Calculate PC for metric_matrix to see similarities between models and metrics. If omit_models_with_NA is set to TRUE models with NA will be omitted as opposed to default behavior, when metrics are omitted.

fairness_pca(x, omit_models_with_NA = FALSE)

Arguments

x

object of class fairness object

omit_models_with_NA

logical, if TRUE omits rows in metric_matrix, else omits columns (default)

Value

fairness_pca object It is list containing following fields:

Examples


data("german")

y_numeric <- as.numeric(german$Risk) -1

lm_model <- glm(Risk~.,
                data = german,
                family=binomial(link="logit"))

rf_model <- ranger::ranger(Risk ~.,
                           data = german,
                           probability = TRUE,
                           num.trees = 200,
                           num.threads = 1)

explainer_lm <- DALEX::explain(lm_model, data = german[,-1], y = y_numeric)
#> Preparation of a new explainer is initiated
#>   -> model label       :  lm  (  default  )
#>   -> data              :  1000  rows  9  cols 
#>   -> target variable   :  1000  values 
#>   -> predict function  :  yhat.glm  will be used (  default  )
#>   -> predicted values  :  No value for predict function target column. (  default  )
#>   -> model_info        :  package stats , ver. 4.1.0 , task classification (  default  ) 
#>   -> predicted values  :  numerical, min =  0.1369187 , mean =  0.7 , max =  0.9832426  
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -0.9572803 , mean =  1.940006e-17 , max =  0.8283475  
#>   A new explainer has been created!  
explainer_rf <- DALEX::explain(rf_model, data = german[,-1], y = y_numeric)
#> Preparation of a new explainer is initiated
#>   -> model label       :  ranger  (  default  )
#>   -> data              :  1000  rows  9  cols 
#>   -> target variable   :  1000  values 
#>   -> predict function  :  yhat.ranger  will be used (  default  )
#>   -> predicted values  :  No value for predict function target column. (  default  )
#>   -> model_info        :  package ranger , ver. 0.12.1 , task classification (  default  ) 
#>   -> predicted values  :  numerical, min =  0.05815476 , mean =  0.6969663 , max =  0.9975069  
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -0.7217679 , mean =  0.003033675 , max =  0.6242611  
#>   A new explainer has been created!  

fobject <- fairness_check(explainer_lm, explainer_rf,
                          protected = german$Sex,
                          privileged = "male")
#> Creating fairness classification object
#> -> Privileged subgroup		: character ( Ok  )
#> -> Protected variable		: factor ( Ok  ) 
#> -> Cutoff values for explainers	: 0.5 ( for all subgroups ) 
#> -> Fairness objects		: 0 objects 
#> -> Checking explainers		: 2 in total (  compatible  )
#> -> Metric calculation		: 10/12 metrics calculated for all models ( 2 NA created )
#>  Fairness object created succesfully  

 # same explainers with different cutoffs for female
fobject <- fairness_check(explainer_lm, explainer_rf, fobject,
                          protected = german$Sex,
                          privileged = "male",
                          cutoff = list( female = 0.4),
                          label = c("lm_2", "rf_2"))
#> Creating fairness classification object
#> -> Privileged subgroup		: character ( Ok  )
#> -> Protected variable		: factor ( Ok  ) 
#> -> Cutoff values for explainers	: female: 0.4, male: 0.5 
#> -> Fairness objects		: 1 object (  compatible  )
#> -> Checking explainers		: 4 in total (  compatible  )
#> -> Metric calculation		: 10/12 metrics calculated for all models ( 2 NA created )
#>  Fairness object created succesfully  

fpca <- fairness_pca(fobject)
#> Warning: Found metric with NA: FNR, FOR, omiting it

plot(fpca)