This is an implementation of principal component analysis algorithm for dimensionality reduction, running purely in the browser using TensorFlow.js. In this project, we apply PCA to higher dimensional data and present multiple visualizations to generate intuition while viewing the data in lower dimensional space.
- It has been shown how adding an outlier can have significant effect on the principal components generated.
- Kernel PCA has been demonstrated using RBF kernel on the moon dataset.
- Demonstrate results on applying PCA to iris dataset.
- Overall, It lets a user visualize the different aspects of PCA.
To run it locally, you must install Python 3 or above and run the following command at the repository's root to set up a python server.
python -m http.serverYou can then browse to localhost:8000 and select index.html to view the application.
- Ankit Biswas
- Sahil Goyal
- Shashank Gupta
- Yash Vardhan Sharma