Publication: Performance Prediction of Jupyter Notebook in JupyterHub using Machine Learning
0
0
Issued Date
2018
Resource Type
File Type
application/pdf
Other identifier(s)
2-s2.0-85060037072
Rights Holder(s)
Scopus
Bibliographic Citation
2018 International Conference on Intelligent Informatics and Biomedical Sciences, ICIIBMS 2018. Vol , No. (2018), p.157-162
Suggested Citation
Prathanrat P., Polprasert C. Performance Prediction of Jupyter Notebook in JupyterHub using Machine Learning. 2018 International Conference on Intelligent Informatics and Biomedical Sciences, ICIIBMS 2018. Vol , No. (2018), p.157-162. doi:10.1109/ICIIBMS.2018.8550030 Retrieved from: https://hdl.handle.net/20.500.14740/5788
Author(s)
Abstract
In this paper, we employ machine learning to predict the performance of Jupyter notebook on JupyterHub. We show that the notebook's CPU profile, the notebook's RAM profile, number of users and average delay between cells are crucial features that impact the performance of the machine learning models to accurately predict the performance of Jupyter notebook in term of the response time. We characterize the performance of our model to predict the notebook's response time in terms of the mean absolute error (MAE) and mean absolute percentage error (MAPE). Results show that the random forest model yields strongest performance to predict the performance of Jupyter notebook with MAPE equal to 9.849% and MAE equal to 13.768 seconds. with r-square equal to 0.93. © 2018 IEEE.