Skip to content

rel-stack: post votes (Regression)

RelBench rel-stack post-votes graphreduce flow

Open full-size: SVG

This docs page now reflects the current runner path: the example materializes the official rel-stack tables from the relbench Python library and then builds the GraphReduce post-votes regression frame locally.

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:

  • in-time holdout MAE (2020): 0.0613
  • out-of-time MAE (2021): 0.0625
  • feature count: 217
  • rows: train 139575, future eval 160172
  • runtime: 60.3s (2026-04-09T22:52:48Z)

Interactive Runner

Idle