INT3095代做、代写Python语言编程

日期：2023-12-14 09:31

Page 1 of 3

INT3095 Practical Programming for Artificial Intelligence

Group Project Specifications (2023-23)

1. Introduction

In this project, you are going to work as a group to demonstrate your knowledge

and skills in conducting data mining with machine learning algorithms in Python.

2. Summary task description

More specifically, you are required to:

− Choose a publicly available dataset from sources such as Kaggle,

data.gov.hk, data.gov, etc.

− Conduct regression, classification, clustering, or association on this

dataset using machine learning algorithm(s) in Python. You should

include the complete dataset as well as the codes so that the marker can

re-run all the results. In case you are fetching from an online dataset

directly, you should submit a backup copy of the dataset to Moodle as

well.

− Evaluate and compare the performance of your machine learning

algorithm(s) with different parameters.

− Discuss and conclude your findings in terms of the insights you obtain

from the data mining, as well as the performance of your machine

learning algorithm(s) under different parameters.

2. Grouping

Maximum of 5 members per group

3. Development

You may use Colab or Thonny, or AI analysis tool to develop this project. If

you use software tool, that means the coding effort will be limited. Therefore,

you need to provide an enhance description on your findings. Please zip all

files related to your project and submit to moodle.

4. Submission schedule

Project Report and Source Code, or files of using AI tools, if any, and the

used data file, and other related files (if any).

Zip all files and submit to Moodle (Only submit one copy is required).

Date: 16 Dec 2023 (week 15, Saturday)

Late Submission Penalty: A 20 marks (out of 100) deduction per day of

late submission without permission may be applied to the total mark of the

project. The project will NOT be accepted if late submitted over 3 days.

[Moodle will set CANNOT submit after 3 days]

Page 2 of 3

5. Project Report

Word Limit

Around 2500 words, with suitable scree capture photos of testing outcome

of the project. The contents need to directly relate to the project issues, and

is able to fulfill the following general requirements.

Report file format

Word .docx format; or establish a website on your project report (submit all

html file if you use this approach)

Cover Page

Include the Project title, and the full name and student ID of all members, a

contribution table with [Highly Contributed, Contributed, Low Contributed]

identified every member’s contribution.

Content requirements on the group report

The report should consist of (but is not limited to) the following:

− Explain the information provide by your selected dataset. For example,

how it can give value for a real-world application.

− Provide an implementation of the data mining algorithms to analyze the

dataset so as implement your idea on data mining on that selected

dataset.

− Explain the design principles behind your data mining algorithms.

− Report the findings from your outcomes of data-mining algorithm. You

may provide the screenshots of the algorithm testing outcome.

− Evaluation of the performance of your machine learning algorithms

under the data set of parameters

− Discussions on the improvement of your algorithm to carry out mote

insight of your evaluation parameters.

− A summary and conclusion of your findings regarding the data mining

results and the performance evaluation of the algorithms and parameters.

− Reference in APA format

Note:

1. it is not limited to only these features in your report. You may add any

contents that can facilitate your report to get a better outcome.

2. You are also optionally to submit a recording on your project execution to

get your reader more understanding you algorithm design. The recording

needs to be limited on 10 minutes. Provide an access link on the cover page

of the report if any.

6. Plagiarism

Plagiarism is serious matter. Please refer to the Policy on Academic Honesty,

Responsibility and Integrity with the following link:

(https://www.eduhk.hk/re/modules/downloads/visit.php?cid=9&lid=89).

Page 3 of 3

7. Grading criteria

Group report (80% of total project marks)

0 1 2 3 4

Introduction and

theoretical

background

(20 marks)

Background

information is

missing or

contains major

gaps or

inaccuracies.

Background

information is

accurate, but

irrelevant or too

disjointed to

make relevance

clear.

Background

information is

accurate but has

omissions that

detract from the

theme of the

project.

Background

information may

contain minor

omissions or

inaccuracies but

does not detract

from the major

theme of the

project.

Background

information is

accurate and has

the appropriate

level of

specificity to

provide concise

and useful

context to aid the

reader's

understanding.

Data preparation

(10 marks)

The dataset is

incomplete or is

not loaded into

the notebook.

The dataset is

loaded into the

notebook, but its

key properties

and sample

records are not

adequately

illustrated.

The dataset is

loaded and wellillustrated, but it

is not

appropriately

split into training

set and testing

set.

The dataset is

correctly loaded,

illustrated, and

appropriately

split, but lacking

a detailed

description.

The dataset is

correctly loaded,

illustrated, and

appropriately

split, with

detailed

description.

Data mining

(30 marks)

The data mining

is incomplete.

The data mining

is complete but

contains major

errors.

The data mining

is done but

contains minor

errors.

The data mining

is correctly done

but not clearly

explained.

The data mining

is correctly done

and clearly

explained.

Evaluation and

discussions

(20 marks)

No evaluation or

discussion is

performed or

discussed.

Evaluation is

performed but

with omissions or

errors, or not

discussed in

sufficient detail.

Evaluation is

properly

performed but

only briefly

discussed.

Evaluation is

properly

performed and

reasonably well

explained or

discussed.

Evaluation is

appropriate,

correct, and

clearly explained

or discussed.

Some good

points are made.

Conclusion,

limitations, and

recommendation

s (10 marks)

The conclusions

and

recommendation

s section is

incomplete or

non-existent.

The conclusions

and

recommendation

s have major

omissions.

The conclusion

relates

appropriately to

the project

objectives but

the limitations

and

recommendation

s were not well

discussed.

The conclusion

relates

appropriately to

the project

objectives. The

limitations and

recommendation

s are written but

not always well

justified.

The conclusion

relates

appropriately to

the project

objectives and

contains welljustified

limitations or

recommendation

s.

Clarity of

presentation

(10 marks)

The report has

terrible spelling

or grammar.

Sections are not

put under

appropriate

headings.

The report has

significant errors

in spelling,

formatting, or

grammars.

Sections are not

put under

appropriate

headings.

The report has

some spelling,

formatting or

grammatical

errors. Sections

are put under

appropriate

headings.

The report has

some minor

spelling,

formatting or

grammatical

errors. Sections

are put under

appropriate

headings.

The report is

written with good

spelling,

formatting, and

grammar.

Sections are put

under

appropriate

headings.