These learning materials are designed for the UNIGIS distance-learning study programs as part of a module that introduces into Application Development.
The contents of this module are based on R for Geographic Data Science by Stefano De Sabbata, University of Leicester.
In this module, the materials will be adapted and extended to fit the UNIGIS curriculum and layout of materials. Like the source materials, this work is licensed under the GNU General Public License v3.0.
Has a high probability of changing way faster then state of the art packages or syntax of R language.
- Consider creating an innovative lesson on integrating ChatGPT with R.
- Assess the complexity and relevance of the topic.
- Explore whether to use ChatGPT or explore alternative technologies.
- Determine the required frequency of updates for the lesson (Note: with a high probability that it may require more updates than even the packages.. Main reason why I would debate).
- Although, there are very interesting plugins for programming and data visualizations see GPT-4 (although, so far, Advanced Data Analysis only uses Python - Time of Writing: (11.09.2023) - and the data analysis tool is for paying customers.)
Very debatable, ... ML workloads normally need a lot of foundation in mathematical understanding...
- Introduce machine learning techniques tailored for spatial data.
- Discuss spatial autocorrelation and its implications in predictive modeling.
- Introduce the concept of creating web applications to showcase spatial analyses.
- Discuss the importance of interactive web maps and dashboards.
- Explore the shiny package and its integration with spatial packages.
- Dives deeper into advanced visualization techniques specific to spatial data.
- Explore 3D visualizations, interactive maps, and animation of spatial-temporal data.
- Introduce packages like mapview, leaflet, and rayshader.
- Dives into the world of spatial networks, such as transportation and social networks.
- Discuss shortest path, network flow, and centrality measures in a spatial context.
- Explore packages like sfnetworks.
- Discuss the importance of temporal data in spatial analyses.
- Introduce techniques to analyze spatial data that changes over time.
- Introduce the concept of remote sensing and its importance in spatial analyses.
- Discuss the processing and analysis of satellite imagery.
- Explore packages like stars, and tools for specific satellite data.
(Could actually be quite beneficial!)
- Introduction to TDD: What it is, How it works
- Testing Scopes (Unit, Integration, Blackbox-testing)
- When to use it ..
- packagechecker.R - to lookup the packages used in the .RMD files (R)
- broken_links.py - to check for any broken links in the .RMD files (Python)