"""
Push the Arabic GSM8K reasoning dataset to the Hub as a PRIVATE dataset repo.

Usage: python push_dataset.py [--repo oddadmix/gsm8k-reasoning-ar] [--dry-run]
"""
import argparse
import json
from pathlib import Path

import pyarrow.parquet as pq
from huggingface_hub import HfApi

OUT = Path("out_gsm")
PARQUET = OUT / "gsm8k_reasoning_ar.parquet"
SOURCE = "Ajhesh7/gsm8k-reasoning-SFT-datas"
MT_MODEL = "ByteDance-Seed/Seed-X-PPO-7B"

CARD = """---
license: apache-2.0
language:
- ar
- en
task_categories:
- text-generation
tags:
- arabic
- reasoning
- chain-of-thought
- math
- gsm8k
- machine-translated
size_categories:
- 100K<n<1M
dataset_info:
  features:
  - name: text
    dtype: string
  - name: question
    dtype: string
  - name: thinking
    dtype: string
  - name: answer
    dtype: string
  - name: question_en
    dtype: string
  - name: thinking_en
    dtype: string
  - name: source_index
    dtype: int64
  splits:
  - name: train
    num_examples: {rows}
configs:
- config_name: default
  data_files:
  - split: train
    path: data/train-*
---

# GSM8K Reasoning — Arabic (مترجم آليًا)

**{rows:,}** grade-school math reasoning items translated from English into Arabic with
[`{mt}`](https://huggingface.co/{mt}), a 7B translation model.

Source: [`{source}`](https://huggingface.co/datasets/{source}) (600,000 rows).

> **بالعربية:** مجموعة بيانات للاستدلال الرياضي بالعربية، مترجمة آليًا من الإنجليزية.
> كل مثال يحتوي على سؤال، وخطوات التفكير، والإجابة النهائية.

## Format

`text` keeps the source's tag layout, with Arabic content:

```
<question>يجمع فريا 168 صندوقًا وجمعت هانا 19 صندوقًا...</question> <thinking>دعونا نفكر خطوة بخطوة...</thinking> <answer>187</answer>
```

The parts are also available as separate columns — `question`, `thinking`, `answer` (Arabic;
`answer` is the untouched numeral) — with `question_en` / `thinking_en` carrying the English
source so every row is auditable, and `source_index` pointing back into the source dataset.

## How it was built

1. **Sampling.** {selected:,} of the 600,000 source rows. The corpus is generated from only
   **2,814** underlying question patterns (numbers and names masked), so the sample is stratified
   by pattern with a floor of {floor} rows per pattern — every pattern is represented rather than
   over-weighting the common ones.
2. **Translation.** Question and reasoning translated separately, each as its own sentence, with
   `Translate the following English sentence into Arabic:\\n{{text}} <ar>` and greedy decoding.
   Numbers and names were left in place rather than masked, so Arabic gender agreement follows the
   actual name (`اشترت` for Aisha) and number agreement follows the actual quantity. The final
   `answer` numeral is never sent to the translator.
3. **Validation.** A row is kept only if, for **both** segments, the numbers in the Arabic exactly
   match the English (order-insensitive), the output is non-empty Arabic script, has no degenerate
   repetition loop, and has no significant Latin-script residue. **{kept_pct:.2f}%** of translated
   rows passed.

Rejection breakdown: `{rejects}`

## Limitations

This is **machine translation**, not human-verified Arabic. It inherits the source's synthetic,
templated phrasing — {selected:,} rows expand from 2,814 patterns, so linguistic diversity is far
lower than the row count suggests.

**Gender agreement.** The English source pairs names with pronouns arbitrarily ("This week Emil
did chores and earned $76. **She** bought a bottle…"), which English mostly hides but Arabic does
not: a row can read `قام جورج …` and then `اشترت …` for the same person. The translator rendered
the source faithfully; the disagreement is upstream, and it is visible throughout. The arithmetic itself is copied from the source and was not
re-verified; in the source, the reasoning's final number agrees with the `answer` field ~96.6% of
the time, so a small fraction of items are internally inconsistent. Suitable for SFT on reasoning
*format* and basic Arabic math phrasing; not a benchmark.
"""


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--repo", default="oddadmix/gsm8k-reasoning-ar")
    ap.add_argument("--dry-run", action="store_true")
    args = ap.parse_args()

    stats = json.loads((OUT / "build_stats.json").read_text(encoding="utf-8"))
    rows = pq.ParquetFile(PARQUET).metadata.num_rows
    floor = max(1, stats["selected"] // (2814 * 4))

    card = CARD.format(
        rows=rows, mt=MT_MODEL, source=SOURCE, selected=stats["selected"],
        kept_pct=stats["kept_pct"], rejects=stats["rejects"], floor=floor,
    )
    (OUT / "README.md").write_text(card, encoding="utf-8")
    print(f"[+] wrote card ({len(card)} chars), {rows} rows")

    if args.dry_run:
        print("[dry-run] not pushing")
        return

    api = HfApi()
    api.create_repo(args.repo, repo_type="dataset", private=True, exist_ok=True)
    api.upload_file(path_or_fileobj=str(PARQUET), path_in_repo="data/train-00000-of-00001.parquet",
                    repo_id=args.repo, repo_type="dataset")
    api.upload_file(path_or_fileobj=str(OUT / "README.md"), path_in_repo="README.md",
                    repo_id=args.repo, repo_type="dataset")
    for script in ("gsm_common.py", "translate_gsm.py", "build_dataset.py"):
        api.upload_file(path_or_fileobj=script, path_in_repo=f"scripts/{script}",
                        repo_id=args.repo, repo_type="dataset")
    print(f"[+] https://huggingface.co/datasets/{args.repo}")


if __name__ == "__main__":
    main()