silhouette_score.py

"""
MIT License
Copyright (c) 2017-2020 Packt, grouns0state
https://github.com/PacktPublishing/Artificial-Intelligence-with-Python/blob/master/LICENSE
"""
from sklearn.cluster import KMeans
from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs


X, _ = make_blobs(n_samples=1000, centers=6, n_features=5, random_state=0)

scores = []
values = np.arange(2, 10)

for num_clusters in values:
    kmeans = KMeans(init='k-means++', n_clusters=num_clusters, n_init=10)
    kmeans.fit(X)
    score = metrics.silhouette_score(X, kmeans.labels_,
                                     metric='euclidean', sample_size=len(X))
    print("\nNumber of clusters =", num_clusters)
    print("Silhouette score =", score)

    scores.append(score)

plt.figure()
plt.bar(values, scores, width=0.7, color='black', align='center')
plt.title('Silhouette score vs number of clusters')
plt.show()

num_clusters = np.argmax(scores) + values[0]
print('Optimal number of clusters =', num_clusters)