks, matching config.py's TOML-load path (§4.2). 9. validate_config now rejects stage2_model.n_sec.mode = "truth" for a rollout-capable checkpoint (§9). Also cleared all pre-existing `ty check` noise (44 -> 0 diagnostics), mostly a test-helper dict-unpack pattern that made every unrelated constructor keyword look like a type error. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
159 lines
4.7 KiB
Python
159 lines
4.7 KiB
Python
import uuid
|
|
|
|
import yaml
|
|
|
|
from giant.cli import (
|
|
_CEPH_PREDICTIONS,
|
|
_resolve_prediction_output,
|
|
_write_prediction_ref,
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _resolve_prediction_output
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_non_ceph_path_goes_to_data_parent(tmp_path):
|
|
data = tmp_path / "pools" / "pbwo4" / "full.manifest"
|
|
out, dataset_path, pred_uuid = _resolve_prediction_output(data, None)
|
|
|
|
assert out.parent == data.parent
|
|
assert out.name == f"{pred_uuid}.parquet"
|
|
assert dataset_path == data.resolve()
|
|
|
|
|
|
def test_ceph_path_goes_to_central_store(tmp_path, monkeypatch):
|
|
# Patch resolve() so /ceph/... exists on any machine running the tests.
|
|
ceph_data = _CEPH_PREDICTIONS.parent / "pools" / "pbwo4" / "full.manifest"
|
|
monkeypatch.setattr(
|
|
"giant.cli.Path.resolve",
|
|
lambda self: ceph_data if self == ceph_data else self.absolute(),
|
|
)
|
|
out, _, pred_uuid = _resolve_prediction_output(ceph_data, None)
|
|
|
|
assert out.parent == _CEPH_PREDICTIONS
|
|
assert out.name == f"{pred_uuid}.parquet"
|
|
|
|
|
|
def test_explicit_out_is_used_as_is(tmp_path):
|
|
data = tmp_path / "data.parquet"
|
|
explicit = tmp_path / "my_output.parquet"
|
|
out, _, _ = _resolve_prediction_output(data, explicit)
|
|
|
|
assert out == explicit
|
|
|
|
|
|
def test_uuid_is_valid(tmp_path):
|
|
data = tmp_path / "data.parquet"
|
|
_, _, pred_uuid = _resolve_prediction_output(data, None)
|
|
parsed = uuid.UUID(pred_uuid)
|
|
assert parsed.version == 4
|
|
|
|
|
|
def test_each_call_produces_a_distinct_uuid(tmp_path):
|
|
data = tmp_path / "data.parquet"
|
|
_, _, uuid1 = _resolve_prediction_output(data, None)
|
|
_, _, uuid2 = _resolve_prediction_output(data, None)
|
|
assert uuid1 != uuid2
|
|
|
|
|
|
def test_dataset_path_is_resolved(tmp_path):
|
|
data = tmp_path / "data.parquet"
|
|
_, dataset_path, _ = _resolve_prediction_output(data, None)
|
|
assert dataset_path.is_absolute()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# _write_prediction_ref
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_ref_file_created_in_checkpoint_dir(tmp_path):
|
|
ckpt_dir = tmp_path / "checkpoints" / "run1"
|
|
ckpt_dir.mkdir(parents=True)
|
|
checkpoint = ckpt_dir / "best.pt"
|
|
checkpoint.touch()
|
|
|
|
out = tmp_path / "predictions" / "abc.parquet"
|
|
dataset = tmp_path / "pools" / "pbwo4" / "full.manifest"
|
|
pred_uuid = str(uuid.uuid4())
|
|
|
|
ref_path = _write_prediction_ref(checkpoint, pred_uuid, out, dataset)
|
|
|
|
assert ref_path == ckpt_dir / f"{pred_uuid}.yaml"
|
|
assert ref_path.exists()
|
|
|
|
|
|
def test_ref_yaml_contains_expected_fields(tmp_path):
|
|
ckpt_dir = tmp_path / "checkpoints"
|
|
ckpt_dir.mkdir()
|
|
checkpoint = ckpt_dir / "best.pt"
|
|
checkpoint.touch()
|
|
|
|
out = tmp_path / "pred.parquet"
|
|
dataset = tmp_path / "full.manifest"
|
|
pred_uuid = str(uuid.uuid4())
|
|
|
|
ref_path = _write_prediction_ref(checkpoint, pred_uuid, out, dataset)
|
|
data = yaml.safe_load(ref_path.read_text())
|
|
|
|
assert data["prediction_id"] == pred_uuid
|
|
assert data["output"] == str(out)
|
|
assert data["dataset"] == str(dataset)
|
|
assert data["checkpoint"] == str(checkpoint.resolve())
|
|
assert "timestamp" in data
|
|
assert "comment" not in data
|
|
|
|
|
|
def test_ref_yaml_includes_comment_when_provided(tmp_path):
|
|
ckpt_dir = tmp_path / "checkpoints"
|
|
ckpt_dir.mkdir()
|
|
checkpoint = ckpt_dir / "best.pt"
|
|
checkpoint.touch()
|
|
|
|
out = tmp_path / "pred.parquet"
|
|
dataset = tmp_path / "full.manifest"
|
|
pred_uuid = str(uuid.uuid4())
|
|
|
|
ref_path = _write_prediction_ref(
|
|
checkpoint, pred_uuid, out, dataset, comment="baseline sweep run 3"
|
|
)
|
|
data = yaml.safe_load(ref_path.read_text())
|
|
|
|
assert data["comment"] == "baseline sweep run 3"
|
|
|
|
|
|
def test_ref_timestamp_is_iso_format(tmp_path):
|
|
from datetime import datetime
|
|
|
|
ckpt_dir = tmp_path / "checkpoints"
|
|
ckpt_dir.mkdir()
|
|
checkpoint = ckpt_dir / "best.pt"
|
|
checkpoint.touch()
|
|
|
|
pred_uuid = str(uuid.uuid4())
|
|
ref_path = _write_prediction_ref(
|
|
checkpoint, pred_uuid, tmp_path / "p.parquet", tmp_path / "d"
|
|
)
|
|
data = yaml.safe_load(ref_path.read_text())
|
|
|
|
# Must parse without error and be timezone-aware (UTC).
|
|
ts = datetime.fromisoformat(data["timestamp"])
|
|
assert ts.tzinfo is not None
|
|
|
|
|
|
def test_ref_checkpoint_path_is_absolute(tmp_path):
|
|
ckpt_dir = tmp_path / "checkpoints"
|
|
ckpt_dir.mkdir()
|
|
checkpoint = ckpt_dir / "best.pt"
|
|
checkpoint.touch()
|
|
|
|
pred_uuid = str(uuid.uuid4())
|
|
ref_path = _write_prediction_ref(
|
|
checkpoint, pred_uuid, tmp_path / "p.parquet", tmp_path / "d"
|
|
)
|
|
data = yaml.safe_load(ref_path.read_text())
|
|
|
|
assert data["checkpoint"].startswith("/")
|