Experimenting with Scala and R for multivariate analyses:
-
statistical theory from Quinn and Keough 2002 "Experimental design and data analysis for biologists",
-
R code and theory from Kabacoff 2015 "R in action" and from Crawley 2013 "The R book",
-
neural networks theory and code from Trask 2017 "Grokking deep learning",
-
implementing ML code in Scala using "Learning Scala" (Jason Swartz 2015), "Programming in Scala", Second Edition (Martin Odersky, Lex Spoon, Bill Venners, 2010), "Learning Spark" (Karau et al. 2015), "Coursera" (Martin Odersky et al.) https://www.coursera.org/learn/progfun1, "Scala for Machine Learning" (Patrick R. Nicolas 2015), "Statistical Computing with Scala: A functional approach to data science" (Darren Wilkinson 2017) https://github.com/darrenjw/scala-course, "Machine learning in action" (Peter Harrington, 2012)
-
linear algebra theory from Paul Dawkins 2017 "Paul's Math Notes on Linear Algebra",
-
spatial data analysis with R from Bivand, Pebesma and Gomez-Rubio 2008 "Spatial data analysis with R" and Chris Garrard 2016 "Geoprocessing with Python".
The final aim is to be able to build neural networks to investigate the relationships between abundance of species and site characteristics or species composition and site characteristics.