Merge pull request #85 from EcoJulia/rr/updates

Updates to workflows and dependency versions

.github/workflows/CI.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       matrix:
         version:
-          - '1.5'
+          - '1'
         os:
           - ubuntu-latest
           - macOS-latest
@@ -25,15 +25,15 @@ jobs:
           - x64
         experimental: [false]
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - uses: julia-actions/setup-julia@v1
         with:
           version: ${{ matrix.version }}
           arch: ${{ matrix.arch }}
-      - uses: julia-actions/julia-buildpkg@latest
-      - uses: julia-actions/julia-runtest@latest
+      - uses: julia-actions/julia-buildpkg@v1
+      - uses: julia-actions/julia-runtest@v1
       - uses: julia-actions/julia-processcoverage@v1
-      - uses: codecov/codecov-action@v1
+      - uses: codecov/codecov-action@v3
         with:
           file: ./lcov.info
           flags: unittests

.github/workflows/CompatHelper.yml

@@ -1,19 +1,40 @@
 name: CompatHelper
 
 on:
+  push:
+    branches:
+      - master
   schedule:
     - cron: '00 00 * * *'
 
 jobs:
   CompatHelper:
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        julia-version:
+          - '1'
+        arch:
+          - x86
+        os:
+          - ubuntu-latest
     steps:
-      - uses: julia-actions/setup-julia@latest
+      - uses: julia-actions/setup-julia@v1
         with:
-          version: 1.3
-      - name: Pkg.add("CompatHelper")
-        run: julia -e 'using Pkg; Pkg.add("CompatHelper")'
-      - name: CompatHelper.main()
+          version: ${{ matrix.julia-version }}
+          arch: ${{ matrix.arch }}
+      - name: "Install CompatHelper"
+        run: |
+          import Pkg
+          name = "CompatHelper"
+          uuid = "aa819f21-2bde-4658-8897-bab36330d9b7"
+          version = "3"
+          Pkg.add(; name, uuid, version)
+        shell: julia --color=yes {0}
+      - name: "Run CompatHelper"
+        run: |
+          import CompatHelper
+          CompatHelper.main()
+        shell: julia --color=yes {0}
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: julia -e 'using CompatHelper; CompatHelper.main()'
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/Documentation.yml

@@ -12,11 +12,11 @@ jobs:
     name: "Build the documentation"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: julia-actions/setup-julia@latest
+      - uses: actions/checkout@v4
+      - uses: julia-actions/setup-julia@v1
         with:
-          version: '1.5'
-      - uses: julia-actions/julia-buildpkg@latest
+          version: '1'
+      - uses: julia-actions/julia-buildpkg@v1
       - name: Install dependencies
         run: julia --project=docs/ -e 'using Pkg; Pkg.develop(PackageSpec(path=pwd())); Pkg.instantiate()'
       - name: Build and deploy

Project.toml

@@ -4,7 +4,7 @@ keywords = ["macroecology", "ecology", "biology", "geography"]
 license = "MIT"
 desc = "Julia framework for spatial ecology"
 authors = ["mkborregaard <mkborregaard@snm.ku.dk"]
-version = "0.9.15"
+version = "0.9.16"
 
 [deps]
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
@@ -21,14 +21,14 @@ StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 
 [compat]
 DataFrames = "1.0, 1.1, 1.2"
-DataFramesMeta = "0.5, 0.6, 0.7, 0.8, 0.9"
+DataFramesMeta = "0.5, 0.6, 0.7, 0.8, 0.9, 0.10, 0.11, 0.12, 0.13, 0.14"
 Distances = "0.8, 0.9, 0.10"
 EcoBase = "0.1"
 RandomBooleanMatrices = "0.1"
 RandomNumbers = "1.4"
 RecipesBase = "0.7, 0.8, 1"
 StableRNGs = "1"
-StatsBase = "0.32, 0.33"
+StatsBase = "0.32, 0.33, 0.34"
 julia = "1.2"
 
 [extras]

README.md

@@ -3,14 +3,12 @@
 [![d_stable](https://img.shields.io/badge/Doc-stable-green?style=flat-square)](https://ecojulia.github.io/SpatialEcology.jl/stable/)
 [![d_latest](https://img.shields.io/badge/Doc-latest-blue?style=flat-square)](https://ecojulia.github.io/SpatialEcology.jl/dev/)
 
