"""Verify what is on Hugging Face from a clean machine (no access to the Vast box). uv run --with xgboost --with pandas --with pyarrow --with huggingface_hub python scripts/60_verify_hf.py 1. Downloads TrendeX90/expected-greenness at tag v1, runs the golden test with its own predict.py. 2. Reads naryn-cube: manifest, cells.parquet, one year of monthly data, products summary. """ from __future__ import annotations import importlib.util import json import sys import tempfile from pathlib import Path import numpy as np import pandas as pd from huggingface_hub import HfApi, hf_hub_download, snapshot_download MODEL, CUBE = "TrendeX90/expected-greenness", "TrendeX90/naryn-cube" def main() -> None: api = HfApi() tags = [t.name for t in api.list_repo_refs(MODEL).tags] print("model tags:", tags) with tempfile.TemporaryDirectory() as tmp: root = Path(snapshot_download(MODEL, revision="v1", local_dir=Path(tmp) / "model")) print("model files:", sorted(p.name for p in root.iterdir() if not p.name.startswith("."))) spec = importlib.util.spec_from_file_location("predict", root / "predict.py") mod = importlib.util.module_from_spec(spec) sys.modules["predict"] = mod spec.loader.exec_module(mod) m = mod.load(root) got = m.predict(pd.read_parquet(root / "golden" / "inputs.parquet")) want = pd.read_parquet(root / "golden" / "expected.parquet") diff = float(np.max(np.abs(got.values - want.values))) print(f"golden test on this machine: max diff {diff:.2e} -> {'PASS' if diff < 1e-6 else 'FAIL'}") metrics = json.loads((root / "metrics.json").read_text()) print("gate:", metrics["gate"]) files = api.list_repo_files(CUBE, repo_type="dataset") print(f"cube files: {len(files)} | monthly years: {sum(f.startswith('monthly/') for f in files)} | " f"products: {sorted(f for f in files if f.startswith('products/'))}") man = json.loads(Path(hf_hub_download(CUBE, "manifest.json", repo_type="dataset")).read_text()) print("manifest: synthetic =", man["synthetic"], "| partial =", man["partial"], "| sources =", man["sources_used"]) cells = pd.read_parquet(hf_hub_download(CUBE, "cells.parquet", repo_type="dataset")) print("cells:", len(cells), "| in oblast:", int(cells["in_oblast"].sum())) y = pd.read_parquet(hf_hub_download(CUBE, "monthly/year=2024/part.parquet", repo_type="dataset")) print("monthly 2024 rows:", len(y), "| columns:", list(y.columns)) summ = json.loads(Path(hf_hub_download(CUBE, "products/products_summary.json", repo_type="dataset")).read_text()) print("residual trend shares:", summ["residual_trend_cell_class_shares"]) print("VERIFY_DONE") if __name__ == "__main__": main()