Session 1: Introduction to R

This session provides an introduction to the most basic operations and functions in R.

a. 1: Demo

b. 1: Slides

You can access the full slideshow used in the 1-Introduction narration here.

The dataset called ‘coralreefherbivores.csv’ can be downloaded here.

c. 1: Exercises

Part I

• 1. create the following vectors:
  • 4 5 6 4 5 6 4 5 6 4 5 6 4 5 6 4 5 6
  • a sequence from 2 to 36, repeated three times
  • the words “bluefish” “redfish” and “whitefish” in this sequence, six times
  • combine the last two vectors into a new vector
    
    
• 2. create a vector using rpois(100, 10)
  • determine the frequency of the number 8 in your vector
  • determine how many numbers in your vector are greater than 10
  • determine how many numbers in your vector are smaller than 10 but greater than 5
    
    
• 3. build a matrix that looks like this:

[,1]	[,2]	[,3]	[,4]	[,5]
[1,]	1	2	3	4
[2,]	5	6	7	8
[3,]	9	10	11	12
[4,]	13	14	15	16
[5,]	17	18	19	20

• create a sequence of multiples of nines between 0 and 100, repeated ten times
  
  

• create a vector with random values using rnorm(1000, 0) , with an explanation of what rnorm() does
  
  

• create a second vector using rnorm, but this time with 10,000 elements, a mean of 50, and a standard deviation of 10
  
  

• tell me what the following functions tell you about your vectors: length(), str(), summary(), head(), tail()
  
  

• retain only the elements from your previous vector that are greater than the mean but smaller than the 3rd Quantile
  
  

Part II

• 1. create a vector using rpois(500, 10)
  • determine the proportional frequency of numbers that are >15
  • sort the vector in descending order
  • take the log of the vector and then determine the mean value
  • replace every 10th value in the vector with 0, take the log, and calculate the mean. Exclude values that cause the mean to be -Inf
    
    
• 2. build a matrix that looks like this:

[]	redfish	bluefish	whitefish	yellowfish
S1	0	3	6	9
S2	12	15	18	21
S3	24	27	30	33
S4	24	22	20	18
S5	16	14	12	10
S6	8	6	4	2

• turn your matrix into a data.frame and add a column entitled “Location” that contains the following sequence: Texas, Belize, Texas, Belize, Texas

• determine the mean number of fish at site S3

• determine the difference in the mean number of bluefish and yellowfish across all sites
  
  

• 3. build the following matrix:
  • 100 rows, 20 columns, filled column-wise with randomly-drawn, normally distributed values with a mean of 100 and a standard deviation of 10
  • determine the value of the second-to-last row in column 5
  • determine which column has the largest value in the matrix and which column has the greatest deviation from the mean (100)
    
    
• 4. load in the ‘coralreefherbivores.csv’ dataset and
  • turn it into a tibble
  • determine the data classes of each column
  • compare the snoutlength of the species Chlorurus microrhinos and Zebrasoma velifer
    
    

d. 1: Solutions

Part I

-a)

a1<-rep(seq(from=4,to=6,by=1),times=6) %>%
  print()

 [1] 4 5 6 4 5 6 4 5 6 4 5 6 4 5 6 4 5 6

a2 <- rep(seq(from = 2, to = 36, by = 1), times = 3)
a2

  [1]  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22
 [22] 23 24 25 26 27 28 29 30 31 32 33 34 35 36  2  3  4  5  6  7  8
 [43]  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29
 [64] 30 31 32 33 34 35 36  2  3  4  5  6  7  8  9 10 11 12 13 14 15
 [85] 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36

a3 <- rep(c("bluefish", "redfish", "whitefish"), times = 6)
a3

 [1] "bluefish"  "redfish"   "whitefish" "bluefish"  "redfish"  
 [6] "whitefish" "bluefish"  "redfish"   "whitefish" "bluefish" 
[11] "redfish"   "whitefish" "bluefish"  "redfish"   "whitefish"
[16] "bluefish"  "redfish"   "whitefish"

