Arena is an interactive tool that allows you to explore and compare any model regardless of its internal structure.
The arena can be run in two modes - live (R runs in the background and calculates all necessary explanations) and serverless (all necessary explanations are calculated earlier).
Using the Arena is trivially simple. An example with different levels of advancement is available at http://arenar.drwhy.ai/.
ArenaR package from GitHub.
Examples generated with ArenaR
library(arenar) library(gbm) library(DALEX) library(dplyr) # Create models and DALEX explainers model_gbm100 <- gbm(m2.price ~ ., data = apartments, n.trees = 100) expl_gbm100 <- explain( model_gbm100, data = apartments, y = apartments$m2.price, label = "gbm [100 trees]" ) model_gbm500 <- gbm(m2.price ~ ., data = apartments, n.trees = 500) expl_gbm500 <- explain( model_gbm500, data = apartments, y = apartments$m2.price, label = "gbm [500 trees]" ) create_arena(live = TRUE) %>% # Pushing explainers for each models push_model(expl_gbm100) %>% push_model(expl_gbm500) %>% # Push dataframe of observations push_observations(apartments) %>% # Run server of default port and ip run_server()