Fits a k-LIME model on predictions produced by a ML model. Provides explanations/reason codes.
h2o.klime(training_frame, x, y, model_id = NULL, max_k = 20,
estimate_k = TRUE, alpha = 0.5, min_cluster_size = 20, seed = -1)
Id of the training data frame (Not required, to allow initial validation of model parameters).
A vector containing the names or indices of the predictor variables to use in building the model. If x is missing,then all columns except y are used.
The name of the response variable in the model.If the data does not contain a header, this is the first column index, and increasing from left to right. (The response must be either an integer or a categorical variable).
Destination id for this model; auto-generated if not specified.
Maximum number of clusters to be considered. Defaults to 20.
Logical
. Automatically determine the number of clusters in an unsupervised manner. Defaults to TRUE.
Balance between L1 and L2 regularization. Use alpha=0 to switch off L1 variable selection. Defaults to 0.5.
Required minimum cluster size to build a local regression model, smaller clusters will use a global model. Defaults to 20.
Seed for random numbers (affects certain parts of the algo that are stochastic and those might or might not be enabled by default) Defaults to -1 (time-based random number).