feat(hf-space): leaderboard app for the OCB dataset

.github/workflows/hf-space-deploy.yml

@@ -0,0 +1,82 @@
+name: HF Space deploy
+
+# Pushes scripts/hf_space/ to the HF Space at
+# https://huggingface.co/spaces/OpenChainBench/leaderboard.
+#
+# Trigger:
+# - push to main that touches scripts/hf_space/**
+# - workflow_dispatch for manual redeploys
+#
+# Required secrets:
+# HF_TOKEN write-scoped token for the Space repo (same token as the
+# dataset publisher).
+
+on:
+ push:
+ branches: [main]
+ paths:
+ - "scripts/hf_space/**"
+ - ".github/workflows/hf-space-deploy.yml"
+ workflow_dispatch:
+
+concurrency:
+ group: hf-space-deploy
+ cancel-in-progress: false
+
+jobs:
+ deploy:
+ runs-on: ubuntu-latest
+ timeout-minutes: 10
+ permissions:
+ contents: read
+ env:
+ HF_TOKEN: ${{ secrets.HF_TOKEN }}
+ HF_SPACE_REPO_ID: OpenChainBench/leaderboard
+ steps:
+ - uses: actions/checkout@v4
+
+ - uses: actions/setup-python@v5
+ with:
+ python-version: "3.11"
+
+ - name: Install huggingface_hub
+ run: pip install "huggingface_hub>=0.26"
+
+ - name: Upload to HF Space
+ env:
+ GIT_SHA: ${{ github.sha }}
+ run: |
+ python - <<'PY'
+ import os
+ from huggingface_hub import HfApi
+
+ token = os.environ["HF_TOKEN"]
+ repo_id = os.environ["HF_SPACE_REPO_ID"]
+ sha = os.environ.get("GIT_SHA", "manual")
+ api = HfApi(token=token)
+ api.create_repo(
+ repo_id=repo_id,
+ repo_type="space",
+ space_sdk="gradio",
+ exist_ok=True,
+ private=False,
+ )
+ info = api.upload_folder(
+ folder_path="scripts/hf_space",
+ repo_id=repo_id,
+ repo_type="space",
+ commit_message=f"deploy from {sha}",
+ )
+ print("uploaded:", getattr(info, "oid", "ok"))
+ PY
+
+ - name: Summary
+ if: always()
+ run: |
+ {
+ echo "## HF Space deploy ${{ job.status }}"
+ echo ""
+ echo "**Space:** https://huggingface.co/spaces/${HF_SPACE_REPO_ID}"
+ echo "**Commit:** ${{ github.sha }}"
+ echo "**Time:** $(date -u +%FT%TZ)"
+ } >> "$GITHUB_STEP_SUMMARY"

.gitignore

@@ -62,7 +62,8 @@ harnesses/*/monitor
 harnesses/*/cmd/script/script
 harnesses/*/cmd/monitor/monitor
 
-# Python venvs for the HF publisher (created locally for dry-runs)
+# Python venvs for the HF publisher and Space (created locally for dry-runs)
 scripts/hf_publisher/.venv/
+scripts/hf_space/.venv/
 **/__pycache__/
 *.pyc

scripts/hf_space/README.md

@@ -0,0 +1,52 @@
+---
+title: OpenChainBench Leaderboard
+emoji: 📊
+colorFrom: indigo
+colorTo: blue
+sdk: gradio
+sdk_version: 4.44.1
+python_version: "3.11"
+app_file: app.py
+license: cc-by-4.0
+pinned: false
+short_description: Interactive leaderboard for OpenChainBench crypto infra benchmarks
+---
+
+# OpenChainBench leaderboard
+
+A small Gradio app that reads the daily parquet snapshot from the
+[OpenChainBench/benchmarks](https://huggingface.co/datasets/OpenChainBench/benchmarks)
+dataset and lets you browse it. Four tabs: today's leaderboard, per-chain
+leaders, per-provider rankings, and an about page.
+
+The dataset itself is the source of truth. This Space is a viewer on top
+of it. If you want raw access, query the parquet files directly with
+`polars`, `duckdb`, `pandas`, or any tool that speaks parquet.
+
+```python
+import polars as pl
+
+df = pl.scan_parquet(
+ "hf://datasets/OpenChainBench/benchmarks/headlines/**/*.parquet",
+ hive_partitioning=True,
+)
+print(df.collect().head())
+```
+
+For the full website with methodology, per-bench detail pages, and the
+historical view, head to [openchainbench.com](https://openchainbench.com).
+
+## Local dev
+
+```bash
+pip install -r requirements.txt
+python app.py
+```
+
+Open http://127.0.0.1:7860.
+
+## License
+
+Code in this Space is part of the OpenChainBench repo. The dataset is
+released under CC-BY-4.0. Attribution: link back to openchainbench.com or
+the dataset page.