RMIT Classification: Trusted
Assignment 1
COSC 2673-2793 | Semester 1 2021 (computational) Machine Learning
Image: Freepik.com
RMIT Classification: Trusted
Key Dates and Important Information
Ø Assignment Type: Individual
Ø Due: Friday 16th April 2021 (Week 6)
Ø Marks: 30%
Ø Specifications: on canvas – Specification PDF & Marking rubric
Ø Late policy: After the due date, you will have 5 days to submit your assignment as a late submission. Late submissions will incur a penalty of 10% per day. After these five days, Canvas will be closed and you will lose ALL the assignment marks.
Clarifications/updates may be made via announcements/relevant discussion forums.
COSC2673 | COSC2793 Week 4: Evaluating Hypotheses 3
RMIT Classification: Trusted
Task
The machine learning task we are interested in is:
“Predict if a given patient (i.e. newborn child) will be discharged from the hospital within 3 days (class 0) or will stay in hospital beyond that – 4 days or more (class 1).”
COSC2673 | COSC2793 Week 4: Evaluating Hypotheses 4
RMIT Classification: Trusted
Dataset
The data set for this assignment is available on Canvas.
Ø README.md: Description of dataset.
Ø train_data.csv: This data is to be used in developing the
Ø test_data.csv: You need to make predictions for this data and submit the prediction via canvas.
Ø s1234567_predictions.csv: expected format for your predictions on the unseen test data. Any deviation from this format will result on zero marks for the results part.
COSC2673 | COSC2793 Week 4: Evaluating Hypotheses 5
RMIT Classification: Trusted
Restrictions
ØYou must NOT explicitly perform manual feature selection. That is, your models should have all features (attributes) as input (except the “ID” and “Health Service Area” fields which are not attributes).
ØYou are only allowed to use techniques taught in class up to week 5 (inclusive) for this assignment. That is, you are NOT allowed to use ML techniques such as: Neural networks or SVM for this task.
COSC2673 | COSC2793 Week 4: Evaluating Hypotheses 6
RMIT Classification: Trusted
Deliverables
Ø The PDF version of the python notebook used for the model development including critical analysis of your approach and ultimate judgement.
Ø A set of predictions from your ultimate judgement. Should be in CSV format. If your model predicts the patient will be discharged from the hospital within 3 days, the associated “LengthOfStay” value in CSV should be 0 (1 otherwise).
Ø Your code (Jupyter notebooks) used to perform your analysis. Should be a ZIP le containing all the support les. will be used for plagiarism checking – notebook should match PDF.
COSC2673 | COSC2793 Week 4: Evaluating Hypotheses 7
Marking Guidelines
Ø Approach 50%;
Ø Ultimate Judgment & Analysis
20%;
Ø Performance on test set (Unseen data) 20%;
Ø Implementation 10%; Rubric attached on canvas
Practice the typical machine learning process which includes:
• Selecting the appropriate ML techniques and applying them to solve a real-world ML problem.
• Analysing the output of the algorithm(s).
• Research how to extend the modelling techniques that are taught in class.
• Providing an ultimate judgement of the nal trained model that you would use in a real-world setting.
RMIT Classification: Trusted
COSC2673 | COSC2793 Week 4: Evaluating Hypotheses 8
RMIT Classification: Trusted
Academic Integrity and Plagiarism
You code and report will be screened using plagiarism checking software.
ØPDF Notebook: Turnitin ØCode: CodeQuiry
See section 6 on assignment specifications for more details.
COSC2673 | COSC2793 Week 4: Evaluating Hypotheses 9