Data Science with Python Unsupervised Learning Algorithms Flashcards

Which distance metric is most sensitive to outliers in clustering?

Answer: Euclidean distance

Euclidean distance squares differences, amplifying the effect of outliers compared to other metrics.

In DBSCAN, what is a 'border point'?

Answer: A point within epsilon of a core point but not itself a core point

A border point is reachable from a core point but has fewer than MinPts neighbors within epsilon.

Which Python library provides the `AgglomerativeClustering` class?

Answer: sklearn.cluster

`AgglomerativeClustering` is part of scikit-learn's `sklearn.cluster` module.

What does the cophenetic correlation coefficient measure in hierarchical clustering?

Answer: How faithfully the dendrogram preserves pairwise distances

The cophenetic correlation coefficient compares original pairwise distances to dendrogram distances to evaluate linkage quality.

When applying PCA, what does a negative eigenvalue indicate?

Answer: A numerical error, since covariance matrices always yield non-negative eigenvalues

Covariance matrices are positive semi-definite, so all eigenvalues must be ≥ 0; negatives indicate numerical precision errors.

Which linkage criterion in hierarchical clustering tends to produce compact, roughly equal-sized clusters?

Answer: Ward linkage

Ward linkage minimizes the total within-cluster variance, producing compact and balanced clusters.

In t-SNE, what does the perplexity parameter control?

Answer: The effective number of neighbors considered for each point

Perplexity in t-SNE balances attention between local and global structure by controlling the effective neighborhood size.