-
 ![version](https://img.shields.io/github/v/tag/EcoJulia/SpatialEcology.jl?sort=semver&style=flat-square)
-![CI](https://img.shields.io/github/workflow/status/EcoJulia/SpatialEcology.jl/CI?label=CI&style=flat-square)
+[![CI](https://github.com/EcoJulia/SpatialEcology.jl/actions/workflows/CI.yml/badge.svg)](https://github.com/EcoJulia/SpatialEcology.jl/actions/workflows/CI.yml)
 ![Doc](https://img.shields.io/github/workflow/status/EcoJulia/SpatialEcology.jl/Documentation?label=Doc&style=flat-square)
-[![Coverage](https://img.shields.io/codecov/c/github/EcoJulia/SpatialEcology.jl?style=flat-square)](https://codecov.io/gh/EcoJulia/SpatialEcology.jl)
-
-### Primary author: Michael Krabbe Borregaard (@mkborregaard)
+[![codecov](https://codecov.io/gh/EcoJulia/SpatialEcology.jl/graph/badge.svg?token=DeSFZuHa99)](https://codecov.io/gh/EcoJulia/SpatialEcology.jl)
 
+## Primary author: Michael Krabbe Borregaard (@mkborregaard)
 
 A package for community- and macro-ecological analysis in julia.
 This package offers a set of base types for interoperability in spatial ecology. The idea is to provide a powerful framework for expressing a great variety of analyses in a flexible manner. It presently holds types for presence-absence matrices, site data and species traits, and will be included with phylogenies and ecological interaction networks. SpatialEcology takes care of aligning all data for analysis.
@@ -20,10 +18,10 @@ The emphasis is on fast, flexible code operating mainly with views into the larg
 The package originated as a port of the R package `nodiv`, available from CRAN.
 
 - Types:
-    - Assemblage (holds presence-absence information along with information on traits and sites)
-    - ComMatrix (presence-absence matrix)
-    - SpatialData (Grid or Point data with site information)
+  - Assemblage (holds presence-absence information along with information on traits and sites)
+  - ComMatrix (presence-absence matrix)
+  - SpatialData (Grid or Point data with site information)
 
 ## Relevant other packages
-This package is part of the [EcoJulia](https://ecojulia.org) organisation, which aims to bring together a coherent set of packages for ecological data analysis.For other relevant packages check the [BioJulia](https://biojulia.net) organisation focusing on molecular biology, and the [JuliaGeo](https://juliageo.org/) organisation focusing on geographical data analysis. A long-term goal of the EcoJulia organisation is to interface as seamlessly as possible with these projects to create an integrated data analysis framework for julia.
 
+This package is part of the [EcoJulia](https://ecojulia.org) organisation, which aims to bring together a coherent set of packages for ecological data analysis.For other relevant packages check the [BioJulia](https://biojulia.net) organisation focusing on molecular biology, and the [JuliaGeo](https://juliageo.org/) organisation focusing on geographical data analysis. A long-term goal of the EcoJulia organisation is to interface as seamlessly as possible with these projects to create an integrated data analysis framework for julia.

docs/src/examples/nodebased.md

@@ -1,7 +1,7 @@
 ## Node-based analysis of species distributions
 
 This example demonstrates how to do a node-based comparison of species
-distributions, as described in [Borregaard, M.K., Rahbek, C., Fjeldså, J., Parra, J.L., Whittaker, R.J. and Graham, C.H. (2014). Node-based analysis of species distributions. _Methods in Ecology and Evolution_ **5**: 1225-1235](http://macroecointern.dk/pdf-reprints/Borregaard_MEE_2014.pdf). 
+distributions, as described in [Borregaard, M.K., Rahbek, C., Fjeldså, J., Parra, J.L., Whittaker, R.J. and Graham, C.H. (2014). Node-based analysis of species distributions. _Methods in Ecology and Evolution_ **5**: 1225-1235](http://macroecointern.dk/pdf-reprints/Borregaard_MEE_2014.pdf).
 
 We will reimplement the method from the paper from first principles, using
 SpatialEcology functionality and the ecojulia phylogenetics package Phylo.
@@ -14,35 +14,38 @@ are defined on a regular grid with a cellsize of 1 lat/long degree. This is
 one of the datasets used in the Borregaard _et al._ (2014) paper.
 
