By the end of the course, students will be able to design a reproducible, non-interactive R script that can be executed from start to finish without user intervention between steps. The script should import, check, clean, transform, analyse and visualise data, and then export the processed data and results.
The analyses and graphical representations should be selected according to the nature of the data and the question being addressed.
More specifically, students will be able to perform the operations listed below. These learning outcomes correspond to different levels of complexity (0-4). Some may fall within two levels depending on the difficulty of the dataset or task.
Learning outcome Level
Import a dataset and extract specific observations or variables. 0
Detect and correct import or encoding errors. 0
Calculate descriptive statistics, such as the mean or range, for the complete dataset or by group. 0/1
Modify the structure of a dataset, including conversion from wide to long format, definition of factors and merging of multiple datasets. 1
Use an R function and adjust its arguments. 0
Use the available resources to solve problems independently, including R help pages, vignettes, reference sheets, and course and practical-session materials. 0/1
Select a graphical representation appropriate to the data and the question, and use ggplot2 to produce a clear and correctly labelled figure. 1
Save or export tables, figures, scripts and R objects, including in .RData format. 0/1
Manipulate text by concatenating or splitting character strings and searching for patterns. 2
Produce a reproducible HTML report using R Markdown. 2
Repeat a series of instructions using a loop and execute code conditionally. 3
Generalise code so that it can be run again by changing only the intended parameters, including by creating functions when appropriate. 4
Perform and interpret exploratory analyses, including unsupervised clustering, heatmaps and correlation analyses. 4
The objective of the course is to provide the tools for future scientists to import, manipulate, visualise and analyse datasets using R software.
The course develops the use of R for data processing, analysis and visualisation. It covers the main stages of an analytical workflow, from data import and quality control to data transformation, analysis, visualisation and the export of results.
Students learn to develop reproducible, non-interactive scripts, generalise their code using functions, loops and conditional statements, and produce reports with R Markdown. The course also introduces exploratory methods, including unsupervised clustering, heatmaps and correlation analyses. These concepts are applied through examples and exercises completed with increasing independence.
The course covers the following topics:
Review of basic R functions, their arguments and the main types of R objects.
Data import, quality control, cleaning and selection.
Data transformation and organisation: factors, long and wide formats, and merging datasets.
Calculation of descriptive statistics for the complete dataset or by group.
Selection and creation of graphs and tables appropriate to the data and the question being addressed.
Development of reproducible, non-interactive scripts using functions, loops, conditional statements and text manipulation.
Export of data and results, and production of reports using R Markdown.
Exploratory analyses, including unsupervised clustering, heatmaps and correlation analyses.
Independent resolution of exercises integrating the different stages of data processing and analysis.
The exercises are of various types, designed to promote the progressive acquisition of skills. Some follow a project-based format, in which students carry out a series of analyses of increasing complexity using the same dataset.
Attendance at practical sessions is strongly recommended.
The materials for the theoretical classes will be available from the beginning of the semester. Before each in-person session, students will be expected to have consulted the relevant materials. A significant part of the learning will rely on independent study.
During the practical sessions, students will use basic R functions and learn to use new ones. To do so, they will be expected to consult the course materials, R help pages and online resources such as tutorials, courses and forums.
Assessment takes place during the examination session and consists of a single computer-based examination comprising data analysis and R programming exercises.
This is an open-book examination conducted without Internet access, artificial intelligence tools or communication between students. Students may consult all course and practical-session materials, as well as their own notes. These resources may be brought in paper form or on a USB drive and must be available offline.
Material on webcampus and online resources
| Training | Study programme | Block | Credits | Mandatory |
|---|---|---|---|---|
| Bachelor in Geography : General | Standard | 2 | 2 | Yes |
| Bachelor in Geology | Standard | 2 | 2 | Yes |
| Bachelor in Biology | Standard | 2 | 2 | Yes |
| Bachelor in Veterinary Medicine | Nouveau | 2 | 2 | No |