Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit

ITS70104 (March 2022 B2)

Principle of Programming 

Declaration (need to be signed by students. Otherwise, the assessment will not be evaluated)

Certify that this assignment is entirely my own work, except where I have given fully documented references to the work of others, and that the material contained in this assignment has not previously been submitted for assessment in any other formal course of study.

Signature of Students:

 Assessment Criteria

Assessment Task

 

Weightage

MLO

Assessed

Formative / Summative

Assessment Instrument

 

Topics

 

Week

 

MCQ2.0

Assessment Task 3: Project

 

30%

 

MLO 3

 

Formative

Individual

Assignment Project

 

5,6,7

 

6

C2, C3D, C3E

  Objectives / Module Learning Outcomes (MLO 3)

The objective of this assessment is to enable the students to:

Analyze and design programs using appropriate programming concepts in real-world problems.

 Scenario

The Immigration Department has decided to automate their preliminary approval for its permanent residence application based on the applicant’s age, gender, years in the country, and education level. Once the applicants get this preliminary approval, then only they can proceed with the real applications and interviews. The current MCQ test vetting process could not promptly process thousands of applications they had received since they have to manage and conduct the test at their premises. To solve this problem, they have decided to build an application system to predict the probability of the applicants passing this preliminary approval based on the parameters aforementioned. Therefore, the department will conduct their own data gathering, data cleaning, and prediction model.

The system has 4 main activities:

 STAGE 1 COMPONENT - Gathering and analyzing data component

Historical data is gathered by testing sufficient new applicants using automated MCQ Generation, Assessment and Analysis System. To allow accurate prediction model that predicts the result of the test, variables such as the applicant’s age, gender, years in the country, and education level will become part of the input. The Test is developed using Python with appropriate graphical user interface.

 

Each test consists of TEN (10) questions related to your chosen country, and each question has FOUR (4) choices. The questions are input from an external input file. The passing percentage for the test is 80%. The 10 questions are categorized into TWO (2) types of questions: Type 1 – Question in text format.

Type 2 – Question that includes an image.

Your 10 questions should have a fair combination of type 1 and type 2 questions. All questions should be generated from an input file using colon ”:” as the delimiter.

 

Minimum of TWENTY (20) applicants with varying age, gender, years in the country, education level and nationality will take the test. The application system will save the applicants’ answers in an external output file along with the applicants’ identifications such as the name and application no. Once all the twenty applicants have taken the Test, the Application should analyze the result by performing basic statistical analysis with at least TEN (10) statistical analysis result such as maximum, average and mode scores. In addition, at least FOUR (4) simple statistical charts tabulated from the test result are created using Matplotlib.

 STAGE 2 COMPONENT – Cleaning of Data

In addition to the twenty tested applicants’ result, you need to add another THIRTY (30) applicants hypothetical result that contains various types of dirty data. Based on these combined results, you need to perform any TWO (2) different types of data cleaning using NumPy and Pandas.

 STAGE 3 COMPONENT - Developing prediction model

The result from the cleaned data should become the input file for the machine learning prediction analysis using KERAS. The system should be able to properly format the input to ensure data validity and integrity using Numpy and Pandas. Once the prediction neural model is developed, it will be tested for accuracy using the previous twenty applicants’ result.

 STAGE 4 COMPONENT - Applying prediction model to new applicants

Once the prediction model testing is completed, the new prediction model will be applied to FIVE

(5) new applicants to automatically accept or reject their applications without needing them to sit for the Test. The applicants should be potential applicants with varying age, gender, education level, and years in the country. This component should be done with proper graphical user interface.

You are engaged to develop all four components of the system based on the country of your choice.

Conduct an in-depth analysis of solution to the problem above documenting the followings:

1. Documentation of the country selected and the 10 questions related to the country.

2. Few high-level design diagrams showing the relationships among all the files involved.

3. Your design and strategy for the prediction model testing including adding another TWO

(2) critical variables to make the predication model more accurate.

4. Your FIVE (5) applicants’ details for prediction model application.

 Part 1 Deliverables

A well-structured and properly formatted academic document that contains the questions details, associated solution high level design diagrams, prediction strategy, and new applicants’ details. Ensure that your submission includes a cover page which shows your name and student ID. All submissions should be in pdf format (ProjectPart1_StudentID.pdf).

Submission Due Date: 1155pm 09/10/2022 submit via times.taylors.edu.my submission link.

Based on your design in Task 1, create a full Python project application that demonstrates:

1. Ability to process input and output file to cater the test for the 20 applicants.

2. Use of simple Python GUI controls programming.

3. Use of Pandas to read and format external data.

4. Use of NumPy and Matplotlib to analyze the result, and draw your relevant charts.

5. Use of NumPy and Pandas to clean all dirty data.

6. Use of NumPy and Pandas to convert and validate KERAS input data.

7. Use of KERAS to predict the test outcome of new applicants.

8. Ability to process acceptance or rejection of new applicants.

9. Documentation of the processes to run and use your examination system including its result and prediction systems.

 Part 2 Deliverables

A well-structured and properly formatted academic document that includes the source code of ALL Python files created for the program along with sample screenshots of your program’s output. Follow proper coding style, use proper names for your variables, indent the code, and comment the code where appropriate. Ensure that your submission includes a cover page which shows your name and student ID. All submissions should be in pdf format (ProjectPart2_StudentID.pdf).

Submission Due Date: 1155pm 19/10/2022 submit via times.taylors.edu.my submission link.

 Task Part 3 (5%) PRESENTATION

Present your system identifying all items conforming to the system requirements. In addition, present the live demonstration of your running system. Each person is limited to a 10-minute presentation.

 Presentation Deliverables

No deliverables required.

Presentation Date: 6pm 16/10/2022 online (Live video session is compulsory for online class).

 Ethics

Students should submit original work. Proper citations should be provided if any references to publicly accessible materials are used. Students who are found to be plagiarized will receive severe penalties.