 |
DTA621S - DATA ANALYTICS - 2ND OPP - JAN 2025 |
|
|
1 Page 1 |
▲back to top |
n Am I BI A u n IVER s ITY
OF SCIEnCE Ano TECHnOLOGY
FACULTY OF COMPUTING AND INFORMATICS
DEPARTMENT OF INFORMATICS
QUALIFICATION: BACHELOR OF INFORMATICS, BACHELOR OF COMPUTER SCIENCE
QUALIFICATION CODE: 07BAIT,07BCMS LEVEL: 6
COURSE: DATA ANALYTICS
COURSE CODE: DTA621S
DATE: JANUARY 2025
SESSION: 2
DURATION: 2 HOURS
MARKS: 85
SUPPLEMENT ARY/SECOND OPPORTUNITY EXAMINATION QUESTION PAPER
EXAMINER($) MRS RUUSA IPINGE
MODERATOR: MR SEBASTIAN MUKUMBIRA
THIS QUESTION PAPER CONSISTS OF 11 PAGES
(Excluding this front page)
INSTRUCTIONS
• Answer ALL questions in Part 1, Part 2 and Part 3,
• NUST examinations rules apply
• DO NOT open this examination cover until you are instructed to do so.
• DO NOT FORGET to write down your student number at the designated places in the
examination page.
1
|
|
2 Page 2 |
▲back to top |
PART 1: MULTIPLE CHOICE QUESTIONS (25 MARKS MAXIMUM 1 MARK FOR EACH
CORRECT ANSWER)
Answer all questions. Select ONLY ONE BEST ANSWER to each question.
1. This helps in ensuring that a model is generalizable to new data rather than just
fitting the training data well.
a) Classification
b) Clustering
c) Data mining
d) Cross validation
2. This is the process of selecting a subset of relevant features (variables, predictors)
from a larger set to improve model performance, reduce overfitting, and enhance
interpretability. It's a crucial step in the machine learning pipeline, especially when
dealing with high-dimensional data.
a) Feature Selection
b) Generalisation
c) Overfitting
d) Underfitting
3. Logistic regression is used to find the probability of event= Success and event=
a) Failure
b) Success
c) Both A and B
d) None of the mentioned above
4. It includes functions to visualize distributions, relationships, and categorical data,
making it easy to create complex visualizations such as heatmaps, violin plots, and
pair plots.
a) Matplotlib
b) Pandas
c) Seaborn
d) Normalisation
2
|
|
3 Page 3 |
▲back to top |
5. This is the type of research that it answers key questions such as , "what" and
"why".
a) Quantitative
b) Qualitative
c) Nominal
d) Category
6. This shows how a specific variable changes across time periods (especially with
grouped or stacked plot).
a) Bar graph
b) Scatterplot
c) Line graph
d) Pie chart
7. This refers to the graph that uses vertical bars to represent data is called a __ .
a) Bar graph
b) Line graph
c) Scatterplot
d) All the mentioned above
8. Data Analytics uses _ to get insights from data.
a) Science tools
b) Numerical aspects
c) Statistical methods
d) None of the mentioned above
9. This approach is commonly employed in regression analysis to find the best-fitting
line or model for a given set of data point.
a) Least Square Method
b) Linear regression
c) Linear sequence
d) None of the mentioned above
3
|
|
4 Page 4 |
▲back to top |
10. Look at the confusion matrix above containing 263 observations. What is the
accuracy of the predictions?
39
Surmed·
8
51
Truih
a) The accuracy is equal to (165 + 51)/263 (82.1%).
b) The accuracy is equal to (165 + 8)/263 (65.8%).
c) The accuracy is equal to (51 )/263 (19.4%).
d) The accuracy is equal to (39 + 8)/263 (17.9%)
11. What is Machine learning?
a) The autonomous acquisition of knowledge using manual programs.
b) The selective acquisition of knowledge using manual programs.
c) The autonomous acquisition of knowledge using computer programs.
d) The selective acquisition of knowledge using computer program.
4
|
|
5 Page 5 |
▲back to top |
12. What is the primary distinction between Artificial Intelligence (Al) and Machine
Learning (ML)?
a) Al is solely about mimicking human behaviour, while ML is about programming
machines to perform specific tasks.
b) Al encompasses a wide range of technologies that simulate human intelligence,
whereas ML specifically focuses on algorithms that allow machines to learn from
data.
c) Al and ML are interchangeable terms that refer to the same concept of creating
intelligent machines.
d) Al requires large amounts of data to function, while ML does not depend on data.