 ### Load data and create objects
-First, let's load the data. 
+
+First, let's load the data.
 
 Species occurrence data for spatial ecological analysis exists in a variety of
 different formats. A common format is to have the data in one or several CSV files.
 
 In this case, we have the data in two CSV tables, one of species
-occurrences in each grid cell, and one with the lat-long coordinates of each 
-grid cell. 
-
-The CSV table of occurrences is in the widely used phylocom format, 
-which is a long-form format for associating the occurrence of species in sites. 
-It consists of three columns, a column of species names, one of abundances 
-(here all have the value 1, as it's a presence-absence data set) and a column 
-of sites. 
+occurrences in each grid cell, and one with the lat-long coordinates of each
+grid cell.
+
+The CSV table of occurrences is in the widely used phylocom format,
+which is a long-form format for associating the occurrence of species in sites.
+It consists of three columns, a column of species names, one of abundances
+(here all have the value 1, as it's a presence-absence data set) and a column
+of sites:
+
 ```@example nodebased
 using CSV, DataFrames, SpatialEcology
 phylocom = CSV.read("../../data/tyrann_phylocom.tsv", DataFrame)
 first(phylocom, 4) # hide
 ```
 
-The coordinates is a simple DataFrame with a column of sites, one of latitude 
-and one of longitude
+The coordinates is a simple DataFrame with a column of sites, one of latitude
+and one of longitude:
+
 ```@example nodebased
 coord = CSV.read("../../data/tyrann_coords.tsv", DataFrame)
 first(coord, 4) # hide
 ```
 
-We ensure that the column of sites are represented as `string`s in both data 
-sets. We then construct the Assemblage object. The site columns are used to 
+We ensure that the column of sites are represented as `string`s in both data
+sets. We then construct the Assemblage object. The site columns are used to
 match the two DataFrames together.
 
 ```@example nodebased
@@ -51,15 +54,17 @@ coord.cell = string.(coord.cell)
 tyrants = Assemblage(phylocom, coord)
 ```
 
-Let's have a look at the data
+Let's have a look at the data:
+
 ```@example nodebased
 using Plots
 ENV["GKSwstype"]="nul" # hide
 default(color = cgrad(:Spectral, rev = true))
 plot(tyrants)
 ```
 
-Next, we'll read in the phylogenetic tree
+Next, we'll read in the phylogenetic tree:
+
 ```@example nodebased
 using Phylo 
 tree = open(parsenewick, "../../data/tyrannid_tree.tre")
@@ -68,7 +73,8 @@ plot(tree, treetype = :fan, tipfont = (5,))
 ```
 
 ### Extract information from a single clade
-The [Phylo](http://docs.ecojulia.org/Phylo/stable) package uses iterators over 
+
+The [Phylo](http://docs.ecojulia.org/Phylo/stable) package uses iterators over
 vertices in the phylogeny for almost everything. For example, to get a vector
 of all internal (non-tip) nodes in the phylogeny, we would create an iterator
 over the names of all nodes in the tree, filtered by the function `isleaf`, which
@@ -89,7 +95,7 @@ randnode = nodevec[131]
 ```
 
 We can get a list of the names of all tips/species descending from the node by
-getting all descendant nodes with `getdescendants` and filtering with `isleaf`. 
+getting all descendant nodes with `getdescendants` and filtering with `isleaf`.
 We need to pass an anonymous function to `filter` here, because the `isleaf`
 function takes two arguments.
 
@@ -101,7 +107,7 @@ first(nodespecies(tree, randnode), 4) # hide
 
 We can use that species list to subset an `Assemblage` object. For instance, we
 can make a function to create a smaller `Assemblage` of all species descending
-from our selected node. 
+from our selected node.
 
 ```@example nodebased
 get_clade(assemblage, tree, node) = view(assemblage, species = nodespecies(tree, node))
@@ -111,11 +117,12 @@ plot(rand_clade, title = randnode)
 ```
 
 ### Comparing the richness of sister clades
+
 The question we are interested in addressing here is: At a given node where the
 lineage splits into two sister clades - are the two descendant clades distributed
 differently? This could be an indication that an evolutionary or biogeographic
-event happened at that time, of consequence for the current distribution of 
-the species. 
+event happened at that time, of consequence for the current distribution of
+the species.
 
 So let's get the two descendant clades, and plot their distribution
 in comparison to the parent clade
@@ -135,16 +142,18 @@ end
 
 plot_node(tyrants, tree, randnode)
 ```
+
 It is clear that the two clades have distinct distributions, with the first
 descendant appearing to be overrepresented in the tropical rainforest biome,
-mainly in the Amazon. 
+mainly in the Amazon.
 
