{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T03:35:12Z","timestamp":1779075312633,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T00:00:00Z","timestamp":1712534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","award":["Wallenberg Academy Fellowship"],"award-info":[{"award-number":["Wallenberg Academy Fellowship"]}],"id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,8]]},"DOI":"10.1145\/3605098.3636056","type":"proceedings-article","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T17:59:16Z","timestamp":1716314356000},"page":"1272-1281","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["A Large-Scale Study of ML-Related Python Projects"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4143-322X","authenticated-orcid":false,"given":"Samuel","family":"Idowu","sequence":"first","affiliation":[{"name":"Chalmers | University of Gothenburg, Gothenburg, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5845-5887","authenticated-orcid":false,"given":"Yorick","family":"Sens","sequence":"additional","affiliation":[{"name":"Ruhr University Bochum, Bochum, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3870-5167","authenticated-orcid":false,"given":"Thorsten","family":"Berger","sequence":"additional","affiliation":[{"name":"Ruhr University Bochum and Chalmers | University of Gothenburg, Bochum, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0283-248X","authenticated-orcid":false,"given":"Jacob","family":"Krueger","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2672-9230","authenticated-orcid":false,"given":"Michael","family":"Vierhauser","sequence":"additional","affiliation":[{"name":"Ruhr University Bochum, Bochum, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,21]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2021. Most popular machine learning libraries - 2014\/2021. https:\/\/statisticsanddata.org\/data\/most-popular-machine-learning-libraries"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Mohannad Alahdab and G\u00fcl \u00c7al\u0131kl\u0131. 2019. Empirical analysis of hidden technical debt patterns in machine learning software. In PROFES.","DOI":"10.1007\/978-3-030-35333-9_14"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Saleema Amershi Andrew Begel Christian Bird Robert DeLine Harald Gall Ece Kamar Nachiappan Nagappan Besmira Nushi and Thomas Zimmermann. 2019. Software engineering for machine learning: A case study. In ICSE\/SEIP.","DOI":"10.1109\/ICSE-SEIP.2019.00042"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"A Arpteg B Brinne L Crnkovic-Friis and J Bosch. 2018. Software Engineering Challenges of Deep Learning. In SEAA.","DOI":"10.1109\/SEAA.2018.00018"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Amine Barrak Ellis E Eghan and Bram Adams. 2021. On the co-evolution of ml pipelines and source code-empirical study of dvc projects. In SANER.","DOI":"10.1109\/SANER50967.2021.00046"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2019.20866"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Aaditya Bhatia Ellis E Eghan Manel Grichi William G Cavanagh Zhen Ming Bram Adams et al. 2022. Towards a Change Taxonomy for Machine Learning Systems. arXiv preprint arXiv:2203.11365 (2022).","DOI":"10.1007\/s10664-022-10282-8"},{"key":"e_1_3_2_1_8_1","volume-title":"Yijia Huang, and Hridesh Rajan.","author":"Biswas Sumon","year":"2019","unstructured":"Sumon Biswas, Md Johirul Islam, Yijia Huang, and Hridesh Rajan. 2019. Boa meets python: a boa dataset of data science software in python language. In MSR."},{"key":"e_1_3_2_1_9_1","volume-title":"In-The-Small, and In-The-Large. arXiv:2112.01590","author":"Biswas Sumon","year":"2021","unstructured":"Sumon Biswas, Mohammad Wardat, and Hridesh Rajan. 2021. The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Large. arXiv:2112.01590 (2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Dan Bohus Sean Andrist and Mihai Jalobeanu. 2017. Rapid development of multimodal interactive systems: a demonstration of platform for situated intelligence. In ICMI.","DOI":"10.1145\/3136755.3143021"},{"key":"e_1_3_2_1_11_1","volume-title":"Javier Luis C\u00e1novas Izquierdo, and Jordi Cabot","author":"Cosentino Valerio","year":"2016","unstructured":"Valerio Cosentino, Javier Luis C\u00e1novas Izquierdo, and Jordi Cabot. 2016. Findings from GitHub: methods, datasets and limitations. In MSR."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/240455.240464"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2020.100551"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Danielle Gonzalez Thomas Zimmermann and Nachiappan Nagappan. 2020. The state of the ml-universe: 10 years of artificial intelligence & machine learning software development on github. In MSR.","DOI":"10.1145\/3379597.3387473"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Georgios Gousios and Diomidis Spinellis. 2017. Mining software engineering data from GitHub. In ICSE-C.","DOI":"10.1109\/ICSE-C.2017.164"},{"key":"e_1_3_2_1_16_1","volume-title":"On the Effectiveness of Machine Learning Experiment Management Tools. In 44th International Conference on Software Engineering, Software Engineering in Practice track (ICSE\/SEIP).","author":"Idowu Samuel","year":"2022","unstructured":"Samuel Idowu, Osman Osman, Daniel Strueber, and Thorsten Berger. 2022. On the Effectiveness of Machine Learning Experiment Management Tools. In 44th International Conference on Software Engineering, Software Engineering in Practice track (ICSE\/SEIP)."},{"key":"e_1_3_2_1_17_1","volume-title":"Article 144 (dec","author":"Idowu Samuel","year":"2022","unstructured":"Samuel Idowu, Daniel Str\u00fcber, and Thorsten Berger. 2022. Asset Management in Machine Learning: State-of-research and State-of-practice. Comput. Surveys 55, 7, Article 144 (dec 2022), 35 pages."