Group Repository for the Data Science Mini-Project (EMATM0050)

Please edit the fields below with your information

Group Number: 19

Problem Assigned: Problem B, JP Morgan

Group Members:

Key Information

Refer to DSMP_ProbB_JPMorgan_2024.pdf for specification.

Miro: https://miro.com/app/board/uXjVN1HIwH0=/

Planner: https://docs.google.com/spreadsheets/d/1NDi2MzhVfda5drRDP5jcF_mk6-M7fUVzl-QAB9SO84U/edit#gid=1342127810

Note: Need to make planner private

Structure

Store raw LOB data within Data/LOB

Store raw Tapes data within Data/Tapes

Store processed LOB data into Processed_Data/Clean_LOB

Setting up the environment

Open the command prompt and navigate to the local github's directory, this is my example:

cd C:\Users\wwden\OneDrive\Documents\GitHub\Group_19_DSMP_Task_B

Assuming you have python3 installed run:

python -m venv venv

This will take a few minutes to install a vitrual environment, then we will active the virtual environment and install python modules, this will take up to 10 minutes:

venv\Scripts\Activate.bat
pip install -r requirements.txt

Then to run the jupyter notebook:

jupyter notebook

Then navitage to http://127.0.0.1:8888/tree

Dev Log

Week 14

• Finished Planner
• Started literature review
• Started ARIMA
• Started EDA

25/01/2024 - Week 13 First Group meeting

• Talked through the problem definition and structure of the project
• Set up the Github and Miro