cancer-estimator-model

Our model search repository to find the best model to calculate risk of having lung cancer.

How to setup

Dependencies

You should have installed:

• git for code versioning
• dvc for data versioning
• pdm for project managing

Install env and run notebooks

After cloning the repository, at the root of the repository call the following commands.

Install the libraries necessary to run the code:

pdm install

Mount datasets folder with proper data for analysis and model search:

pdm run dvc pull

Run the jupyter notebook server with all libraries, including our lib cancer_estimator_model:

pdm notebook

Data integration

To perform data integration you will need the R environment installed in your machine, then you can call as:

pdm data-integration

It will integrate all data and write in the path datasets/lung-cancer/dataset_integrated.csv.

At first call it may take sometime to install all libraries.