How do I use the silhouette score in clustering?

What is the silhouette score and how is it used in clustering?

The silhouette score is a metric used to evaluate the quality of clustering. It measures how similar an object is to its own cluster compared to other clusters.

How do I calculate the silhouette score for my clustering results?

You can calculate the silhouette score using the formula: (b - a) / max(a, b), where 'a' is the average distance to points in the same cluster, and 'b' is the average distance to points in the nearest cluster.

Are there any libraries in Python that can help me compute the silhouette score?

Yes, you can use the sklearn library in Python. The silhouette_score function from sklearn.metrics can compute it easily for your clustering results.

Can you give me an example of how to implement this in code?

Sure! Here's a simple example:

from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
import numpy as np

# Sample data
X = np.array([[1, 2], [1, 4], [1, 0], [4, 2], [4, 4], [4, 0]])

# Clustering
kmeans = KMeans(n_clusters=2)
kmeans.fit(X)
labels = kmeans.labels_

# Calculate silhouette score
score = silhouette_score(X, labels)
print('Silhouette Score:', score)