evaluate_classifiers_from_file

tsml_eval.evaluation.evaluate_classifiers_from_file(load_paths, save_path, error_on_missing=True, eval_name=None, verify_results=True, estimator_names=None)

Evaluate multiple classifiers on multiple datasets from file.

Writes multiple csv files and figures to save_path, one for each statistic evaluated. Provides a summary csv file with the average statistic and average rank for each classifier.

Parameters:

load_pathslist of str

The paths to the classifier result files to evaluate.

save_pathstr

The path to save the evaluation results to.

error_on_missingbool, default=True

Whether to raise an error if results are missing.

eval_namestr, default=None

The name of the evaluation, used in save_path.

verify_resultsbool, default=True

If the verification should be performed on the loaded results values.

estimator_nameslist of str, default=None

The names of the estimator for each classifier result. If None, uses the estimator_name attribute of each classifier result.