a4 <- paste(a2, a3)
a4

  [1] "2 bluefish"   "3 redfish"    "4 whitefish"  "5 bluefish"  
  [5] "6 redfish"    "7 whitefish"  "8 bluefish"   "9 redfish"   
  [9] "10 whitefish" "11 bluefish"  "12 redfish"   "13 whitefish"
 [13] "14 bluefish"  "15 redfish"   "16 whitefish" "17 bluefish" 
 [17] "18 redfish"   "19 whitefish" "20 bluefish"  "21 redfish"  
 [21] "22 whitefish" "23 bluefish"  "24 redfish"   "25 whitefish"
 [25] "26 bluefish"  "27 redfish"   "28 whitefish" "29 bluefish" 
 [29] "30 redfish"   "31 whitefish" "32 bluefish"  "33 redfish"  
 [33] "34 whitefish" "35 bluefish"  "36 redfish"   "2 whitefish" 
 [37] "3 bluefish"   "4 redfish"    "5 whitefish"  "6 bluefish"  
 [41] "7 redfish"    "8 whitefish"  "9 bluefish"   "10 redfish"  
 [45] "11 whitefish" "12 bluefish"  "13 redfish"   "14 whitefish"
 [49] "15 bluefish"  "16 redfish"   "17 whitefish" "18 bluefish" 
 [53] "19 redfish"   "20 whitefish" "21 bluefish"  "22 redfish"  
 [57] "23 whitefish" "24 bluefish"  "25 redfish"   "26 whitefish"
 [61] "27 bluefish"  "28 redfish"   "29 whitefish" "30 bluefish" 
 [65] "31 redfish"   "32 whitefish" "33 bluefish"  "34 redfish"  
 [69] "35 whitefish" "36 bluefish"  "2 redfish"    "3 whitefish" 
 [73] "4 bluefish"   "5 redfish"    "6 whitefish"  "7 bluefish"  
 [77] "8 redfish"    "9 whitefish"  "10 bluefish"  "11 redfish"  
 [81] "12 whitefish" "13 bluefish"  "14 redfish"   "15 whitefish"
 [85] "16 bluefish"  "17 redfish"   "18 whitefish" "19 bluefish" 
 [89] "20 redfish"   "21 whitefish" "22 bluefish"  "23 redfish"  
 [93] "24 whitefish" "25 bluefish"  "26 redfish"   "27 whitefish"
 [97] "28 bluefish"  "29 redfish"   "30 whitefish" "31 bluefish" 
[101] "32 redfish"   "33 whitefish" "34 bluefish"  "35 redfish"  
[105] "36 whitefish"

-b)

b1 <- rpois(100,10)
b1

  [1] 12  7 12  7 17  8  9  6 10  7 12 10  9 12  7 11 13  1 11 11 13
 [22]  3  8 14  9  6 10 13 13  8 11 10  6  7  8 14  6 12  5  8  7 10
 [43]  8 12  6 13  7 10  8  6  4 10 11 15 20 12 13 14 10 13  9  9  9
 [64] 12 12 14 12  9  6 12  9 11  7 12 12  7  8 14  5  9 12 13 11  6
 [85] 11 17 11  5  3  9 18 12  7  7  8  5  9 11 12 12

b2 <- b1[b1 == 8]
table(b2)

b2
8 
9 

length(b2)

[1] 9

b3 <- b1[b1 >10]
b3

 [1] 12 12 17 12 12 11 13 11 11 13 14 13 13 11 14 12 12 13 11 15 20 12
[23] 13 14 13 12 12 14 12 12 11 12 12 14 12 13 11 11 17 11 18 12 11 12
[45] 12

b4 <- b1[b1 <10 & b1 >5]
b4

 [1] 7 7 8 9 6 7 9 7 8 9 6 8 6 7 8 6 8 7 8 6 7 8 6 9 9 9 9 6 9 7 7 8 9
[34] 6 9 7 7 8 9

-c)

c1 <- matrix(1:20, nrow = 5, byrow = TRUE)
c1

     [,1] [,2] [,3] [,4]
[1,]    1    2    3    4
[2,]    5    6    7    8
[3,]    9   10   11   12
[4,]   13   14   15   16
[5,]   17   18   19   20

