• Uma calculadora?

2+2

## [1] 4

4*10

## [1] 40

sqrt(16)

## [1] 4

• Um software de estatística?

mean(c(2,3,5,8,9,5))

## [1] 5.333333

sd(c(2,3,5,8,9,5))

## [1] 2.73252

median(c(2,3,5,8,9,5))

## [1] 5

• Grande quantidade de desenvolvedores (open-source)
• Instalando e baixando pacotes (apenas na 1ª vez)

install.packages('ggplot2')

• Carregando pacotes (sempre que for usar)

library(ggplot2)

https://obis.org/

data<-occurrence(scientificname = "Caretta caretta", 
                 startdate = '2020-01-01')

• Nº de registros

nrow(data)

## [1] 110

• Nº de variáveis

length(data)

## [1] 84

names(data)

##  [1] "date_year"                     "scientificNameID"             
##  [3] "scientificName"                "superfamilyid"                
##  [5] "individualCount"               "associatedReferences"         
##  [7] "dropped"                       "aphiaID"                      
##  [9] "decimalLatitude"               "type"                         
## [11] "taxonRemarks"                  "phylumid"                     
## [13] "familyid"                      "catalogNumber"                
## [15] "occurrenceStatus"              "basisOfRecord"                
## [17] "superclass"                    "modified"                     
## [19] "id"                            "order"                        
## [21] "recordNumber"                  "georeferencedDate"            
## [23] "superclassid"                  "verbatimEventDate"            
## [25] "dataset_id"                    "decimalLongitude"             
## [27] "collectionCode"                "date_end"                     
## [29] "speciesid"                     "occurrenceID"                 
## [31] "superfamily"                   "suborderid"                   
## [33] "license"                       "date_start"                   
## [35] "genus"                         "dateIdentified"               
## [37] "ownerInstitutionCode"          "bibliographicCitation"        
## [39] "eventDate"                     "scientificNameAuthorship"     
## [41] "coordinateUncertaintyInMeters" "absence"                      
## [43] "taxonRank"                     "genusid"                      
## [45] "originalScientificName"        "marine"                       
## [47] "subphylumid"                   "vernacularName"               
## [49] "institutionCode"               "date_mid"                     
## [51] "eventTime"                     "identificationRemarks"        
## [53] "class"                         "suborder"                     
## [55] "nomenclaturalCode"             "orderid"                      
## [57] "footprintWKT"                  "datasetName"                  
## [59] "geodeticDatum"                 "taxonomicStatus"              
## [61] "kingdom"                       "waterBody"                    
## [63] "specificEpithet"               "classid"                      
## [65] "phylum"                        "species"                      
## [67] "coordinatePrecision"           "subphylum"                    
## [69] "datasetID"                     "occurrenceRemarks"            
## [71] "family"                        "category"                     
## [73] "kingdomid"                     "node_id"                      
## [75] "flags"                         "sss"                          
## [77] "shoredistance"                 "sst"                          
## [79] "bathymetry"                    "dynamicProperties"            
## [81] "organismID"                    "sex"                          
## [83] "lifeStage"                     "organismRemarks"

• https://r-spatial.github.io/sf/

library(sf)
s<-read_sf("input_data/sbs_case_study.shp")
s$area<-st_area(s)
s<-s[1,]
s

## Simple feature collection with 1 feature and 2 fields
## Geometry type: POLYGON
## Dimension:     XY
## Bounding box:  xmin: -53.37375 ymin: -34.69682 xmax: -41.31725 ymax: -22.89115
## Geodetic CRS:  WGS 84
## # A tibble: 1 × 3
##     fid          area                                                   geometry
##   <dbl>         [m^2]                                              <POLYGON [°]>
## 1     1 271881508394. ((-52.09875 -32.15986, -52.08375 -32.15846, -52.08375 -32…

• Um data frame comum (com n variáveis)
• Uma variável especial: geometria (pontos, linhas, polígonos)

plot(s)

s_simple<-st_simplify(s,dTolerance=5000)
plot(s_simple)

data<-occurrence( scientificname = "Annelida",
                 geometry=st_as_text(s_simple$geometry))
nrow(data)

## [1] 8311

• Ferramenta rápida e consistente para manipular df

library(dplyr)
dataf<- data%>%
        filter(institutionCode=='USP')%>%
        select(date_year,scientificName, family, sst, shoredistance, depth)%>%
        mutate(costeira=shoredistance<19312)%>%
        arrange(date_year)
nrow(dataf)

## [1] 100

• Lindos gráficos altamente customizáveis
• Excelente documentação
• https://r-graphics.org/

  

library(ggplot2)
ggplot(data,aes(x=subclass))+geom_histogram(stat='count')

ggplot(data,aes(x=depth))+geom_histogram()+
  theme_bw()

ggplot(data,aes(x=depth))+geom_histogram(bins=10)+
  theme_bw()+xlab('Profundidade (m)')+ylab('Nº de Ocorrências')

ggplot(data,aes(x=as.numeric(year),fill=order))+geom_bar()+
  theme_bw()+ xlab(NULL)+ylab('Nº de Ocorrências')+xlim(c(1990,2020))

ggplot(data,aes(x=order,y=depth))+geom_boxplot()+
  theme_bw()+xlab(NULL)+ylab('Profundidade')

ggplot(data,aes(y=decimalLatitude))+geom_density()+
  theme_bw()+
  xlab('Densidade de Ocorrência')+ylab('Latitude')

map_leaflet(data, color='black', provider_tiles = "Esri.OceanBasemap",
            popup=function(x){x["scientificName"]})

• CSV

write.csv2(data,file='annelida.csv')

• Excel

library(writexl)
write_xlsx(data,path = 'annelida.xlsx')

• Arquivo do R

save(data,file='annelida.Rda')

data_sf<-st_as_sf(data, 
                  coords=c("decimalLongitude","decimalLatitude"),
                  crs=4326)
plot(data_sf[5])

write_sf(data_sf,dsn = 'annelida.shp')

• Pacote rgbif ## Próximos passos?
• Definição dos grupos taxonômicos de interesse
• Agregação por grids
• Presença/Ausência
• Mesclar com GBIF
• What else?