CodelessML: A Beginner's Web Application for Getting Started with Machine Learning
Öz
Building machine learning models requires intensive coding and installation of certain software. This is frequently a barrier for beginners learning about machine learning. To overcome this situation, we present CodelessML, a reproducible web-based application designed for Machine Learning beginners due to its coding-free and installation-free design, published under Code Ocean capsule. It provides a common workflow that eases the process of building Machine Learning models and using the model for predictions. Using the Agile method, CodelessML was successfully built using Python, Anaconda, and Streamlit It. By using CodelessML, users can get a walkthrough and interactive experience of building machine learning through a simplified machine learning process: exploratory data analytics (EDA), modelling, and prediction. The impact of the software was evaluated based on feedback from 79 respondents, which showed that based on a 5-scale Likert, CodelessML received average ratings of 4.4 in accessibility, 4.3 in content, and 4.4 in functionality. CodelessML serves as an accessible entry point for learning machine learning, offering online, free, and reproducible features.
Anahtar Kelimeler
Machine learning, learning, barrier, software
Proje Numarası
01
Etik Beyan
Acknowledgement
Due to the scope and method of the study, ethics committee permission was not required.
Kaynakça
- Adeniran, A. O. (2019). Application of Likert scale’s type and Cronbach’s alpha analysis in an airport perception study. Scholar Journal of Applied Sciences and Research, 2(4), 1-5.
- Aeberhard, S., & Forina, M. (1991). Wine [Data set]. UCI Machine Learning Repository, 10, C5PC7J.
- Botchkarev, A. (2018). Performance metrics (Error Measures) in machine learning regression, forecasting and prognostics: Properties and typology. ArXiv.
- Botchkarev, A. (2019). A new typology design of performance metrics to measure errors in machine learning regression algorithms. Interdisciplinary Journal of Information Knowledge and Management, 14, 045–076. https://doi.org/10.28945/4184 .
- Burscher, B., Odijk, D., Vliegenthart, R., De Rijke, M., & De Vreese, C. H. (2014). Teaching the computer to code frames in news: comparing two supervised machine learning approaches to frame analysis. Communication Methods and Measures, 8(3), 190–206.
- Chapman, P., Clinton, J., Kerber, R., Khabaza, T., Reinartz, T., Shearer, C. & Wirth, R. (2000). CRISP-DM 1.0 - Step-by-step data mining guide. CRISP-DM Consortium.
- Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785-794. https://doi.org/10.1145/2939672.2939785.
- Dyck, J. (2018). Machine learning for engineering. In: Proceedings of the 23rd Asia and South Pacific Design Automation Conference. IEEE Press, pp. 422–427.
- Fabian, P. (2011). Scikit-learn: Machine learning in Python. Journal of machine learning research 12, 2825-2830, https://doi.org/10.1145/3369834.
- Ferguson, A. L. (2017). Machine learning and data science in soft materials engineering. Journal of Physics: Condensed Matter 30(4).
