Repository files navigation

Spatial Analysis Done Right

You want to do spatial statistics, and it's going to involve binning.

Binning with a rectangular grid introduces messy distortions. At the macro-scaleusing a rectangular grid does things like making Greenland bigger than theUnited States and Antarctica the largest continent.

But this kind of distortion is present no matter what the resolution is; infact, it shows up whenever you project a sphere onto a plane.

What you want are bins of equal size, regardless of where they are on the globe,regardless of their resolution.

dggridR solves this problem.

dggridR builds discrete global grids which partition the surface of the Earthinto hexagonal, triangular, or diamond cells,all of which have the samesize. (There are some minor caveats which are detailed in the vignettes.)

(Naturally, you can usemuch smaller cells than those shown in the image above.)

This package includes everything you need to make spatial binning great again.

Many details and examples are included in the vignette.

dggridR is available from CRAN via:

install.packages('dggridR')

If you want your code to be as up-to-date as possible, you can install it using:

install.packages('dggridR', repos = 'https://fastverse.r-universe.dev')

Okay.

Your analysis could be as easy as this:

library(dggridR)library(collapse)#Construct a global grid with cells approximately 1000 miles acrossdggs<- dgconstruct(spacing=1000,metric=FALSE,resround='down')#Load included test data setdata(dgquakes)#Get the corresponding grid cells for each earthquake epicenter (lat-long pair)dgquakes$cell<- dgGEO_to_SEQNUM(dggs,dgquakes$lon,dgquakes$lat)$seqnum#Get the number of earthquakes in each equally-sized cellquakecounts<-dgquakes|> fcount(cell)

In R, typing

vignette('dggridR')

will bring up many examples.

Many different grid resolutions are available for many different grids. Thefollowing chart shows the number of cells, their area, and statistics regardingthe spacing of their center nodes for the ISEA3H grid type.

The code in the 'src' directory is based off ofDGGRIDv6.2b by Kevin Sahr.

However, Richard Barnes has made some significant alterations. These include:

• Replacement of gpclib with clipper, thus making DGGRID into FLOSS softwareavailable for both commercial and non-commercial use without restriction
• Restructuring and simplifying all of the makefiles to enable compilation in R
• Direct inclusion of the shapelib library
• Addition of the SEQTOPOLY option under the GENERATE_GRID faculty
• Alterations that enable the code to be compiled under GCC6
• Alterations that make the code ISO C conformant
• Alterations to resolve -pedantic and -Wall warnings

The package relies on several libraries, as noted in theLicensing sectionbelow.

This package uses the following libraries:

• clipper: The clipper library has been released under the Boostv1 license byAngus Johnson

• dggrid: Kevin Sahr has released dggrid as a"public domain software program"

• proj4lib: Gerald Evenden has released this code into the public domain. Morerecent versions of the library, not used here, are under anMIT-style license.

• shapelib: Frank Warmerdam has released shapelib under an MIT-style license.There is also an LGPL licensing option which I have chosen not touse.

This package, and all code and documentation not otherwise mentioned above(essentially anything outside thesrc/ directory of this package) are releasedunder the MIT (Expat) license, as stated in theLICENSE file. TheLICENCEfile exists for use with CRAN.

This packageshould operate in the manner described here, in the package'smain documentation, and in Kevin Sahr'sdggrid documentation. Unfortunately,none of us are paid enough to make absolutely, doggone certain that that's thecase. That said, if you find bugs or are seeking enhancements, we want to hearabout them.

Please cite this package as:

Richard Barnes and Kevin Sahr (2017). dggridR: Discrete Global Grids for R. R package version 2.0.4. "https://github.com/r-barnes/dggridR/" doi:10.5281/zenodo.1322866