plot.ceteris_paribus_explainer {ingredients}

Plots Ceteris Paribus Profiles

Description

Function plot.ceteris_paribus_explainer plots Individual Variable Profiles for selected observations. Various parameters help to decide what should be plotted, profiles, aggregated profiles, points or rugs.

Find more details in Ceteris Paribus Chapter.

Usage

## S3 method for class 'ceteris_paribus_explainer'
plot(
  x,
  ...,
  size = 1,
  alpha = 1,
  color = "#46bac2",
  variable_type = "numerical",
  facet_ncol = NULL,
  facet_scales = NULL,
  variables = NULL,
  title = "Ceteris Paribus profile",
  subtitle = NULL,
  categorical_type = "profiles"
)

Arguments

x

a ceteris paribus explainer produced with function ceteris_paribus()

...

other explainers that shall be plotted together

size

a numeric. Size of lines to be plotted

alpha

a numeric between 0 and 1. Opacity of lines

color

a character. Either name of a color or name of a variable that should be used for coloring

variable_type

a character. If numerical then only numerical variables will be plotted. If categorical then only categorical variables will be plotted.

facet_ncol

number of columns for the facet_wrap

facet_scales

a character value for the facet_wrap. Default is "free_x", but "free_y" if categorical_type="bars".

variables

if not NULL then only variables will be presented

title

a character. Plot title. By default "Ceteris Paribus profile".

subtitle

a character. Plot subtitle. By default NULL - then subtitle is set to "created for the XXX, YYY model", where XXX, YYY are labels of given explainers.

categorical_type

a character. How categorical variables shall be plotted? Either "profiles" (default) or "bars" or "lines".

Value

a ggplot2 object

References

Explanatory Model Analysis. Explore, Explain, and Examine Predictive Models. https://ema.drwhy.ai/

Examples

library("DALEX")

model_titanic_glm <- glm(survived ~ gender + age + fare,
                         data = titanic_imputed, family = "binomial")

explain_titanic_glm <- explain(model_titanic_glm,
                               data = titanic_imputed[,-8],
                               y = titanic_imputed[,8],
                               verbose = FALSE)

cp_glm <- ceteris_paribus(explain_titanic_glm, titanic_imputed[1,])
cp_glm

plot(cp_glm, variables = "age")


library("ranger")
model_titanic_rf <- ranger(survived ~., data = titanic_imputed, probability = TRUE)

explain_titanic_rf <- explain(model_titanic_rf,
                              data = titanic_imputed[,-8],
                              y = titanic_imputed[,8],
                              label = "ranger forest",
                              verbose = FALSE)

selected_passangers <- select_sample(titanic_imputed, n = 100)

cp_rf <- ceteris_paribus(explain_titanic_rf, selected_passangers)
cp_rf

plot(cp_rf, variables = "age") +
  show_observations(cp_rf, variables = "age") +
  show_rugs(cp_rf, variables = "age", color = "red")

selected_passangers <- select_sample(titanic_imputed, n = 1)
selected_passangers

cp_rf <- ceteris_paribus(explain_titanic_rf, selected_passangers)

plot(cp_rf) +
  show_observations(cp_rf)

plot(cp_rf, variables = "age") +
  show_observations(cp_rf, variables = "age")

plot(cp_rf, variables = "class")
plot(cp_rf, variables = c("class", "embarked"), facet_ncol = 1)
plot(cp_rf, variables = c("class", "embarked"), facet_ncol = 1, categorical_type = "bars")
plotD3(cp_rf, variables = c("class", "embarked", "gender"),
              variable_type = "categorical", scale_plot = TRUE,
              label_margin = 70)