The goal of this project is to create a supervised ML model to be able to predict risk of heart disases aith a self-diagnosis tool.
Historical dataset about heart diseases obtained from UCI Machine Learning Repository https://archive.ics.uci.edu/ml/datasets/Heart+Disease.
I used the following models in the Streamlit app:
-BernoulliNB : Bernoulli Naïve Bayes is a probabilistic classifier based on Bayes Theorem with a strong independence assumption between the features. It is suitable for classification of binomial data with discrete features.
-ExtraTreesClassifier : Ensemble method composed of a large number of decision trees, where the final decision is obtained taking into account the prediction of every tree.
As a background research, I analysed data from WHO on causes of mortality and showed percentages of causes in each country on a map.
Link to Tableau: https://public.tableau.com/app/profile/ildem.sanli/viz/CausesofMortality_2019/Dashboard1#1