PyEvALL 0.1.68

PyEvALL (The Python library to Evaluate ALL) is a evaluation tool for information systems that allows assessing a wide range of metrics covering various evaluation contexts, including classification, ranking, or LeWiDi (Learning with disagreement).

PyEvALL

PyEvALL (The Python library to Evaluate ALL) is an evaluation tool for information systems that allows assessing a wide range of metrics covering various evaluation contexts, including classification, ranking, or LeWiDi (Learning with disagreement). PyEvALL is designed based on the following concepts: (i) persistence, users can save evaluations and retrieve past evaluations; (ii) replicability, all evaluations are conducted using the same methodology, making them strictly comparable; (iii) effectiveness, all metrics are unified under measurement theory and have been doubly implemented and compared; (iv) generalization, achieved through the use of a standardized input format enabling users to evaluate all evaluation contexts.