# Get details on dataset?reefs# Load datasetdata("reefs")# Available variablescolnames(reefs)## [1] "r_number" "name" "formation" "system" "series" ## [6] "interval" "biota_main" "biota_sec" "lng" "lat" ## [11] "country" "authors" "title" "year"
Reference datasets
Two reference datasets are available.
Geological Time Scale 2012 & 2020 (Gradstein et al. 2012; 2020).
# Get details on dataset?GTS2012?GTS2020# Load datasetdata("GTS2012")data("GTS2020")# Increase output widthoptions(width =120)# Print first few rowshead(GTS2012, n =3)## interval_number interval_name rank max_ma mid_ma min_ma duration_myr font colour abbr## 1 1 Holocene stage 0.0117 0.0059 0.0000 0.0117 black #FDEDEC <NA>## 2 2 Upper Pleistocene stage 0.1260 0.0688 0.0117 0.1143 black #FFF2D3 <NA>## 3 3 Middle Pleistocene stage 0.7810 0.4535 0.1260 0.6550 black #FFF2C7 <NA>head(GTS2020, n =3)## interval_number interval_name rank max_ma mid_ma min_ma duration_myr font colour abbr## 1 1 Meghalayan stage 0.0042 0.00210 0.0000 0.0042 black #FDEDEC <NA>## 2 2 Northgrippian stage 0.0082 0.00620 0.0042 0.0040 black #FDECE4 <NA>## 3 3 Greenlandian stage 0.0117 0.00995 0.0082 0.0035 black #FEECDB <NA>
Stratigraphic time bins
# Get stage-level time binsbins <-time_bins(interval ="Phanerozoic", rank ="stage", plot =TRUE)
# Get first few rowshead(bins, n =3)## bin interval_name rank max_ma mid_ma min_ma duration_myr abbr colour font## 1 1 Fortunian stage 541 535.0 529 12 Fo #99B575 black## 2 2 Stage 2 stage 529 525.0 521 8 S2 #A6BA80 black## 3 3 Stage 3 stage 521 517.5 514 7 S3 #A6C583 black
Macrostrat time bins
# Get North American Land Mammal Agesbins <-time_bins(scale ="North American Land Mammal Ages", plot =TRUE)
# Get first few rowshead(bins, n =3)## bin interval_name rank max_ma mid_ma min_ma duration_myr abbr colour font## 1 1 Puercan North American Land Mammal Ages 66.00 65.375 64.75 1.25 P #FDB469 black## 2 2 Torrejonian North American Land Mammal Ages 64.75 63.500 62.25 2.50 To #FEBA64 black## 3 3 Tiffanian North American Land Mammal Ages 62.25 59.875 57.50 4.75 Ti #FEBF6A black
Near-equal-length time bins
# Get stage-level time binsbins <-time_bins(interval ="Phanerozoic", rank ="stage", size =15, plot =TRUE)
# Get first few rowshead(bins, n =3)## bin max_ma mid_ma min_ma duration_myr grouping_rank intervals colour font## 1 1 541 535.00 529.0 12.0 stage Fortunian #80cdc1 black## 2 2 529 521.50 514.0 15.0 stage Stage 3, Stage 2 #80cdc1 black## 3 3 514 507.25 500.5 13.5 stage Drumian, Wuliuan, Stage 4 #80cdc1 black
Temporal occurrence binning
Five temporal binning methods for age range data:
# Use tetrapod example dataoccdf <- tetrapods# Get stage-level time binsbins <-time_bins(interval ="Phanerozoic", rank ="stage")# Assign via midpoint age of fossil occurrence dataex1 <-bin_time(occdf = occdf, bins = bins, method ="mid")# Assign to all bins that age range coversex2 <-bin_time(occdf = occdf, bins = bins, method ="all")# Assign via majority overlap based on fossil occurrence age rangeex3 <-bin_time(occdf = occdf, bins = bins, method ="majority")# Randomly assign to overlapping bins based on fossil occurrence age rangeex4 <-bin_time(occdf = occdf, bins = bins, method ="random", reps =10)# Randomly assign point estimates (e.g. uniform distribution) based on fossil occurrence age rangeex5 <-bin_time(occdf = occdf, bins = bins, method ="point", reps =10)
# Use reef example dataoccdf <- reefs# Bin occurrencesoccdf <-bin_lat(occdf = occdf, bins = bins, lat ="lat")
Spatial occurrence binning
Generate and bin spatial data:
# Get reef dataoccdf <- reefs[1:500, ]# Bin data using a hexagonal equal-area gridoccdf <-bin_space(occdf = occdf, spacing =250, return =TRUE)# Plot world and grid using ggplot2library(ggplot2)library(rnaturalearth)world <-ne_countries(scale ="small",returnclass ="sf")ggplot() +geom_sf(data = world, colour ="black", fill ="lightgrey") +geom_sf(data = occdf$grid, fill ="orange", colour ="black") +theme_void()
# Example with a few occurrencesoccdf <-data.frame(lng =c(2, -103, -66),lat =c(46, 35, -7),age =c(88, 125, 200))# Estimate palaeocoordinates using the GPlates APIex1 <-palaeorotate(occdf = occdf, method ="point")# Estimate palaeocoordinates using reconstruction filesex2 <-palaeorotate(occdf = occdf, method ="grid")# Estimate palaeocoordinates and uncertainty using reconstruction filesex3 <-palaeorotate(occdf = occdf, method ="grid", uncertainty =TRUE)# Increase output widthoptions(width =400)# Get first few rowshead(ex3)## lng lat age rot_model rot_age rot_lng rot_lat p_lng p_lat## 1 2 46 88 MERDITH2021 88 1.80 46.42 13.0134 37.6406## 2 -103 35 125 MERDITH2021 127 -102.61 34.63 -41.8928 35.0437## 3 -66 -7 200 MERDITH2021 200 -65.52 -6.95 -22.5209 -16.7714
Taxonomic spell check
