Visit: https://www.geocaceres.com/
—————————————————————————————————————————————————————————————————
GETTING STARTED WITH R AND RSTUDIO
Coding Club Workshop 1 - R Basics:
Learning how to import and explore data, and make graphs about Edinburgh’s biodiversity
Written by Gergana Daskalova 06/11/2016 University of Edinburgh, last updated 28th March 2019
Transcribed by Carlos Caceres 01/04/2020 National University from Colombia
Take From: https://ourcodingclub.github.io/tutorials/intro-to-r/
1.Begin to write the script
Loading the packages dplyr by use the filter () function and assign the working directory
#If the dplyr package isn´t installed: install.package("dplyr").
#Note that there are quotation marks when installing a package
library(dplyr) # Note that there aren´t quotation marks when when loading a package
#Assign the working directory
setwd("C:/Users/GEOMATICS/PR/Getting_Started")#Remember, in R should use forward slashes ("C:/folder/data")2.Import and check data
Importing Edinburgh Biodiversity Data. You can find all the files needed in the Github repository: https://github.com/ourcodingclub/CC-RBasics
edidiv <- read.csv("C:/Users/GEOMATICS/PR/Getting_Started/CC-RBasics-master/edidiv.csv")
View(edidiv)
#Check that your data was imported without any mistakes
head(edidiv) # Displays the first few rows## organisationName gridReference year taxonName
## 1 Joint Nature Conservation Committee NT265775 2000 Sterna hirundo
## 2 Joint Nature Conservation Committee NT235775 2000 Sterna hirundo
## 3 Joint Nature Conservation Committee NT235775 2000 Sterna paradisaea
## 4 British Trust for Ornithology NT27 2000 Branta canadensis
## 5 British Trust for Ornithology NT27 2000 Branta leucopsis
## 6 The Wildlife Information Centre NT27S 2001 Turdus merula
## taxonGroup
## 1 Bird
## 2 Bird
## 3 Bird
## 4 Bird
## 5 Bird
## 6 Birdtail(edidiv) # Displays the last rows## organisationName gridReference year
## 25679 The Mammal Society NT278745 2016
## 25680 The Mammal Society NT277724 2016
## 25681 The Mammal Society NT266728 2016
## 25682 The Mammal Society NT270728 2016
## 25683 The Mammal Society NT257762 2016
## 25684 People's Trust for Endangered Species NT2372 2016
## taxonName taxonGroup
## 25679 Sciurus carolinensis Mammal
## 25680 Capreolus capreolus Mammal
## 25681 Sciurus carolinensis Mammal
## 25682 Oryctolagus cuniculus Mammal
## 25683 Vulpes vulpes Mammal
## 25684 Erinaceus europaeus Mammalstr(edidiv) # Tells you whether the variables are continuous, integers, categorical or characters## 'data.frame': 25684 obs. of 5 variables:
