h2o.get_regression_influence_diagnostics {h2o}R Documentation

Extracts a list of H2OFrames containing regression influence diagnostics for predictor subsets of various sizes or just one H2OFrame containing regression influence diagnostics for predictor subsets of one fixed size

Description

Extracts a list of H2OFrames containing regression influence diagnostics for predictor subsets of various sizes or just one H2OFrame containing regression influence diagnostics for predictor subsets of one fixed size

Usage

h2o.get_regression_influence_diagnostics(model, predictorSize = -1)

Arguments

model

an H2OModel object.

predictorSize

predictor subset size. If specified, will only return model coefficients of that subset size. If not specified will return a lists of model coefficient dicts for all predictor subset size.

Examples

## Not run: 
library(h2o)
h2o.init()

f <- "https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv"
cars <- h2o.importFile(f)
predictors <- c("displacement", "power", "weight", "acceleration", "year")
response <- "acceleration"
cars_model <- h2o.modelSelection(y=response, 
                                 x=predictors, 
                                 training_frame = cars, 
                                 min_predictor_number=2, 
                                 mode="backward", 
                                 influence="dfbetas",
                                 lambda=0.0,
                                 family="gaussian")
rid_frame <- h2o.get_regression_influence_diagnostics(cars_model, predictorSize=3)

## End(Not run)

[Package h2o version 3.44.0.3 Index]