-But is the difference great enough that we can say that 
+But is the difference great enough that we can say that
 this is not just a random pattern? We can use randomization to find out.
 
 ### Using randomization to assess significance of distribution differences
+
 SpatialEcology `Assemblage`s can be randomized using the `curveball` matrix
-randomization algorithm defined in [RandomBooleanMatrices.jl](http://docs.ecojulia.org/RandomBooleanMatrices/stable). 
+randomization algorithm defined in [RandomBooleanMatrices.jl](http://docs.ecojulia.org/RandomBooleanMatrices/stable).
 
 This algorithm randomizes a species-by-site
 matrix while keeping row and column sums constant, and is very fast. We can
@@ -156,6 +165,7 @@ rmg = matrixrandomizer(rand_clade)
 newcomm = rand(rmg)
 plot(newcomm, title = "randomized version of $randnode")
 ```
+
 Because row and column sums are kept constant, the richness of the randomized
 community is the same. But the richness of the two descendant clades will be
 different - let's look at our focal node:
@@ -169,8 +179,9 @@ plot(
     layout = (1,3), size = (1000, 350), title = ["parent" "child 1" "child 2"]
 )
 ```
+
 This represents a random expectation for the species richness of the two
-descendant clades should be. 
+descendant clades should be.
 
 We can repeat this process 100 times and store
 the species richness of one of the clades in order to get a sampling
@@ -200,9 +211,10 @@ sims = simulate_descendants(rand_clade, tree, ch2)
 Then we calculate the mean and standard deviation across simulations and use this
 to express the empirical richness values as standardized effect sizes.
 The resulting standardized effect size for each grid cell constitutes the `SOS`
-metric of Borregaard et al. (2014). 
+metric of Borregaard et al. (2014).
 
 To calculate this for our focal cell and plot it we can do:
+
 ```@example nodebased
 using Statistics
 function calculate_SOS(sims)
@@ -213,14 +225,16 @@ end
 
 sims = simulate_descendants(rand_clade, tree, ch1)
 SOS = calculate_SOS(sims)
-plot(SOS, rand_clade, clim = (-8,8), fillcolor = :RdYlBu, title = "SOS for clade $randnode)
+plot(SOS, rand_clade, clim = (-8,8), fillcolor = :RdYlBu, title = "SOS for clade $randnode")
 ```
+
 We see a clear distinction between the two clades descending from our focal node,
 where one descendant is overrepresented in tropical moist forest and the other in
 colder regions.
 
 The strength of divergence among the two clades is summarized by the GND value
 (Borregaard et al. 2014)
+
 ```@example nodebased
 using StatsBase: tiedrank
 
@@ -241,8 +255,9 @@ first(GND, 4) # hide
 ```
 
 ### Putting it all together
+
 We can use all of the above to go through the entire phylogeny and generate SOS
-and GND values. 
+and GND values.
 
 First, let us create a function that calculates both metrics
 
@@ -264,10 +279,12 @@ SOS, GND = process_node(tyrants, tree, randnode)
 ```
 
 ### Final step: Applying the method to the entire tree
+
 Finally, we can now go through every node on the tree and calculate the metrics.
 
 This function recreates the functionality of the main `Node_analysis` function of
-the [nodiv](https://github.com/mkborregaard/nodiv) R package
+the [nodiv](https://github.com/mkborregaard/nodiv) R package:
+
 ```@example nodebased
 using ProgressLogging
 function node_based_analysis(assemblage::Assemblage, tree::AbstractTree)
@@ -283,7 +300,8 @@ end
 SOSs, GNDs = node_based_analysis(tyrants, tree);
 ```
 
-Let's visualize the GND values on the tree
+Let's visualize the GND values on the tree:
+
 ```@example nodebased
 plot(tree, 
      showtips = false, marker_z = GNDs, 

docs/src/man/getters.md

@@ -25,9 +25,6 @@ sitenames
 speciesnames
 coordinates
 occurring
-noccurring
 occupied
-noccupied
 occurrences
-cooccurring
-```
+```