# Coding Club Workshop 1 - R Basics
# Aprendiendo como importar y explorar datos, y hacer graficos sobre l biodiversidad de Edinburgo
# Written by Jesús Ortiz 11/03/2020 Universidad Nacional de Colombia
getwd()
## [1] "C:/Users/yisus/Documents"
setwd("C:/Users/yisus/Documents/CC-1-RBasics-master")
edidiv <- read.csv("C:/Users/yisus/Documents/CC-1-RBasics-master/CC-RBasics-master/edidiv.csv")
head(edidiv) # Muestra las primeras filas.
## 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 Bird
tail(edidiv) # Muestra las ultimas filas.
## 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 Mammal
str(edidiv) # Indica si las variables son continuas, enteras, categóricas o caracteres.
## '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 ...
head(edidiv$taxonGroup) # Muestra solo las primeras filas de esta columna
## [1] Bird Bird Bird Bird Bird Bird
## 11 Levels: Beetle Bird Butterfly Dragonfly Flowering.Plants ... Mollusc
class(edidiv$taxonGroup) # Dice con qué tipo de variable estamos tratando: su carácter ahora, pero queremos que sea un factor
## [1] "factor"
edidiv$taxonGroup <- as.factor(edidiv$taxonGroup)
class(edidiv$taxonGroup)
## [1] "factor"
# More exploration
dim(edidiv) # Muestra el numero de filas y Columnas
## [1] 25684 5
summary(edidiv) # Da un resumen de los datos
## organisationName gridReference
## Biological Records Centre :6744 NT2673 : 2741
## RSPB :5809 NT2773 : 2031
## Butterfly Conservation :3000 NT2873 : 1247
## Scottish Wildlife Trust :2070 NT2570 : 1001
## Conchological Society of Great Britain & Ireland:1998 NT27 : 888
## The Wildlife Information Centre :1860 NT2871 : 767
## (Other) :4203 (Other):17009
## year taxonName taxonGroup
## Min. :2000 Maniola jurtina : 1710 Butterfly :9670
## 1st Qu.:2006 Aphantopus hyperantus: 1468 Bird :7366
## Median :2009 Turdus merula : 1112 Flowering.Plants:2625
## Mean :2009 Lycaena phlaeas : 972 Mollusc :2226
## 3rd Qu.:2011 Aglais urticae : 959 Hymenopteran :1391
## Max. :2016 Aglais io : 720 Mammal : 960
## (Other) :18743 (Other) :1446
summary(edidiv$taxonGroup) # Da un resumen de una variable particular
## Beetle Bird Butterfly Dragonfly
## 426 7366 9670 421
## Flowering.Plants Fungus Hymenopteran Lichen
## 2625 334 1391 140
## Liverwort Mammal Mollusc
## 125 960 2226
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
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")
a <- length(unique(Beetle$taxonName))
b <- length(unique(Bird$taxonName))
c <- length(unique(Dragonfly$taxonName))
d <- length(unique(Flowering.Plants$taxonName))
e <- length(unique(Fungus$taxonName))
f <- length(unique(Hymenopteran$taxonName))
g <- length(unique(Lichen$taxonName))
h <- length(unique(Liverwort$taxonName))
i <- length(unique(Mammal$taxonName))
j <- length(unique(Mollusc$taxonName))
K <- length(unique(Butterfly$taxonName))
biodiv <- c(a,b,c,d,e,f,g,h,i,j,K)
names(biodiv) <- c("Beetle",
"Bird",
"Butterfly",
"Dragonfly",
"Flowering.Plants",
"Fungus",
"Hymenopteran",
"Lichen",
"Liverwort",
"Mammal",
"Mollusc")
help(barplot)
## starting httpd help server ...
## done
help(par)
png("barplot.png", width=1600, height=600)
barplot(biodiv ,xlab="Taxa",ylab="Number of species", ylim=c(0,600), cex.names= 1.5, cex.axis=1.5, cex.lab=1.5)
dev.off()
## png
## 2
barplot(biodiv)
taxa <- c("Beetle",
"Bird",
"Butterfly",
"Dragonfly",
"Flowering.Plants",
"Fungus",
"Hymenopteran",
"Lichen",
"Liverwort",
"Mammal",
"Mollusc")
taxa_f <- factor(taxa)
richness <- c(a,b,c,d,e,f,g,h,i,j,K)
biodata <- data.frame(taxa_f, richness)
write.csv(biodata, file="biodata.csv")
png("barplot2.png", width=1600, height=600)
barplot(biodata$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