df.info()

df.describe()

# from sklearn.metrics import silhouette_score # k = [2, 3, 4, 5, 6, 7] # score=[] # for n_cluster in k: # kmeans = KMeans(n_clusters=n_cluster).fit(df_normalized) # score.append(silhouette_score(df_normalized,kmeans.labels_)) # plt.plot(k, score, 'o-') # plt.xlabel("Value for k") # plt.ylabel("Silhouette score") # plt.title('Silhouette Method') # plt.show()

df_clustered.to_csv('final_clustering.csv')