microsoft / microsoft/SynapseML

Load and save the lightGBM classifier not producing the same results

Open
#2,053 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug triage
Dominant language
Scala
Stars
5.2k
Forks
868
Avg merge
22h 9m
Merged PRs (30d)
45

Description

### SynapseML version

0.10.2

### System information

- **Language version** (e.g. python 3.8, scala 2.12): python 3.8
- **Spark Version** (e.g. 3.2.3): 3.3.2
- **Spark Platform** (e.g. Synapse, Databricks): Databricks

### Describe the problem

Trained a lightGBM classifier. I tried to save this in the native format and load it back again with the below code -

`LightGBMClassificationModel.loadNativeModelFromString(model.getNativeModel())`

I am not getting the same results with the load and save model as compared to original.

Can someone please help?

### Code to reproduce issue

```python
LightGBMClassificationModel.loadNativeModelFromString(model.getNativeModel())
```

### Other info / logs

_No response_

### What component(s) does this bug affect?

- [ ] `area/cognitive`: Cognitive project
- [ ] `area/core`: Core project
- [ ] `area/deep-learning`: DeepLearning project
- [ ] `area/lightgbm`: Lightgbm project
- [ ] `area/opencv`: Opencv project
- [ ] `area/vw`: VW project
- [ ] `area/website`: Website
- [ ] `area/build`: Project build system
- [ ] `area/notebooks`: Samples under notebooks folder
- [ ] `area/docker`: Docker usage
- [ ] `area/models`: models related issue

### What language(s) does this bug affect?

- [ ] `language/scala`: Scala source code
- [ ] `language/python`: Pyspark APIs
- [ ] `language/r`: R APIs
- [ ] `language/csharp`: .NET APIs
- [ ] `language/new`: Proposals for new client languages

### What integration(s) does this bug affect?

- [ ] `integrations/synapse`: Azure Synapse integrations
- [ ] `integrations/azureml`: Azure ML integrations
- [ ] `integrations/databricks`: Databricks integrations

Contributor guide

Open the 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.

Research direction

Start by reproducing the discrepancy with the provided Python call to LightGBMClassificationModel.loadNativeModelFromString(model.getNativeModel()) in the stated SynapseML, Spark, and Databricks versions. Compare predictions before and after native serialization, then trace the corresponding LightGBM model save/load entry points; done means the loaded model produces the same results as the original.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.