h2o_impute: Impute missing values using a H2O Random Forest model

In NSAPH/airpred: A Framework For Building Air Pollution Estimation Models

Description

Impute missing values using a H2O Random Forest model

Usage

h2o_impute(info, var)

Arguments

info	h2o data frame
var	String containing the name of the variable to be imputed

Details

This function assumes that the h2o cluster has already been initialized and that the data has already been loaded to the h2o cluster. To protect against errors it is not exported.

H2O's Random Forests interpret missingness in the input as containing information and therefore the output will have values for all inputs, regardless of the missingness of the input.

NSAPH/airpred documentation built on May 7, 2020, 10:49 a.m.