{"url":"/dataset/data-science-problems","name":"Data Science Problems","full_name":null,"description_markdown":"Evaluate a natural language code generation model on real data science pedagogical notebooks! Data Science Problems (DSP) includes well-posed data science problems in Markdown along with unit tests to verify correctness and a Docker environment for reproducible execution. About 1/3 of notebooks in this benchmark also include data dependencies, so this benchmark not only can test a model's ability to chain together complex tasks, but also evaluate the solutions on real data! See our paper [Training and Evaluating a Jupyter Notebook Data Science Assistant](https://arxiv.org/abs/2201.12901) for more details about state of the art results and other properties of the dataset.","description_withheld":null,"homepage":"https://github.com/microsoft/DataScienceProblems","introduced_date":"2022-01-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/training-and-evaluating-a-jupyter-notebook","title":"Training and Evaluating a Jupyter Notebook Data Science Assistant","first_author":"Shubham Chandel","url":null},"license":{"name":"MIT","url":"https://github.com/microsoft/DataScienceProblems/blob/main/LICENSE.txt"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Data Science Problems"],"data_loaders":[{"repo":"https://github.com/microsoft/DataScienceProblems","url":"https://github.com/microsoft/DataScienceProblems","frameworks":[]}],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}