MLDSII - Assignment

Spamfilter

This is the repository for the Machine Learning & Data Science 2 final Assignment. The goal is to create a spam filter for emails. The datasets are from the SpamAssassin Public Corpus and are in the 'Datasets' folder. The source code is in the 'main.py' file. The report with explanation of the code and decisions is in the 'Report_SpamFilter_Maximilian_Nachbaur.pdf' file.

Setup

For this project I used:

• python as programming language
• PDM for the python package management since we also used this in the course

Python

The Version is python 3.12.* for this project. For the complete dependencies see pyproject.toml.

PDM

To install pdm run

curl -sSL https://pdm-project.org/install-pdm.py | python3 -

Initialize

The pdm project already exists so all you need to do is to run

pdm sync

or

pdm install

to initialize the project.

Start a script

To start a script use

pdm run python <SCRIPT.py> <arguments>

You can also start a python console via

pdm run python

Note, that both will respect the .env file and load the variables accordingly.