Identify and count potential spelling variations of the same taxon:
Code
# load occurrence datadata("tetrapods")# Check taxon names alphabeticallyex1 <-tax_check(taxdf = tetrapods, name ="genus", dis =0.05, verbose =FALSE)# Get first few rowshead(ex1)## group greater lesser count_greater count_lesser## 1 D Dvinosaurus Dinosaurus 23 2## 2 V Varanopus Varanops 5 3
Code
# Check taxon names by groupex2 <-tax_check(taxdf = tetrapods, name ="genus", group ="family", dis =0.05, verbose =FALSE)# Get first few rowshead(ex2)## NULL
Convert range data to bin-level pseudo-occurrences:
# Generate example dftaxdf <-data.frame(name =c("A", "B", "C"),max_age =c(150, 60, 30),min_age =c(110, 20, 0))# Generate pseudo-occurrencesex1 <-tax_expand_time(taxdf = taxdf, max_ma ="max_age", min_ma ="min_age")# Increase output widthoptions(width =200)# See first few rowshead(ex1)## name max_age min_age ext orig interval_number interval_name rank max_ma mid_ma min_ma duration_myr font colour abbr## 1 C 30 0 FALSE FALSE 1 Meghalayan stage 0.0042 0.00210 0.0000 0.0042 black #FDEDEC <NA>## 2 C 30 0 FALSE FALSE 2 Northgrippian stage 0.0082 0.00620 0.0042 0.0040 black #FDECE4 <NA>## 3 C 30 0 FALSE FALSE 3 Greenlandian stage 0.0117 0.00995 0.0082 0.0035 black #FEECDB <NA>## 4 C 30 0 FALSE FALSE 4 Upper Pleistocene stage 0.1290 0.07035 0.0117 0.1173 black #FFF2D3 <NA>## 5 C 30 0 FALSE FALSE 5 Chibanian stage 0.7740 0.45150 0.1290 0.6450 black #FFF2C7 <NA>## 6 C 30 0 FALSE FALSE 6 Calabrian stage 1.8000 1.28700 0.7740 1.0260 black #FFF2BA <NA>
Latitudinal pseudo-occurrences
Convert range data to bin-level pseudo-occurrences:
# Generate latitudinal binsbins <-lat_bins()# Generate example dftaxdf <-data.frame(name =c("A", "B", "C"),max_lat =c(60, 20, -10),min_lat =c(20, -40, -60))# Generate pseudo-occurrencesex1 <-tax_expand_lat(taxdf = taxdf, bins = bins)# See first few rowshead(ex1)## name max_lat min_lat bin max mid min## 1 A 60 20 4 60 55 50## 2 A 60 20 5 50 45 40## 3 A 60 20 6 40 35 30## 4 A 60 20 7 30 25 20## 5 B 20 -40 8 20 15 10## 6 B 20 -40 9 10 5 0
Phylogeny wrangling
Compare a list of taxonomic names to tip names in a user-provided phylogeny:
# Read in example tree of ceratopsians# from paleotreelibrary(paleotree)data(RaiaCopesRule)# Set smaller margins for plottingpar(mar =rep(0, 4))# Plot treeplot(ceratopsianTreeRaia)
# Specify list of namesdinosaurs <-c("Nasutoceratops_titusi", "Diabloceratops_eatoni","Zuniceratops_christopheri","Psittacosaurus_major")# Table of taxon names in list, tree or bothex1 <-phylo_check(tree = ceratopsianTreeRaia,list = dinosaurs)# Get first few rowshead(ex1)## taxon_name present_in_tree present_in_list## 8 Diabloceratops_eatoni TRUE TRUE## 33 Psittacosaurus_major TRUE TRUE## 38 Nasutoceratops_titusi FALSE TRUE## 39 Zuniceratops_christopheri FALSE TRUE## 1 Centrosaurus_apertus TRUE FALSE## 2 Styracosaurus_albertensis TRUE FALSE
Interval linking
Link and match interval names to the Geological Time Scale:
## Link numeric age values# Create exemplary dfoccdf <-data.frame(name =c("A", "B", "C"),early_interval =c("Maastrichtian","Campanian","Sinemurian"),late_interval =c("Maastrichtian","Campanian","Bartonian"))# Assign stages and numerical agesoccdf <-look_up(occdf)## Use exemplary int_key# Get internal reef dataoccdf <- reefs# Get internal interval keyint_key <- interval_key# Assign stages and numerical agesoccdf <-look_up(occdf,early_interval ="interval",late_interval ="interval",int_key = int_key)
# Get tetrapod dataoccdf <- tetrapods# Count number of occurrences from each countryex1 <-group_apply(occdf = occdf, group ="cc", fun = nrow)# Remove NA dataoccdf <-subset(occdf, !is.na(genus))# Unique genera per collection with group_apply and input argumentsex2 <-group_apply(occdf = occdf,group =c("collection_no"),fun = tax_unique,genus ="genus",family ="family",order ="order",class ="class",resolution ="genus")# Use multiple variables (number of occurrences per collection & formation)ex3 <-group_apply(occdf = occdf,group =c("collection_no", "formation"),fun = nrow)
