Skip to content

rel-stack: user badges (Classification)

This docs example now reflects the current runner path: the local script materializes the official rel-stack tables from the relbench library and then runs the GraphReduce badge pipeline. The old S3 CSV download and separate Tags.csv dependency are no longer part of the example.

from pathlib import Path
from relbench_dataset_utils import materialize_relbench_dataset

materialized = materialize_relbench_dataset(
    "rel-stack",
    Path("tests/data/relbench/rel-stack"),
    {
        "users": "Users.csv",
        "posts": "Posts.csv",
        "badges": "Badges.csv",
        "postHistory": "PostHistory.csv",
        "postLinks": "PostLinks.csv",
        "votes": "Votes.csv",
        "comments": "Comments.csv",
    },
)
print(materialized)

Current implementation:

Latest Tested Result

Latest local run from tests/data/relbench/run_reports/relbench_results.json:

  • test ROC AUC: 0.8442
  • test average precision: 0.2749
  • feature count: 490
  • rows: train 239926, validation 247379, test 255341
  • runtime: 89.8s (2026-04-09T22:54:40Z)

Interactive Runner

Idle