DeepCoreML 0.4.0

A collection of Machine Learning techniques for data management, engineering and augmentation.

DeepCoreML is a collection of Machine Learning techniques for data management, engineering, and augmentation. More specifically, DeepCoreML includes modules for:

• Data management
• Text data preprocessing
• Text representation, vectorization, embeddings
• Dimensionality reduction
• Generative modeling
• Imbalanced datasets

Licence: Apache License, 2.0 (Apache-2.0)

Dependencies:NumPy, pandas, Natural Language Toolkit (nltk), Matplotlib, seaborn, Gensim, joblib, Reversible Data Transforms(RDT), bs4, scikit-learn, imblearn, pytorch, transformers, Synthetic Data Vault

GitHub repository: https://github.com/lakritidis/DeepCoreML

Publications:

• L. Akritidis, P. Bozanis, "A Clustering-Based Resampling Technique with Cluster Structure Analysis forSoftware Defect Detection in Imbalanced Datasets", Information Sciences, vol. 674, pp. 120724, 2024.
• 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), pp. 444-451, 2023, 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.