evaluate module

Automated Machine Learning Environment (AMLE)

Evaluate library provides a class with methods to evaluate result data against desired results

class evaluate.Evaluate(logger)

Bases: object

Class with methods for evaluating result data

simple_accuracy(results, threshold)

Evaluation of simple results data that is in the form of a list of dictionaries, each of which contain two KVPs:

  • actual
  • computed

All result values are floats

A threshold is passed in, and if the actual result is +/- threshold of computed result then it is recorded as correct otherwise incorrect.

Returns accuracy percentage as an integer between 0 and 100.