auditor 01

auditor

library(auditor)
library(DALEX)
data(dragons)
head(dragons)

##   year_of_birth   height   weight scars colour year_of_discovery
## 1         -1291 59.40365 15.32391     7    red              1700
## 2          1589 46.21374 11.80819     5    red              1700
## 3          1528 49.17233 13.34482     6    red              1700
## 4          1645 48.29177 13.27427     5  green              1700
## 5            -8 49.99679 13.08757     1    red              1700
## 6           915 45.40876 11.48717     2    red              1700
##   number_of_lost_teeth life_length
## 1                   25   1368.4331
## 2                   28   1377.0474
## 3                   38   1603.9632
## 4                   33   1434.4222
## 5                   18    985.4905
## 6                   20    969.5682

# Linear regression
lm_model <- lm(life_length ~ ., data = dragons)
glm_model <- glm(life_length ~ ., data = dragons)


# Random forest
library(randomForest)
set.seed(59)
rf_model <- randomForest(life_length ~ ., data = dragons)
library(earth)
nlr_model <- earth(life_length ~ ., data = dragons)
lm_exp <- DALEX::explain(lm_model, label = "lm", data = dragons, y = dragons$life_length)

## Preparation of a new explainer is initiated
##   -> model label       :  lm 
##   -> data              :  2000  rows  8  cols 
##   -> target variable   :  2000  values 
##   -> model_info        :  package stats , ver. 3.6.2 , task regression (  default  ) 
##   -> predict function  :  yhat.lm  will be used (  default  )
##   -> predicted values  :  numerical, min =  540.9447 , mean =  1370.986 , max =  3925.691  
##   -> residual function :  difference between y and yhat (  default  )
##   -> residuals         :  numerical, min =  -108.2062 , mean =  -3.701928e-12 , max =  113.8603  
##   A new explainer has been created! 

rf_exp <- DALEX::explain(rf_model, label = "rf", data = dragons, y = dragons$life_length)

## Preparation of a new explainer is initiated
##   -> model label       :  rf 
##   -> data              :  2000  rows  8  cols 
##   -> target variable   :  2000  values 
##   -> model_info        :  package randomForest , ver. 4.6.14 , task regression (  default  ) 
##   -> predict function  :  yhat.randomForest  will be used (  default  )
##   -> predicted values  :  numerical, min =  610.9752 , mean =  1370.181 , max =  3292.296  
##   -> residual function :  difference between y and yhat (  default  )
##   -> residuals         :  numerical, min =  -135.4756 , mean =  0.8047108 , max =  720.0888  
##   A new explainer has been created! 

nlr_exp <- DALEX::explain(nlr_model, label = "nlr", data = dragons, y = dragons$life_length)

## Preparation of a new explainer is initiated
##   -> model label       :  nlr 
##   -> data              :  2000  rows  8  cols 
##   -> target variable   :  2000  values 
##   -> model_info        :  package Model of class: earth package unrecognized , ver. Unknown , task regression (  default  ) 
##   -> predict function  : yhat.default will be used (  default  )
##   -> predicted values  :  numerical, min =  488.5581 , mean =  1370.986 , max =  3948.308  
##   -> residual function :  difference between y and yhat (  default  )
##   -> residuals         :  numerical, min =  -92.19618 , mean =  4.752655e-12 , max =  101.6223  
##   A new explainer has been created! 

glm_exp <- DALEX::explain(glm_model, label = "glm", data = dragons, y = dragons$life_length)

## Preparation of a new explainer is initiated
##   -> model label       :  glm 
##   -> data              :  2000  rows  8  cols 
##   -> target variable   :  2000  values 
##   -> model_info        :  package stats , ver. 3.6.2 , task regression (  default  ) 
##   -> predict function  :  yhat.glm  will be used (  default  )
##   -> predicted values  :  numerical, min =  540.9447 , mean =  1370.986 , max =  3925.691  
##   -> residual function :  difference between y and yhat (  default  )
##   -> residuals         :  numerical, min =  -108.2062 , mean =  -3.701928e-12 , max =  113.8603  
##   A new explainer has been created! 

library(auditor)
lm_mr <- model_residual(lm_exp)
rf_mr <- model_residual(rf_exp)
nlr_mr <- model_residual(nlr_exp)
glm_mr <- model_residual(glm_exp)


plot(rf_mr, lm_mr,  nlr_mr ,glm_mr, type = "prediction", abline = TRUE)

plot(rf_mr, lm_mr, nlr_mr ,glm_mr,  variable = "scars", type = "prediction")

plot(rf_mr, lm_mr, nlr_mr ,glm_mr,  variable = "height", type = "prediction")

plot(lm_mr, rf_mr,  nlr_mr ,glm_mr,  type = "residual")

plot(rf_mr, lm_mr,  nlr_mr ,glm_mr, type = "residual", variable = "_y_hat_")

plot(rf_mr, lm_mr,  nlr_mr ,glm_mr, type = "residual", variable = "scars")

plot_residual(rf_mr, variable = "_y_hat_", nlabel = 10)

plot_residual(nlr_mr, variable = "_y_hat_", nlabel = 10)

plot_residual(lm_mr, variable = "_y_hat_", nlabel = 10)

plot(rf_mr, lm_mr,   nlr_mr ,glm_mr, type = "residual_density")

plot_residual_density(rf_mr, lm_mr,  nlr_mr ,glm_mr, variable = "colour")

plot(rf_mr, lm_mr,  nlr_mr ,glm_mr, type = "rroc")