Measure performance in both fairness metric and

performance_and_fairness(x, fairness_metric = NULL, performance_metric = NULL)

Arguments

x

object of class fairness_object

fairness_metric

fairness metric, one of metrics in fairness_objects parity_loss_metric_data (ACC, TPR, PPV, ...) Full list in fairness_check documentation.

performance_metric

performance metric, one of

Value

performance_and_fairness object. It is list containing:

  • paf_data - performance and fairness data.frame containing fairness and performance metric scores for each model

  • fairness_metric - chosen fairness metric name

  • performance_metric - chosen performance_metric name

  • label - model labels

Details

Creates perfomance_and_fairness object. Measure model performance and model fairness metric at the same time. Choose best model according to both metrics. When plotted y axis is inversed to accentuate that models in top right corner are the best according to both metrics.

Examples


data("german")

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

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


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. 4.1.1 , 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!  

fobject <- fairness_check(explainer_lm,
  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		: 1 in total (  compatible  )
#> -> Metric calculation		: 13/13 metrics calculated for all models
#>  Fairness object created succesfully  

paf <- performance_and_fairness(fobject)
#> Fairness Metric is NULL, setting deafult parity loss metric ( TPR )  
#> Performace metric is NULL, setting deafult ( accuracy )  
#> 
#> Creating object with: 
#> Fairness metric: TPR 
#> Performance metric: accuracy 
plot(paf)

# \donttest{

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

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. 0.13.1 , task classification (  default  ) 
#>   -> predicted values  :  numerical, min =  0.06497024 , mean =  0.6993924 , max =  0.9978889  
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -0.7234539 , mean =  0.0006076457 , max =  0.6197718  
#>   A new explainer has been created!  

fobject <- fairness_check(explainer_rf, fobject)
#> Creating fairness classification object
#> -> Privileged subgroup		: character ( from first fairness object  ) 
#> -> Protected variable		: factor ( from first fairness object  ) 
#> -> Cutoff values for explainers	: 0.5 ( for all subgroups ) 
#> -> Fairness objects		: 1 object (  compatible  )
#> -> Checking explainers		: 2 in total (  compatible  )
#> -> Metric calculation		: 10/13 metrics calculated for all models ( 3 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		: 10/13 metrics calculated for all models ( 3 NA created )
#>  Fairness object created succesfully  

paf <- performance_and_fairness(fobject)
#> Fairness Metric is NULL, setting deafult parity loss metric ( TPR )  
#> Performace metric is NULL, setting deafult ( accuracy )  
#> 
#> Creating object with: 
#> Fairness metric: TPR 
#> Performance metric: accuracy 

plot(paf)

# }