1. training_notebook.ipynb is the jupyter notebook that contains the source code for training a Species Distribution Model (SDM).
2. prediction_notebook.ipynb contains the source code for test prediction

git clone https://github.com/chong915/2022DSC.git

conda env create -n <env_name> -f 2022DSC/environment.yaml

conda activate <env_name>

train.py is the source code for training the SDM model. MLflow is also used for managing the trained models.

python 2022DSC/train.py <n_iter> <cv>

1. n_iter (Default - 10) : Number of parameters settings that are sample in randomized search cross validation
2. cv (Default - 5) : Determines how many folds of cross validation

mlflow ui