ALE {cito} | R Documentation |
Performs an ALE for one or more features.
ALE(
model,
variable = NULL,
data = NULL,
K = 10,
type = c("equidistant", "quantile")
)
model |
a model created by |
variable |
variable as string for which the PDP should be done |
data |
data on which ALE is performed on, if NULL training data will be used. |
K |
number of neighborhoods original feature space gets divided into |
type |
method on how the feature space is divided into neighborhoods. |
If the defined variable is a numeric feature, the ALE is performed. Here, the non centered effect for feature j with k equally distant neighborhoods is defined as:
\hat{\tilde{f}}_{j,ALE}(x)=\sum_{k=1}^{k_j(x)}\frac{1}{n_j(k)}\sum_{i:x_{j}^{(i)}\in{}N_j(k)}\left[\hat{f}(z_{k,j},x^{(i)}_{\setminus{}j})-\hat{f}(z_{k-1,j},x^{(i)}_{\setminus{}j})\right]
Where N_j(k)
is the k-th neighborhood and n_j(k)
is the number of observations in the k-th neighborhood.
The last part of the equation,
\left[\hat{f}(z_{k,j},x^{(i)}_{\setminus{}j})-\hat{f}(z_{k-1,j},x^{(i)}_{\setminus{}j})\right]
represents the difference in model prediction when the value of feature j is exchanged with the upper and lower border of the current neighborhood.
A list of plots made with 'ggplot2' consisting of an individual plot for each defined variable.
if(torch::torch_is_installed()){
library(cito)
# Build and train Network
nn.fit<- dnn(Sepal.Length~., data = datasets::iris)
ALE(nn.fit, variable = "Petal.Length")
}