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.