Get working directory
# use getwd() to find out where you are
getwd()## [1] "/Users/jcasey/Documents/Teaching/Marine Community Ecology/Spring 2023/Coding"# install the tidyverse package by running install.packages()
# you typically don't need to set repos when installing a package
install.packages("tidyverse", repos = "http://cran.us.r-project.org")# load the tidyverse package in your current R session
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.4.0 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.10
## ✔ tidyr 1.2.1 ✔ stringr 1.4.1
## ✔ readr 2.1.2 ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()# get help
?install.packages
# assign value
one <- 1
one## [1] 1# check matching values (ouput will be TRUE or FALSE)
5==5## [1] TRUE5==6## [1] FALSEone==5## [1] FALSE# R is a basic calculator
4*4## [1] 1623*sin(19)/sqrt(12) + log(58)## [1] 5.055557Assign values to objects
# assign obj1 the value of 4*4
obj1 <- 4*4
obj1## [1] 16# assign obj2 a more complex value
obj2 <- 23/sqrt(58)*21^2
obj2## [1] 1331.841# assign obj3 a non-numerical value
obj3 <- "fish"
obj3## [1] "fish"Combine objects
# combine numerical objects
obj4 <- obj1 + obj2
obj4## [1] 1347.841# combine two non-numerical objects with a function(), like paste()
obj5 <- "goby"
obj6 <- paste(obj3, obj5)
obj6## [1] "fish goby"Familiarize with function format
# c() is the concatenate function - use it to combine numbers or words
conc.vals <- c(1,2,3,4,5)
conc.vals## [1] 1 2 3 4 5# find the mean of conc.vals
mean(conc.vals)## [1] 3Create vector with a sequence
# use seq() to create sequences
seq.obj <- seq(from = 1, to = 10, by = 1)
seq.obj## [1] 1 2 3 4 5 6 7 8 9 10# alternative way to create the same sequence
seq.obj.1 <- seq(1:10)
seq.obj.1[1:10]## [1] 1 2 3 4 5 6 7 8 9 10Create vector with repetitions
# use rep() to create repetitions
rep.obj <- rep(1, times = 20)
rep.obj## [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1# alternative way to create the same repetition
rep.obj.each <- rep(1:10, each = 2)
rep.obj.each## [1] 1 1 2 2 3 3 4 4 5 5 6 6 7 7 8 8 9 9 10 10# you can also repeat characters
rep.obj.ch <- rep("fish", times = 20)
rep.obj.ch## [1] "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish"
## [11] "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish"Create vector of repeat sequences
# create repetitions of sequences
rep.obj.seq <- rep(seq(0, 5, by = 1), 4)
rep.obj.seq## [1] 0 1 2 3 4 5 0 1 2 3 4 5 0 1 2 3 4 5 0 1 2 3 4 5Combine numerical vectors
# add two numerical vectors
reps.comb <- rep.obj + rep.obj.each
# multiply a numerical vector
reps.mult5 <- rep.obj.seq*5
reps.mult5## [1] 0 5 10 15 20 25 0 5 10 15 20 25 0 5 10 15 20 25 0 5 10 15 20 25# take the square root of a numerical vector
reps.sqrt <- sqrt(rep.obj.seq)
reps.sqrt## [1] 0.000000 1.000000 1.414214 1.732051 2.000000 2.236068 0.000000 1.000000
## [9] 1.414214 1.732051 2.000000 2.236068 0.000000 1.000000 1.414214 1.732051
## [17] 2.000000 2.236068 0.000000 1.000000 1.414214 1.732051 2.000000 2.236068Combine vectors of different classes
# combining a numerical and non-numerical vector does not work well
reps.comb.ch <- c(rep.obj, rep.obj.ch)
reps.comb.ch## [1] "1" "1" "1" "1" "1" "1" "1" "1" "1" "1"
## [11] "1" "1" "1" "1" "1" "1" "1" "1" "1" "1"
## [21] "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish"
## [31] "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish" "fish"# again, combining a numerical and non-numerical vector does not work well
reps.comb.ch.paste <- paste(rep.obj, rep.obj.ch)
head(reps.comb.ch.paste)## [1] "1 fish" "1 fish" "1 fish" "1 fish" "1 fish" "1 fish"Work with distinct elements
# call one of your vectors
seq.obj## [1] 1 2 3 4 5 6 7 8 9 10# select only the third element
