.Rhistory

rbind(
dfFrequentNames %>% select(Species),
dfFrequentNames %>% select(SpeciesNew) %>% rename(Species = SpeciesNew)) %>%
unique %>%
arrange(Species) %>%
# filter(SpeciesNew %in% TBMFspp) %>% # Exclude species from Cascadia ecoregions
pull(Species) %>%
paste(collapse = "” OR “") -> BooleanSpp
paste("(seed OR seeds) AND (dormancy OR germination) AND (“", BooleanSpp, "”)", sep ="") %>%
write.table(here("results", "Boolean search string.txt"), row.names = F)
read.csv("../#data/germination/results/TBMF_Database.csv") -> TBMF
read.csv("../#data/germination/results/TBMF_Database.csv") -> TBMFDB
readr::write_excel_csv(TBMFDB, here::here("results", "TBMF_Database.csv"))
readr::write_excel_csv(TBMFDB, here::here("data", "TBMF_Database.csv"))
paste("(seed OR seeds) AND (dormancy OR germination) AND (“", BooleanSpp, "”)", sep ="") %>%
write.table(here("data", "Boolean search string.txt"), row.names = F)
library(tidyverse); library(here); library(sp); library(openxlsx)
# Cleaning of the search string
## TPL Names from common source
read.csv("../#data/tpl/results/TPLNames.csv") -> Names # TPL taxonomy files are in my home drive
read.csv("../#data/tpl/results/Families.csv") -> SeedFamilies # TPL taxonomy files are in my home drive
## Clean species file
rbind(
read.csv("../#data/plots/data/sPlot12/species_Edu.csv") %>% # sPlot vegetation files are in my home drive
select(PlotObservationID, species, Relative.cover) %>%
rename(Cover = Relative.cover, PlotID = PlotObservationID, Taxon = species) %>%
mutate(PlotID = paste("Rest", PlotID, sep = "_")),
read.csv("../#data/plots/data/sPlot12/forest2_1500.csv", sep = "\t") %>% # sPlot vegetation files are in my home drive
select(Relevé.number, Species.name, Cover..) %>%
rename(Cover = Cover.., PlotID = Relevé.number, Taxon = Species.name) %>%
mutate(PlotID = paste("Japan", PlotID, sep = "_"))) %>%
merge(Names, by = "Taxon", all.x = TRUE) %>%
filter(Family %in% SeedFamilies$Family) %>%
select(PlotID, New.ID, Cover) -> dfSpeciesRevised
## Clean plot header file
rbind(
read.csv("../#data/plots/data/sPlot12/TDFNH3_Edu.csv") %>% # sPlot vegetation files are in my home drive
filter(Herbs.identified..y.n. != "N" |
! Plants.recorded %in% c("All trees & dominant shrubs",
"All woody species",
"Dominant woody plants >= 2.5 cm dbh",
"Woody plants >= 2.5 cm dbh")) %>%
select(PlotObservationID, ECO_NAME, Altitude..m., Aspect..Â..,
Slope..Â.., POINT_X, POINT_Y) %>%
rename(PlotID = PlotObservationID,
Ecoregion = ECO_NAME,
Altitude = Altitude..m.,
Aspect = Aspect..Â..,
Slope = Slope..Â..,
Longitude = POINT_X,
Latitude = POINT_Y) %>%
mutate(PlotID = paste("Rest", PlotID, sep = "_")),
read.table("../#data/plots/data/sPlot12/japan2.txt", sep = ";", header = T) %>% # sPlot vegetation files are in my home drive
