Steve L. Nyemba 5 years ago
parent 3750d8b408
commit 766ef9694e

@ -1,5 +1,4 @@
## Introduction ## Introduction
---
This package is designed to generate synthetic data from a dataset from an original dataset using deep learning techniques This package is designed to generate synthetic data from a dataset from an original dataset using deep learning techniques
@ -7,12 +6,11 @@ This package is designed to generate synthetic data from a dataset from an origi
- With "Earth mover's distance" - With "Earth mover's distance"
## Installation ## Installation
---
pip install git+https://hiplab.mc.vanderbilt.edu/git/aou/data-maker.git@release pip install git+https://hiplab.mc.vanderbilt.edu/git/aou/data-maker.git@release
## Usage ## Usage
---
After installing the easiest way to get started is as follows (using pandas). The process is as follows: After installing the easiest way to get started is as follows (using pandas). The process is as follows:
1. Train the GAN on the original/raw dataset 1. Train the GAN on the original/raw dataset
@ -35,7 +33,6 @@ After installing the easiest way to get started is as follows (using pandas). Th
## Limitations ## Limitations
---
GANS will generate data assuming the original data has all the value space needed: GANS will generate data assuming the original data has all the value space needed:
@ -49,7 +46,6 @@ GANS will generate data assuming the original data has all the value space neede
e.g:measurements (height, blood pressure, ...) e.g:measurements (height, blood pressure, ...)
## Credits : ## Credits :
---
- [Ziqi Zhang](ziqi.zhang@vanderbilt.edu) - [Ziqi Zhang](ziqi.zhang@vanderbilt.edu)
- [Brad Malin](b.malin@vanderbilt.edu) - [Brad Malin](b.malin@vanderbilt.edu)

Loading…
Cancel
Save