dmlc / dmlc/xgboost

[dask] Support prediction with empty partition.

Open
#9,318 0 comments 1 reaction 0 assignees View on GitHub
feature-request
Dominant language
C++
Stars
28.8k
Forks
8.9k
Avg merge
1d 12h
Merged PRs (30d)
54

Description

It seems in some cases dask can call `map_partitions` with empty partitions. We should add well-defined behavior for prediction in the face of empty input.

Related: https://github.com/dask/dask/pull/9637 .

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by tracing the Dask prediction path that calls map_partitions with empty partitions, then review the related dask PR #9637 for context. Define and verify the intended prediction behavior for empty input, including tests for empty partitions.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
distributed-systems, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.