select(PlotID, REALM:ECO_NAME) %>%
merge(read.csv("../#data/plots/data/sPlot12/forest2_1500.hea", sep = "\t", quote = ""), by = "PlotID") %>% # sPlot vegetation files are in my home drive
filter(BIOME == 4) %>%
select(Relevé.number, ECO_NAME, Altitude..m., Aspect....,
Slope...., DEG_LON, DEG_LAT) %>%
rename(PlotID = Relevé.number,
Ecoregion = ECO_NAME,
Altitude = Altitude..m.,
Aspect = Aspect....,
Slope = Slope....,
Longitude = DEG_LON,
Latitude = DEG_LAT) %>%
mutate(PlotID = paste("Japan", PlotID, sep = "_"),
Longitude = as.numeric(gsub("*,", ".", Longitude)),
Latitude = as.numeric(gsub("*,", ".", Latitude)))) -> dfHeader
## Calculate frequencies, filter out rare species
dfHeader %>%
select(PlotID, Ecoregion) %>%
unique %>%
group_by(Ecoregion) %>%
summarise(T = length(Ecoregion)) -> dfTotals
merge(dfSpeciesRevised, dfHeader, by = "PlotID") %>%
select(PlotID, New.ID, Ecoregion) %>%
unique %>%
group_by(Ecoregion, New.ID) %>%
summarise(N = length(New.ID)) -> dfCounts
merge(dfCounts, dfTotals, by = "Ecoregion") %>%
mutate(F = N/T) %>%
filter(F > 0.05) %>%
pull(New.ID) %>%
unique -> FrequentSpp
Names %>%
filter(New.ID %in% FrequentSpp) %>%
mutate(Species = paste(Genus, Species, sep = " "),
SpeciesNew = paste(New.Genus, New.Species, sep = " ")) %>%
select(New.ID, Species, SpeciesNew) %>%
arrange(Species) -> dfFrequentNames
merge(dfCounts, dfTotals, by = "Ecoregion") %>%
mutate(F = N/T) %>%
filter(! Ecoregion %in% c("Cascade Mountains leeward forests", "Central and Southern Cascades forests",
"Eastern Cascades forests")) %>% # These ecoregions are in the vegetation db, but belong to different biome
filter(F > 0.05) %>%
select(New.ID) %>%
unique %>%
merge(Names) %>%
mutate(Species = paste(Genus, Species, sep = " "),
SpeciesNew = paste(New.Genus, New.Species, sep = " ")) %>%
select(SpeciesNew) %>%
unique %>%
arrange(SpeciesNew) %>%
pull(SpeciesNew) -> TBMFspp
## Create Boolean search string
rbind(
dfFrequentNames %>% select(Species),
dfFrequentNames %>% select(SpeciesNew) %>% rename(Species = SpeciesNew)) %>%
unique %>%
arrange(Species) %>%
# filter(SpeciesNew %in% TBMFspp) %>% # Exclude species from Cascadia ecoregions
pull(Species) %>%
paste(collapse = "” OR “") -> BooleanSpp
paste("(seed OR seeds) AND (dormancy OR germination) AND (“", BooleanSpp, "”)", sep ="") %>%
write.table(here("data", "Boolean search string.txt"), row.names = F)
# Cleaning of the database
read.csv("../#data/germination/results/TBMF_Database.csv") -> TBMFDB
readr::write_excel_csv(TBMFDB, here::here("data", "TBMF_Database.csv"))
# Calculate numbers for the manuscript main text
dfFrequentNames %>%
filter(SpeciesNew %in% TBMFspp) %>%
pull(SpeciesNew) %>% unique %>% length -> MSfrequentspp
