library("DALEX")
#> Welcome to DALEX (version: 2.4.3).
#> Find examples and detailed introduction at: http://ema.drwhy.ai/
#> Additional features will be available after installation of: ggpubr.
#> Use 'install_dependencies()' to get all suggested dependencies
#> 
#> Attaching package: ‘DALEX’
#> The following object is masked from ‘package:modelStudio’:
#> 
#>     happiness_train
library("modelStudio")

#:# ex1 classification on 'titanic' data

# fit a model
model_titanic <- glm(survived ~., data = titanic_imputed, family = "binomial")

# create an explainer for the model
explainer_titanic <- explain(model_titanic,
                             data = titanic_imputed,
                             y = titanic_imputed$survived,
                             label = "Titanic GLM")
#> Preparation of a new explainer is initiated
#>   -> model label       :  Titanic GLM 
#>   -> data              :  2207  rows  8  cols 
#>   -> target variable   :  2207  values 
#>   -> predict function  :  yhat.glm  will be used (  default  )
#>   -> predicted values  :  No value for predict function target column. (  default  )
#>   -> model_info        :  package stats , ver. 4.3.1 , task classification (  default  ) 
#>   -> predicted values  :  numerical, min =  0.008128381 , mean =  0.3221568 , max =  0.9731431  
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -0.9628583 , mean =  -2.569721e-10 , max =  0.9663346  
#>   A new explainer has been created!  

# pick observations
new_observations <- titanic_imputed[1:2,]
rownames(new_observations) <- c("Lucas","James")

# make a studio for the model
modelStudio(explainer_titanic,
            new_observations,
            N = 200,  B = 5) # faster example


# \donttest{

#:# ex2 regression on 'apartments' data
if (requireNamespace("ranger", quietly=TRUE)) {
  library("ranger")
  model_apartments <- ranger(m2.price ~. ,data = apartments)

  explainer_apartments <- explain(model_apartments,
                                  data = apartments,
                                  y = apartments$m2.price)

  new_apartments <- apartments[1:2,]
  rownames(new_apartments) <- c("ap1","ap2")

  # change dashboard dimensions and animation length
  modelStudio(explainer_apartments,
              new_apartments,
              facet_dim = c(2, 3),
              time = 800)

  # add information about true labels
  modelStudio(explainer_apartments,
              new_apartments,
              new_observation_y = new_apartments$m2.price)

  # don't compute EDA plots
  modelStudio(explainer_apartments,
              eda = FALSE)
}
#> Preparation of a new explainer is initiated
#>   -> model label       :  ranger  (  default  )
#>   -> data              :  1000  rows  6  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. 0.15.1 , task regression (  default  ) 
#>   -> predicted values  :  numerical, min =  1862.603 , mean =  3488.076 , max =  6151.122  
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -395.6787 , mean =  -1.057155 , max =  612.919  
#>   A new explainer has been created!  
#> `new_observation` argument is NULL. `new_observation_n` observations needed to calculate local explanations are taken from the data.


#:# ex3 xgboost model on 'HR' dataset
if (requireNamespace("xgboost", quietly=TRUE)) {
  library("xgboost")
  HR_matrix <- model.matrix(status == "fired" ~ . -1, HR)

  # fit a model
  xgb_matrix <- xgb.DMatrix(HR_matrix, label = HR$status == "fired")
  params <- list(max_depth = 3, objective = "binary:logistic", eval_metric = "auc")
  model_HR <- xgb.train(params, xgb_matrix, nrounds = 300)

  # create an explainer for the model
  explainer_HR <- explain(model_HR,
                          data = HR_matrix,
                          y = HR$status == "fired",
                          type = "classification",
                          label = "xgboost")

  # pick observations
  new_observation <- HR_matrix[1:2, , drop=FALSE]
  rownames(new_observation) <- c("id1", "id2")

  # make a studio for the model
  modelStudio(explainer_HR,
              new_observation)
}
#> Preparation of a new explainer is initiated
#>   -> model label       :  xgboost 
#>   -> data              :  7847  rows  6  cols 
#>   -> target variable   :  7847  values 
#>   -> predict function  :  yhat.default will be used (  default  )
#>   -> predicted values  :  No value for predict function target column. (  default  )
#>   -> model_info        :  package Model of class: xgb.Booster package unrecognized , ver. Unknown , task regression (  default  ) 
#>   -> model_info        :  type set to  classification 
#>   -> model_info        :  Model info detected classification task but 'y' is a logical . Converted to numeric.  (  NOTE  )
#>   -> predicted values  :  numerical, min =  1.158531e-06 , mean =  0.36388 , max =  0.9997931  
#>   -> residual function :  difference between y and yhat (  default  )
#>   -> residuals         :  numerical, min =  -0.9830738 , mean =  -4.673041e-05 , max =  0.9703595  
#>   A new explainer has been created!  

# }