Part II

-a)

a1 <- rpois(500, 10)
head(a1)

[1]  7 15 10 10 13 17

a2 <- a1[a1 > 15]
length(a2)/length(a1)

[1] 0.048

a3 <- rev(sort(a1))
head(a3)

[1] 23 20 20 19 18 18

a4 <- log(a1)
head(a4)

[1] 1.945910 2.708050 2.302585 2.302585 2.564949 2.833213

#a5
a1[seq(from=0,to=500,by=10)]<-0
#or
replace(a1, (seq(from=0, to=500, by=10)), 0)

  [1]  7 15 10 10 13 17 14 12 12  0  9  9 10 13  9  6  7 10 13  0 13
 [22]  9 16  8 15 11 12  8  9  0 11  7 15  5  9 12 11  8  6  0  9  7
 [43] 15 10  7  9  9  9 15  0  8  9  9 11  9 12  7 10 17  0 16 13  7
 [64] 14 16 11  7  7 13  0 16 10 10  5 14  4 14  3  9  0 10 11 16  3
 [85]  6  9  7  8  8  0  9  8 10  7  8  9  7  7  8  0 15 11 14 19  9
[106]  6 10  6  6  0  6  5 13  5 15  6  9 10  9  0  9  6  6  9  9  6
[127]  9  9  4  0 10  6 10 11  9 11 13 12  9  0  6 10 14  7 10  6  8
[148] 10  7  0  7  8  6 11 12  5 15  9 10  0  6 10  9 14  9 10  9 11
[169] 14  0  9  8  7 10 11  7 12 12 15  0 14 11 12  9  8  8 10  9  8
[190]  0  9 10 11  7 17  4  6 18 13  0 14  8  9  7 14 12 11 11 10  0
[211] 12  8  6 10 17  9 12  9 14  0  8  6 13 11  9 12  8 17  7  0 14
[232] 10 14  6 13 13 10 11 12  0  7  8  6 15 11  5 11 11 13  0  7  9
[253] 10 12 13 20  9 12 16  0 11  5  9 14  8 10 10  8 10  0 15 12  9
[274] 10 13 10 13  8 11  0  9  9  9 12  8 10  7  8 11  0 11 15 12 10
[295] 18 10 11 11  5  0  7  8 12 13  7 14 11 14 12  0  7  8 14 13 15
[316]  9 11 10 10  0 10 14 12 13 12 17 10  9 13  0 10 12  5  9  5 10
[337] 12 15 10  0 13  7 23  8 12 10 10 15 13  0 13 15 14 10 15  7  4
[358] 11  8  0 13  8  6 18 13 11  5 16 11  0 12  8 13  9  9 15 11  5
[379]  8  0 10  6 11 13  9 12  7  9 15  0 10 11 10 10 12 18 11 10 14
[400]  0  3 13  7  8 12  3 20  7  7  0  9 10  7 11  7  8 15  7 15  0
[421] 10  2  9 10  9 10 11 12 13  0  9  6 14  8 14 15 16 12 14  0 10
[442]  7  1  9 12 12  8  5 11  0  6 16 11 13 10 14 11 11  8  0 11  9
[463]  9 11  9 11  4 12 10  0 15  8  7  9  8 12 11 13 13  0  9 13 12
[484] 11  7 11 14 10 13  0  5  9  5 12 11 11 14 10 13  0

a5logmean <- mean(log(a1[seq(from=0,to=500,by=10)]<-0)) # doesn't work because of -Inf values, so let's go step-by-step

a5step1 <- replace(a1, (seq(from=0, to=500, by=10)), 0) # replace with 0s
a5step2 <- a5step1[a5step1 > 0] # remove the 0s
a5step3 <- mean(log(a5step2)) # take the log of the mean

