This PR is the second of many to restructure the evaluate model module and output the evaluations in tidy long format for later figure generation.
In this PR, a separate notebook is created to display the f1 scores for the final and shuffled baseline models' predictions for the train and test datasets. These f1 scores are converted to tidy long format and saved.
This is ready for review!
This PR is the second of many to restructure the evaluate model module and output the evaluations in tidy long format for later figure generation.
In this PR, a separate notebook is created to display the f1 scores for the final and shuffled baseline models' predictions for the train and test datasets. These f1 scores are converted to tidy long format and saved.