Some Important Questions
Part-A
1. How do you import a CSV file into R?
2. What is the difference between NA and NULL in R?
3. Describe how to use a boxplot to identify outliers in a dataset.
4. What is the purpose of the summary() function in R?
5. What is the primary concept behind the k-nearest neighbors (kNN) algorithm?
6. Why is kNN considered a lazy learning algorithm?
7. How is distance calculated in the kNN algorithm?
8. Define the term 'classification' in the context of machine learning.
9. What are the advantages and disadvantages of using the kNN algorithm?
10. What is the Naive Bayes classifier, and why is it called "naive"?
11. What is the Laplace estimator, and why is it used in Naive Bayes?
12. How does Naive Bayes handle missing data?
13. Describe the role of conditional probability in Naive Bayes.
14. What are the limitations of the Naive Bayes algorithm?
15. How does the C5.0 algorithm differ from the traditional decision tree algorithms?
16. Define "classification rules" in the context of decision trees.
17. What is the difference between the "divide and conquer" approach and the "separate and
conquer" approach?
18. How does the "One Rule" (OneR) algorithm work?
19. What are the advantages of using decision trees for classification?
20. What is simple linear regression, and how is it used in numeric prediction?
21. What is the purpose of the R² (R-squared) statistic in regression analysis?
22. How is the Ordinary Least Squares (OLS) method used in linear regression?
23. What is a correlation matrix, and how is it useful in regression analysis?
24. What is the difference between linear regression and regression trees?
Part-B
1. Explain the different data structures in R (vectors, lists, matrices, arrays, and data frames)
with examples.
2. Discuss the process of importing, cleaning, and exploring a dataset in R. Include the
methods for handling missing data.
3. Describe the steps involved in implementing the k-nearest neighbors (kNN) algorithm.
Include a discussion on data preparation, model training, and performance evaluation.
4. Discuss the process of training and evaluating a Naive Bayes model, including handling
categorical and continuous features.
5. Explain the process of building and evaluating a decision tree model using the C5.0
algorithm. Include a discussion on pruning and boosting techniques.
6. Discuss the process of building, training, and evaluating a multiple linear regression
model. Include steps such as data preparation, feature selection, and performance metrics.
7. Explain how regression trees and model trees are used for numeric prediction. Compare
them with linear regression in terms of their approach and applications.