Spatial Analysis using R – ONLINE

Spatial Analysis using R – ONLINE

  • Days 1 and 2
    19/11/2020 - 20/11/2020
    1:00 pm - 5:00 pm
  • Days 3 and 4
    26/11/2020 - 27/11/2020
    1:00 pm - 5:00 pm
  • Day 5
    03/12/2020
    1:00 pm - 5:00 pm

Course details

statistics course | level: intermediate | register now
for questions related to this event, contact ugent@flames-statistics.com
affiliation: Ghent University


Abstract

Starting from the 19th of November, we will start a workshop where we will cover the basis of R, introduce data wrangling tools for data analysis with the tidyverse and data.table, and introduce tools and methods for mapping and spatial statistics. The course will be taught online, and it will be organized in a series of 5*4h classes.

Important: It is mandatory to have R (https://www.r-project.org) and RStudio (https://rstudio.com/products/rstudio) installed on your computer, prior to the starting date (https://r4ds.had.co.nz/introduction.html#prerequisites). We will distribute some datasets and packages that will have to be downloaded/installed prior to the starting date as there might be a substantial time needed to do so.

The course content might be slightly adjusted a few days prior to the starting date, based on the number of registered participants.

R for spatial data – syllabus

Day 1 (19th November)

1- Introduction to R and RStudio
a. Menus
b. Scripts
c. Basic Data Values
i. Numeric and integer, logical, factors, missing values and time.
d. Basic Data Structures
i. Vectors, matrices, lists and data.frames
e. Functions, Loops and conditions
2- Tidyverse – Part I
a. Functions, pipes, tibbles.

Day 2 (20th November)

3- Tidyverse – Part II
a. dplyr, ggplot2, lubridate, forcats.
4- Data.Table
a. DT[i, j, by], order, filter, arrange
5- Exercise:
a. Working with large datasets: the cab data example
b. Differences in speed, memory and when to use Tidyverse or Data.Table.

Day 3 (26th November)

6- Spatial Packages
a. Rgdal, sf/sp, rgeos, ggmap, igraph
7- Coordinate systems/Spatial Projections
8- Plotting Data (Introduction) – Part I
a. Leaflet, ggplot2 (part II), ggmap (part II)
9- Spatial Statistics – Part I
a. Spatial interpolation
i. Kriging
ii. Introduction to Thiessen polygons, IDW
10- Exercise:
a. Precipitation data

Day 4 (27th November)

11- Spatial Statistics – Part II
a. Point Pattern Analysis
i. Density based analysis
ii. Distance based analysis
b. Clustering algorithms and analysis in R
12- Network Analysis in R
13- Exercise:
a. Crime data.
b. Air transport data.

Day 5 (3rd December)

14- Uncertainty in Spatial Data
15- Plotting Data – Part II
a. Covid-19 data
16- Exercise:
a. Bring your own data


Prerequisites

While there are no prior requirements on knowing R, it is expected that the students are familiar with RStudio, handling csv files and with spatial data. It is advised but not mandatory that students follow the FLAMES introduction to R, or read the first chapters to R for Data Science (https://r4ds.had.co.nz). The first day will be merely introductory to R, RStudio and to the tidyverse.


Background readings


Fee

PhDs and postdocs of a Flemish university: free
Other academics: 120 €
Non-profit/Social sector: 200 €
Private sector: 400 €


Venue

Online course


Instructor

Filipe Marques Teixeira


Sign up (price ticket depends on affiliation)

You will receive payment details later from the organiser by email.