ML_Classifiers_CVD

This repository is a project to predict CVD instance using the following dataset:

https://www.kaggle.com/datasets/sulianova/cardiovascular-disease-dataset

I am comparing the ability of multiple machine learning algorithms (implemented from scratch) to predict CVD instance, both with a basic approach (utilizing the dataset as-is and without adjusting parameters), as well as after some basic attempts at improving performance.

This project mostly serves as practice in implementing ML algorithms. Later I plan to expand on this to integrate other datasets (omics data such as transcriptomics and genotyping).

Exploratory data analysis: A brief look at the features within the dataset. EDA.ipynb

Logistic regression: Logistic_Regression.ipynb

SVM: SVM.ipynb