paigemiller / culex-sdm Goto Github PK
View Code? Open in Web Editor NEWPaige Miller, Robert Richards, Gio Righi -- ECOL 8910 class project (2016)
Paige Miller, Robert Richards, Gio Righi -- ECOL 8910 class project (2016)
Here is a chunk of code that splits the first column into three (ID, Year, Var). It's a tad slow but.. works for now!
col1 <- ghcn$V1
ghcn.col1 <- data.frame(matrix(NA, now = length(ghcn[,1]), ncol = 3))
colnames(ghcn.col1) <- c("ID", "year", "var")
for (i in 1:length(col1)){
split.i <- unlist(strsplit(col1[i], split=""))
ghcn.col1$ID[i] <- paste(split.i[1:11], sep="", collapse="")
ghcn.col1$year[i] <- paste(split.i[12:15], sep="", collapse="")
ghcn.col1$var[i] <- paste(split.i[16:19], sep="", collapse="")
}
I've figured out how to evaluate spatial autocorrelation of our data (Ripley's K) but in order to effectively calculate it I want to set the bounds as the boundaries of the continent (or country with which we are concerned). There are a couple of places that will give you shape files of the world or continents which are great. Unfortunately they load into R as SpatialPolygonsDataFrames which are essentially a form of raster object and entirely incompatible with the "Kest" function in the "spatstat" package in R. It seems to want a simple vector description of the polygon window. Any thoughts on how to deal with this would be awesome. I feel like I'm missing something obvious.
It's seeming that (at least with the cluster style sampling we discussed last time) though the biasing of the data set definitely lowers the AUC on testing data it doesn't seem to lower it any more (and sometimes less) than simply randomly subsetting the data. Thus the AUC decrease seems largely due to decreased sample size. Currently I'm working with LOBAG-OC and we know from John and my work that sample size has a substantial effect on its performance, so I guess this was to be expected. Not sure exactly where to go from here with that. I'll try MaxEnt tomorrow (when fitting it with the swiss-veg data just feed it all the presence and absence points of the training set as background), and we can hope that it works a little better.
P.S. I'm already working with only the 8 most abundant species.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.