Machine Learning: Feature Engineering for Regression Models
Package mlfeaturer aims to provide data manipulation support for a subset of machine learning problems, currently regression problems with multiple input variables and a single input variable and a single input variable . A typical initial task is to transform and scale the variables, split them into training and test sets, and then and, after model fitting, compare the model outputs with the original data, with the test data, and with test data, and with independent new data.
It fills a gap between a style of creating a large number of intermediate data frames and variables, as found in some introductory tutorials, and full-fledged packages like caret, recipes or mlr3.
It uses R’s S4 object orientation, is intentionally simple and mostly intended for our own tasks.
Documentation
The documentation is found on https://tpetzoldt.github.io/mlfeaturer/.