Deleted dependency Makie

Project.toml

@@ -17,7 +17,6 @@ Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 
 [compat]
-CairoMakie = "0.11.1"
 Clustering = "0.15.5"
 Combinatorics = "1.0.2"
 Distances = "0.10.10"

docs/src/lib/helper_methods.md

@@ -2,9 +2,4 @@
 ```@docs
 standardize_tree
 distance
-```
-
-# Visualize results
-```@docs
-plot_clusters
 ```

docs/src/model/hclust.md

@@ -24,12 +24,6 @@ matrix = distance(tree);
 label = hc_label(matrix, 2)
 ```
 
-We can visualize the result using build-in function [`plot_clusters`](@ref).
-
-```@example 1
-plot_clusters(trees', label)
-```
-
 **Reference**
 
 The implementation of *hierarchical clustering* is provided by [`Clustering.jl`](https://github.com/JuliaStats/Clustering.jl).

docs/src/model/kmeans.md

@@ -32,12 +32,6 @@ tree = standardize_tree(trees);
 label = kmeans_label(tree, 2, rng=rng)
 ```
 
-We can visualize the result using build-in function [`plot_clusters`](@ref).
-
-```@example 1
-plot_clusters(trees', label)
-```
-
 **Reference**
 
 The implementation of *Yinyang K-means* is provided by [`ParallelKMeans.jl`](https://github.com/PyDataBlog/ParallelKMeans.jl).

src/PhyloClustering.jl

@@ -11,7 +11,6 @@ export
     hc_label,
     dbscan_label,
     standardize_tree,
-    plot_clusters,
     distance,
     num_bipartitions,
     show_bipartitions,

src/helper.jl

@@ -1,4 +1,4 @@
-using MultivariateStats, StatsBase, CairoMakie, Distances
+using MultivariateStats, StatsBase, Distances
 
 """
     standardize_tree(tree::AbstractMatrix{<:Real})
@@ -12,31 +12,14 @@ It is recommended to standardize the data before inputting it into the model.
  A standardized B * N tree `Matrix` with a mean of about 0 and a standard deviation of about 1.
     This tree `Matrix` can be the input of [model](@ref basics).
 """
-function standardize_tree(tree::AbstractMatrix{<:Real})    
-    data = collect(tree');
+function standardize_tree(tree::AbstractMatrix{<:Real})
+    data = collect(tree')
     dt = fit(ZScoreTransform, data, dims=2)
     data = StatsBase.transform(dt, data)
-    replace!(data, NaN=>0)
+    replace!(data, NaN => 0)
     return data
 end
 
-"""
-    plot_clusters(tree::AbstractMatrix{<:Real}, label::Vector{Int64})
-
-Visualize the result of models.
-
-# Arguments
- - `tree`: a B * N tree Matrix (each column of tree Matrix is a B-dimensional tree in bipartiton format).
- - `label`: an N-length Vector containing predicted labels for each tree. People can use the output of the models.
-# Output
- A scatter plot showing tree clusters.
-"""
-function plot_clusters(tree::AbstractMatrix{<:Real}, label::Vector{Int64})
-    PCA_model = fit(PCA, tree, maxoutdim = 2);
-    PCA_data = predict(PCA_model,tree)
-    scatter(PCA_data[1,:], PCA_data[2,:], markersize = 5, color = label)
-end
-
 """
     distance(tree::AbstractMatrix{<:Real})
 

test/test_helper.jl

@@ -5,40 +5,39 @@ include("../src/helper.jl")
         tree = split_weight(trees, 4)
         N = size(tree)[1]
         B = size(tree)[2]
-        @test !(mean(tree[1,:]) ≈ 0)
+        @test !(mean(tree[1, :]) ≈ 0)
         tree = standardize_tree(tree)
-        @test size(tree) == (B,N)
-        @test [std(tree[i,:]) for i in 1:7] ≈ [1,1,1,1,1,0,1] atol=0.1
-        @test [mean(tree[i,:]) for i in 1:7] ≈ [0,0,0,0,0,0,0] atol=0.1
+        @test size(tree) == (B, N)
+        @test [std(tree[i, :]) for i in 1:7] ≈ [1, 1, 1, 1, 1, 0, 1] atol = 0.1
+        @test [mean(tree[i, :]) for i in 1:7] ≈ [0, 0, 0, 0, 0, 0, 0] atol = 0.1
 
