Benchmark framework for scientists
Project description
Metrika is a library to run and measure benchmarks with scientific rigor. By automating the process of benchmark running, scientists can avoid common mistakes. Metrika allows to obtain statistically solid measures without accidentally introducing methodological errors. In order to do that, the library executes the benchmarks many times and presents results taking into account things like expected value, standard deviation, etc.
This version requires Python 3 or later