## $ organisationName: Factor w/ 28 levels "BATS & The Millennium Link",..: 14 14 14 8 8 28 28 28 28 28 ...
## $ gridReference : Factor w/ 1938 levels "NT200701","NT200712",..: 1314 569 569 1412 1412 1671 1671 1671 1671 1671 ...
## $ year : int 2000 2000 2000 2000 2000 2001 2001 2001 2001 2001 ...
## $ taxonName : Factor w/ 1275 levels "Acarospora fuscata",..: 1126 1126 1127 192 193 1202 365 977 472 947 ...
## $ taxonGroup : Factor w/ 11 levels "Beetle","Bird",..: 2 2 2 2 2 2 2 2 2 2 ...#The taxonGroup variable shows as a character variable, but it should be a factor (categorical variable)
#So we'll force it to be factor
head(edidiv$taxonGroup) # Displays the first few rows of taxonGroup column only## [1] Bird Bird Bird Bird Bird Bird
## 11 Levels: Beetle Bird Butterfly Dragonfly Flowering.Plants ... Molluscclass(edidiv$taxonGroup) # Tells you what type of variable we're dealing## [1] "factor"edidiv$taxonGroup <- as.factor(edidiv$taxonGroup) #This function turns whatever values you put inside into a factor
dim(edidiv) # Displays number of rows and columns## [1] 25684 5summary(edidiv) # Gives you a summary of the data## organisationName gridReference
## Biological Records Centre :6744 NT2673 : 2741
## RSPB :5809 NT2773 : 2031
## Butterfly Conservation :3000 NT2873 : 1247
## Scottish Wildlife Trust :2070 NT2570 : 1001
## Conchological Society of Great Britain & Ireland:1998 NT27 : 888
## The Wildlife Information Centre :1860 NT2871 : 767
## (Other) :4203 (Other):17009
## year taxonName taxonGroup
## Min. :2000 Maniola jurtina : 1710 Butterfly :9670
## 1st Qu.:2006 Aphantopus hyperantus: 1468 Bird :7366
## Median :2009 Turdus merula : 1112 Flowering.Plants:2625
## Mean :2009 Lycaena phlaeas : 972 Mollusc :2226
## 3rd Qu.:2011 Aglais urticae : 959 Hymenopteran :1391
## Max. :2016 Aglais io : 720 Mammal : 960
## (Other) :18743 (Other) :1446summary(edidiv$taxonGroup) # Gives you a summary of that particular variable (column)## Beetle Bird Butterfly Dragonfly
## 426 7366 9670 421
## Flowering.Plants Fungus Hymenopteran Lichen
## 2625 334 1391 140
## Liverwort Mammal Mollusc
## 125 960 2226The edidiv object has occurrence records of various species collected in Edinburgh from 2000 to 2016. To explore Edinburgh’s biodiversity, we will create a graph showing how many species were recorded in each taxonomic group. We will filter out the data for each taxon group and then count the unique species within it
3.Calculate species richness
#Rememeber install.packages("dplyr") and then load it using library(dplyr)
Beetle <- filter(edidiv, taxonGroup == "Beetle")
Bird <- filter(edidiv, taxonGroup == "Bird")
Butterfly <- filter(edidiv, taxonGroup == "Butterfly")
Dragonfly <- filter(edidiv, taxonGroup == "Dragonfly")
Flowering.Plants <- filter(edidiv, taxonGroup == "Flowering.Plants")
Fungus <- filter(edidiv, taxonGroup == "Fungus")
Hymenopteran <- filter(edidiv, taxonGroup == "Hymenopteran")
Lichen <- filter(edidiv, taxonGroup == "Lichen")
Liverwort <- filter(edidiv, taxonGroup == "Liverwort")
Mammal <- filter(edidiv, taxonGroup == "Mammal")
Mollusc <- filter(edidiv, taxonGroup == "Mollusc")
#Calculate we the number of different species in each group
#unique(), which identifies different species, and length(), which counts them
a <- length(unique(Beetle$taxonName))
b <- length(unique(Bird$taxonName))
c <- length(unique(Butterfly$taxonName))
d <- length(unique(Dragonfly$taxonName))
e <- length(unique(Flowering.Plants$taxonName))
f <- length(unique(Fungus$taxonName))
g <- length(unique(Hymenopteran$taxonName))
h <- length(unique(Lichen$taxonName))
i <- length(unique(Liverwort$taxonName))
j <- length(unique(Mammal$taxonName))
k <- length(unique(Mollusc$taxonName))4. Create a vector and plot it
biodiv <- c(a,b,c,d,e,f,g,h,i,j,k) # Combine all those object in one vector
names(biodiv) <- c("Beetle", # Add labels
"Bird",
"Butterfly",
"Dragonfly",
"Fl.Plants",
"Fungus",
"Hymenopteran",
"Lichen",
"Liverwort",
"Mammal",
"Mollusc")
barplot(biodiv,main="Species Richness") #Visualise species richness with the barplot() function
help(barplot) # For help with the barplot() function## starting httpd help server ... donehelp(par) # For help with plotting in general
#Save the plot
png("barplot.png", width=1600, height=600) #Customise the size and resolution of the image
barplot(biodiv, xlab="Taxa", ylab="Number of species", ylim=c(0,600), cex.names= 1.5, cex.axis=1.5, cex.lab=1.5)
# The cex code increases the font size when greater than one (and decreases it when less than one).
dev.off() #close the diagram## png
## 25. Create a dataframe and plot it
Data frames are tables of values: they have a two-dimensional structure with rows and columns, where each column can have a different data type.
taxa <- c("Beetle",
"Bird",
"Butterfly",
"Dragonfly",
"Flowering.Plants",
"Fungus",
"Hymenopteran",
"Lichen",
"Liverwort",
"Mammal",
"Mollusc")
taxa_f <- factor(taxa) # Turning the object in a factor
richness <- c(a,b,c,d,e,f,g,h,i,j,k) # Combining all the values for the number of species in an object called richness
biodata <- data.frame(taxa_f, richness) # Create the data frame from the two vectors
write.csv(biodata, file="biodata.csv") # Saving the file
View(biodata)
png("barplot2.png", width=1600, height=600)
barplot(biodata$richness, names.arg=c("Beetle",
"Bird",
"Butterfly",
"Dragonfly",
"Flowering.Plants",
"Fungus",
"Hymenopteran",
"Lichen",
"Liverwort",
"Mammal",
"Mollusc"),
xlab="Taxa", ylab="Number of species", ylim=c(0,600))
dev.off()## png
## 2