R package pmut is a collection of utility functions that facilitate general predictive modeling work. Function usages include but not limited to diagnostic visualization, model metric, data quality check.

Installation

Development version:

devtools::install_github("chengjunhou/pmut")

Documentation

Pacakge vignette is available on RPubs.

Usage Description

• pmut.edap.cont: this function creates visualization with a line plot of a specified continuous feature against the response, plus a distribution histogram for that feature.

• pmut.edap.disc: this function creates visualization with a line plot of a specified discrete feature against the response, plus a distribution histogram for that feature.

• pmut.edap: this function creates visualization for a vector of features, using either pmut.edap.disc or pmut.edap.cont, depending on the feature class.

• pmut.data.pmis: this function checks percenrage of NA (include empty string for character) for every column inside the data.

• pmut.data.same: this function checks if there is any duplicated column inside the data.

• pmut.data.scal: this function standardizes every numeric column inside the data.

• pmut.base.find: this function finds the meta information for each column within training data, which will be used to process testing and/or new data so that it can be scored without error, check pmut.base.prep for the part of testing data processing.

• pmut.base.prep: this function takes meta information generated by pmut.base.find, prepares new data so that it can be scored without error.

• pmut.auc: this function calculates area under the ROC curve for model prediction, without any package dependency.

• pmut.gini: this function calculates the standardized gini coefficient for model prediction.