Machine learning implementation in Python: Performance analysis of different libraries
Student, Computer Science, University of Virginia, USA.
Review Article
World Journal of Advanced Research and Reviews, 2023, 20(01), 1390-1398
Article DOI: 10.30574/wjarr.2023.20.1.2144
Publication history:
Received on 29 August 2023; revised on 17 October 2023; accepted on 19 October 2023
Abstract:
This research paper presents a comprehensive performance analysis of popular machine learning libraries in Python. We compare the efficiency, accuracy, and scalability of scikit-learn, TensorFlow, PyTorch, and XGBoost across various machine learning tasks, including classification, regression, and clustering. The study evaluates these libraries using standardized datasets and benchmarks, considering factors such as execution time, memory usage, and model performance. Our findings provide valuable insights for data scientists and developers in selecting the most appropriate library for their specific machine learning projects. The results demonstrate that while scikit-learn excels in simplicity and ease of use for traditional machine learning tasks, TensorFlow and PyTorch offer superior performance for deep learning applications. XGBoost shows remarkable efficiency in gradient boosting tasks. This analysis aims to guide practitioners in making informed decisions when choosing machine learning libraries for their Python-based projects.
Keywords:
Machine Learning; Python; Performance Analysis; scikit-learn; TensorFlow; PyTorch; XGBoost
Full text article in PDF:
Copyright information:
Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0