首页 > > 详细

辅导KIT108解析Python语言程序

Page 1 KIT108 Artificial Intelligence 
Generated by Akari 
 
 
 
KIT108 
ARTIFICIAL INTELLIGENCE 
Assignment 
Stage 1 submission: Due 23.59PM Wednesday 27th May 2020 (already includes a 5 day 
extension) 
Stage 2 submission: Due 23.59PM Sunday 07th June 2020 (already includes a 5 day extension) 
STOCK PRICE PREDICTION 
Description 
In this assignment, we will apply machine learning techniques learned in the lectures 
and tutorials to predict the highest price of a stock in the next day. 
 
1. The date - "Date" 
2. The opening price of the stock - "Open" 
3. The low price of that day - "Low" 
4. The closed price of that day - "Close" 
5. The amount of stocks traded during that day - "Volume" 
Page 2 KIT108 Artificial Intelligence 
Generated by Akari 
6. The high price of next day - "Next High" 
 
Part A: Programming- 70% 
In this task, you will train an AI model using the open price, the low price, and the 
volume of a day to predict the high price on the next day. In this task you need to 
design a RapidMiner process OR Python program to: 
1. Read the stock_data.csv file. 
2. Identify irrelevant information from the data and filter it out to construct 
the target data. Explain in the report how you do this. 
3. Identify the number of missing values in each attribute. Explain in the 
report. 
4. Fill the missing values by using the techniques you have learned. Explain 
the way you handled this issue in the report. 
5. Normalise the data so that all attributes are in the same range. Explain what 
method you used and what your chosen range was in the report. NOTE: 
DON’T NORMALISE THE TARGET (LABEL) ATTRIBUTE. 
6. Decide your own strategy to train, evaluate a model from the data from 
stock_data.csv. 
7. Design your own strategy to select the best model. 
8. Apply the selected model to the data in predict_stock_data.csv. This data 
does not have the label and you have to generate the predicted value for the 
high price. Export the predicted high price in to a csv file using your 
student ID (for example 342435.csv). 
When you complete the step 8, you will do stage-1 submission in week 13 (see below) 
to score the performance of your model. 
Part B: Analysis- 30% 
You will receive the performance score after week 13 and the ground truths. You will 
need to revise your design to: 
- Explain why your model is good or bad. Write it in the report. 
- What will you do to improve the prediction results if your model is scored as 
“NOT GOOD”. Write this in the report. Those whose models are scored as 
“GOOD” do not need to do this step. 
Page 3 KIT108 Artificial Intelligence 
Generated by Akari 
Evaluation of the assignment 
See Page 7 and Page 8 for the details of the evaluation criteria. 
How What to submit. 
Assignments will be submitted via MyLO (an Assignment submission will be created). 
Stage 1 submission (week 13): 
• An XML file for your design OR a python source code, the file is named using 
your student ID (for example, 342435.xml or 342435.py) 
• The predicted output in a csv format. The file must be named using your 
student ID (for example 342435.csv). 
After stage 1 submission, you will receive the score (GOOD or NOT GOOD) for 
the model, from which you will complete a report for the stage 2 submission. 
Stage 2 submission (week 15): 
• A report file (docx or pdf) using the provided template (see the attached file) 
 
Appendix 01: How to export an XML file for the model with RapidMiner 
 
 
• Click File -> Export Process 
• Choose save path -> Name file with ID -> Select Process File (*.xml) 
NOTE: YOU NEED TO CHECK YOUR XML FILE BEFORE SUMISSION, FOR 
EXAMPLE BY CLOSING RAPIDMINER STUDIO THEN OPENNING IT AGAIN 
AND LOADING THE XML FILE FOR DOUBLE CHECK. 
 
 
 
 
Page 4 KIT108 Artificial Intelligence 
Generated by Akari 
 
 
 
 
 
 
Appendix 02: How to export an csv file for the predicted output using RapidMiner 
 
 
• Use Select Attributes operator to filter output with only predicted high 
price attributes left 
• Put Write CSV operator and connect with the filtered output 
• Set csv file path 
• Use symbol “,” for column separator 
• Unselect quote nominal values 
• Run process and output csv file 
Plagiarism and Academic misconduct 
Plagiarism 
Plagiarism is a form of cheating. It is taking and using someone else's 
thoughts, writings or inventions and representing them as your own; for 
example, using an author's words without putting them in quotation 
marks and citing the source, using an author's ideas without proper 
acknowledgement and citation, copying another student's work. 
If you have any doubts about how to refer to the work of others in your 
assignments, please consult your lecturer or tutor for relevant referencing 
guidelines. You may also find the Academic Honesty site on MyLO of 
assistance. 
Page 5 KIT108 Artificial Intelligence 
Generated by Akari 
The intentional copying of someone else’s work as one’s own is a serious 
offence punishable by penalties that may range from a fine or 
deduction/cancellation of marks and, in the most serious of cases, to 
exclusion from a unit, a course or the University. 
The University and any persons authorised by the University may 
submit your assessable works to a plagiarism checking service, to 
obtain a report on possible instances of plagiarism. Assessable 
works may also be included in a reference database. It is a 
condition of this arrangement that the original author’s 
permission is required before a work within the database can be 
viewed. 
For further information on this statement and general referencing guidelines, see the 
Plagiarism and Academic Integrity page on the University web site or the Academic 
Honesty site on MyLO. 
Academic misconduct includes cheating, plagiarism, allowing another student to copy 
work for an assignment or an examination, and any other conduct by which a student: 
a. seeks to gain, for themselves or for any other person, any academic advantage 
or advancement to which they or that other person are not entitled; or 
b. improperly disadvantages any other student. 
Students engaging in any form of academic misconduct may be dealt with under the 
Ordinance of Student Discipline, and this can include the imposition of penalties that 
range from a deduction/cancellation of marks to exclusion from a unit or the 
University. Details of penalties that can be imposed are available in Ordinance 9: 
Student Discipline – Part 3 Academic Misconduct. 
Page 6 KIT108 Artificial Intelligence 
Generated by Akari 
KIT108 ARTIFICIAL INTELLIGENCE: MAJOR ASSIGNMENT 
Synopsis of the task and its context 
This is an individual assignment making up 20% of the overall unit assessment. The assessment criteria for this task are: 
1) Apply machine learning pipeline to solve a real-world problem. 
a) Identify relevant data 
b) Process and clean data 
c) Transform data 
d) Apply and select machine learning techniques 
e) Analysis of the results. 
f) Identify the best technique for this problem. 
Match between learning outcomes and criteria for the task: 
Unit learning outcomes 
On successful completion of this unit… Task criteria: 
1. understand the local and global impact of AI on individuals, organizations, and society 2 
2. adapt and apply techniques for acquiring, representing, and reasoning with data, information, and knowledge 1 
3. select and effectively apply techniques to develop simple AI solutions 1 
4. analyze a problem, apply knowledge of AI principles, and use ICT technical skills to develop potential solutions 1, 2 
5. evaluate strengths and weaknesses of potential AI solutions 1, 2 
 
