DBSCAN clustering in ML Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding DBSCAN Core Concepts

Which statement best describes the role of the epsilon (eps) parameter in DBSCAN clustering?

A It sets the minimum number of clusters to find in the data.

B It defines the maximum distance between two points to be considered neighbors.

C It controls the maximum number of iterations during clustering.

D It specifies the initial number of centroids for clustering.

❓ Predict Output

intermediate

DBSCAN Cluster Labels Output

What is the output of the following code snippet?

ML Python

from sklearn.cluster import DBSCAN
import numpy as np

X = np.array([[1, 2], [2, 2], [2, 3], [8, 7], [8, 8], [25, 80]])
model = DBSCAN(eps=1.5, min_samples=2)
labels = model.fit_predict(X)
print(labels.tolist())

A [0, 0, 0, 1, 1, -1]

B [0, 0, 0, 1, 1, 1]

C [0, 0, 1, 1, 1, -1]

D [-1, -1, -1, 0, 0, 1]

❓ Hyperparameter

advanced

Effect of Changing min_samples in DBSCAN

What is the most likely effect of increasing the min_samples parameter in DBSCAN while keeping eps constant?

A The eps parameter will automatically adjust to compensate.

B Clusters will merge into fewer larger clusters.

C The algorithm will run faster due to fewer clusters.

D More points will be labeled as noise because clusters require more neighbors.

❓ Metrics

advanced

Evaluating DBSCAN Clustering Quality

Which metric is most appropriate to evaluate the quality of clusters produced by DBSCAN when true labels are unknown?

A Cross-Entropy Loss

B Accuracy

C Silhouette Score

D Mean Squared Error

🔧 Debug

expert

Identifying the Cause of Unexpected DBSCAN Output

Given the code below, why does the DBSCAN model assign all points to noise (-1)?

ML Python

from sklearn.cluster import DBSCAN
import numpy as np

X = np.array([[1, 2], [2, 2], [2, 3], [8, 7], [8, 8], [25, 80]])
model = DBSCAN(eps=0.5, min_samples=2)
labels = model.fit_predict(X)
print(labels.tolist())

A The eps value is too small, so no points have enough neighbors to form clusters.

B The min_samples value is too low, causing all points to be noise.

C The input data must be normalized before applying DBSCAN.

D DBSCAN requires at least 10 points to form clusters.