Master 10 Popular Clustering Algorithms in Python with Scikit‑Learn

1. Clustering

Clustering (or cluster analysis) is an unsupervised learning task that automatically discovers natural groupings in data. It differs from supervised learning because it does not predict predefined classes; instead it finds structure in the feature space.

Clustering techniques are used when there is no target class, but the goal is to partition instances into natural groups.

Clustering helps with data analysis, market segmentation, anomaly detection, and feature engineering, though evaluating clusters is often subjective and may require domain expertise.

2. Clustering Algorithms

Many clustering algorithms exist, each using similarity or distance measures in feature space. Before applying them, scaling the data is recommended.

Some algorithms require specifying the number of clusters, others need a distance threshold. The scikit‑learn library provides a variety of implementations. Below are ten widely used algorithms:

Affinity Propagation

Agglomerative Clustering

BIRCH

DBSCAN

K‑Means

Mini‑Batch K‑Means

Mean Shift

OPTICS

Spectral Clustering

Gaussian Mixture Model

3. Algorithm Examples

Library Installation

sudo pip install scikit-learn

Verify the installation:

# check scikit-learn version
import sklearn
print(sklearn.__version__)

Dataset Generation

Create a synthetic binary classification dataset with two informative features:

# synthetic classification dataset
from numpy import where
from sklearn.datasets import make_classification
from matplotlib import pyplot
X, y = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
for class_value in range(2):
    row_ix = where(y == class_value)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

1. Affinity Propagation

Affinity Propagation exchanges real‑valued messages between data points until a set of exemplars and clusters emerges.

# Affinity Propagation clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.cluster import AffinityPropagation
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = AffinityPropagation(damping=0.9)
model.fit(X)
yhat = model.predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

2. Agglomerative Clustering

# Agglomerative clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.cluster import AgglomerativeClustering
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = AgglomerativeClustering(n_clusters=2)
yhat = model.fit_predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

3. BIRCH

BIRCH incrementally clusters multidimensional data points using a tree structure to balance memory and time constraints.

# BIRCH clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.cluster import Birch
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = Birch(threshold=0.01, n_clusters=2)
model.fit(X)
yhat = model.predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

4. DBSCAN

DBSCAN discovers clusters of arbitrary shape based on density, requiring only an epsilon and a minimum sample count.

# DBSCAN clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.cluster import DBSCAN
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = DBSCAN(eps=0.30, min_samples=9)
yhat = model.fit_predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

5. K‑Means

K‑Means partitions data into k groups by minimizing intra‑cluster variance.

# k-means clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.cluster import KMeans
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = KMeans(n_clusters=2)
model.fit(X)
yhat = model.predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

6. Mini‑Batch K‑Means

# mini-batch k-means clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.cluster import MiniBatchKMeans
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = MiniBatchKMeans(n_clusters=2)
model.fit(X)
yhat = model.predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

7. Mean Shift

# Mean Shift clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.cluster import MeanShift
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = MeanShift()
yhat = model.fit_predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

8. OPTICS

# OPTICS clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.cluster import OPTICS
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = OPTICS(eps=0.8, min_samples=10)
yhat = model.fit_predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

9. Spectral Clustering

# spectral clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.cluster import SpectralClustering
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = SpectralClustering(n_clusters=2)
yhat = model.fit_predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

10. Gaussian Mixture Model

# Gaussian Mixture Model clustering
from numpy import unique, where
from sklearn.datasets import make_classification
from sklearn.mixture import GaussianMixture
from matplotlib import pyplot
X, _ = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0, n_clusters_per_class=1, random_state=4)
model = GaussianMixture(n_components=2)
model.fit(X)
yhat = model.predict(X)
clusters = unique(yhat)
for cluster in clusters:
    row_ix = where(yhat == cluster)
    pyplot.scatter(X[row_ix, 0], X[row_ix, 1])
pyplot.show()

Summary

Clustering is an unsupervised problem that discovers natural groups in feature space.

There is no single best algorithm for all datasets; multiple methods should be explored.

The tutorial shows how to install scikit‑learn and use ten top clustering algorithms in Python, providing ready‑to‑run code and visual results.