Dendrogram with custom colouring

Hi, I am preparing dendrograms in MATLAB. I can set the colour threshold as follows:

>> figure()
H = dendrogram(tree,0,'ColorThreshold',1);
set(H,'LineWidth',1.5)

this gives the following output:

I have two questions regarding the above:

1) How can I have MATLAB only colour the largest cluster below my threshold (this would be the one in red)

2) How can I specify the colour

Thanks in advance.

Answer 1

[Adam]

If you use the

hLines = dendrogram(...)

syntax you will get an array of handles as output. These will be handles to the lines created. These can be coloured individually and with any colour you want. I assume the lines are ordered as specified by the leafOrder although I haven't checked.

X = rand(10,3);
tree = linkage(X,'average');
D = pdist(X);
leafOrder = optimalleaforder(tree,D);
figure()
h = dendrogram(tree,'Reorder',leafOrder);

h(1).Color = 'r';
h(8).Color = [0 0.5 0];

[KA]

Hello Adam,

Thank you for the answer. But the code runs with an error:

>> Untitled

    Structure assignment to non-structure object.
      Error in Untitled (line 7)
      h(1).Color = 'r';

Any clues?

[Adam]

Which version of Matlab are you using? If you are pre R2014b you will instead need

set( h(1), 'Color', 'r' )

etc.

Using this syntax you can also set multiple at the same time which you can't with the newer syntax e.g.

set( h( [1 3 7] ), 'Color', 'r' );

[KA]

Sorted - thank you.

Answer 2

[micholeodon]

Here is how you get colors from your dendrogram and link it with the observations.

By changing 'Color' property in lines stored in h variable below you can change colors in your dendrogram.

clear; close all; clc;
%% Generate example data
rng('default') % For reproducibility
N = 10; % number of observations
X = rand(N,3);
%% Get linkage
tree = linkage(X, 'average');
%% Get desired number of clusters
nClusters   = 2;
cutoff      = median([tree(end-nClusters+1,3) tree(end-nClusters+2, 3)]);
%% plot tree
figure
h = dendrogram(tree, 'ColorThreshold', cutoff); % h contains Line objects
%% get colors
linesColor = cell2mat(get(h,'Color')); % get lines color; 
colorList = unique(linesColor, 'rows');
% NOTE that each row is single line corresponding to the same row in tree
% variable. I use that property below.
X_color     = zeros(N,3);
X_cluster   = zeros(N,1);
for iLeaf = 1:N
    [iRow, ~] = find(tree==iLeaf);
    color = linesColor(iRow,:); % !
    
    % assign color to each observation
    X_color(iLeaf,:) = color; 
    % assign cluster number to each observation
    X_cluster(iLeaf,:) = find(ismember(colorList, color, 'rows')); 
end
%% changing lines color
h(5).Color = [0 1 0]

[Niraj Desai]

Thank you! I've been going in circles all afternoon trying to figure this out. Much obliged.

[T0m07]

I don't think this works if you have more than 30 data points, since then you have more data points than leaves, and your code errors during the for loop.

For your code to work, you need to provide N as an additional input to dendrogram() to define the Maximum number of leaf nodes.