Hierarchical Clustering

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

import numpy as np
from sklearn.datasets import make_blobs
from scipy.cluster.hierarchy import dendrogram, linkage
import matplotlib.pyplot as plt

X, _ = make_blobs(n_samples=50, centers=3, cluster_std=0.7, random_state=42)

Z = linkage(X, method="ward")

plt.figure(figsize=(8, 4))
dendrogram(Z, truncate_mode="level", p=5)
plt.title("Hierarchical clustering (Ward)")
plt.xlabel("sample index")
plt.ylabel("distance")
plt.show()

1
2
3
4
5
6
7
8

from sklearn.cluster import AgglomerativeClustering

clustering = AgglomerativeClustering(
    n_clusters=3,
    linkage="average",
    affinity="euclidean",
)
labels = clustering.fit_predict(X)