DomBennett

# R script for splitting grid space
# Variables:
# obs_lat = vector of observed lats
# obs_lon = vector of observed lons
# lats = vector of lists for the max and min values of each grid in lat-space
# lons = vector of lists for the max and min values of each grid in lon-space
# gird = matrix of indexes pointing to the lists in =lats and lons
# res = vector of indexes referring to indexes in grid

# Steps:

DomBennett

# Libraries
library(MoreTreeTools)  # package in dev, install via github: https://github.com/DomBennett/MoreTreeTools
library(doMC)  # use doSNOW if using Windows
# find out how many cores you have
n <- detectCores()
# set-up
registerDoMC(cores=n)
# example tree
tree <- rtree(1000)
# find all internal nodes in tree

DomBennett

getGroups <- function(tree) {
  getCnnctngEdges <- function(edge) {
    nd <- tree$edge[edge, 1]
    edge <- which(tree$edge[ ,2] == nd)
    if(length(edge) > 0) {
      edge <- c(edge, getCnnctngEdges(edge))
    }
    edge
  }
  .fillInEdgeTips <- function(i) {

DomBennett

# PREDICTS AND DPLYR
# D. Bennett & L. Graham

# BRIEF:
# PREDICTS is a large dataset of multiple ecological studies that
# have sampled (through counting, trapping, sighting... etc.) a given
# taxonomic group.
# Each study contains information regarding the number of samples taken,
# the taxonomy of the group, the study area etc.
# Here we will read in a small example dataset of PREDICTS and demonstrate

DomBennett

# PLOTTING WITH HIGHLIGHTED TIPS

# LIB
library(ape)

# FUNCTIONS FROM MoreTreeTools
getEdges <- function (tree, node = NULL, tips = NULL, type = 1) 
{
  if (!is.null(node)) {
    edges <- c()

DomBennett

# EXAMPLE TEXT DISTANCES

# FUNCTIONS
justText <- function(txt) {
  # converts text to its readable form by removing punctuation and numbers
  gsub("[^a-zA-Z ]", "", txt)
}

calcStrDst <- function(txts) {
  # calculate the distance between vector of texts

DomBennett

getGroups <- function(tree, get_edges=TRUE) {
  .fillInRes <- function(i) {
    res <- vector('list', length=2)
    names(res) <- c('g1', 'g2')
    res[['g1']] <- which(edge.tips[i, ] == 1)
    res[['g2']] <- which(edge.tips[i, ] == 0)
    res
  }
  .addEdges <- function(i) {
    res[[i]][['edglngth']] <<- edglngths[[i]]

DomBennett

# LIB
library(treeman)
library(doMC)
library(foreach)

# FUNCTION
randTreeList <- function(n) {
  res <- vector(mode='list', length=n)
  for(i in 1:n) {
    res[[i]] <- randTree(20, wndmtrx=TRUE)

DomBennett

# Take sequences from fasta file and write as separate files

# FUNCTION
readSqs <- function(fl) {
 all_data <- readLines(fl)
 sqs <- list()
 for(i in seq_along(all_data)) {
   bit <- all_data[[i]]
   if(grepl(pattern='^>', x=bit)) {
     nm <- sub(pattern='^>', '', x=bit)

DomBennett

# LIB
library(ape)

# DATA
# tree string produced by `RAxML -J ` arg
trstr <- "(A,B,(C,((D,((E,F):1.0[80],((G,H):1.0[100],(I,J):1.0[100]):1.0[67]):1.0[58]):1.0[98],(K,(L,(M,N):1.0[89]):1.0[91]):1.0[100]):1.0[97]):1.0[97]);"

# FAIL
tree <- read.tree(text=trstr)
# node.label = NULL