Machine Learning 加簽表單 Solution

● Link


Machine Learning HW1
COVID-19 Cases Prediction
ML TAs

Outline
● Objectives
● Task Description
● Data
● Evaluation Metric
● Kaggle
● Grading
● Code Submission
● Hints
● Regulations
● Useful Links

Objectives
● Solve a regression problem with deep neural networks (DNN).
● Understand basic DNN training tips e.g. hyper-parameter tuning, feature selection, regularization, …
● Get familiar with PyTorch.
Task Description
● COVID-19 Cases Prediction
● Source: Delphi group @ CMU
Try to find out the data and use it to your training is forbidden
Task Description
● Given survey results in the past 5 days in a specific state in U.S., then predict the percentage of new tested positive cases in the 5th day.

Day1&2&3&4 Day5
Data

Conducted surveys via facebook (every day & every state)
Survey: symptoms, COVID-19 testing, social distancing, mental health, demographics, economic effects, ...
Data
● States (37, encoded to one-hot vectors)
● COVID-like illness (4)
○ cli、ili …
● Behavior Indicators (8) ○ wearing_mask、travel_outside_state …
● Mental Health Indicators (3)
○ anxious、depressed …
● Tested Positive Cases (1)
○ tested_positive (this is what we want to predict)
Data -- One-hot Vector
● One-hot vectors:
Vectors with only one element equals to one while others are zero.
Usually used to encode discrete values.

●
Kaggle
● Display name: <student ID>_<anything>
○ e.g. b08901000_public跟private差好多
○ For auditing, don’t put student ID in your displayed name.
● Submission format: .csv file
○ See sample code
● link
Kaggle -- Submission
● Up to 2 submissions will be considered for the private leaderboard

Grading
● simple (public) +1 pts
● simple (private) +1 pts
● medium (public) +1 pts
● medium (private) +1 pts
● strong (public) +1 pts
● strong (private) +1 pts
● boss (public) +1 pts
● boss (private) +1 pts
● code submission +2 pts
Total : 10 pts
Grading -- Kaggle
Grading -- Bonus
● If your ranking in private set is top 3, you can choose to share a report to NTU COOL and get extra 0.5 pts.
● About the report
○ Your name and student_ID ○ Methods you used in code
○ Reference Report Template
○ in 200 words
○ Please upload to NTU COOL’s discussion of HW1

● NTU COOL
○ Compress your code and pack them into .zip file
<student_ID>_hw1.zip
● Do not submit models and data
● Submit the code you chose in Kaggle (One of the best)
● Your .zip file should include only ○ Code: either .py or .ipynb
● Example:

● How to download your code ● from Google Colab?
● How to compress your folder?
● Method 1 (for Windows users)
○ https://support.microsoft.com/en-us/windows/zip-and-unzip-files-f6dde0a7-0fec-8294-e1d3-703ed85e7ebc

● How to compress your folder?
● Method 2 (for Mac users)
○ https://support.apple.com/zh-tw/guide/mac-help/mchlp2528/mac

● How to compress your folder?
● Method 3 (command line)


Hints
simple : sample code medium : Feature selection strong : Different model architectures and optimizers boss : L2 regularization and try more parameters
Deadlines
● Kaggle
● NTU COOL
Regulations
● You should finish your homework on your own.
● You should not modify your prediction files manually
● Do not share codes or prediction files with any living creatures.
● Do not use any approaches to submit your results more than 5 times a day.
● Do not search or use additional data or pre-trained models.
● Your final grade x 0.9 and this HW will get 0 pt if you violate any of the above rules.
● Prof. Lee & TAs preserve the rights to change the rules & grades.
Contact us if you have problems…
● NTU COOL (Best way) ○ link
● Email
○ The title should begin with “[hw1]”
Useful Links
● Hung-yi Lee, Gradient Descent (Mandarin)
○ link1, link2, link3, link4
● Hung-yi Lee, Tips for Training Deep Networks (Mandarin)
○ link1, link2
● Pytorch Toolkit
● Link that can find all things
FAQ
FAQ
1. L2 regularization 除了 sample code 提供的在計算 loss 時處理之外，也可以使用 optimizer 的 weight_decay 實現，可參考 🔗 PyTorch 官方文檔
2. sklearn、 TensorFlow、 xgboost 是可以使用的（使用額外線上資源請附上 Reference）
3. 只要 Post-processing 是由程式自動完成，且並未違反規定（如使用 pre-trained model、直接輸出 hardcode 的結果、上網爬資料等），都是可以接受的，另外，請記得將後處理的程式一併交上，若沒有交上，將視為違反規定。
4. 同學只要確認上傳時的檔名正確，COOL 系統內部會在同名的檔案依照版本順序加上編號，忽略即可（如 "學號_hw1-1.zip" 等）。另外請同學確認最後一次上傳的版本是正確的，我們只會認最新的版本