Introduction to Clustering (K-Means)

Clustering is an unsupervised learning method where the goal is to group similar data points into clusters without using labels.

One of the most popular algorithms for clustering is K-Means.

---

1. Choose k – the number of clusters.
2. Initialize k cluster centers randomly.
3. Assign points to the nearest center.
4. Update centers to be the mean of their assigned points.
5. Repeat steps 3–4 until the cluster assignments stop changing.

K-Means tries to minimize the distance between points in the same cluster and their cluster center.

---

• You want to group data by similarity without predefined labels.
• Your dataset has numerical features and a moderate number of dimensions.
• You suspect there are clear groups in the data.

---

Copy
# Install scikit-learn in Jupyter Lite
import piplite
await piplite.install('scikit-learn')

from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

# Load data (only first two features for visualization)
iris = load_iris()
X = iris.data[:, :2]

# Apply K-Means
kmeans = KMeans(n_clusters=3, random_state=42)
labels = kmeans.fit_predict(X)

# Plot clusters
plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', edgecolor='k')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1],
            s=200, c='red', marker='X', label='Centers')
plt.xlabel(iris.feature_names[0])
plt.ylabel(iris.feature_names[1])
plt.title("K-Means Clustering (Iris)")
plt.legend()
plt.show()

---

• Unsupervised learning means no labels are provided.
• K-Means groups data into k clusters by minimizing within-cluster distances.
• Choosing the right value of k is critical — often done via the elbow method.

In the next lesson, we’ll look at Model Selection and Cross-Validation to ensure our models generalize well to unseen data.