Normalization MCQ with answers in DBMS 19

Normalization in DBMS, solved exercises in DBMS, lossless join decomposition, dependency preserving decomposition, bcnf decomposition

RDBMS MCQ solved quiz and answers

1. Let us assume that a relation R (A, B, C, D, E) with set of functional dependencies F = {A → BC, C → D} is decomposed into relations R1 (A, B, C) and R2 (A, D, E). This decomposition is ___________.

a) Lossless join decomposition

b) Dependency preserving decomposition

c) Not a dependency preserving decomposition

d) Lossy decomposition

Answer: (a) and (c) Common attribute between R1 and R2 is A, and, attribute A determines all attributes of R1. Hence, it is a lossless decomposition. It is not a dependency preserving decomposition because the FD C → D is lost. Lossless join decomposition Decomposition of relation R into R1 and R2 is said to be lossless join decomposition if one of the following holds; (R1 ∩ R2) → R1 (R1 ∩ R2) → R2 Dependency preserving decomposition If a relation R with set F of functional dependencies is decomposed into relations R1, R2, R3, …, Ri then the closure of set of functional dependencies for these relations should satisfy the following;  (F1 U F2 U F3 U … U Fi)+ = F+  That is the closure of union of set of functional dependencies of relations R1, R2, …, Ri should be equal to the closure of set of functional dependencies F of R. In other words, all the functional dependencies in (F1 U F2 U F3 U … U Fi)+ should be in F+ also.

 

2. Let us assume that a relation R (A, B, C, D, E, F, G, H) with set of functional dependencies F = {AB → E, C → D, D → E, FG → A} is decomposed into relations R1(ABE), R2(CD), R3(FGA) and R4(BCFGH). The decomposition _____.

a) is resulted in all BCNF relations

b) is dependency preserving decomposition

c) is not a dependency preserving decomposition

d) is lossless decomposition

Answer: (a) and (c) R1(ABE), R2(CD), R3(FGA) and R4(BCFGH). Keys are underlined. All relations are in BCNF. The functional dependency D → E is lost. Hence, decomposition of R into R1, R2, R3 and R4 is not a dependency preserving decomposition.

 

3. Consider a relation R(A, B, C, D, E) with the set of functional dependencies F = {A → B, B → E, E → A}. Relation R is in ____.

a) Un-normalized form

b) Third Normal Form

c) Boyce-Codd Normal Form

d) Domain Key Normal Form

Answer: (b) 3NF The candidate keys for R are ACD, BCD, and ECD. No non-key dependencies found in R. Hence, relation R is in third normal form.

 

************************

Related posts:

• Go to Multiple Choice Questions in DBMS home

• Go to Normalization - MCQs page

• Go to General Mixed Quiz in all topics of DBMS page

• Go to Advanced DBMS Concepts page

Quiz questions with answers on DBMS introduction concepts

How many keys a leaf node can have in a B+ tree in DBMS

Find the keys of relation in DBMS

Check whether the decomposition is dependency preserving or not

Is the decomposition a lossless join decomposition

List down rules for dependency preserving and lossless join decomposition

Machine Learning Multiple Choice Questions and Answers 22

Top 3 Machine Learning Quiz Questions with Answers explanation, Interview questions on machine learning, quiz questions for data scientist answers explained, machine learning exam questions, question bank in machine learning, classification, decision tree, two class classification, bayes net

Machine learning MCQ - Set 22

 

1. Which of the following classifiers can perfectly classify the following data?

a) Decision tree

b) Logistic regression

c) Gaussian Naïve Bayes

d) All of the above

Click here to view answer

Ans : (a)

Answer: (a) Decision tree Decision Tree only. Decision trees of depth 2 which first splits on X and then on Y will perfectly classify it. Logistic regression leads to linear decision boundaries, hence cannot classify this data perfectly. Due to conditional independence requirement, it is not possible to fit a Gaussian that peaks at the labels of only one class and has no covariance between features, so Gaussian Naive Bayes cannot classify this data perfectly.

 

2. Which is the correct joint distribution for the following Bayesian net?

a) P(A,B,C,D,E) = P(E)P(C)P(D|E)P(A|C)P(B|D,E)

b) P(A,B,C,D,E) = P(A)P(B)P(C|A)P(D|A,B,C)P(E|D)

c) P(A,B,C,D,E) = P(A)P(B)P(C)P(D)P(E)P(E|A,B,C,D)

d) P(A,B,C,D,E) = P(A)P(B)P(D|A,B,C)P(E|D)

Click here to view answer

Ans : (b)

Answer: (b) P(A,B,C,D,E) = P(A)P(B)P(C|A)P(D|A,B,C)P(E|D) A Bayesian network is a directed acyclic graph in which each edge corresponds to a conditional dependency, and each node corresponds to a unique random variable.

 

3. For a two class classification problem, which among the following are true?

a) In case both the covariance matrices are spherical and equal, the within class variance term has an effect on the LDA derived direction.

b) In case both the covariance matrices are spherical and equal, the within class variance term has no effect on the LDA derived direction.

c) In case both the covariance matrices are spherical but unequal, the within class variance term has an effect on the LDA derived direction.

d) In case both the covariance matrices are spherical but unequal, the within class variance term has no effect on the LDA derived direction.

Click here to view answer

Ans : (b) and (d)

Answer: (b) and (d) It is easy to see that if the covariance matrix for a particular class is spherical, then the ‘within class variance’ is the same along all directions, and hence we can ignore this component and focus solely on the ‘between class variance’ (i.e., identify the direction along which the between class variance is maximised). Two class classification A classification problem with two classes is referred as two class classification or binary classification problem. It is used to predict one of two possible outcomes.

 

**********************

Related links:

• Machine learning MCQ home page

• Machine learning TRUE / FALSE questions home page

• Computer science engineering quiz questions and answers page

• Data Warehousing and Data Mining MCQ with answers home
  

Which classification algorithm can perfectly classify the given data

Define two class classification

What is the effect of 'within class variance' on LDA derived direction if both the covariance matrices are spherical

How to calculate the joint distribution of a bayes network