https://github.com/rcamino/multi-categorical-gans

Code for the paper "Generating Multi-Categorical Samples with Generative Adversarial Networks"
https://github.com/rcamino/multi-categorical-gans

Last synced: about 2 months ago
JSON representation

Code for the paper "Generating Multi-Categorical Samples with Generative Adversarial Networks"

• Host: GitHub
• URL: https://github.com/rcamino/multi-categorical-gans
• Owner: rcamino
• License: bsd-3-clause
• Created: 2018-07-02T11:59:17.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2023-07-06T21:31:52.000Z (about 1 year ago)
• Last Synced: 2024-04-08T02:26:42.907Z (5 months ago)
• Language: Python
• Size: 55.7 KB
• Stars: 50
• Watchers: 4
• Forks: 15
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-data-synthesis - MC-MedGAN - Multi-Categorical GANs - [Paper](https://arxiv.org/pdf/1807.01202.pdf) (Data-driven methods / Tabular)

README

        
# IMPORTANT UPDATE!

Please consider checking the [code](https://github.com/rcamino/imputation-dgm) for my new work [Improving Missing Value Imputation with Deep Generative Models](https://arxiv.org/abs/1902.10666).

# Multi-Categorical GANs

Code for the paper [Generating Multi-Categorical Samples with Generative Adversarial Networks](https://arxiv.org/abs/1807.01202)

## Pre-requisites

The project was developed using python 3.6.7 with the following packages:

- future==0.17.1

- numpy==1.16.0

- scikit-learn==0.20.2

- scipy==1.2.0

- torch==1.0.0

Installation with pip:

```bash

pip install -r requirements.txt

```

## Contents

- [Datasets](multi_categorical_gans/datasets)

  - [Synthetic data generation](multi_categorical_gans/datasets/synthetic/)

  - [US Census 1990](multi_categorical_gans/datasets/uscensus/)

- [Methods](multi_categorical_gans/methods)

  - [ARAE and MC-ARAE](multi_categorical_gans/methods/arae/)

  - [MedGAN and MC-MedGAN](multi_categorical_gans/methods/medgan/)

  - [MC-Gumbel](multi_categorical_gans/methods/mc_gumbel/)

  - [MC-WGAN-GP](multi_categorical_gans/methods/mc_wgan_gp/)

- [Metrics](multi_categorical_gans/metrics)

## Changelog

- 2019-01-28: changed to Python 3 as suggested (and still compatible with 2.7 ... I hope).

- 2018-07-25: now we use WGAN-GP for ARAE following the author updates.