show_aggregated_profiles {ingredients} | R Documentation |
Adds a Layer with Aggregated Profiles
Description
Function show_aggregated_profiles
adds a layer to a plot created
with plot.ceteris_paribus_explainer
.
Usage
show_aggregated_profiles(
x,
...,
size = 0.5,
alpha = 1,
color = "#371ea3",
variables = NULL
)
Arguments
x |
a ceteris paribus explainer produced with function |
... |
other explainers that shall be plotted together |
size |
a numeric. Size of lines to be plotted |
alpha |
a numeric between |
color |
a character. Either name of a color or name of a variable that should be used for coloring |
variables |
if not |
Value
a ggplot2
layer
References
Explanatory Model Analysis. Explore, Explain, and Examine Predictive Models. https://ema.drwhy.ai/
Examples
library("DALEX")
library("ingredients")
selected_passangers <- select_sample(titanic_imputed, n = 100)
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])
cp_rf <- ceteris_paribus(explain_titanic_glm, selected_passangers)
pdp_rf <- aggregate_profiles(cp_rf, type = "partial", variables = "age")
plot(cp_rf, variables = "age") +
show_observations(cp_rf, variables = "age") +
show_aggregated_profiles(pdp_rf, size = 3)
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)
cp_rf <- ceteris_paribus(explain_titanic_rf, selected_passangers)
cp_rf
pdp_rf <- aggregate_profiles(cp_rf, type = "partial", variables = "age")
head(pdp_rf)
plot(cp_rf, variables = "age") +
show_observations(cp_rf, variables = "age") +
show_rugs(cp_rf, variables = "age", color = "red") +
show_aggregated_profiles(pdp_rf, size = 3)
[Package ingredients version 2.3.0 Index]