13. Which of the following is not a supervised learning?
a) PCA (Principal Component Analysis)
b) Naive Bayesian
c) Linear Regression
d) Decision Tree
14. Which of the following Machine Learning technique helps in detecting the outliers
in data.
a) Clustering
b) Classification
c) Anomaly Detection
d) All the above
15. Which answer best describes standard deviation?
a) Standard deviation is a measure of the spread of a dataset.
b) Standard deviation indicates how much individual values vary from the mean.
c) Standard deviation helps scientists summarize how much variation there is in a
dataset or population.
d) All the above
16. What is the primary goal of supervised learning?
a) To find patterns in unlabelled data
b) To predict outcomes based on labelled data
c) To optimize a model without any data
d) To cluster similar items
5
|
|
6 Page 6 |
▲back to top |
17. Which of the following algorithms is commonly used for classification tasks?
a) Linear Regression
b) K-Means Clustering
c) Decision Trees
d) Principal Component Analysis
18. In Python, what is the result of the following operation 1+2?
a) '2'
b) '3'
c) 3
d) '12'
19. In Python, if you executed name= 'Lizz', what would be the output of print(name
(0:2])?
a) Lizz
b) L
c) LI
d) Liz
20. How can you read a CSV file into a Pandas DataFrame?
a) pd.read_table('file.csv')
b) pd.load_csv('file.csv')
c) pd.read_csv('file.csv')
d) pd.import_csv('file.csv')
21. What method would you use to get a quick overview of a DataFrame's structure and
data types?
a) df.describe()
b) df.info()
c) df.head()
d) df.summary()
6
|
|
7 Page 7 |
▲back to top |
22. How do you select a specific column in a DataFrame named df?
a) df.column_name
b) df['column_name']
c) df.column_name()
d) df.get('column_name')
23. What does DPIA stand for in the context of GDPR?
a) Data Protection and Information Assessment
b) Data Processing Impact Analysis
c) Data Privacy and Incident Assessment
d) Data Protection Impact Assessment
24. What role does a Data Protection Officer (DPO) play under the GDPR?
a) Ensuring marketing compliance
b) Overseeing data protection compliance
c) Managing IT infrastructure
d) Handling customer support
25. How soon should organizations report a data breach to the supervisory authority
under the GDPR?
a) Within 24 hours
b) Within 48 hours
c) Within 72 hours
d) Within one week
7
|
|
8 Page 8 |
▲back to top |
PART 2: STRUCTURED QUESTIONS [60 MARKS]
ANSWER ALL QUESTIONS
QUESTIONS 1
1. Explain the difference between the following terms
[8]
a) Supervised and Unsupervised machine learning.
b)
Logistic and Polynomial regression
c)
Tuple and list
d) Variance and standard deviation
QUESTION 2
2. a) A class contains 39 children. The following children were chosen at random, and their
weight were recorded in cm: 38, 51, 46, 79, and 57. Calculate their weight's standard
deviation.
[6]
8
|
|
9 Page 9 |
▲back to top |
QUESTION 3
3. Explain the output of the following codes written in python programming language. [10]
a) a= 2
b= 330
if a> b
else
print("B")
b) Gemuse=["apple", "banana", "cherry"]
print(type( Gem use))
c) fruits=("apple", "banana", "cherry")
mytuple=fruits* 2
print(mytuple)
d) thislist=["apple", "banana", "cherry"]
del thislist[0]
print(thislist)
e) x= 41
if x> 10:
print("Aboveten, ")
if x> 20:
print("and also above 20!")
else:
print("but not above 20.")
9
|
|
10 Page 10 |
▲back to top |
QUESTION 5
s. Explain the following pandas codes output
(16]
a) filtered_df = df[df['Age'] > 28]
b) df.describe()
c) df.info()
d) df.head(10)
e) df.summary()
f) df['Salary'] = [50000, 60000, 70000]
g) df.to_csv('output.csv', index=False)
h) df = df.drop{'Salary', axis=1)
6. QUESTION 6
a) Under the GDPR, organisations must meet six data protection principles whenever they
process personal data. Explain the % principles of the General Data protection Regulation
(GDPR) (10].
END OF QUESTION PAPER
11