Practice knn and kmeans with heart-disease-dataset

This is the code to practice knn and k-means with heart disease dataset.
I used sklearn modules like sklearn.neighbors.KNeighborsClassifier, sklearn.cluster.KMeans and etc.

Dataset

Heart Disease Data

• Features(13): [ 'age', 'sex', 'cp', 'trestbps', 'chol', 'fbs', 'restecg', 'thalach', 'exang', 'oldpeak', 'slope', 'ca', 'thal']
• Target: diagnosis of heart disease (angiographic disease status)
  • integer valued from 0 (no presence) to 4 -> binarization: 0 means 'No heart disease', 1 means 'heart disease'
• For more information, visit a webpage

Experimental Result

1. knn

The result is evaluating the preformance of the models.

2. kmeans

To draw clusters in 2D, I used sklearn.decomposition.PCA to reduce dimension.
That is why the x and y axes are the principal component.

Environment

• python 3.7
• Used Modules - numpy, pandas, matplotlib, seaborn, scikit-learn
  
  

Detailed algorithm and experimental setup are explained in here.