from sklearn import metrics

import matplotlib.pyplot as plt

from sklearn.cluster import KMeans

from sklearn import preprocessing

import pandas as pd

data = pd.read_csv('tae.csv')

info_scaled = preprocessing.scale(data)

X = info_scaled

score = []

for i in range(2, 18):

    km = KMeans(n_clusters=i, init='k-means++', n_init=10, max_iter=300, random_state=0)

    km.fit(X)

    score.append(metrics.silhouette_score(X, km.labels_, metric='euclidean'))

plt.figure(dpi=150)

plt.plot(range(2, 18), score, marker='o')

plt.xlabel('Number of clusters')

plt.ylabel('silhouette_score')

plt.show()