An Investigation on the UK Traffic Accidents Dataset: https://www.kaggle.com/datasets/silicon99/dft-accident-data/data [ECE356]
- Created a normalized and scalable entity-relationship model & relational schema
- Instantiated a database instance and loaded all SQL tables with data + respective transformations
- Developed a python cli and a random-forest classification model from the ground up
Please contact me if you want learn more about the project and/or want to see the code. (Redacted for confidentiality and compliance with P-71)
- Languages: Python, SQL
- Libraries/Frameworks/Tools: Pandas, Juypter Notebooks
- Other:
- Concepts: ER Diagrams, Relational Schema Mapping, Normal Forms, Data Redundancy, Indexes, Database Performance, Multi-classification, Random-Forest Classification, Feature Engineering & Selection