-b)

b1 <- matrix(c(seq(from = 0, to = 33, by = 3), seq(from = 24, to = 2, by = -2)), ncol = 4, byrow = TRUE)
rownames(b1) <- c("S1", "S2", "S3", "S4", "S5", "S6")
colnames(b1) <- c("redfish", "bluefish", "whitefish", "yellowfish")

b2 <- as.data.frame(b1) # turn into data frame
b2$Location <- c(rep(c("Texas", "Belize"), times = 3)) # add new column

b3 <- as.matrix(b2[3,c(1:4)]) # turn row 3 and columns 1:4 back into a matrix
mean(b3) # take the mean of the matrix 

[1] 28.5

print(b4blue <- mean(b2$bluefish)) # mean of bluefish

[1] 14.5

print(b4yellow <- mean(b2$yellowfish)) # mean of yellowfish

[1] 15.5

print(b4difference <- b4blue - b4yellow) # difference

[1] -1

-c)

c1 <- matrix(rnorm(2000, 100, 10), ncol = 20, byrow = F)
head(c1)

          [,1]      [,2]      [,3]      [,4]      [,5]      [,6]
[1,]  97.21767  98.19251  93.45351  89.30902 101.48067  85.42450
[2,] 112.99639 112.76412  84.48413 118.81134 103.40519  81.40670
[3,] 106.45122 119.29482  94.46852 102.80781 108.28285  82.31760
[4,]  97.25306  86.76533 108.07064 105.26943  97.04863 109.94568
[5,] 104.41281  97.21637 106.48560  78.29566 101.93544 112.42794
[6,]  94.24697  84.24974 113.55471 109.67638  92.92682  97.39542
          [,7]      [,8]      [,9]     [,10]     [,11]     [,12]
[1,] 122.58092  93.95745 109.08302 108.11612  95.05754  87.91288
[2,] 103.40033 113.22225 104.07990  86.97251 103.88598  96.43647
[3,]  92.12816 104.02716  99.04348  99.30539  98.11165  96.91853
[4,] 109.72486 109.90308  92.09482 114.19912  95.20120 112.57355
[5,] 109.10043 102.44735 104.95061  86.14095  99.82553 112.21784
[6,]  97.95533 103.50476 110.38871  94.10369  95.68369 102.20491
         [,13]     [,14]     [,15]     [,16]     [,17]     [,18]
[1,] 100.65613 104.29737  98.61514 112.52038 105.34923  97.80894
[2,]  84.19144 107.08536  92.61325 112.71201  85.42717 120.30674
[3,]  87.59011  95.12201  98.32900 119.76084  99.52681 101.18667
[4,] 105.11519 108.86852 105.44996 101.44141 108.39526 112.43779
[5,] 105.29518  88.91743 104.73334  88.17577 103.43581 100.49787
[6,] 112.98843 107.75935  92.63203  97.43995  92.39601  91.03433
         [,19]     [,20]
[1,] 104.97778  95.40465
[2,] 103.55934 112.22857
[3,] 106.81857  91.54977
[4,]  79.84788 122.38293
[5,]  83.26464  98.83141
[6,]  99.76014 116.80139

c2 <- c1[98, 5] # look for value in row 98 column 5
c2

[1] 87.66383

summary(c1) # look for maximum value and largest deviation from the specified mean (100)

