This function returns default options for modelStudio. It is possible to modify values of this list and pass it to the options parameter in the main function. WARNING: Editing default options may cause unintended behavior.

ms_options(...)

modelStudioOptions(...)

Arguments

...

Options to change in the form option_name = value.

Value

list of options for modelStudio.

Options

Main options:

scale_plot

TRUE Makes every plot the same height, ignores bar_width.

show_boxplot

TRUE Display boxplots in Feature Importance and Shapley Values plots.

show_subtitle

TRUE Should the subtitle be displayed?

subtitle

label parameter from explainer.

ms_title

Title of the dashboard.

margin_*

Plot margins. Change margin_left for longer/shorter axis labels.

w

420 in px. Inner plot width.

h

280 in px. Inner plot height.

bar_width

16 in px. Default width of bars for all plots, ignored when scale_plot = TRUE.

line_size

2 in px. Default width of lines for all plots.

point_size

3 in px. Default point radius for all plots.

[bar,line,point]_color

[#46bac2,#46bac2,#371ea3]

positive_color

#8bdcbe for Break Down and Shapley Values bars.

negative_color

#f05a71 for Break Down and Shapley Values bars.

default_color

#371ea3 for Break Down bar and highlighted line.

Plot specific options:

** is a two letter code unique to each plot, might be one of [bd,sv,cp,fi,pd,ad,fd,tv,at].

**_title

Plot specific title. Default varies.

**_subtitle

Plot specific subtitle. Default is subtitle.

**_bar_width

Plot specific width of bars. Default is bar_width, ignored when scale_plot = TRUE.

**_line_size

line_size Plot specific width of lines. Default is line_size.

**_point_size

Plot specific point radius. Default is point_size.

**_*_color

Plot specific [bar,line,point] color. Default is [bar,line,point]_color.

References

  • The input object is implemented in DALEX

  • Feature Importance, Ceteris Paribus, Partial Dependence and Accumulated Dependence plots are implemented in ingredients

  • Break Down and Shapley Values plots are implemented in iBreakDown

See also

Examples

library("DALEX")
library("modelStudio")

# fit a model
model_apartments <- glm(m2.price ~. , data = apartments)

# create an explainer for the model
explainer_apartments <- explain(model_apartments,
                                data = apartments,
                                y = apartments$m2.price)

# pick observations
new_observation <- apartments[1:2,]
rownames(new_observation) <- c("ap1","ap2")

# modify default options
new_options <- ms_options(
  show_subtitle = TRUE,
  bd_subtitle = "Hello World",
  line_size = 5,
  point_size = 9,
  line_color = "pink",
  point_color = "purple",
  bd_positive_color = "yellow",
  bd_negative_color = "orange"
)

# make a studio for the model
modelStudio(explainer_apartments,
            new_observation,
            options = new_options,
            N = 200,  B = 5) # faster example