Plot and compare performance of model between training and test set

Function plot.training_test_comparison plots dependency between model performance on test and training dataset based on training_test_comparison object. Green line indicates y = x line.

# S3 method for training_test_comparison
plot(x, ...)

Arguments

x

- object created with training_test_comparison function.

...

- other parameters

Value

ggplot object

Examples

library("mlr")
library("DALEXtra")
task <- mlr::makeRegrTask(
 id = "R",
  data = apartments,
   target = "m2.price"
)
 learner_lm <- mlr::makeLearner(
 "regr.lm"
)
model_lm <- mlr::train(learner_lm, task)
explainer_lm <- explain_mlr(model_lm, apartmentsTest, apartmentsTest$m2.price, label = "LM")
#> Preparation of a new explainer is initiated
#>   -> model label       :  LM 
#>   -> data              :  9000  rows  6  cols 
#>   -> target variable   :  9000  values 
#>   -> predict function  :  yhat.WrappedModel  will be used (  default  )
#>   -> predicted values  :  No value for predict function target column. (  default  )
#>   -> model_info        :  package mlr , ver. 2.19.0 , task regression (  default  ) 
#>   -> predicted values  :  numerical, min =  1792.597 , mean =  3506.836 , max =  6241.447  
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -257.2555 , mean =  4.687686 , max =  472.356  
#>   A new explainer has been created!  

learner_rf <- mlr::makeLearner(
"regr.ranger"
)
model_rf <- mlr::train(learner_rf, task)
explainer_rf <- explain_mlr(model_rf, apartmentsTest, apartmentsTest$m2.price, label = "RF")
#> Preparation of a new explainer is initiated
#>   -> model label       :  RF 
#>   -> data              :  9000  rows  6  cols 
#>   -> target variable   :  9000  values 
#>   -> predict function  :  yhat.WrappedModel  will be used (  default  )
#>   -> predicted values  :  No value for predict function target column. (  default  )
#>   -> model_info        :  package mlr , ver. 2.19.0 , task regression (  default  ) 
#>   -> predicted values  :  numerical, min =  1804.141 , mean =  3504.064 , max =  6267.479  
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -523.2376 , mean =  7.459475 , max =  740.8489  
#>   A new explainer has been created!  

learner_gbm <- mlr::makeLearner(
"regr.gbm"
)
model_gbm <- mlr::train(learner_gbm, task)
explainer_gbm <- explain_mlr(model_gbm, apartmentsTest, apartmentsTest$m2.price, label = "GBM")
#> Preparation of a new explainer is initiated
#>   -> model label       :  GBM 
#>   -> data              :  9000  rows  6  cols 
#>   -> target variable   :  9000  values 
#>   -> predict function  :  yhat.WrappedModel  will be used (  default  )
#>   -> predicted values  :  No value for predict function target column. (  default  )
#>   -> model_info        :  package mlr , ver. 2.19.0 , task regression (  default  ) 
#>   -> predicted values  :  numerical, min =  2136.593 , mean =  3504.174 , max =  6055.176  
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -533.5925 , mean =  7.350052 , max =  735.7954  
#>   A new explainer has been created!  

data <- training_test_comparison(explainer_lm, list(explainer_gbm, explainer_rf),
                                 training_data = apartments,
                                 training_y = apartments$m2.price)
plot(data)