merge(dfHeader, dfSpeciesRevised, by = "PlotID") %>%
filter(! Ecoregion %in% c("Cascade Mountains leeward forests", "Central and Southern Cascades forests",
"Eastern Cascades forests")) %>% # These ecoregions are in the vegetation db, but belong to different biome
select(New.ID) %>%
unique %>%
merge(Names, by = "New.ID") %>%
mutate(SpeciesNew = paste(New.Genus, New.Species, sep = " ")) %>%
pull(SpeciesNew) %>% unique %>% length -> MStotalspp
dfHeader %>%
filter(! Ecoregion %in% c("Cascade Mountains leeward forests", "Central and Southern Cascades forests",
"Eastern Cascades forests")) %>% # These ecoregions are in the vegetation db, but belong to different biome
pull(PlotID) %>% unique %>% length -> MSplots
dfHeader %>%
filter(! Ecoregion %in% c("Cascade Mountains leeward forests", "Central and Southern Cascades forests",
"Eastern Cascades forests")) %>% # These ecoregions are in the vegetation db, but belong to different biome
pull(Ecoregion) %>% unique %>% length -> MSecoregions
TBMFDB %>% tally() -> MSrecords
TBMFDB %>% pull(Reference) %>% unique %>% length -> MSreferences
TCFDB %>% pull(Reference) %>% unique %>% length -> MSreferencesTCF
TBMFDB %>% pull(Family) %>% unique %>% length -> MSfamilies
TBMFDB %>% pull(TPLName) %>% unique %>% length -> MSspecies
TBMFDB %>% pull(Year) %>% unique() %>% min -> MSoldest
TBMFDB %>% group_by(Country) %>% tally() %>% arrange(-n) -> MScountries
TBMFDB$Number_seeds %>% sum -> MSseeds
TBMFDB %>% pull(Tmean) %>% min -> MSminT
TBMFDB %>% pull(Tmean) %>% max -> MSmaxT
TBMFDB %>% filter(Alternating == "Y") %>% tally -> MSaltY
TBMFDB %>% filter(Alternating == "N") %>% tally -> MSaltN
TBMFDB %>% filter(Light == "Y") %>% tally -> MSlightY
TBMFDB %>% filter(Light == "N") %>% tally -> MSlightN
TBMFDB %>% filter(is.na(Light)) %>% tally -> MSlightNA
TBMFDB %>% filter(Stratification_type == "None") %>% tally -> MSstratN
TBMFDB %>% filter(Stratification_type == "Cold") %>% tally -> MSstratCold
TBMFDB %>% filter(Scarification == "Y") %>% tally -> MSscarY
TBMFDB %>% arrange(Reference) %>% pull(Reference) %>% unique -> MSrefapp
save(MSaltN, MSaltY, MScountries, MSlightN, MSlightNA, MSlightY,
MSrecords, MSscarY, MSstratCold, MSstratN,
MSecoregions, MSfamilies, MSfrequentspp, MSmaxT, MSminT,
MSoldest, MSplots, MSreferences, MSseeds, MSspecies, MStotalspp,
MSrefapp,
file = here::here("results", "msnumbers.RData"))
# Create files for the app
library(metafor); library(binom); library(data.table)
## A function to metanalize proportions...
metanalize <- function(d)
{
m <- rma.glmm(measure = "PLO", xi = Germinated, ni = Number_seeds, data = d)
p <- predict(m, transf = transf.ilogit, digits = 3)
data.frame(mean = p$pred, lower = p$ci.lb, upper = p$ci.ub)