Page 7 KIT108 Artificial Intelligence 
Generated by Akari 
Criteria HD (High Distinction) DN (Distinction) CR (Credit) PP (Pass) NN (Fail) 
1. Machine learning pipeline 
a) Data collection (10%) Load the data and choose the 
irrelevant attribute (date) and be 
able to perform removal of that 
attribute from the original dataset. 
Load the data and remove 
the irrelevant attribute 
date, but also identify and 
remove one attribute 
wrongly. 
Load the data and remove 
the irrelevant attribute 
date, but also identify and 
remove more than one 
attribute wrongly. 
Load but cannot remove 
the irrelevant attribute. 
Cannot load the data. 
b) Data processing (10%) Fill all the missing values and 
explain clearly the technique used 
to do that. 
Fill all the missing values 
and can explain technique 
used to do that with minor 
mistakes. 
Fill all the missing values 
but cannot explain the 
techniques correctly. 
Fill all the missing values 
but do not explain the 
techniques (no attempt). 
Cannot fill all the 
missing values. 
c) Data transformation 
(10%) 
Correctly normalise all the 
attributes into a range, except for 
the target attribute (next high). 
Correctly normalise all the 
attributes into a range but 
mistakenly normalise the 
target attribute (next high). 
Correctly normalise some 
of the attributes into a 
range, except the target 
attribute (next high). 
Correctly normalise some 
of the attributes into a 
range but mistakenly 
normalise the target 
attribute (next high). 
Cannot normalise the 
data. 
d) Data Mining (30%) Correctly use more than 2 models 
to select the best model to 
generate a prediction result from 
the predict_stock_data.scv. The 
selection process is explained 
correctly. 
Correctly use more than 2 
models to select the best 
model to generate a 
prediction result from the 
predict_stock_data.scv. The 
selection process is 
explained with some 
mistakes. 
Correctly use more than 1 
models to select the best 
model to generate a 
prediction result from the 
predict_stock_data.scv. The 
selection process is 
explained with some 
mistakes. 
Correctly use only 1 
model to generate a 
prediction result from the 
predict_stock_data.scv. 
Cannot apply a model 
for the prediction. 
e) Pattern Evaluation 
(10%) 
Correctly design the evaluation 
step and choose a relevant 
evaluation metric. 
Design the evaluation step 
and choose a relevant 
evaluation metric with 
some minor mistakes. 
Design the evaluation step 
but using a wrong 
evaluation metric. 
Design a wrong 
evaluation step and use a 
wrong evaluation metric 
but the system can still 
run. 
Cannot evaluate a 
model. 
2. Analysis (30%) 
Page 8 KIT108 Artificial Intelligence 
Generated by Akari 
a) Explain why the 
submitted model works 
well/badly (15%) 
Explain correctly why the selected 
model gave good or bad results 
using the evaluation score and the 
ground truth given after the stage 1 
submission. 
Explain with minor 
mistakes why the selected 
model gave good or bad 
results using the evaluation 
score and the ground truth 
given after the stage 1 
submission. 
Explain why the selected 
model gave good or bad 
results, partly using the 
evaluation score and the 
ground truth given after the 
stage 1 submission. 
Explain why the selected 
model works gave good or 
bad results BUT NOT 
using the evaluation score 
and the ground truth 
given after the stage 1 
submission. 
Cannot provide any 
explanation. 
b) Make a GOOD model 
(15%) 
Already have the GOOD 
evaluation score after stage 1 
submission. OR 
Explain correctly how to improve 
the performance using the ground 
truth. Provide evidence for the 
explanation (i.e. new results) 
Explain correctly how to 
improve the performance 
using the ground truth. 
Evidence for the 
explanation is not provided. 
Explain how to improve the 
performance using the 
ground truth with minor 
mistake. 
Attempt to explain how 
to improve the 
performance. 
No attempt 
 
联系我们 - QQ: 99515681 微信:codinghelp
程序辅导网!