Learning repo to train a model using StackOverflow data set questions and classify questions as good questions or bad questions
- install pip packages
- Download dataset from: https://www.kaggle.com/datasets/stackoverflow/rquestions?resource=download and move to
/src/assets/questions.csv
- Pré-process the dataset on
src/assets/questions.csv
running on root:python3 ./src/pre_process.py
- Train and run the model
python ./src/train.py