}
## Data grouped by experimental and species
TBMFDB %>%
mutate(group = paste(TPLName, Scarification, Stratification_type,
Light, Alternating, Temperature, sep = "_")) %>%
data.table(.) -> df
## First we check for which groups the metanalysis works...
listd <- split(df, by = "group", drop = TRUE)
ms <- lapply(listd, function(d) tryCatch(metanalize(d), error = function(e) e))
rma.works <- names(ms)[lapply(ms, length) >= 3]
## Now we do the MA for the species that work
df.rma <- df[group %in% rma.works]
df.rma %>%
group_by(group) %>%
do(metanalize(.)) %>%
group_by -> rma.species
## And for the rest, we simply calculate the proportions and CI
df[! group %in% rma.works] %>%
group_by(group) %>%
summarise(Germinated = sum(Germinated), Number_seeds = sum(Number_seeds)) %>%
data.frame -> GermDF
cbind(group = GermDF[, 1],
binom.confint(GermDF$Germinated, GermDF$Number_seeds, method = "wilson")[, 4:6]) %>%
as_tibble()-> germdf
rbind(germdf, rma.species)  %>%
separate(group, into = c("Species", "Scarification", "Stratification_type",
"Light", "Alternating", "Temperature"), sep = "_",
convert = TRUE) %>%
mutate(Light = ifelse(is.na(Light), "Light unknown", Light),
Species = as.factor(Species),
Scarification = as.factor(Scarification),
Stratification_type = as.factor(Stratification_type),
Light = as.factor(Light),
Alternating = as.factor(Alternating),
Scarification = recode_factor(Scarification, "N" = "Unscarified", "Y" = "Scarified"),
Stratification_type = recode_factor(Stratification_type, "C+W" = "C+W-stratified",
"Cold" = "Cold-stratified",
"None" = "Non-stratified",
"W+C" = "W+C-stratified",
"Warm" = "Warm-stratified"),
Light = recode_factor(Light, "N" = "Darkness", "Y" = "Light"),
Alternating = recode_factor(Alternating, "N" = "Constant temperature",
"Y" = "Alternating temperature"),
Experiment = paste(Light, Alternating, Stratification_type, Scarification, sep = ",\n"),
Experiment = as.factor(Experiment)) %>%
rename(Stratification = Stratification_type) -> Germination
## Biome map
library(raster); library(sp)
library(maps); library(mapdata); library(rgdal)
library(plyr)
## Prepare WWF shapefile
readOGR(dsn = "../#wwfmap/WWF",
layer = "wwf_terr_ecos") -> Ecoregions # Map files are in my home drive
rownames(Ecoregions@data) -> Ecoregions@data$id
fortify(Ecoregions, region = "id") -> Ecoregions.points
join(Ecoregions.points, Ecoregions@data, by = "id") %>%
inner_join(read.csv("../#wwfmap/Biomes.csv"), by = "BIOME") %>%
filter(BIOME == 4) ->
TBMF
TBMFDB %>%
dplyr::select(TPLName, Country, Latitude, Longitude) %>%
dplyr::rename(Species = TPLName) %>%
unique -> coordinates
coordinates %>%
dplyr::select(Longitude, Latitude) %>%
SpatialPoints(proj4string = CRS(proj4string(Ecoregions))) %over% Ecoregions %>%
cbind(coordinates) -> Places
save(Germination,TBMFDB, Places, TBMF,
file = here::here("results", "appdata.RData"))
# Manuscript figures
TBMFDB %>%
ggplot(aes(x = Longitude, y = Latitude)) +
geom_polygon(data = map_data("world"), aes(x = long, y = lat, group = group),
color = "gainsboro", fill = "gainsboro") +
geom_polygon(data = TBMF, aes(x = long, y = lat,group =  group),
fill = "darkolivegreen4", color = "darkolivegreen4") +
geom_point(color = "gold", size = 1.25, alpha = 0.5) +
ggthemes::theme_map() +
theme(legend.position = "none",
axis.title = element_blank()) +
coord_cartesian(xlim = c(-160, 180), ylim = c(-55, 80)) -> p1
Germination %>%
filter(Species == "Fagus sylvatica") %>%
ggplot(aes(x = as.factor(Temperature), y = mean, ymin = lower, ymax = upper, fill = Experiment)) +