element3 <- seq.obj[3]
element3## [1] 3Select multiple elements
# use c() or x:y to select multiple elements
three.elements <- seq.obj[c(3,4,5)]
three.elements## [1] 3 4 5# get the last 8 elements
last.eight <- seq.obj[2:10]
last.eight## [1] 2 3 4 5 6 7 8 9 10# alternative way to get the last 8 elements
last.eight.2 <- seq.obj[-1]
last.eight.2## [1] 2 3 4 5 6 7 8 9 10Extract values based on a condition with logical operators
# create a new vector with random values
random.vals <- rpois(30, lambda = 5)
random.vals## [1] 2 7 5 5 8 6 3 3 6 9 4 7 5 4 8 5 2 4 6 6 7 2 5 3 7 6 4 3 9 5# select values that are greater than 4
selected.vals <- random.vals[random.vals > 4]
selected.vals## [1] 7 5 5 8 6 6 9 7 5 8 5 6 6 7 5 7 6 9 5# select values that are not 6
values.not.6 <- random.vals[random.vals != 6]
values.not.6## [1] 2 7 5 5 8 3 3 9 4 7 5 4 8 5 2 4 7 2 5 3 7 4 3 9 5Use Boolean expression (logical statement) that is either true or false
# call random vector
random.vals## [1] 2 7 5 5 8 6 3 3 6 9 4 7 5 4 8 5 2 4 6 6 7 2 5 3 7 6 4 3 9 5# get values between 4 and 8
boolean.and <- random.vals[random.vals >= 4 & random.vals <= 8]
boolean.and## [1] 7 5 5 8 6 6 4 7 5 4 8 5 4 6 6 7 5 7 6 4 5# get values that are 3 or 5
boolean.or <- random.vals[random.vals == 3 | random.vals == 5]
boolean.or## [1] 5 5 3 3 5 5 5 3 3 5Assign a new value to replace a value
# replace the first value of the vector with 1000
random.vals[1] <- 1000
random.vals## [1] 1000 7 5 5 8 6 3 3 6 9 4 7 5 4 8
## [16] 5 2 4 6 6 7 2 5 3 7 6 4 3 9 5# replace values >5 with 1000
random.vals[random.vals > 5] <- 1000# create a vector of words
fish.comm <- paste(rep(c("whitefish", "bluefish", "yellowfish"), 5))
fish.comm## [1] "whitefish" "bluefish" "yellowfish" "whitefish" "bluefish"
## [6] "yellowfish" "whitefish" "bluefish" "yellowfish" "whitefish"
## [11] "bluefish" "yellowfish" "whitefish" "bluefish" "yellowfish"# remove whitefish
white.extinct <- fish.comm[fish.comm != "whitefish"]
white.extinct## [1] "bluefish" "yellowfish" "bluefish" "yellowfish" "bluefish"
## [6] "yellowfish" "bluefish" "yellowfish" "bluefish" "yellowfish"# replace yellowfish with greenfish
white.extinct[white.extinct == "yellowfish"] <- "greenfish"
white.extinct## [1] "bluefish" "greenfish" "bluefish" "greenfish" "bluefish" "greenfish"
## [7] "bluefish" "greenfish" "bluefish" "greenfish"# create a vector of values
# rpois() creates a random sample of integer values following a Poisson distribution
more.vals <- rpois(20, 5)
more.vals## [1] 4 3 7 7 5 5 4 7 2 10 9 7 5 3 3 2 6 8 8 5# use sort() to sort values in increasing order
more.vals.sorted <- sort(more.vals)
more.vals.sorted## [1] 2 2 3 3 3 4 4 5 5 5 5 6 7 7 7 7 8 8 9 10# sort the values in decreasing order using "decreasing = TRUE" or the rev() function
more.vals.sorted.dec <- rev(sort(more.vals))
more.vals.sorted.dec## [1] 10 9 8 8 7 7 7 7 6 5 5 5 5 4 4 3 3 3 2 2# create vector with Poisson distribution
fish.numbers <- rpois(20, 5)
fish.numbers## [1] 6 4 12 3 3 3 7 1 6 5 5 6 7 7 4 7 1 9 5 4# replace some values with NAs
fish.numbers[c(5,15)] <- NA
fish.numbers## [1] 6 4 12 3 NA 3 7 1 6 5 5 6 7 7 NA 7 1 9 5 4# create a vector of an area
area <- rep(100, 20)
# calculate fish density
fish.density <- fish.numbers/area
fish.density## [1] 0.06 0.04 0.12 0.03 NA 0.03 0.07 0.01 0.06 0.05 0.05 0.06 0.07 0.07 NA
## [16] 0.07 0.01 0.09 0.05 0.04# calculate mean fish density
# use na.rm = TRUE to exclude NAs
mean.density.nona <- mean(fish.density, na.rm = TRUE)
mean.density.nona## [1] 0.05444444Data classes in R
# create vector of numbers
numbers <- seq(1:20)
# find data class using class() or str()
class(numbers)## [1] "integer"# check data class using "is" and "as"
