Coding Club Workshop 1 - Conceptos básicos de R

Aprender a importar y explorar datos, y hacer gráficos sobre la biodiversidad de Edimburgo

Escrito por Diego Arturo Gonzalez Delgadillo 13/03/2020 Universidad nacional de Colombia

install.packages("dplyr")
library(dplyr)
# Note that there are quotation marks when installing a package, but not when loading it
# and remember that hashtags let you add useful notes to your code! 

setwd("C:\User\CC-1-RBasics-master")
# This is an example filepath, alter to your own filepath
edidiv <- read.csv("C:/Users/spedrazam/Music/edidiv.csv")
head(edidiv)                # Displays the first few rows
tail(edidiv)                # Displays the last rows
str(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 ...
head(edidiv$taxonGroup)     # Displays the first few rows of this column only
[1] Bird Bird Bird Bird Bird Bird
11 Levels: Beetle Bird Butterfly Dragonfly ... Mollusc
class(edidiv$taxonGroup)    # Tells you what type of variable we're dealing with: it's character now but we want it to be a factor
[1] "factor"
edidiv$taxonGroup <- as.factor(edidiv$taxonGroup)     # What are we doing here?!
# More exploration
dim(edidiv)                 # Displays number of rows and columns
[1] 25684     5
summary(edidiv)             # Gives you a summary of the data
                                             organisationName
 Biological Records Centre                           :6744   
 RSPB                                                :5809   
 Butterfly Conservation                              :3000   
 Scottish Wildlife Trust                             :2070   
 Conchological Society of Great Britain &amp; Ireland:1998   
 The Wildlife Information Centre                     :1860   
 (Other)                                             :4203   
 gridReference        year                      taxonName    
 NT2673 : 2741   Min.   :2000   Maniola jurtina      : 1710  
 NT2773 : 2031   1st Qu.:2006   Aphantopus hyperantus: 1468  
 NT2873 : 1247   Median :2009   Turdus merula        : 1112  
 NT2570 : 1001   Mean   :2009   Lycaena phlaeas      :  972  
 NT27   :  888   3rd Qu.:2011   Aglais urticae       :  959  
 NT2871 :  767   Max.   :2016   Aglais io            :  720  
 (Other):17009                  (Other)              :18743  
            taxonGroup  
 Butterfly       :9670  
 Bird            :7366  
 Flowering.Plants:2625  
 Mollusc         :2226  
 Hymenopteran    :1391  
 Mammal          : 960  
 (Other)         :1446  
summary(edidiv$taxonGroup)  # Gives you a summary of that particular variable (column) in your dataset
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