tanav2202 / Tabular-Data-Generation

Synthetic Data Generation End to End

Tabular Data Generation

Pre-requisite: should have python libraries used in code installed in the system's python environment

Note: Model used is a test model similar to actual one used in research by me but not the same

How to Run:

Clone the project

  git clone https://github.com/tanav2202/Tabular-Data-Generation

Go to the project directory

  cd Tabular-Data-Generation

Run the container and build command.

  docker compose up --build

Local Demo (of Backend System) :

1. Visit http://127.0.0.1:5000/docs to see all the CRUD operations inside the API

2. Screen should look like this:

3. Execute the DELETE operation to remove pre-existing files (if present)

4. Execute the PUT (/load data) opertation to add .csv file then execute

Dataset used for this model: https://www.kaggle.com/datasets/brunogrisci/breast-cancer-gene-expression-cumida

6. Then use GET (/train) to run the model
7. output.csv file is generated after the model is run.
8. To download use the last GET (/output) operation