Question One
The table below is the staff records from a firm in the Ga East District of Accra. Use the table
answer the Question One and Question 2A
StaffiD
EB001 Emma Boswell
Ritlynn Davis
RD010
IW210
AS003
EB002
KB022
NAD30
SA205
Name:
AM030
YK011
lan Wright
M
Nana Ama Serwaa 1
Esl Benson
Kwame Boateng
Nana Ayele Kwao
Selorm Agorvi
Andy Mills
Maame Yaa Korang
DoB
Sex
02/12/1980 Female
23/05/1990 Female
12/12/1982 Male
07/09/2001 Female
25/07/1978 Female
23/09/1974 Male
15/01/2002 Female
Marital
Status
Department
Yes Legal
No Marketing
Yes
Operations
Yes
No
Yes
No
No
HR
IT
Adminitration
IT
Legal
Operations
31/12/1979 Male
01/03/1999 Male
Yes
01/06/1998 Female Yes HR
No of years
worked
16
5
11.
3
21.
15
4
10.
12
7
Basic
Salary
X12000
9500
17000
8000
19500
21000
9600
16500
14500
8900
Benefits
1800
1425
2550
1200
2925
3150
1440
2475
2175
1335
Deductio
ns
A. While considering all the necessary constraints and attributes, write a Python statement/s to
represent the structure of the above dataset - 5 Marks.
B. Assuming the national income tax is 15.5% for all working-class males and 12.5% for
working-class females, write a Python statement to compute the net monthly salary of
employees of this firm - 10 marks
C. Assuming the firm (employer) decides to use the rate of national income taxes as a margin
to compute staff SSNIT contributions; Calculate the total annual SSNIT contributions the
employer will make to all male employees - 8 Marks
D. Assuming the employer decides to give 18.5% of basic salary as a monthly bonus for all
married employees, calculate the total net monthly income for all married staff - 7 Marks
69
106
550
250
890
110
85
1200
190
210
Question Two
A. From the dataset above, computer the 5-number Summary Statistics and the Outlier on
basic salaries for all staff with at least 10 years working experience - 9 Marks
B. One of the key principles of data analysis in decision-making is how analysts address the
issue of noise in data. Explain two ways the issue of noise in data could be addressed to
Mail
improve decision making - 6 marks-
Question Three
average
пор avainje a
A. With the use of an annotated diagram, explain the key processes involved in data mining
from a data repository stage to knowledge acquisition - 10 marks.
B. With the use of appropriate examples differentiate between the population mean and the
sample mean - 5 Marks-
1
Question Four
A. While explaining association rule in data science, discuss how Ghana Library Authority
could apply the principles of association rule to improve the reading skills among children in
rural Ghana - 10 Marks he ate
joos
B. Discuss two (2) scenarios in which cluster analysis could be problematic as a tool for
demographic analysis - 5 marks