Question: Alternative to MLeap for Real-Time Inference Without Spark Context with SparkXGBClassifier

Open
  • Is something wrong?
#882 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
20/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Stale
Tech stack
python
Domain
machine-learning

Research direction

The issue names no repository files, tests, or entry points to inspect. Begin by reproducing the Spark-based and non-Spark evaluation comparison described, then investigate the serialization and preprocessing boundary. Done would require a documented portable serving approach whose predictions match Spark evaluation without a Spark context.

Written by the indexing model from the issue text.

Description

Question: Alternative to MLeap for Real-Time Inference Without Spark Context

We are exploring alternatives to MLeap for running inference without Spark, since MLeap has limitations with Spark/PySpark version compatibility and library updates.

Our Setup & Goal
  • Environment: PySpark 3.5.5
  • Algorithm: Distributed ML training using XGBoost with Spark.
  • Goal: Run real-time inference without requiring a Spark session/context, to reduce overhead and response latency.
What We Did
  1. Took a dataset (Titanic), converted it to Parquet, and split it into 80% (train) and 20% (test).
  2. Trained with Spark (80% data) including preprocessing + XGBoost.
  3. Evaluated on Spark (20% data) and logged the trained model.
  4. Tried multiple logging/serialization approaches:
    • MLflow pyfunc
    • ONNX
    • XGBoost native model
  5. For inference: loaded the same 20% data, applied preprocessing outside Spark, reloaded the trained model, and ran predictions.
The Problem
  • In all approaches tested (MLflow pyfunc, ONNX, XGBoost native save/load), accuracy differs between:
    • Spark-based evaluation (during training)
    • Non-Spark inference (real-time service)
  • It seems precision is lost when the model is saved and reloaded outside Spark.
Main Requirement
  • The accuracy from Spark-based evaluation and non-Spark inference must match.
  • Need a solution to serialize/deserialize models that works across Spark training and non-Spark inference.
  • Prefer portable formats (JSON or similar).
  • Must avoid Spark context overhead at inference for real-time serving.
Question

👉 Is there any solution or alternative to MLeap for serving models trained with Spark (e.g., XGBoost with PySpark), but performing inference outside of Spark (lightweight, real-time)?

  • Should support PySpark 3.5.5
  • Must work with XGBoost distributed training
  • Should prevent accuracy mismatch between Spark and non-Spark inference
  • JSON or portable serialization preferred

Any recommendations for frameworks, libraries, or best practices beyond MLeap would be greatly appreciated.

Dominant language
Scala
Stars
1.5k
Forks
313
Avg merge
22m
Merged PRs (30d)
1

Getting set up

Open in Codespaces

Starts the project's dev container in your browser, under your own GitHub account.

  • No Dockerfile or Docker Compose file
  • No pull request template
  • No contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from combust/mleap

All issues in combust/mleap

Similar issues

More Scala issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.