DWDM
IMPORTANT QUESTIONS
1. Explain the general approaches for solving a classification problem.
2. Consider the following dataset (D) of transactions in a retail store
and Explain how Sampling technique work to pick a random sample S from a given dataset D to search
for frequent item sets in a sample data set S instead of given data set D.
3. Explain FP-growth technique to find frequent item sets without candidate generation using the
following transaction and show the Steps to draw the FP tree.
4. Discuss Compact representation of Frequent Item set and its types
----------------------------------------------------------------------------------------------------------------------------------
5. Explain the concept of Bayesian Belief Networks and their components with an example.
6. Consider the below dataset and explain how Information Gain helps (or works) for selecting the best
attribute to split the data at each node in decision tree construction?
7. Explain the general approaches to solving a classification problem.
8. Compare and contrast the Naive Bayes Classifier and Bayesian Belief Networks.
9. Given a decision tree, you have the option of (a) converting the decision tree to rules and then
pruning the resulting rules, or (b) pruning the decision tree and then converting the pruned tree to
rules. What advantage does (a) have over (b)?
10. Consider the following dataset with two features (height and weight) and two classes (athlete and
non-athlete).
Assume that the new data instance is Height = 165 cm, Weight = 68 kg and the value of k is 3
Calculate the following using KNN
1. Calculate the distance between the new instance and all training instances.
2. Select the 𝑘 nearest neighbours.
3. Determine the most common class among these neighbours.
4. Classify the new data instance is of which class.
---------------------------------------------------------------------------------------------------------------------------------
11. Discuss the K-Means algorithm and its basic working principle.
12. Consider the following data set, and make your assumption to randomly choose the initial
centroids for K = 2
Use K-Means clustering and calculate the distances between each point and the centroids, then find
the final Clusters.
13. Describe and give examples of hierarchical clustering methods .
14. Briefly describe and give examples of hierarchical clustering methods
15. Using the below given small dataset with five points and their coordinates (x, y), perform
Agglomerative Hierarchical Clustering with single-linkage criteria. Show the steps involved in forming
clusters.
16. Compare the K-Means algorithm and the PAM algorithm in terms of their approach to clustering
and handling outliers.
