Entering edit mode
3.0 years ago
DNAngel
▴
250
I'm trying to create some MDS plots for my data. I'm using vegan package's vegdist which does not produce any errors but when I view my resulting matrix there are empty values everywhere in the lower diagonal where only the upper diagonal should be empty.
my code:
data <- read.csv("nematoda.csv",header=TRUE) # 180 samples with 22 values, 6 of which are env variables
data <- data[apply(data[,-1:-6],1,function(x) !all(x==0)),] # to get rid of sites with no species information
# Transform data into relative abundances
data.total <- decostand(data[,7:length(data)], method="total")
# Distance with Bray-Curtis
data.bray <- vegdist(data.total, method="bray")
data.bray
1 2 3 5 7 8 10 11 12 13
2 0.00000000
3 0.00000000 0.00000000
5 0.41421356 0.41421356 0.41421356
7 0.00000000 0.00000000 0.00000000 0.41421356
8 0.00000000 0.00000000 0.00000000 0.41421356 0.00000000
10 0.00000000 0.00000000 0.00000000 0.41421356 0.00000000 0.00000000
14 15 16 17 18 20 21 22 23 24
2
3
5
7
8
10
25 27 28 29 30 31 32 33 34 36
2
3
5
7
8
10
37 38 40 42 44 45 46 47 48 49
2
3
5
7
8
10
50 51 52 53 55 56 57 58 60 61
2
3
5
7
8
10
62 63 64 65 66 67 68 69 70 71
2
3
5
7
8
10
72 73 75 76 77 78 79 80 81 82
2
3
5
7
8
10
83 84 85 86 87 88 89 90 91 93
2
3
5
7
8
10
94 95 96 97 98 99 100 101 102 103
2
3
5
7
8
10
104 106 107 108 109 110 111 112 115 117
2
3
5
7
8
10
118 119 120 121 122 124 125 126 127 128
2
3
5
7
8
10
129 130 131 132 133 134 135 136 137 138
2
3
5
7
8
10
139 140 141 142 143 144 145 147 148 149
2
3
5
7
8
10
150 151 152 153 154 155 156 157 158 159
2
3
5
7
8
10
160 161 162 163 164 165 166 167 168 169
2
3
5
7
8
10
170 171 172 173 174 175 176 177 179
2
3
5
7
8
10
[ reached getOption("max.print") -- omitted 153 rows ]
I've tried different transformations, but all the same. When I used sample datasets and even a friend's dataframe from a different project - with the exact same code I see their whole table...not sure why mine is causing an issue. A lot of my species abundance values are 0 though however so would this be causing the incomplete distance matrix?