Skip to main content

Conditional GAN for Tabular Data

Project description

“DAI-Lab” An open source project from Data to AI Lab at MIT.

PyPI Shield Travis CI Shield

CTGAN

Implementation of our NeurIPS paper Modeling Tabular data using Conditional GAN.

CTGAN is a GAN-based data synthesizer that can generate synthetic tabular data with high fidelity.

Overview

Based on previous work (TGAN) on synthetic data generation, we develop a new model called CTGAN. Several major differences make CTGAN outperform TGAN.

  • Preprocessing: CTGAN uses more sophisticated Variational Gaussian Mixture Model to detect modes of continuous columns.
  • Network structure: TGAN uses LSTM to generate synthetic data column by column. CTGAN uses Fully-connected networks which is more efficient.
  • Features to prevent mode collapse: We design a conditional generator and resample the training data to prevent model collapse on discrete columns. We use WGANGP and PacGAN to stabilize the training of GAN.

Install

Requirements

CTGAN has been developed and tested on Python 3.5, 3.6 and 3.7

Install from PyPI

The recommended way to installing CTGAN is using pip:

pip install ctgan

This will pull and install the latest stable release from PyPI.

Install from source

Alternatively, you can clone the repository and install it from source by running make install on the stable branch:

git clone git@github.com:DAI-Lab/CTGAN.git
cd CTGAN
git checkout stable
make install

Install for Development

If you want to contribute to the project, a few more steps are required to make the project ready for development.

Please head to the Contributing Guide for more details about this process.

Quickstart

In this short tutorial we will guide you through a series of steps that will help you getting started with CTGAN.

Data format

The data is a space (or tab) separated file. For example,

100        A        True
200        B        False
105        A        True
120        C        False
...        ...        ...

Metafile describes each column as one line. C or D at the beginning of each line represent continuous column or discrete column respectively. For continuous column, the following two number indicates the range of the column. For discrete column, the following strings indicate all possible values in the column. For example,

C    0    500
D    A    B    C
D    True     False

Run model

USAGE:
    python3 ctgan/cli.py [flags]
flags:
  --data: Filename of training data.
    (default: '')
  --max_epoch: Epoches to train.
    (default: '100')
    (an integer)
  --meta: Filename of meta data.
    (default: '')
  --model_dir: Path to save model.
    (default: '')
  --output: Output filename.
    (default: '')
  --sample: Number of rows to generate.
    (default: '1000')
    (an integer)

Example

It's easy to try our model using example datasets.

git clone https://github.com/DAI-Lab/ctgan
cd ctgan
python3 -m ctgan.cli --data examples/adult.dat --meta examples/adult.meta

What's next?

For more details about CTGAN and all its possibilities and features, please check the documentation site.

Citing TGAN

If you use CTGAN, please cite the following work:

  • Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante, Kalyan Veeramachaneni. Modeling Tabular data using Conditional GAN. NeurIPS, 2019.
@inproceedings{xu2019modeling,
  title={Modeling Tabular data using Conditional GAN},
  author={Xu, Lei and Skoularidou, Maria and Cuesta-Infante, Alfredo and Veeramachaneni, Kalyan},
  booktitle={Advances in Neural Information Processing Systems},
  year={2019}
}

History

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for ctgan, version 0.1.0.dev0
Filename, size File type Python version Upload date Hashes
Filename, size ctgan-0.1.0.dev0-py2.py3-none-any.whl (10.6 kB) File type Wheel Python version py2.py3 Upload date Hashes View hashes
Filename, size ctgan-0.1.0.dev0.tar.gz (54.1 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page