},{"key":"e_1_3_2_1_18_1","volume-title":"EMMM: A Unified Meta-Model for Tracking Machine Learning Experiments. In Euromicro Conference on Software Engineering and Advanced Applications (SEAA).","author":"Idowu Samuel","year":"2022","unstructured":"Samuel Idowu, Daniel Strueber, and Thorsten Berger. 2022. EMMM: A Unified Meta-Model for Tracking Machine Learning Experiments. In Euromicro Conference on Software Engineering and Advanced Applications (SEAA)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Samuel Idowu Daniel Str\u00fcber and Thorsten Berger. 2021. Asset Management in Machine Learning: A Survey. In ICSE\/SEIP.","DOI":"10.1109\/ICSE-SEIP52600.2021.00014"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Richard Isdahl and Odd Erik Gundersen. 2019. Out-of-the-Box Reproducibility: A Survey of Machine Learning Platforms. In eScience.","DOI":"10.1109\/eScience.2019.00017"},{"key":"e_1_3_2_1_21_1","unstructured":"Microsoft. 2017. Team Data Science Process Documentation. https:\/\/docs.microsoft.com\/en-us\/azure\/machine-learning\/team-data-science-process\/"},{"key":"e_1_3_2_1_22_1","unstructured":"Ml-Tooling. [n. d.]. ML-tooling\/best-of-ml-python: A ranked list of awesome machine learning python libraries. updated weekly. https:\/\/github.com\/ml-tooling\/best-of-ml-python"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc5020020"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Aiswarya Raj Munappy Jan Bosch and Helena Homstr\u00f6m Olsson. 2020. Data pipeline management in practice: Challenges and opportunities. In PROFES.","DOI":"10.1007\/978-3-030-64148-1_11"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111359"},{"key":"e_1_3_2_1_26_1","volume-title":"Jan Bosch, Helena Holmstr\u00f6m Olsson, and Anas Dakkak.","author":"Munappy Aiswarya Raj","year":"2020","unstructured":"Aiswarya Raj Munappy, David Issa Mattos, Jan Bosch, Helena Holmstr\u00f6m Olsson, and Anas Dakkak. 2020. From ad-hoc data analytics to dataops. In ICSSP."},{"key":"e_1_3_2_1_27_1","unstructured":"Nadia Nahar Haoran Zhang Grace Lewis Shurui Zhou and Christian K\u00e4stner. 2023. A Dataset and Analysis of Open-Source Machine Learning Products. arXiv:2308.04328 [cs.SE]"},{"key":"e_1_3_2_1_28_1","volume-title":"A taxonomy of tools for reproducible machine learning experiments. AIxIA","author":"Quaranta Luigi","year":"2021","unstructured":"Luigi Quaranta, Fabio Calefato, and Filippo Lanubile. 2021. A taxonomy of tools for reproducible machine learning experiments. AIxIA (2021)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-022-10229-z"},{"key":"e_1_3_2_1_30_1","volume-title":"Python machine learning: Machine learning and deep learning with Python, scikit-learn, and TensorFlow 2","author":"Raschka Sebastian","unstructured":"Sebastian Raschka and Vahid Mirjalili. 2019. Python machine learning: Machine learning and deep learning with Python, scikit-learn, and TensorFlow 2. Packt Publishing Ltd."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14257\/ijseia.2015.9.11.05"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Marius Schlegel and Kai-Uwe Sattler. 2022. Management of Machine Learning Lifecycle Artifacts: A Survey. SIGMOD Rec. (2022) 18--35.","DOI":"10.1145\/3582302.3582306"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Andrew J Simmons Scott Barnett Jessica Rivera-Villicana Akshat Bajaj and Rajesh Vasa. 2020. A large-scale comparative analysis of coding standard conformance in open-source data science projects. In ESEM.","DOI":"10.1145\/3382494.3410680"},{"key":"e_1_3_2_1_34_1","unstructured":"Rachael Tatman Jake Vanderplas and Sohier Dane. 2018. A Practical Taxonomy of Reproducibility for Machine Learning Research. In ICML."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Bart van Oort Lu\u00eds Cruz Maur\u00edcio Aniche and Arie van Deursen. 2021. The Prevalence of Code Smells in Machine Learning projects. In WAIN.","DOI":"10.1109\/WAIN52551.2021.00011"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Jiawei Wang Li Li and Andreas Zeller. 2021. Restoring execution environments of Jupyter notebooks. In ICSE.","DOI":"10.1109\/ICSE43902.2021.00144"},{"key":"e_1_3_2_1_37_1","volume-title":"Mapping platforms into a new open science model for machine learning. it - Information Technology 61, 4","author":"Wei\u00dfgerber Thomas","year":"2019","unstructured":"Thomas Wei\u00dfgerber and Michael Granitzer. 2019. Mapping platforms into a new open science model for machine learning. it - Information Technology 61, 4 (2019), 197--208."},{"key":"e_1_3_2_1_38_1","unstructured":"R\u00fcdiger Wirth and Jochen Hipp. 2000. CRISP-DM : Towards a standard process model for data mining. In KDD."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Yue Yu Gang Yin Huaimin Wang and Tao Wang. 2014. Exploring the patterns of social behavior in GitHub. In CrowdSoft.","DOI":"10.1145\/2666539.2666571"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392826"}],"event":{"name":"SAC '24: 39th ACM\/SIGAPP Symposium on Applied Computing","location":"Avila Spain","acronym":"SAC '24","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the 39th ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605098.3636056","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605098.3636056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:00Z","timestamp":1750291440000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605098.3636056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,8]]},"references-count":40,"alternative-id":["10.1145\/3605098.3636056","10.1145\/3605098"],"URL":"https:\/\/doi.org\/10.1145\/3605098.3636056","relation":{},"subject":[],"published":{"date-parts":[[2024,4,8]]},"assertion":[{"value":"2024-05-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}