Clustering_model_evaluation.py

from sklearn.cluster import KMeans

wcss = []
silhouette_scores = []
calinski_harabasz_scores = []
davies_bouldin_scores = []

for i in range(2, 7):
    kmeans = KMeans(n_clusters = i, init = 'k-means++', random_state = 42)
    y_pred = kmeans.fit_predict(X)

    wcss.append(kmeans.inertia_)
    silhouette_scores.append(silhouette_score(X,y_pred))
    calinski_harabasz_scores.append(calinski_harabasz_score(X,y_pred))
    davies_bouldin_scores.append(davies_bouldin_score(X,y_pred))
    
   
    print(f'WCSS At k = {i}: ',kmeans.inertia_)
    print('Silhouette Cofficient: ',silhouette_score(X,y_pred))
    print('Calinski-Harabasz Index: ',calinski_harabasz_score(X,y_pred))
    print('Davies-Bouldin Index: ',davies_bouldin_score(X,y_pred))
    print('--------------------------------')