NVIDIA-Merlin / NVIDIA-Merlin/Merlin
Offline Batch Processing - Create required operator level functions (predict, my_input_type, transform_df, etc...)
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 907
- Forks
- 129
- PR merge metrics
- No merged PRs in 30d
Description
Create required operator level functions (predict, my_input_type, transform_df, etc...)
- predict -> function that calls predict against model (support any framework)
- my_input_type -> Function that returns the expected type of my inputs. (to be used by operator executor to ensure inputs are in correct format for next operator)
- transform_df -> Function that can be used to house generic operator execution behavior. Should mimic what is happening in inference op logic.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the existing inference op logic and tracing how the operator executor handles inputs. Identify the entry points for predict, my_input_type, and transform_df, then confirm that the three functions cover model prediction, input-type validation, and generic operator execution across supported frameworks.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100