Chapter 3 Wrangling Data in the Tidyverse
In the last course we spent a ton of time talking about all the most common ways data are stored and reviewed how to get them into a tibble (or data.frame) in R.
So far we’ve discussed what tidy and untidy data are. We’ve (hopefully) convinced you that tidy data are the right type of data to work with. What we may not have made perfectly clear yet is that data are not always the tidiest when they come to you at the start of a project. An incredibly important skill of a data scientist is to be able to take data from an untidy format and get it into a tidy format. This process is often referred to as data wrangling. Generally, data wranglings skills are those that allow you to wrangle data from the format they’re currently in into the tidy format you actually want them in.
Beyond data wrangling, it’s also important to make sure the data you have are accurate and what you need to answer your question of interest. After wrangling the data into a tidy format, there is often further work that has to be done to clean the data.
