1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
|
# Copyright (C) Tal Galili
#
# This file is part of dendextend.
#
# dendextend is free software: you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 2 of the License, or
# (at your option) any later version.
#
# dendextend is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# A copy of the GNU General Public License is available at
# http://www.r-project.org/Licenses/
#
#' @title Correlation matrix between a list of trees.
#' @export
#' @description
#' A correlation matrix between a list of trees.
#'
#' Assumes the labels in the two trees fully match. If they do not
#' please first use \link{intersect_trees} to have them matched.
#'
#' @param dend a \link{dendlist} of trees
#' @param method a character string indicating which correlation coefficient
#' is to be computed. One of "cophenetic" (default), "baker",
#' "common_nodes", or "FM_index".
#' It can be abbreviated.
#' @param ... passed to cor functions.
#'
#' @seealso
#' \link{cophenetic}, \link{cor_cophenetic}, \link{cor_bakers_gamma},
#' \link{cor_common_nodes}, \link{cor_FM_index}
#' @return
#' A correlation matrix between the different trees
#'
#' @examples
#'
#' \dontrun{
#'
#' set.seed(23235)
#' ss <- sample(1:150, 10)
#' dend1 <- iris[ss, -5] %>%
#' dist() %>%
#' hclust("com") %>%
#' as.dendrogram()
#' dend2 <- iris[ss, -5] %>%
#' dist() %>%
#' hclust("single") %>%
#' as.dendrogram()
#' dend3 <- iris[ss, -5] %>%
#' dist() %>%
#' hclust("ave") %>%
#' as.dendrogram()
#' dend4 <- iris[ss, -5] %>%
#' dist() %>%
#' hclust("centroid") %>%
#' as.dendrogram()
#' # cutree(dend1)
#' cors <- cor.dendlist(dendlist(d1 = dend1, d2 = dend2, d3 = dend3, d4 = dend4))
#'
#' cors
#'
#' # a nice plot for them:
#' library(corrplot)
#' corrplot(cor.dendlist(dend1234), "pie", "lower")
#' }
cor.dendlist <- function(dend, method = c("cophenetic", "baker", "common_nodes", "FM_index"), ...) {
if (!is.dendlist(dend)) stop("dend needs to be a dendlist object")
method <- match.arg(method)
n_list <- length(dend)
the_cor <- matrix(1, n_list, n_list)
pairwise_combn <- combn(n_list, 2)
for (i in 1:ncol(pairwise_combn)) {
l1 <- pairwise_combn[1, i]
l2 <- pairwise_combn[2, i]
the_cor[l1, l2] <- the_cor[l2, l1] <-
switch(method,
cophenetic = cor_cophenetic(dend[[l1]], dend[[l2]], ...),
baker = cor_bakers_gamma(dend[[l1]], dend[[l2]], ...),
common_nodes = cor_common_nodes(dend[[l1]], dend[[l2]], ...),
FM_index = cor_FM_index(dend[[l1]], dend[[l2]], ...)
)
}
rownames(the_cor) <- colnames(the_cor) <- names(dend)
the_cor
}
# edgeset_dist
#' Proportion of commong nodes between two trees
#' @export
#' @description
#' Calculates the number of nodes, in each tree, that are common (i.e.: that have the same exact list of labels).
#' The correlation is between 0 (actually, 2*(nnodes-1)/(2*nnodes), for two trees with
#' the same list of labels - since the top node will always be identical for them).
#' Where 1 means that every node in the one tree, has a node in the other tree with the exact
#' same list of labels.
#' Notice this measure is non-parameteric (it ignores the heights and relative position of the nodes).
#'
#' @param dend1 a dendrogram.
#' @param dend2 a dendrogram.
#' @param ... not used.
#'
#' @return
#' A correlation value between 0 to 1 (almost identical trees)
#' @seealso \link{distinct_edges}, \link{cor.dendlist}
#'
#' @examples
#'
#' set.seed(23235)
#' ss <- sample(1:150, 10)
#' hc1 <- iris[ss, -5] %>%
#' dist() %>%
#' hclust("com")
#' hc2 <- iris[ss, -5] %>%
#' dist() %>%
#' hclust("single")
#' dend1 <- as.dendrogram(hc1)
#' dend2 <- as.dendrogram(hc2)
#'
#' cor_cophenetic(dend1, dend2)
#' cor_common_nodes(dend1, dend2)
#' tanglegram(dend1, dend2)
#' # we can see we have only two nodes which are different...
cor_common_nodes <- function(dend1, dend2, ...) {
# dendextend:::edgeset_dist
n_diff_nodes <- edgeset_dist(dend1, dend2)
nnodes_trees <- nnodes(dend1) + nnodes(dend2)
(nnodes_trees - n_diff_nodes) / nnodes_trees
}
#' Correlation of FM_index for some k
#' @export
#' @description
#' Calculates the FM_index Correlation for some k.
#'
#'
#' @param dend1 a dendrogram.
#' @param dend2 a dendrogram.
#' @param k an integer (number of clusters to cut the tree)
#' @param ... not used.
#'
#' @return
#' A correlation value between 0 to 1 (almost identical clusters for some k)
#' @seealso \link{FM_index}, \link{cor.dendlist}, \link{Bk}
#'
#' @examples
#'
#' set.seed(23235)
#' ss <- sample(1:150, 10)
#' hc1 <- iris[ss, -5] %>%
#' dist() %>%
#' hclust("com")
#' hc2 <- iris[ss, -5] %>%
#' dist() %>%
#' hclust("single")
#' dend1 <- as.dendrogram(hc1)
#' dend2 <- as.dendrogram(hc2)
#'
#' cor_FM_index(dend1, dend2, k = 2)
#' cor_FM_index(dend1, dend2, k = 3)
#' cor_FM_index(dend1, dend2, k = 4)
cor_FM_index <- function(dend1, dend2, k, ...) {
if (missing(k)) stop("You need to specifiy k.")
# dendextend:::edgeset_dist
clus1 <- cutree(dend1, k = k)[order.dendrogram(dend1)]
clus2 <- cutree(dend2, k = k)[order.dendrogram(dend2)]
if (all(clus1 == 0) | all(clus2 == 0)) {
warning("Can't calculate k - returning NA")
return(NA)
}
FM_index(clus1, clus2, assume_sorted_vectors = TRUE)
}
|