       V1               V2               V3               V4        
 Min.   : 72.70   Min.   : 72.53   Min.   : 80.57   Min.   : 78.30  
 1st Qu.: 92.89   1st Qu.: 93.38   1st Qu.: 95.36   1st Qu.: 91.04  
 Median : 99.45   Median : 98.22   Median :102.07   Median : 98.11  
 Mean   :100.50   Mean   : 98.82   Mean   :101.54   Mean   : 98.35  
 3rd Qu.:106.90   3rd Qu.:105.01   3rd Qu.:106.90   3rd Qu.:105.09  
 Max.   :127.57   Max.   :126.43   Max.   :127.18   Max.   :125.37  
       V5               V6               V7               V8        
 Min.   : 84.67   Min.   : 76.21   Min.   : 81.34   Min.   : 71.72  
 1st Qu.: 94.21   1st Qu.: 88.71   1st Qu.: 95.66   1st Qu.: 93.95  
 Median :100.78   Median : 97.27   Median :102.19   Median :100.67  
 Mean   :101.06   Mean   : 98.51   Mean   :101.64   Mean   :100.33  
 3rd Qu.:106.08   3rd Qu.:107.31   3rd Qu.:108.66   3rd Qu.:106.66  
 Max.   :125.26   Max.   :124.84   Max.   :127.11   Max.   :119.85  
       V9              V10              V11              V12        
 Min.   : 80.07   Min.   : 78.39   Min.   : 77.27   Min.   : 69.94  
 1st Qu.: 95.15   1st Qu.: 91.83   1st Qu.: 93.18   1st Qu.: 92.57  
 Median :101.82   Median : 99.34   Median : 99.59   Median :100.19  
 Mean   :101.63   Mean   : 99.14   Mean   :100.12   Mean   : 99.34  
 3rd Qu.:109.15   3rd Qu.:105.13   3rd Qu.:105.83   3rd Qu.:106.09  
 Max.   :129.19   Max.   :137.78   Max.   :126.83   Max.   :125.07  
      V13              V14              V15              V16        
 Min.   : 67.65   Min.   : 77.26   Min.   : 78.14   Min.   : 78.45  
 1st Qu.: 91.77   1st Qu.: 92.62   1st Qu.: 94.66   1st Qu.: 93.40  
 Median : 99.78   Median :100.77   Median :100.36   Median :101.48  
 Mean   : 98.99   Mean   :100.36   Mean   :101.11   Mean   :100.34  
 3rd Qu.:106.93   3rd Qu.:106.65   3rd Qu.:108.66   3rd Qu.:107.24  
 Max.   :121.45   Max.   :121.23   Max.   :119.55   Max.   :120.02  
      V17              V18              V19              V20        
 Min.   : 76.08   Min.   : 75.54   Min.   : 65.81   Min.   : 71.11  
 1st Qu.: 93.85   1st Qu.: 94.04   1st Qu.: 95.15   1st Qu.: 94.95  
 Median : 99.28   Median : 99.27   Median :101.63   Median :102.04  
 Mean   : 99.40   Mean   : 99.61   Mean   :100.62   Mean   :100.60  
 3rd Qu.:104.70   3rd Qu.:104.31   3rd Qu.:106.71   3rd Qu.:107.50  
 Max.   :120.81   Max.   :124.68   Max.   :122.01   Max.   :122.38  

-d)

herbivores <- read.csv(file = "data/coralreefherbivores.csv")
herbivore.tbl <- dplyr::as_tibble(herbivores) # turn into tibble - might need a new package here ;-)
herbivore.tbl # tibbles tell you the data classes but str() would also work well

# A tibble: 96 × 10
   family       genus      species gen.spe    sl bodydepth snoutlength
   <chr>        <chr>      <chr>   <chr>   <dbl>     <dbl>       <dbl>
 1 Acanthuridae Acanthurus achill… Acanth… 164.      0.554       0.488
 2 Acanthuridae Acanthurus albipe… Acanth… 213.      0.441       0.440
 3 Acanthuridae Acanthurus aurant… Acanth… 216       0.473       0.539
 4 Acanthuridae Acanthurus blochii Acanth…  82.9     0.559       0.478
 5 Acanthuridae Acanthurus dussum… Acanth… 194.      0.546       0.566
 6 Acanthuridae Acanthurus fowleri Acanth… 266       0.467       0.595
 7 Acanthuridae Acanthurus guttat… Acanth… 150       0.680       0.404
 8 Acanthuridae Acanthurus leucoc… Acanth… 229.      0.491       0.563
 9 Acanthuridae Acanthurus leucop… Acanth… 190.      0.578       0.490
10 Acanthuridae Acanthurus lineat… Acanth… 133.      0.499       0.464
# ℹ 86 more rows
# ℹ 3 more variables: eyediameter <dbl>, size <chr>, schooling <chr>

