What does a clustering task look like and what algorithms do you know?

The task of clustering is to group data objects in such a way that objects within the same group (cluster) are as similar as possible to each other, and objects from different groups are as different as possible. This is an unsupervised learning task where class labels are not known in advance.

Main clustering algorithms:

• K-means — divides data into K clusters, minimizing intra-cluster distance. Requires pre-specifying the number of clusters.
• Hierarchical clustering — builds a tree of clusters (dendrogram), allowing the selection of the splitting level.
• DBSCAN — density-based method, identifies clusters based on point density, works well with noise and clusters of arbitrary shape.
• Mean Shift — searches for areas with maximum point density, does not require pre-specifying the number of clusters.

Example of using K-means in Python:

from sklearn.cluster import KMeans
import numpy as np

X = np.array([[1, 2], [1, 4], [1, 0],
              [10, 2], [10, 4], [10, 0]])

kmeans = KMeans(n_clusters=2, random_state=0).fit(X)
print(kmeans.labels_)