Spaces:

ModelBrew
/

dataset-cleaner

Running

File size: 5,511 Bytes

b485a88

"""Static showcase page for the cleaner (free-tier Space).

Renders the REAL issue report from running modelbrew_cleaner on the bundled
dirty sample — no fabricated output. Run inside the package venv:
    PYTHONPATH= ../modelbrew-cleaner/.venv/bin/python build_static.py
"""
import html
from pathlib import Path

from modelbrew_cleaner import Severity, clean_file, issue_summary

HERE = Path(__file__).parent
rows = clean_file(str(HERE / "sample.jsonl"))
summary = issue_summary(rows)
n_critical_rows = sum(1 for r in rows if any(i.severity == Severity.critical for i in r.issues))

SEV_ORDER = {"critical": 0, "warning": 1, "suggestion": 2}
records = sorted(
    ((r.row_index, i) for r in rows for i in r.issues),
    key=lambda x: (SEV_ORDER[x[1].severity.value], x[0]),
)

table_rows = "".join(
    f"<tr><td>{idx}</td><td><span class='pill {i.severity.value}'>{i.severity.value}</span></td>"
    f"<td><code>{html.escape(i.code)}</code></td><td>{html.escape(i.message)}</td>"
    f"<td>{'✔' if i.auto_fixable else ''}</td></tr>"
    for idx, i in records
)

page = f"""<!doctype html>
<html lang="en"><head><meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>ModelBrew Dataset Cleaner</title>
<style>
:root {{ --bg:#fff; --fg:#1a1a1a; --muted:#6a6a6a; --line:#e3e3e3; --accent:#e17100; --code:#f4f4f4;
  --crit-bg:#fdecea; --crit-fg:#8c1d18; --warn-bg:#fff4e0; --warn-fg:#7a4b00; --sugg-bg:#e8f0fe; --sugg-fg:#1a4b8c; }}
@media (prefers-color-scheme: dark) {{
  :root {{ --bg:#101010; --fg:#eaeaea; --muted:#9a9a9a; --line:#2b2b2b; --accent:#ff9e2c; --code:#1d1d1d;
    --crit-bg:#3a1512; --crit-fg:#ff9d94; --warn-bg:#3a2c10; --warn-fg:#ffce7a; --sugg-bg:#12233a; --sugg-fg:#9cc4ff; }} }}
body {{ margin:0; background:var(--bg); color:var(--fg); font:16px/1.55 system-ui,-apple-system,Segoe UI,Roboto,sans-serif; }}
main {{ max-width:960px; margin:0 auto; padding:2.5rem 1.25rem 4rem; }}
h1 {{ font-size:1.7rem; margin:0 0 .3rem; }} h2 {{ margin:2rem 0 .6rem; font-size:1.15rem; }}
.sub {{ color:var(--muted); margin:0 0 1.2rem; }}
a {{ color:var(--accent); text-decoration:none; }} a:hover {{ text-decoration:underline; }}
pre {{ background:var(--code); padding:.9rem 1rem; border-radius:8px; overflow-x:auto; font-size:.85rem; }}
code {{ background:var(--code); padding:.1rem .35rem; border-radius:4px; font-size:.85em; }}
pre code {{ padding:0; background:none; }}
.tablewrap {{ overflow-x:auto; border:1px solid var(--line); border-radius:8px; }}
table {{ border-collapse:collapse; width:100%; font-size:.85rem; }}
th,td {{ text-align:left; padding:.5rem .65rem; border-bottom:1px solid var(--line); vertical-align:top; }}
th {{ color:var(--muted); font-weight:600; }} tr:last-child td {{ border-bottom:none; }}
.pill {{ padding:.12rem .5rem; border-radius:99px; font-size:.75rem; white-space:nowrap; }}
.pill.critical {{ background:var(--crit-bg); color:var(--crit-fg); }}
.pill.warning {{ background:var(--warn-bg); color:var(--warn-fg); }}
.pill.suggestion {{ background:var(--sugg-bg); color:var(--sugg-fg); }}
.cta {{ display:inline-block; margin:.3rem .6rem .3rem 0; padding:.55rem 1rem; border-radius:8px;
  background:var(--accent); color:#fff !important; font-weight:600; }}
footer {{ margin-top:3rem; color:var(--muted); font-size:.85rem; border-top:1px solid var(--line); padding-top:1rem; }}
</style></head><body><main>
<h1>🧹 ModelBrew Dataset Cleaner</h1>
<p class="sub">90+ quality checks for fine-tuning datasets: PII with real checksum validation,
exact/near duplicates, prompt-injection &amp; jailbreak patterns, label errors, truncated
responses, and more. Free and open source.</p>

<a class="cta" href="https://app.modelbrew.ai/clean">Clean your dataset in the browser →</a>
<a class="cta" href="https://github.com/ackerman404/modelbrew-cleaner" style="background:#333">GitHub</a>

<h2>Or in your pipeline</h2>
<pre><code>pip install modelbrew-cleaner

from modelbrew_cleaner import clean_file, issue_summary, export_clean
rows = clean_file("train.jsonl")     # .jsonl, .json, or .csv
print(issue_summary(rows))           # {summary}
cleaned = export_clean(rows)         # critical rows dropped</code></pre>

<h2>Real output — the bundled dirty sample ({len(rows)} rows)</h2>
<p class="sub">This report is generated by actually running the cleaner on
<a href="sample.jsonl">sample.jsonl</a> at build time — {summary['critical']} critical /
{summary['warning']} warnings / {summary['suggestion']} suggestions;
{n_critical_rows} rows dropped from the cleaned export.</p>
<div class="tablewrap"><table>
<thead><tr><th>row</th><th>severity</th><th>check</th><th>message</th><th>auto-fix</th></tr></thead>
<tbody>{table_rows}</tbody></table></div>

<h2>Why we built it</h2>
<p>We work on fine-tuning without catastrophic forgetting (patent-pending CRMA adapters).
Measuring forgetting honestly forced us to fix our data first — in our measurements, dataset
confounds alone accounted for a 96.9-percentage-point swing in measured forgetting.
Read: <a href="{{{{HF_ARTICLE_URL}}}}">Your forgetting benchmark is lying to you</a> ·
Browse the <a href="https://huggingface.co/spaces/ModelBrew/forgetting-leaderboard">forgetting leaderboard</a>.</p>

<footer><a href="https://modelbrew.ai">ModelBrew</a> · Apache-2.0 · every number we publish links to a raw results file.</footer>
</main></body></html>
"""

(HERE / "index.html").write_text(page)
print(f"wrote index.html ({len(page)} bytes) — report rows: {len(records)}")