Datasets:
Tasks:
Text2Text Generation
Modalities:
Text
Formats:
json
Languages:
code
Size:
1K - 10K
Tags:
code-generation
License:
license: cc-by-sa-4.0 | |
language: | |
- code | |
task_categories: | |
- text2text-generation | |
tags: | |
- code-generation | |
pretty_name: DS-1000 | |
<h1 align="center"> DS-1000 in simplied format </h1> | |
This is a reformatting of the DS-1000 dataset with improved ease of use. | |
* the test process is cleaned up and all contained in the field `code_context`, with the unnecessary pickle and multiple file IOs removed. | |
* `code_context` defines `test_execution(code: str)` and `test_string(code: str)` which takes the generated code and evalutes their correctness. | |
* Python is upgraded to 3.10 and libraries upgraded to the latest versions (`environment.yaml`) | |
* checked that the performance is not overly sensitive to library versions (`enviroment-old-lib.yaml`). | |
* Removed obsolete `parser` module and simplified string testing | |
* a few problems were manually fixed and minor inconsistency with the origin due to import side effects etc. | |
Testing code and examples are in the [original repo](https://github.com/xlang-ai/DS-1000/simplified). | |
Reformatting credits: Yuhang Lai, Sida Wang | |