VERIFY
- class verify(**kwargs)
Class containing all the functions from the VERIFY module.
Parameters
- kwargsargument class
Specify any arguments from the VERIFY module (for a complete list of variables, visit the ROBERT documentation)
- analyze_tests(verify_results)
Function to check whether the tests pass and retrieve the corresponding colors: 1. Blue for passing tests 2. Red for failing tests
- onehot_test(verify_results, Xy_data, model_data)
Calculate the accuracy of the model when using one-hot models. All X values that are not 0 are considered to be 1 (NaN from missing values are converted to 0).
- print_verify(results_print, verify_results, print_ver, model_data)
Print and store the results of VERIFY
- ymean_test(verify_results, Xy_data, model_data)
Calculate the accuracy of the model when using a flat line of predicted y values. For regression, the mean of the y values is used. For classification, the value that is predicted more often is used.
- yshuffle_test(verify_results, Xy_data, model_data)
Calculate the accuracy of the model when the y values are randomly shuffled in the validation set For example, a y array of 1.3, 2.1, 4.0, 5.2 might become 2.1, 1.3, 5.2, 4.0.
Parameters
- destinationstr, default=None,
Directory to create the output file(s).
- varfilestr, default=None
Option to parse the variables using a yaml file (specify the filename, i.e. varfile=FILE.yaml).
- params_dirstr, default=''
Folder containing the database and parameters of the ML model to analyze.
- seedint, default=0
Random seed used in the ML predictor models and other protocols.
- kfoldint, default=5
Number of random data splits for the cross-validation of the models.
- repeat_kfoldsint, default=10
Number of repetitions for the k-fold cross-validation of the models.