Data Mining - ISZC415 - Quiz 2 - BITS- WILP

Data Mining - ISZC415 - Quiz 2

BITS- WILP - MTEC

1. The entropy of a fair coin toss is:

Select one:
a. 0.25
b. 0.5
c. 1
d. 0

Ans: c. 1


2. A quiz question had names of 10 algorithms of which the student

had to select only the classification algorithms. A student

identified 7 of them as classification algorithms. During evaluation

it was found that 5 of the algorithms identified by the student were

indeed classification algorithms. The student was unable to identify

2 other classification algorithms in the list.

The F-score is:


Select one:
a. 0.59
b. 0.41
c. 0.69
d. 0.71

Ans:  d. 0.71

3. Hash tree is created from:

Select one:
a. transactions
b. frequent itemsets
c. strong rules
d. candidate itemsets

Ans: d. candidate itemsets

4. The following data is about a poll that occurred in 3 states. In

state1, 50% of voters support Party1, in state2, 60% of the voters

support Party1, and in state3, 35% of the voters support Party1. Of

the total population of the three states, 40% live in state1, 25%

live in state2, and 35% live in state3. Given that a voter supports

Party1, what is the probability that he lives in state2?

Select one:
a. 0.52
b. 0.42
c. 0.32
d. 0.22

Ans: c. 0.32

5. A quiz question had names of 6 algorithms of which the student had

to select only the classification algorithms. A student identified 3

of them as classification algorithms. During evaluation it was found

that 2 of the algorithms identified by the student were indeed

classification algorithms. The student was unable to identify 2 other

classification algorithms in the list.

The recall is:


Select one:
a. 0.33
b. 0.5
c. 0.73
d. 0.6

Ans: b. 0.5

6. The table below shows marks in math (x) and marks in statistics

(y).



What is the value of the slope (m) of simple regression line ?


Select one:
a. 0.744
b. 0.644
c. 0.444
d. 0.544

Ans: b. 0.644

7. In case an item occurs N times in a single transaction, the

support count of that item:

Select one:
a. zero times
b. is counted only once
c. is counted N times
d. is counted threshold times

Ans: b. is counted only once

8. In association analysis, confidence measures certainty of the

rule.

Select one:
a. True
b. False

Ans: a. True

9. Decision tree pruning is done to prevent under-fitting the data.

Select one:
a. True
b. False

Ans: b. False

10. A decision tree is split on the attribute with highest Gini

Index.

Select one:
a. True
b. False

Ans: b. False

11. Gini index cannot be used to make a ternary split on an attribute

in decision tree classification.

Select one:
a. True
b. False

Ans: b. False

12. Decision tree splitting decision can be made based upon

information gain of the attributes, but not based upon entropy of the

attributes.

Select one:
a. True
b. False

Ans: b. False

13. Laplace smoothing is applied in Naive Bayes spam classifier

because it prevents the conditional probability from becoming zero if

some words are not present in the sample.
Select one:
a. True
b. False

Ans: a. True

14. In association analysis, support is a symmetric measure of

associations.

Select one:
a. True
b. False

Ans: a. True

15. In classification, we evaluate the performance of a classifier on

training data

Select one:
a. True
b. False

Ans: b. False

Data Mining Quiz1 ISZC415 - BITS PILANI WILP MTEC

Data Mining Quiz 1 ISZC415 - BITS PILANI WILP MTEC

1. 27, 0, 1, 2, 63, 61, 0, 13
The five number summary of the above sample is:
Select one:
a. 63, 27, 13, 2, 0
b. 0, 2, 13, 27, 63
c. 0, 1, 13, 27, 63
d. 0, 0.5, 7.5, 44, 63

Ans: d. 0, 0.5, 7.5, 44, 63

2. 50th percentile is same as

Select one:
a. weighted mean
b. midrange
c. median
d. mean

Ans: c. median

3. Validation set and test set contain the same samples.

Select one:
True
False

Ans: False

4. A boxplot can show outliers as small circles/points,

Select one:
True
False

Ans: True

5. Analysis of patterns for stock market prediction is an example of:

Select one:
a. evolution analysis
b. outlier analysis
c. correlation
d. characterization and discrimination

Ans: a. evolution analysis

6. Pearson's product moment correlation coefficient between two

variables can have values:

Select one:
a. 0 or any positive number
b. greater than or equal to -1 but less than or equal to +1
c. greater than 0 but less than one
d. 0 or positive but less than or equal to 1

Ans: b. greater than or equal to -1 but less than or equal to +1

7. Given two text documents, when we shuffle the words of any one of

the documents, the cosine similarity between the two texts will not

change.

Select one:
True
False

Ans: True

8. If all the tuples in a data set belong to a single class, then its

gini index is:

Select one:
a. 0.5
b. insufficient information to say anything
c. 0
d. 1

Ans: c. 0

9. The mapping of a value by min-max normalization is always in the

range [0,1]

Select one:
True
False

Ans: False

10. We always predict some amount or number in this kind of problems:

Select one:
a. classification
b. preprocessing
c. clustering
d. regression


Ans:  d. regression

11. Holistic measure can be derived from distributive measures

Select one:
True
False

Ans: False

12. If all the data values in a set of data are unique, then

Select one:
a. their is no mode
b. we can select any one number as mode
c. the median is the mode
d. all the numbers are modes

Ans: a. their is no mode


13. A boxplot is nothing but a visual representation of IQR

Select one:
True
False

Ans: False

14.10, 2, 3, 4, 5, 3, 4, 6, 2

How many modes are there?

Select one:
a. 2
b. 1
c. 3
d. 4

Ans: c. 3

15. 10, 2, 3, 4, 5
The midrange of the above sample set is:


Select one:
a. 3
b. 6
c. 7.5
d. 4


Ans: b. 6