data-maker/README.md

## Introduction

This package is designed to generate synthetic data from a dataset from an original dataset using deep learning techniques

    - Generative Adversarial Networks
    - With "Earth mover's distance"

## Installation

    pip install git+https://hiplab.mc.vanderbilt.edu/git/aou/data-maker.git@release

## Usage

After installing the easiest way to get started is as follows (using pandas). The process is as follows:

Read about [data-transport on github](https://github.com/lnyemba/data-transport) or on [healthcareio.the-phi.com/git/code/transport](https://healthcareio.the-phi.com/git/code/transport.git)

**Train the GAN on the original/raw dataset**

1. We define the data sources

The sources will consists in source, target and logger20.

    import pandas as pd
    import data.maker
    import transport
    from transport import providers


The trainer will store the data on disk (for now) in a structured folder that will hold training models that will be used to generate the synthetic data.


**Generate a candidate dataset from the learned features**


    import pandas as pd
    import data.maker

    df  = pd.read_csv('sample.csv')
    id  = 'id'
    column = 'gender'
    context = 'demo'
    data.maker.generate(context=context,data=df,id=id,column=column,logs='logs')

## Limitations

GANS will generate data assuming the original data has all the value space needed:
    
- No new data will be created
    
        Assuming we have a dataset with an gender attribute with values [M,F]. 
            
        The synthetic data will not be able to generate genders outside [M,F]

- Not advised on continuous values

        GANS work well on discrete values and thus are not advised to be used.
        e.g:measurements (height, blood pressure, ...)
- For now will only perform on a single feature.

## Credits :

- [Chao Yan](chao.yan@vanderbilt.edu)
- [Ziqi Zhang](ziqi.zhang@vanderbilt.edu)
- [Brad Malin](b.malin@vanderbilt.edu)
- [Steve L. Nyemba](steve.l.nyemba@vumc.org)