Skip to content

R-package of developing ML models for complex survey data

License

Notifications You must be signed in to change notification settings

hkim-fda/MLSurvey

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MLSurvey

Machine Learning for Complex Survey Data

MLSurvey is a R-package for developing Machine Learning models for complex survey data using appropriate Cross-Validation methods: replicate weights methods. This ML tool currently offers weighted Elastic Net (wElnet), weighted random forest (wRandomforest), and weighted XGBoost (wXGBoost) for linear/logistic regression incorporated with replicate weights methods by R-survey and R-surVarSel. It also provides a visualization function for optimal variable selection for wElnet (plot_wreg) as an extension of R-surVarSel, computation of confidential interval (ci_wauc) for weighted area under the ROC curve (wAUC), where wAUC is optimally computed by R-svyROC. Since all the weighted ML methods are extended by existing algorithms, glmnet, xgboost, and randomForest, the final models can take advantage of their corresponding original packages to get more comprehensive results, such as importance plots, prediction, etc.

Note: This will be extended to wider model developments, such as Cox, Poisson, etc., and will be available for Julia programming language.

Installation

To install from GitHub,

library(devtool)
install_github("hkim-fda/MLSurvey")

Releases

No releases published

Packages

No packages published

Languages