Calculated empirical density and weight based on variable split.

This function calculate an empirical density of raw data based on variable split from Ceteris Paribus profiles. Then calculated weight for values generated by DALEX::predict_profile(), DALEX::individual_profile() or ingredients::ceteris_paribus().

calculate_weight(profiles, data, variable_split)

Arguments

profiles	`data.frame` generated by `DALEX::predict_profile()`, `DALEX::individual_profile()` or `ingredients::ceteris_paribus()`
data	`data.frame` with raw data to model
variable_split	list generated by `vivo::calculate_variable_split()`

Value

Return an weight based on empirical density.

Examples


library("DALEX", warn.conflicts = FALSE, quietly = TRUE)
#> Welcome to DALEX (version: 2.0).
#> Find examples and detailed introduction at: https://pbiecek.github.io/ema/
data(apartments)

split <- vivo::calculate_variable_split(apartments,
                        variables = colnames(apartments),
                        grid_points = 101)

library("randomForest", warn.conflicts = FALSE, quietly = TRUE)
#> randomForest 4.6-14
#> Type rfNews() to see new features/changes/bug fixes.
apartments_rf_model <- randomForest(m2.price ~ construction.year + surface +
                                    floor + no.rooms, data = apartments)

explainer_rf <- explain(apartments_rf_model, data = apartmentsTest[,2:5],
                        y = apartmentsTest$m2.price)
#> Preparation of a new explainer is initiated
#>   -> model label       :  randomForest  (  default  )
#>   -> data              :  9000  rows  4  cols 
#>   -> target variable   :  9000  values 
#>   -> predict function  :  yhat.randomForest  will be used (  default  )
#>   -> predicted values  :  numerical, min =  2105.619 , mean =  3515.128 , max =  5346.334  
#>   -> model_info        :  package randomForest , ver. 4.6.14 , task regression (  default  ) 
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -1235.195 , mean =  -3.604187 , max =  2168.808  
#>   A new explainer has been created!  

new_apartment <- data.frame(construction.year = 1998, surface = 88, floor = 2L, no.rooms = 3)

profiles <- predict_profile(explainer_rf, new_apartment)

library("vivo")
calculate_weight(profiles, data = apartments[, 2:5], variable_split = split)
#> $construction.year
#>   [1] 0.004 0.004 0.011 0.013 0.005 0.012 0.012 0.011 0.016 0.011 0.015 0.000
#>  [13] 0.003 0.016 0.008 0.011 0.012 0.013 0.011 0.011 0.012 0.000 0.008 0.014
#>  [25] 0.011 0.007 0.006 0.012 0.013 0.014 0.013 0.000 0.014 0.017 0.011 0.008
#>  [37] 0.010 0.008 0.009 0.007 0.017 0.000 0.018 0.011 0.016 0.010 0.009 0.010
#>  [49] 0.010 0.009 0.013 0.000 0.007 0.011 0.016 0.011 0.010 0.018 0.010 0.009
#>  [61] 0.006 0.000 0.016 0.003 0.014 0.008 0.005 0.011 0.011 0.006 0.013 0.000
#>  [73] 0.009 0.017 0.009 0.015 0.008 0.012 0.015 0.012 0.015 0.000 0.011 0.016
#>  [85] 0.009 0.013 0.015 0.012 0.012 0.007 0.009 0.000 0.009 0.010 0.015 0.014
#>  [97] 0.004 0.010 0.010 0.012 0.003
#> 
#> $surface
#>   [1] 0.009 0.009 0.004 0.007 0.026 0.010 0.005 0.008 0.006 0.012 0.015 0.007
#>  [13] 0.004 0.004 0.017 0.011 0.014 0.014 0.006 0.007 0.012 0.006 0.008 0.008
#>  [25] 0.015 0.009 0.014 0.012 0.010 0.011 0.012 0.008 0.011 0.011 0.021 0.006
#>  [37] 0.008 0.012 0.006 0.006 0.013 0.005 0.004 0.007 0.016 0.007 0.006 0.016
#>  [49] 0.008 0.009 0.017 0.009 0.008 0.003 0.016 0.008 0.005 0.020 0.009 0.004
#>  [61] 0.012 0.004 0.005 0.007 0.012 0.007 0.014 0.026 0.010 0.006 0.018 0.009
#>  [73] 0.009 0.009 0.014 0.002 0.009 0.008 0.010 0.006 0.017 0.006 0.007 0.017
#>  [85] 0.012 0.009 0.011 0.016 0.004 0.001 0.015 0.007 0.003 0.005 0.019 0.004
#>  [97] 0.012 0.016 0.010 0.017 0.013
#> 
#> $floor
#>   [1] 0.090 0.090 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
#>  [13] 0.116 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.087
#>  [25] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.086 0.000
#>  [37] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.095 0.000 0.000
#>  [49] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.104 0.000 0.000 0.000
#>  [61] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.103 0.000 0.000 0.000 0.000
#>  [73] 0.000 0.000 0.000 0.000 0.000 0.000 0.103 0.000 0.000 0.000 0.000 0.000
#>  [85] 0.000 0.000 0.000 0.000 0.000 0.108 0.000 0.000 0.000 0.000 0.000 0.000
#>  [97] 0.000 0.000 0.000 0.000 0.108
#> 
#> $no.rooms
#>   [1] 0.099 0.099 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
#>  [13] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.202 0.000 0.000 0.000
#>  [25] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
#>  [37] 0.000 0.000 0.000 0.000 0.231 0.000 0.000 0.000 0.000 0.000 0.000 0.000
#>  [49] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
#>  [61] 0.223 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
#>  [73] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.198 0.000 0.000 0.000
#>  [85] 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000
#>  [97] 0.000 0.000 0.000 0.000 0.047
#>