herbivore.tbl$gen.spe # the two species are rows 31 and 96

 [1] "Acanthurus.achilles"       "Acanthurus.albipectoralis"
 [3] "Acanthurus.auranticavus"   "Acanthurus.blochii"       
 [5] "Acanthurus.dussumieri"     "Acanthurus.fowleri"       
 [7] "Acanthurus.guttatus"       "Acanthurus.leucocheilus"  
 [9] "Acanthurus.leucopareius"   "Acanthurus.lineatus"      
[11] "Acanthurus.maculiceps"     "Acanthurus.mata"          
[13] "Acanthurus.nigricans"      "Acanthurus.nigricauda"    
[15] "Acanthurus.nigrofuscus"    "Acanthurus.nigroris"      
[17] "Acanthurus.nubilus"        "Acanthurus.olivaceus"     
[19] "Acanthurus.pyroferus"      "Acanthurus.thompsoni"     
[21] "Acanthurus.triostegus"     "Acanthurus.xanthopterus"  
[23] "Bolbometopon.muricatum"    "Calotomus.carolinus"      
[25] "Calotomus.spinidens"       "Cetoscarus.ocellatus"     
[27] "Chlorurus.bleekeri"        "Chlorurus.bowersi"        
[29] "Chlorurus.frontalis"       "Chlorurus.japanensis"     
[31] "Chlorurus.microrhinos"     "Ctenochaetus.binotatus"   
[33] "Ctenochaetus.flavicauda"   "Ctenochaetus.hawaiiensis" 
[35] "Ctenochaetus.marginatus"   "Ctenochaetus.striatus"    
[37] "Ctenochaetus.strigosus"    "Ctenochaetus.tominiensis" 
[39] "Hipposcarus.longiceps"     "Kyphosus.vaigiensis"      
[41] "Leptoscarus.vaigiensis"    "Naso.annulatus"           
[43] "Naso.brachycentron"        "Naso.brevirostris"        
[45] "Naso.caesius"              "Naso.hexacanthus"         
[47] "Naso.lituratus"            "Naso.lopezi"              
[49] "Naso.thynnoides"           "Naso.tuberosus"           
[51] "Naso.unicornis"            "Naso.vlamingii"           
[53] "Paracanthurus.hepatus"     "Scarus.altipinnis"        
[55] "Scarus.chameleon"          "Scarus.dimidiatus"        
[57] "Scarus.festivus"           "Scarus.flavipectoralis"   
[59] "Scarus.forsteni"           "Scarus.frenatus"          
[61] "Scarus.ghobban"            "Scarus.globiceps"         
[63] "Scarus.hypselopterus"      "Scarus.longipinnis"       
[65] "Scarus.niger"              "Scarus.oviceps"           
[67] "Scarus.prasiognathos"      "Scarus.psittacus"         
[69] "Scarus.quoyi"              "Scarus.rivulatus"         
[71] "Scarus.rubroviolaceus"     "Scarus.schlegeli"         
[73] "Scarus.spinus"             "Scarus.tricolor"          
[75] "Scarus.xanthopleura"       "Siganus.argenteus"        
[77] "Siganus.canaliculatus"     "Siganus.corallinus"       
[79] "Siganus.doliatus"          "Siganus.fuscescens"       
[81] "Siganus.guttatus"          "Siganus.javus"            
[83] "Siganus.lineatus"          "Siganus.niger"            
[85] "Siganus.puellus"           "Siganus.punctatissimus"   
[87] "Siganus.punctatus"         "Siganus.randalli"         
[89] "Siganus.spinus"            "Siganus.stellatus"        
[91] "Siganus.vermiculatus"      "Siganus.vulpinus"         
[93] "Zebrasoma.flavescens"      "Zebrasoma.rostratum"      
[95] "Zebrasoma.scopas"          "Zebrasoma.velifer"        

herbivore.tbl[c(31,96),] # check snoutlength

# A tibble: 2 × 10
  family genus species gen.spe    sl bodydepth snoutlength eyediameter
  <chr>  <chr> <chr>   <chr>   <dbl>     <dbl>       <dbl>       <dbl>
1 Labri… Chlo… micror… Chloru…   417     0.402       0.359       0.149
2 Acant… Zebr… velifer Zebras…   153     0.548       0.625       0.359
# ℹ 2 more variables: size <chr>, schooling <chr>