Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ammahmoudi/covid-19-autoencoder
Using Autoencoder in keras as a nonlinear dimensionality reduction method to encode COVID-19 patients data
https://github.com/ammahmoudi/covid-19-autoencoder
autoencoder covid-19 deep-learning deep-neural-networks dimension-reduction keras-tensorflow machine-learning ml
Last synced: about 2 months ago
JSON representation
Using Autoencoder in keras as a nonlinear dimensionality reduction method to encode COVID-19 patients data
- Host: GitHub
- URL: https://github.com/ammahmoudi/covid-19-autoencoder
- Owner: ammahmoudi
- Created: 2023-10-30T18:02:07.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2023-10-30T18:09:42.000Z (about 1 year ago)
- Last Synced: 2023-10-30T19:26:15.372Z (about 1 year ago)
- Topics: autoencoder, covid-19, deep-learning, deep-neural-networks, dimension-reduction, keras-tensorflow, machine-learning, ml
- Language: Jupyter Notebook
- Homepage:
- Size: 93.8 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# COVID-19-Autoencoder
Using Autoencoder in keras as a nonlinear dimensionality reduction method.The goal is to reduce and encode patients data in a 2d space which could be seperated easily.
## Data Documnetation
We used Symptoms and COVID Presence (May 2020 data) dataset.COVID is a contagious disease. The purpose of this dataset is to provide symptoms as input and it should be able to predict if COVID is possibly present or not. It cannot be used for serious medical purposes.
For more information please read the [data documentation](https://www.kaggle.com/datasets/hemanthhari/symptoms-and-covid-presence).
## Code Explanation
- **0. Preparation**: A section that loads the dataset using pandas, encodes the categorical features using LabelEncoder, and splits the data into train and test sets.
- **1. DNN as nonlinear dimensionality reduction method**: A section that defines and trains an autoencoder using Keras, which compresses the data from 20 dimensions to 2 dimensions and then reconstructs the original data. The section also plots the encoded data using matplotlib.