         trees = readMultiTopology("file/8-taxon-tree.trees")
         tree = split_weight(trees, 8)
         N = size(tree)[1]
         B = size(tree)[2]
         n = num_bipartitions(8)
-        @test !(mean(tree[1,:]) ≈ 0)
+        @test !(mean(tree[1, :]) ≈ 0)
         tree = standardize_tree(tree)
-        @test size(tree) == (B,N)
-        @test [std(tree[i,:]) for i in 1:8] ≈ repeat([1], outer = 8) atol=0.1
-        @test [mean(tree[i,:]) for i in 1:n] ≈ repeat([0], outer = n) atol=0.1
+        @test size(tree) == (B, N)
+        @test [std(tree[i, :]) for i in 1:8] ≈ repeat([1], outer=8) atol = 0.1
+        @test [mean(tree[i, :]) for i in 1:n] ≈ repeat([0], outer=n) atol = 0.1
 
         trees = readMultiTopology("file/16-taxon-tree.trees")
         tree = split_weight(trees, 16)
         N = size(tree)[1]
         B = size(tree)[2]
         n = num_bipartitions(16)
-        @test !(mean(tree[1,:]) ≈ 0)
+        @test !(mean(tree[1, :]) ≈ 0)
         tree = standardize_tree(tree)
-        @test size(tree) == (B,N)
-        @test [std(tree[i,:]) for i in 1:16] ≈ repeat([1], outer = 16) atol=0.1
-        @test [mean(tree[i,:]) for i in 1:n] ≈ repeat([0], outer = n) atol=0.1
+        @test size(tree) == (B, N)
+        @test [std(tree[i, :]) for i in 1:16] ≈ repeat([1], outer=16) atol = 0.1
+        @test [mean(tree[i, :]) for i in 1:n] ≈ repeat([0], outer=n) atol = 0.1
     end
 
     @testset "visualization" begin
         trees = readMultiTopology("file/4-taxon-tree.trees")
         tree = split_weight(trees, 4)
-        label = [1,2,1,2]
-        @test_logs plot_clusters(tree, label)
+        label = [1, 2, 1, 2]
     end
 
     @testset "Euclidean distance matrix" begin
@@ -47,23 +46,23 @@ include("../src/helper.jl")
         tree = standardize_tree(tree)
         matrix = distance(tree)
         @test size(matrix)[1] == size(matrix)[2]
-        @test [matrix[i,i] for i in 1:size(matrix)[1]] == repeat([0], outer = size(matrix)[1])
+        @test [matrix[i, i] for i in 1:size(matrix)[1]] == repeat([0], outer=size(matrix)[1])
         @test matrix ≈ [
-            0.0 5.096169006818051 5.40722180738128 5.625211680819353; 
-            5.096169006818051 0.0 4.37996068613932 5.896362019739273; 
-            5.40722180738128 4.37996068613932 0.0 6.260740103673938; 
-            5.625211680819353 5.896362019739273 6.260740103673938 0.0] atol=0.001
+            0.0 5.096169006818051 5.40722180738128 5.625211680819353;
+            5.096169006818051 0.0 4.37996068613932 5.896362019739273;
+            5.40722180738128 4.37996068613932 0.0 6.260740103673938;
+            5.625211680819353 5.896362019739273 6.260740103673938 0.0] atol = 0.001
 
         trees = readMultiTopology("file/16-taxon-tree.trees")
         tree = split_weight(trees, 16)
         tree = standardize_tree(tree)
         matrix = distance(tree)
         @test size(matrix)[1] == size(matrix)[2]
-        @test [matrix[i,i] for i in 1:size(matrix)[1]] == repeat([0], outer = size(matrix)[1])
+        @test [matrix[i, i] for i in 1:size(matrix)[1]] == repeat([0], outer=size(matrix)[1])
         @test matrix ≈ [
-            0.0 11.3979509761689 11.549754911257478 11.358576754022506; 
-            11.3979509761689 0.0 11.21122183718288 11.930804141875372; 
-            11.549754911257478 11.21122183718288 0.0 11.473318029384393; 
-            11.358576754022506 11.930804141875372 11.473318029384393 0.0] atol=0.001
+            0.0 11.3979509761689 11.549754911257478 11.358576754022506;
+            11.3979509761689 0.0 11.21122183718288 11.930804141875372;
+            11.549754911257478 11.21122183718288 0.0 11.473318029384393;
+            11.358576754022506 11.930804141875372 11.473318029384393 0.0] atol = 0.001
     end
 end