Repository files navigation

1. Installuv
2. Set up the environment:

uv sync

1. Download the dataset fromKaggle

2. Move the downloaded file todata/raw/

Run the data processing script:

uv run src/process.py

Run the model training script:

uv run src/train_model.py

Both scripts use Hydra for configuration management. The default configurations are in theconf/main.yaml file. You can override any configuration parameter using the command line. For example:

# Override test size in process.pyuv run src/process.py process.test_size=0.3# Override hyperparameters in train_model.pyuv run src/train_model.py train.hyperparameters.svm__C=10

To see all available configuration options, you can use the--help flag:

# View configuration options for process.pyuv run src/process.py --help# View configuration options for train_model.pyuv run src/train_model.py --help