From e87c63ca468add9ad533f194c9c4f82a963260d5 Mon Sep 17 00:00:00 2001 From: flyloft Date: Fri, 6 Nov 2026 16:52:26 -0800 Subject: [PATCH 1/2] hello2-6a463bf0: hello under a new name, for flyloft's tier two --- datasets/hello2-6a463bf0/SKILL.md | 36 +++++++++++++++++++++ datasets/hello2-6a463bf0/recipe/build | 23 +++++++++++++ datasets/hello2-6a463bf0/recipe/params.toml | 3 ++ datasets/hello2-6a463bf0/recipe/test | 26 +++++++++++++++ 4 files changed, 88 insertions(+) create mode 100644 datasets/hello2-6a463bf0/SKILL.md create mode 100755 datasets/hello2-6a463bf0/recipe/build create mode 100644 datasets/hello2-6a463bf0/recipe/params.toml create mode 100755 datasets/hello2-6a463bf0/recipe/test diff --git a/datasets/hello2-6a463bf0/SKILL.md b/datasets/hello2-6a463bf0/SKILL.md new file mode 100644 index 0000000..6237854 --- /dev/null +++ b/datasets/hello2-6a463bf0/SKILL.md @@ -0,0 +1,36 @@ +--- +name: hello2-6a463bf0 +description: "300 synthetic antibody pairs of random amino acids in three splits: the repository's smoke dataset. Reach for it to check that reading a dataset works from where you are, never to train." +metadata: + version: 1.0.0 + tools: datascience@1.0.0 + license: mit +--- +# hello2-6a463bf0 + +Hub: `brineylab/hello2-6a463bf0`, tag `v1.0.0` + +## Files + +`train.parquet`, `eval.parquet`, `test.parquet`: 240, 30, and 30 rows, one per pair, columns `pair_id` (`hello-0000` to `hello-0299`), `sequence_heavy` (110 to 130 amino acids), `sequence_light` (105 to 115). The letters are uniform draws from the twenty amino acids: no sequence is an antibody. + +## Reading it + +```python +from huggingface_hub import snapshot_download +import polars as pl +path = snapshot_download("brineylab/hello2-6a463bf0", repo_type="dataset", revision="v1.0.0") +train = pl.read_parquet(f"{path}/train.parquet") +``` + +## Recipe + +No source: `recipe/build` draws `pairs = 300` pairs from `random.Random(seed = 1)`, shuffles them, and splits them `[0.8, 0.1, 0.1]` in that order. It runs in `datascience@1.0.0`. The test checks the three files, their columns, their row counts, and that no `pair_id` is in two splits. + +## Compute + +Seconds on a laptop, one CPU, kilobytes of disk. + +## Gotchas + +- It exists to exercise filing, checking, promoting, and reading; its sequences mean nothing. diff --git a/datasets/hello2-6a463bf0/recipe/build b/datasets/hello2-6a463bf0/recipe/build new file mode 100755 index 0000000..426b511 --- /dev/null +++ b/datasets/hello2-6a463bf0/recipe/build @@ -0,0 +1,23 @@ +#!/usr/bin/env -S python3 -I +"""recipe/build : `pairs` synthetic antibody pairs from params.toml's seed, shuffled and split by +`split` into train, eval, and test parquet files in .""" +import random +import sys +import tomllib +from pathlib import Path + +import polars as pl + +AA = "ACDEFGHIKLMNPQRSTVWY" +params = tomllib.loads((Path(__file__).parent / "params.toml").read_text()) +out = Path(sys.argv[1]) +out.mkdir(parents=True, exist_ok=True) +rng = random.Random(params["seed"]) +chain = lambda lo, hi: "".join(rng.choice(AA) for _ in range(rng.randint(lo, hi))) +rows = [(f"hello-{i:04d}", chain(110, 130), chain(105, 115)) for i in range(params["pairs"])] +rng.shuffle(rows) +n_train, n_eval = (round(f * len(rows)) for f in params["split"][:2]) +splits = {"train": rows[:n_train], "eval": rows[n_train:n_train + n_eval], "test": rows[n_train + n_eval:]} +for split, part in splits.items(): + pl.DataFrame(part, schema=["pair_id", "sequence_heavy", "sequence_light"], orient="row").write_parquet(out / f"{split}.parquet") + print(f"{split}.parquet {len(part)} rows") diff --git a/datasets/hello2-6a463bf0/recipe/params.toml b/datasets/hello2-6a463bf0/recipe/params.toml new file mode 100644 index 0000000..e525260 --- /dev/null +++ b/datasets/hello2-6a463bf0/recipe/params.toml @@ -0,0 +1,3 @@ +seed = 1 +pairs = 300 +split = [0.8, 0.1, 0.1] diff --git a/datasets/hello2-6a463bf0/recipe/test b/datasets/hello2-6a463bf0/recipe/test new file mode 100755 index 0000000..207a24f --- /dev/null +++ b/datasets/hello2-6a463bf0/recipe/test @@ -0,0 +1,26 @@ +#!/usr/bin/env -S python3 -I +"""recipe/test : exit 0 iff holds hello's three splits, with its columns and row counts and no +pair_id in two splits.""" +import sys +from pathlib import Path + +import polars as pl + +out, seen, problems = Path(sys.argv[1]), {}, [] +for split, rows in (("train", 240), ("eval", 30), ("test", 30)): + path = out / f"{split}.parquet" + if not path.is_file(): + problems.append(f"{split}.parquet is missing") + continue + df = pl.read_parquet(path) + if df.columns != ["pair_id", "sequence_heavy", "sequence_light"]: + problems.append(f"{split}.parquet has columns {df.columns}") + if df.height != rows: + problems.append(f"{split}.parquet has {df.height} rows, not {rows}") + for pid in df["pair_id"]: + if pid in seen: + problems.append(f"{pid} is in {seen[pid]} and {split}") + seen[pid] = split + print(f"{split}.parquet {df.height} rows") +print("\n".join(problems) or "ok") +sys.exit(1 if problems else 0) From 97d8e0f8cadca264c938041b033caa730df54838 Mon Sep 17 00:00:00 2001 From: Bryan Briney <821533+briney@users.noreply.github.com> Date: Fri, 6 Nov 2026 16:53:36 -0800 Subject: [PATCH 2/2] hello2-6a463bf0 1.0.0's record: its candidate passed on coreweave-rtx6000 --- results/hello2-6a463bf0/1.0.0.txt | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 results/hello2-6a463bf0/1.0.0.txt diff --git a/results/hello2-6a463bf0/1.0.0.txt b/results/hello2-6a463bf0/1.0.0.txt new file mode 100644 index 0000000..c6f2d56 --- /dev/null +++ b/results/hello2-6a463bf0/1.0.0.txt @@ -0,0 +1,26 @@ +--- +dataset: hello2-6a463bf0 +version: 1.0.0 +hub: brineylab-dev/hello2-6a463bf0 +branch: candidate-22a46dde029a3283d7b17a1b29a48d7f01821605 +commit: d13fe0c7e780743b714f780ce5dbbbf7148f2d46 +tree: 22a46dde029a3283d7b17a1b29a48d7f01821605 +tools: datascience@1.0.0 +runner: sbatch --partition=hpc-low --cpus-per-task=4 --mem=8G --time=00:20:00 +host: sunk.6af0ac-us-east-13a-briney-rtx6000pro.coreweave.app +started: 2026-11-07T00:52:59Z +exit: 0 +--- +pyxis: importing docker image: ghcr.io#brineylab/toolshed/datascience:1.0.0 +pyxis: imported docker image: ghcr.io#brineylab/toolshed/datascience:1.0.0 +train.parquet 240 rows +eval.parquet 30 rows +test.parquet 30 rows +train.parquet 240 rows +eval.parquet 30 rows +test.parquet 30 rows +ok +file eval.parquet 6602 fc311054c3da6268f2dcb7cb9a751697a5542f6fdd0ea5befe7bb7a6a39a234d +file test.parquet 6505 98c0a809593d563ea422663e21185e8b08631be9b7a593a3eda2d0034a0b5234 +file train.parquet 35145 5382f5f36ce977c410e4401ef5dc4c8755e8aa66d5cee8b4e217809473da5b72 +commit: d13fe0c7e780743b714f780ce5dbbbf7148f2d46