Efficient Visual Targets Exploration
Automated Explanatory Data Analysis (EDA) for targets exploration, for both binary and numeric targets. Describes a target by crossing it with any other candidate explanatory variables. Generates aggregated statistics allowing to prioritize inspection, such as Information Value (including an extension of this metric for continuous targets). We also provide plot methods, automated reports based on markdown and a shiny gadget for interactive explorations. Package is aimed at investigating big datasets, both in terms of records and variables through the usage of data.table package.
To install the latest development version of the package directly from GitHub use the following code:
if (!requireNamespace("remotes", quietly = TRUE)) {
install.packages("remotes")
}
remotes::install_github("weloevdatascience/targeter")
- Alec Zhixiao Lin, PayPal Credit, Timonium, MD Tung-Ying Hsieh, Dept. of Mathematics & Statistics, Univ of Maryland, Baltimore, MD - Expanding the Use of Weight of Evidence and Information Value to Continuous Dependent Variables for Variable Reduction and Scorecard Development (2014)
We use the following for support and communications between user and developer community:
- GitHub Issues---for direct feedback, enhancement requests or raising bugs
Along with the authors and contributors, thanks to the following people for their work/input on the package: Manuel Piette (good old Qualifix).