A collection of Machine Learning techniques for data management, engineering and augmentation.
Project description
DeepCoreML is a collection of Machine Learning techniques for data management, engineering, and augmentation. More specifically, DeepCoreML includes modules for:
- Dataset management
- Text data preprocessing
- Text representation, vectorization, embeddings
- Dimensionality reduction
- Generative modeling
- Imbalanced datasets
Licence: Apache License, 2.0 (Apache-2.0)
Dependencies: scikit-learn, imblearn, pytorch, numpy, pandas, transformers, nltk, matplotlib
GitHub repository: https://github.com/lakritidis/DeepCoreML
Publications:
- L. Akritidis, A. Fevgas, M. Alamaniotis, P. Bozanis, "Conditional Data Synthesis with Deep Generative Models for Imbalanced Dataset Oversampling", In Proceedings of the 35th IEEE International Conference on Tools with Artificial Intelligence (ICTAI), to appear, 2023.
- L. Akritidis, P. Bozanis, "A Multi-Dimensional Survey on Learning from Imbalanced Data", Chapter in Machine Learning Paradigms - Advances in Theory and Applications of Learning from Imbalanced Data, to appear, 2023.
- L. Akritidis, P. Bozanis, "Low Dimensional Text Representations for Sentiment Analysis NLP Tasks", Springer Nature (SN) Computer Science, vol. 4, no. 5, 474, 2023.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
DeepCoreML-0.3.4.tar.gz
(43.4 kB
view hashes)