is.numeric(numbers)## [1] TRUEis.character(numbers)## [1] FALSE# turn data into characters
numbers.char <- as.character(numbers)
numbers.char## [1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10" "11" "12" "13" "14" "15"
## [16] "16" "17" "18" "19" "20"#check that data class is character
is.character(numbers.char)## [1] TRUEUnderstand data structures
# data structure: scalar
scalar <- 23
scalar## [1] 23# data structure: vector
many.scalars <- rep(1:23, 2)
many.scalars## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 1 2
## [26] 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23# data structure: matrix
the.matrix <- matrix(1:24, nrow = 4, byrow = FALSE)
the.matrix## [,1] [,2] [,3] [,4] [,5] [,6]
## [1,] 1 5 9 13 17 21
## [2,] 2 6 10 14 18 22
## [3,] 3 7 11 15 19 23
## [4,] 4 8 12 16 20 24Assign names to columns and rows
# create non-numerical matrix
the.matrix <- matrix(rpois(24, 5), nrow = 6, byrow = FALSE)
the.matrix## [,1] [,2] [,3] [,4]
## [1,] 9 9 2 3
## [2,] 3 8 6 4
## [3,] 2 6 5 2
## [4,] 5 9 7 7
## [5,] 7 4 9 4
## [6,] 5 7 6 3# assign column names
colnames(the.matrix) <- c("whitefish", "bluefish", "greenfish", "yellowfish")
# assign row names
rownames(the.matrix) <- c("site1", "site2", "site3", "site4", "site5", "site6")
the.matrix## whitefish bluefish greenfish yellowfish
## site1 9 9 2 3
## site2 3 8 6 4
## site3 2 6 5 2
## site4 5 9 7 7
## site5 7 4 9 4
## site6 5 7 6 3Combine data of different classes
# convert matrix to data frame
fish.df <- as.data.frame(the.matrix)
fish.df## whitefish bluefish greenfish yellowfish
## site1 9 9 2 3
## site2 3 8 6 4
## site3 2 6 5 2
## site4 5 9 7 7
## site5 7 4 9 4
## site6 5 7 6 3# the dollar sign ($) operator indicates a column in a data frame
fish.df$whitefish## [1] 9 3 2 5 7 5# specify a value using square brackets
# show the first row
fish.df[1,] ## whitefish bluefish greenfish yellowfish
## site1 9 9 2 3# make a vector with 6 site locations
locations <- c("Australia", "Indonesia", "Philippines", "Fiji", "Solomons", "Papua New Guinea")
locations## [1] "Australia" "Indonesia" "Philippines" "Fiji"
## [5] "Solomons" "Papua New Guinea"# use $ to add the location column, thus adding a character vector to a data frame
fish.df$location <- locations
fish.df## whitefish bluefish greenfish yellowfish location
## site1 9 9 2 3 Australia
## site2 3 8 6 4 Indonesia
## site3 2 6 5 2 Philippines
## site4 5 9 7 7 Fiji
## site5 7 4 9 4 Solomons
## site6 5 7 6 3 Papua New GuineaTibbles offer more information
# check structure of data frame
str(fish.df)## 'data.frame': 6 obs. of 5 variables:
## $ whitefish : int 9 3 2 5 7 5
## $ bluefish : int 9 8 6 9 4 7
## $ greenfish : int 2 6 5 7 9 6
## $ yellowfish: int 3 4 2 7 4 3
## $ location : chr "Australia" "Indonesia" "Philippines" "Fiji" ...# convert data frame to tibble
fish.tibble <- as_tibble(fish.df)
# view information provided by tibble
fish.tibble## # A tibble: 6 × 5
## whitefish bluefish greenfish yellowfish location
## <int> <int> <int> <int> <chr>
## 1 9 9 2 3 Australia
## 2 3 8 6 4 Indonesia
## 3 2 6 5 2 Philippines
## 4 5 9 7 7 Fiji
## 5 7 4 9 4 Solomons
## 6 5 7 6 3 Papua New GuineaWork with csv files
# use the write.csv() function to save a data frame or tibble in your working directory
# row.names = FALSE specifies to not include a column of row numbers in the csv
write.csv(fish.tibble, file = "data/fishtibble.csv", row.names = FALSE)
# load that csv file back into R
loaded.fish.tibble <- read.csv(file = "data/fishtibble.csv")
loaded.fish.tibble## whitefish bluefish greenfish yellowfish location
## 1 9 9 2 3 Australia
## 2 3 8 6 4 Indonesia
## 3 2 6 5 2 Philippines
## 4 5 9 7 7 Fiji
## 5 7 4 9 4 Solomons
## 6 5 7 6 3 Papua New Guinea