11/22 Meeting - Milestone 2 Tasks

[thomassiu]

Reflections of last week (10 mins)

• Re-group (Briefly understand our backgrounds again)
• What we did well
• What we can improve (Process, Git, Communications... etc)

Milestone 2 checklist (15 mins)

• [x] Write a script that reads the downloaded data and performs and data cleaning/pre-processing, transforming, and/or splitting
  • [x] download script: improve the script based on feedbacks from TA - Carry forward to M3
  • [x] download script: choose a more descriptive filename than the one used for illustrative purpose
  • [x] Data cleaning/pre-processing script: Create the script that takes data from download script
• [x] Write a script which creates exploratory data visualization(s) and table(s) that are useful to help the reader/consumer understand that data set
  • [x] EDA script: A script which creates exploratory data visualisations and tables
  • [x] Improve the EDA analysis
• [x] Write a script that performs some statistical or machine learning analysis and summarizes the results as a figure(s) and a table(s)
  • [x] Analysis script: A script that performs statistical or ML analysis and summarizes the results as figures and tables.
• [ ] Write a literate code document which presents your analysis and findings
  • [ ] Written narrative in .Rmd or .ipynb that introduces and justifies our questions etc
• [ ] Iterate on work done for milestone 1 as required per TA feedback

Division of work and timeline (10 mins)

TBD

AOB (5 mins)

TBD

[thomassiu]

Here are the meeting re-cap:

• For simplicity, we will use Python as the programming language. That is also easier to manage for ML.
• Branching on the forked repo is not a must. As long as we can manage the PR that will be OK.
• Thomas did a trial on:

1. git pull from upstream to local
2. Create a feature branch in forked repo
3. Make a PR directly to the upstream main branch
4. Once it is merged, delete the forked feature branch
5. git pull again from upstream to update the main branch

We should all work together but the following are the person to take charge. Download script + data pre-processing: Thomas EDA script + EDA enhancement: Shi Yan Analysis and model training: Ramiro Literate code document: Jasmine

[thomassiu]

Pull request made for pre-processing script. At the same time models are trained for discussions.

[thomassiu]

Have also explored using jupyter book - need to download to view

https://github.com/thomassiu/DSCI_522_Crime_Prediction_Vancouver/tree/jupyter_book_demo/reports

[sy25wang]

Pull request made for eda analysis.

[thomassiu]

All tasks completed.