Skip to contents

Introduction

Data is meant to be input as a data frame with the dependent variable indicated. TangledFeatures will automatically clean columns in preparation for correlation analysis.

A list of the changes made:

  • Calls the clean_names function from janitor
  • Drops rows that contain NA values
  • Coerce all character columns to factors
  • Set factor order if it is a ordinal variable
  • Set and create dummy columns for unordered factor variables
  • Coerce all numeric columns to numeric data types