Metadata-Version: 2.1
Name: ctdgan
Version: 0.1.1
Summary: A Generative Adversarial Network for synthesizing artificial tabular data.
Home-page: https://github.com/lakritidis/ctdGAN
Author: Leonidas Akritidis
Author-email: lakritidis@ihu.gr
Maintainer: Leonidas Akritidis
Maintainer-email: lakritidis@ihu.gr
License: Apache
Keywords: ctdGAN,GAN,Generative Adversarial Network,imbalanced data,tabular data,deep learning
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: matplotlib
Requires-Dist: seaborn
Requires-Dist: sdv
Requires-Dist: tqdm
Requires-Dist: joblib
Requires-Dist: torch>=2.0.0
Requires-Dist: scikit-learn>=1.4.0
Requires-Dist: rdt<2.0,>=1.3.0

<p>ctdGAN is a Conditional Generative Adversarial Network for alleviating class imbalance in tabular datasets. The model is based on an initial space partitioning step that assigns cluster labels to the input samples. These labels are used to synthesize samples via a probabilistic sampling mechanism. ctdGAN optimizes a loss function that is sensitive to both cluster and class mis-predictions, rendering the modelcapable of generating samples in subspaces that resemble those of the original data distribution.</p><p><b>Licence:</b> Apache License, 2.0 (Apache-2.0)</p><p><b>Dependencies:</b>NumPy, pandas, Matplotlib, seaborn, joblib, Reversible Data Transforms(RDT), scikit-learn, pytorch, Synthetic Data Vault</p><p><b>GitHub repository:</b> <a href="https://github.com/lakritidis/ctdGAN">https://github.com/lakritidis/ctdGAN</a></p>
