Wine classification project
Dependencies for conda and pip are listed in environment.yml
In the project base folder execute in the command line:
conda env create -f environment.yml
From the command line, navigate to the src directory and run:
python get_dataset.py
This will also generate the data directory if not already existing.
To preprocess the data, run:
python notebooks/examine_data.py
From the command line, navigate to the src directory and run:
python preliminary_model.py --study_name {name_of_your_study}
After you have submitted the above model run, open a new terminal and
navigate to the src directory and run:
mlflow ui
Follow the link generated to track your model, performance stats, artifacts and pipelines.
Similar to the above, open a new terminal
navigate to the src directory and run:
optuna-dashboard sqlite:///db.sqlite3
Follow the link generated to track your study.
