NCA-GENL Data Analysis and Visualization Practice Question
A data scientist is analyzing a large corpus of LLM training documents and wants to visualize which topics appear together across documents. After computing TF-IDF vectors, they apply non-negative matrix factorization (NMF) to reduce dimensionality. Which visualization best shows the relationships between the discovered topics and the documents?
⚠ Common exam trap
The trap here is choosing a plot of model training diagnostics, such as reconstruction error, when the question asks about the structure of the factorized topic-document relationships.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
A heatmap of the document-topic matrix with documents on one axis and topics on the other
The document-topic matrix produced by NMF is a two-dimensional array of weights, and a heatmap is the natural visualization for such data. It lets the analyst see which topics are active in each document and which topics tend to co-occur, directly answering the question about topic relationships across the corpus.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A pie chart of the top 10 most frequent words in the corpus
Why it's wrong here
A pie chart of raw word frequencies ignores the topic structure produced by NMF and cannot show relationships between topics and documents. It also fails to represent multi-topic documents, since pie slices are parts of a single whole, making it unsuitable for the matrix-style data the factorization produces.
- ✓
A heatmap of the document-topic matrix with documents on one axis and topics on the other
Why this is correct
A heatmap of the document-topic matrix directly displays the NMF weights, showing which topics are active in each document and revealing co-occurrence patterns across the corpus. It preserves the two-dimensional structure of the factorization and makes it easy to spot documents that mix multiple topics, which is exactly the relationship the data scientist wants to explore.
- ✗
A line chart of the reconstruction error across NMF iterations
Why it's wrong here
A line chart of reconstruction error shows optimization convergence, not topic-document relationships. It tells the data scientist whether the factorization is stable, but it provides no information about which topics appear together across documents, so it does not answer the stated analytical question.
- ✗
A scatter plot of documents positioned by their first two TF-IDF principal components
Why it's wrong here
A PCA scatter plot of raw TF-IDF vectors shows document similarity in a variance-maximizing projection, but it does not incorporate the NMF topic weights and therefore cannot reveal which discovered topics co-occur. It also tends to emphasize dominant lexical variation rather than the interpretable topic structure NMF provides.
About these practice questions
Courseiva writes every NCA-GENL question from scratch — 367 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official NVIDIA exam blueprint
This NCA-GENL practice question is part of Courseiva's free NVIDIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the NCA-GENL exam.