DSE Basic 4 — Questions and Answers
Question 1: Which of the following best describes a 'data pipeline'?
- A single SQL query
- A series of automated steps to move and transform data (Correct answer)
- A visualization dashboard
- A type of machine learning model
Correct answer: A series of automated steps to move and transform data
A data pipeline automates the flow of data through ingestion, transformation, and loading steps.
Question 2: What does the term 'null hypothesis' mean in statistical testing?
- The hypothesis that will definitely be rejected
- The assumption that there is no effect or difference (Correct answer)
- The alternative hypothesis
- The final conclusion of the test
Correct answer: The assumption that there is no effect or difference
The null hypothesis assumes no effect or difference exists; statistical tests try to find evidence against it.
Question 3: Which metric measures the proportion of actual positives correctly identified by a classifier?
- Precision
- Recall (Correct answer)
- F1 Score
- Accuracy
Correct answer: Recall
Recall (sensitivity) is TP / (TP + FN), measuring how well the model finds all true positives.
Question 4: What is the purpose of a train/test split in machine learning?
- To increase the size of the dataset
- To evaluate model performance on unseen data (Correct answer)
- To remove noisy features
- To speed up training time
Correct answer: To evaluate model performance on unseen data
Splitting data ensures the model is evaluated on data it has never seen, giving an honest performance estimate.
Question 5: A correlation coefficient of -0.9 indicates:
- No relationship
- Weak positive relationship
- Strong positive relationship
- Strong negative relationship (Correct answer)
Correct answer: Strong negative relationship
A correlation of -0.9 is close to -1, indicating a strong negative linear relationship between two variables.
Question 6: Which of the following is NOT a common data cleaning task?
- Handling missing values
- Removing duplicate rows
- Training a neural network (Correct answer)
- Fixing inconsistent formatting
Correct answer: Training a neural network
Training a neural network is a modeling step, not a data cleaning task like imputation or deduplication.
Question 7: What does ETL stand for in data engineering?
- Evaluate, Test, Load
- Extract, Transform, Load (Correct answer)
- Export, Transfer, Log
- Execute, Train, Launch
Correct answer: Extract, Transform, Load
ETL stands for Extract, Transform, Load — the standard process of moving data from source systems to a data warehouse.
DSE Basic 4
Which of the following best describes a 'data pipeline'?