Plots waterfall break down for objects of the break_down class.
plotD3(x, ...)
# S3 method for break_down
plotD3(
x,
...,
baseline = NA,
max_features = 10,
digits = 3,
rounding_function = round,
bar_width = 12,
margin = 0.2,
scale_height = FALSE,
min_max = NA,
vcolors = NA,
chart_title = NA,
time = 0,
max_vars = NULL,
reload = FALSE
)an explanation created with break_down
other parameters.
if numeric then veritical line will start in baseline.
maximal number of features to be included in the plot. By default it's 10.
number of decimal places (round) or significant digits (signif) to be used.
See the rounding_function argument.
a function to be used for rounding numbers.
This should be signif which keeps a specified number of significant digits or round (which is default) to have the same precision for all components.
width of bars in px. By default it's 12px
extend x axis domain range to adjust the plot. Usually value between 0.1 and 0.3, by default it's 0.2
if TRUE, the height of the plot scales with window size
a range of OX axis. By deafult NA therefore will be extracted from the contributions of x.
But can be set to some constants, usefull if these plots are used for comparisons.
If NA (default), DrWhy colors are used.
a character. Set custom title
in ms. Set the animation length
alias for the max_features parameter.
Reload the plot on resize. By default it's FALSE.
a r2d3 object.
Explanatory Model Analysis. Explore, Explain and Examine Predictive Models. https://ema.drwhy.ai
library("DALEX")
library("iBreakDown")
set.seed(1313)
model_titanic_glm <- glm(survived ~ gender + age + fare,
data = titanic_imputed, family = "binomial")
explain_titanic_glm <- explain(model_titanic_glm,
data = titanic_imputed,
y = titanic_imputed$survived,
label = "glm")
#> Preparation of a new explainer is initiated
#> -> model label : 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. 4.1.2 , task classification ( default )
#> -> predicted values : numerical, min = 0.1490412 , mean = 0.3221568 , max = 0.9878987
#> -> residual function : difference between y and yhat ( default )
#> -> residuals : numerical, min = -0.8898433 , mean = 4.198546e-13 , max = 0.8448637
#> A new explainer has been created!
bd_glm <- local_attributions(explain_titanic_glm, titanic_imputed[1, ])
bd_glm
#> contribution
#> glm: intercept 0.322
#> glm: gender = male -0.107
#> glm: fare = 7.11 -0.018
#> glm: age = 42 -0.014
#> glm: class = 3rd 0.000
#> glm: embarked = Southampton 0.000
#> glm: sibsp = 0 0.000
#> glm: parch = 0 0.000
#> glm: survived = 0 0.000
#> glm: prediction 0.183
plotD3(bd_glm)
# \dontrun{
## Not run:
library("randomForest")
m_rf <- randomForest(status ~ . , data = HR[2:2000,])
new_observation <- HR_test[1,]
new_observation
#> gender age hours evaluation salary status
#> 1 male 57.72683 42.31527 2 2 fired
p_fun <- function(object, newdata){predict(object, newdata=newdata, type = "prob")}
bd_rf <- local_attributions(m_rf,
data = HR_test,
new_observation = new_observation,
predict_function = p_fun)
bd_rf
#> contribution
#> randomForest.formula.fired: intercept 0.379
#> randomForest.formula.fired: hours = 42.32 0.220
#> randomForest.formula.fired: evaluation = 2 0.054
#> randomForest.formula.fired: salary = 2 -0.152
#> randomForest.formula.fired: age = 57.73 0.204
#> randomForest.formula.fired: gender = male 0.164
#> randomForest.formula.fired: status = fired 0.000
#> randomForest.formula.fired: prediction 0.868
#> randomForest.formula.ok: intercept 0.280
#> randomForest.formula.ok: hours = 42.32 -0.030
#> randomForest.formula.ok: evaluation = 2 0.089
#> randomForest.formula.ok: salary = 2 0.154
#> randomForest.formula.ok: age = 57.73 -0.206
#> randomForest.formula.ok: gender = male -0.160
#> randomForest.formula.ok: status = fired 0.000
#> randomForest.formula.ok: prediction 0.128
#> randomForest.formula.promoted: intercept 0.341
#> randomForest.formula.promoted: hours = 42.32 -0.189
#> randomForest.formula.promoted: evaluation = 2 -0.144
#> randomForest.formula.promoted: salary = 2 -0.002
#> randomForest.formula.promoted: age = 57.73 0.002
#> randomForest.formula.promoted: gender = male -0.004
#> randomForest.formula.promoted: status = fired 0.000
#> randomForest.formula.promoted: prediction 0.004
plotD3(bd_rf)
# }