代做ITS70104 Principle of Programming 2024调试Python程序

ITS70104 (February 2024)

Principle of Programming

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

C1-Knowledge & Understanding, C2=Cognitive Skills, C3A=Practical Skills, C3B=Interpersonal Skills, C3C=Communication Skills, C3D=Digital Skills,C3E=Numeracy Skills, C3F=Leadership, Autonomy & Responsibility, C4A=Personal Skills, C4B=Entrepreneurial Skills,CS=Ethics & Professionalism 

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

After a decade of aggressive expansion, a highly rated international University has decided to automate their entrance applications preliminary approval for undergraduate programs based on the candidates’ age, gender, qualification level, and country of origin. They intend to automatically filter quality applicants only; a process that currently is overwhelmed by thousands of applications received from all corners of the world.   To solve this problem, they have decided to build an application system to predict the quality of the applicants, and instantly accept or reject their university entrance applications. Therefore, each faculty will conduct their own preliminary data gathering, data cleaning, and prediction model since each undergraduate program has their own unique skillset requirements.

The system has 4 main activities:

Gathering and analyzing data → Cleaning of Data → Developing prediction model → Applying prediction model to new applicants

STAGE 1 COMPONENT - Gathering and analyzing data component

Historical data is gathered by testing sufficient new applicant data using  automated MCQ Generation, Assessment and Analysis System. To allow an accurate prediction model that predicts the result of the test, variables such as the applicants’ age, gender, country of origin, and their 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 the undergraduate program for a chosen faculty/school, and each question has FOUR (4) choices. The questions are input from an external input file. The passing percentage for the test is 70%. 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.

A minimum of TWENTY (20) applicants with varying age, gender, 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, passport no, gender, age, education level, and nationality. 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 results such as maximum, average and mode scores. In addition, at least FIVE (5) simple statistical charts tabulated from the test result are created using Matplotlib.

The result of this test will become the training data for the prediction model.

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 (Model Training)

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, nationality, and education level. This component should be done with proper graphical user interface.

Your Tasks

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

Task Part 1 (5%) ANALYSIS AND DESIGN

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

1.   Documentation of the undergraduate program selected and the 10 related questions.

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 15/03/2024 submit via times.taylors.edu.my submission link.

Task Part 2 (20%) IMPLEMENTATION AND PREDICTION

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/NumPy to read and format external data.

4.   Use of Pandas/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 Test 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 testing screenshots of your program’s output. Follow proper coding style, use proper names for your variables, 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 24/03/2024 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 an 8-minute face to face presentation.

Presentation Deliverables

No deliverables required.

Presentation Date: 9am 24/03/2024 during Practical and Tutorial classes.