Senior Data Scientist Project - Neofytos

Overview

This project analyzes order data for 2022 and 2023. The goal is to:

Analyze order journeys and calculate conversion rates.
Develop a recommendation system for items displayed on the website's landing page.

Project Structure

/data/: Raw datasets.
/src/: Python scripts for ETL, analysis, and recommendations.
/tests/: Unit tests.
/database/: The directory where the local database is stored

How to set-up (first time)

Create a virtual environment and install dependencies make install
Copy the input csv file to the data directory.

How to run

Activate the virtual environment make activate
Run ETL and create the DB: make setup_db
Run part A1: make run-A1
Run part A2: make run-A2
Run part B: make run-B1
Run tests: make test

How to run (without using the Makefile)

(only first time) setup venv: python -m venv venv/
Activate the venv: source venv/bin/activate
(only first time) install dependencies: pip install -r requirements.txt
Run ETL and create the DB: python src/setup_db.py
Run part A1: python src/A1.Volumetrics.py
Run part A2: python src/A2.Conversion_rate.py
Run part B: python src/B.recommendation_system.py
Run tests: pytest tests/