Data processing with R tidyverse

Introduction

R is a powerful language for data science in many disciplines of research with a steep learning curve. The tidyverse group of packages provide a dialect that greatly simplifies:

data importing
cleaning
processing
visualization as well as providing reproducible workflows using pipelines (%>%)

Adopt Hadley Wickham, Chief Scientist at RStudio, philosophy: take each step of data science and replace many intricacies of R with clear, consistent and easy to learn syntax. RStudio will be the software to use since it eases package management, scripting, plotting and data handling.

The four day course provides a complete introduction to data science in R with the tidyverse. The course will not go deep into statistics but rather getting data ready, some exploratory analysis, visualization and handling models.

Preparing data takes up to 80% of the time spent in analysis — speeding this up is the mission of this course.

Tidyverse

The tidyverse is an official CRAN package and here is its manifesto. Hadley proposed the following workflow described in his must-read book R for data science

H. Wickham - R for data science, licence CC

In terms of R packages, the workflow is nicely depicted as in this picture, by David Robinson

Requirements

Prior knowledge

Participants should have basic experience in programming environments such as Matlab, Octave or other programming languages or complete a simple free online course.

There is a special session on updates of the tidyverse on 30 November 2020 for participants of previous iterations of the course. No registration is required to attend.

Material

Each student must bring their own laptop with R and Rstudio installed with recent versions. Please look at install tutorial to set it up prior to the course.

Schedule

Dates and time

Each day, the workshop will be a mixture of lectures and practicals from:

9:00 - 9:30 virtual welcome coffee
9:30 - 12:30 course work with a coffee break
12:30 - 13:30 lunch breaks
13:30 - 17:30 course work with a coffee break

Preliminary program

Date	Time	Session	Teacher	Notes
2020-11-26	09:30	Introduction	AG
	11:00	Tidy data	RK
	13:30	String manipulation	RK	`stringr`
	14:30	RMarkdown	AG	`knitr`
	16:00	Import	AG	`readr`
2020-11-27	09:30	Data transformation	RK	`dplyr`, `tidyr`
	13:30	Visualization	AG	`ggplot`
2020-11-30	09:30	Functional programming	AG	`purrr`
	13:30	Tidy models	AG	`broom`
	15:30	Advanced Programming	AG	`tidyeval`
2020-12-01	09:30	New developments in 2020	AG
	10:15	Coffee break
	10:45	Practical	All

Day 1 will review the basics of R and loading data via the readr package as well as Rmarkdown.
Day 2 will introduce tidying and organising data via the tidyr and dplyr packages as well as ggplot2 for visualisation.
Day 3 will look at functional programming tools using the purrr package, which greatly simplifies repeating operations. Many statistical packages have complicated and idiosyncratic data structures. The broom package helps to convert them to consistent data structures.
Participants are encouraged to bring their own data for analysis, convert existing code to tidyverse or perform a project on Day 4.

Location

The course will be held online.

Registration

The course is limited to 30 participants. Registration is currently open.

ECTS

PhD students that enrolled through the doctoral school will receive 2 ECTS in category 1, which requires handing in a short project and practicals as Rmd files that students miss. For example if you are absent the first day, you must do and send back:

practical introduction with datasauRus
practical string manipulation
practical import data

Please note that ECTS can only be received for the course once. If you already have received ECTS for the last version of the course, no ECTS will be awarded for this year’s edition.

Elixir

This event is supported by ELIXIR-Luxembourg