geom_bar(stat = "identity", alpha = 0.6, show.legend = FALSE) +
geom_errorbar(aes(color = Experiment), width = 0.1, size = 1,
position = position_dodge(.9), show.legend = FALSE) +
facet_wrap( ~ Experiment, scales = "free", ncol = 3) +
coord_cartesian(ylim = c(0, 1)) +
ylab(label = "Germination proportion") + xlab(label = "Average germination temperature (ºC)") +
ggthemes::theme_tufte() +
theme(panel.background = element_rect(color = "grey96", fill = "grey96"),
legend.position = "none",
strip.text = element_text(size = 11),
axis.text = element_text(size = 12, face = "bold"),
axis.title = element_text(size = 14, face = "bold"),
legend.text = element_text(size = 16, face = "bold")) -> p2
ggsave(p1, file = "results/Fig1.pdf",
path = NULL, scale = 1, width = 170, height = 70, units = "mm", dpi = 600)
ggsave(p2, file = "results/Fig2.pdf",
path = NULL, scale = 1, width = 170, height = 120, units = "mm", dpi = 600)
dfHeader
dfFrequentNames %>%
filter(SpeciesNew %in% TBMFspp) %>%
pull(SpeciesNew) %>% unique %>% length -> MSfrequentspp
merge(dfHeader, dfSpeciesRevised, by = "PlotID") %>%
filter(! Ecoregion %in% c("Cascade Mountains leeward forests", "Central and Southern Cascades forests",
"Eastern Cascades forests")) %>% # These ecoregions are in the vegetation db, but belong to different biome
select(New.ID) %>%
unique %>%
merge(Names, by = "New.ID") %>%
mutate(SpeciesNew = paste(New.Genus, New.Species, sep = " ")) %>%
pull(SpeciesNew) %>% unique %>% length -> MStotalspp
dfHeader %>%
filter(! Ecoregion %in% c("Cascade Mountains leeward forests", "Central and Southern Cascades forests",
"Eastern Cascades forests")) %>% # These ecoregions are in the vegetation db, but belong to different biome
pull(PlotID) %>% unique %>% length -> MSplots
dfHeader %>%
filter(! Ecoregion %in% c("Cascade Mountains leeward forests", "Central and Southern Cascades forests",
"Eastern Cascades forests")) %>% # These ecoregions are in the vegetation db, but belong to different biome
pull(Ecoregion) %>% unique %>% length -> MSecoregions
TBMFDB %>% tally() -> MSrecords
TBMFDB %>% pull(Reference) %>% unique %>% length -> MSreferences
TCFDB %>% pull(Reference) %>% unique %>% length -> MSreferencesTCF
TBMFDB %>% pull(Family) %>% unique %>% length -> MSfamilies
TBMFDB %>% pull(TPLName) %>% unique %>% length -> MSspecies
TBMFDB %>% pull(Reference) %>% unique %>% length -> MSreferences
TBMFDB %>% pull(Family) %>% unique %>% length -> MSfamilies
TBMFDB %>% pull(TPLName) %>% unique %>% length -> MSspecies
TBMFDB %>% pull(Year) %>% unique() %>% min -> MSoldest
TBMFDB %>% group_by(Country) %>% tally() %>% arrange(-n) -> MScountries
TBMFDB$Number_seeds %>% sum -> MSseeds
TBMFDB %>% pull(Tmean) %>% min -> MSminT
TBMFDB %>% pull(Tmean) %>% max -> MSmaxT
TBMFDB %>% filter(Alternating == "Y") %>% tally -> MSaltY
TBMFDB %>% filter(Alternating == "N") %>% tally -> MSaltN
TBMFDB %>% filter(Light == "Y") %>% tally -> MSlightY
TBMFDB %>% filter(Light == "N") %>% tally -> MSlightN
TBMFDB %>% filter(is.na(Light)) %>% tally -> MSlightNA
TBMFDB %>% filter(Stratification_type == "None") %>% tally -> MSstratN
TBMFDB %>% filter(Stratification_type == "Cold") %>% tally -> MSstratCold
TBMFDB %>% filter(Scarification == "Y") %>% tally -> MSscarY
TBMFDB %>% arrange(Reference) %>% pull(Reference) %>% unique -> MSrefapp
save(MSaltN, MSaltY, MScountries, MSlightN, MSlightNA, MSlightY,
MSrecords, MSscarY, MSstratCold, MSstratN,
MSecoregions, MSfamilies, MSfrequentspp, MSmaxT, MSminT,
MSoldest, MSplots, MSreferences, MSseeds, MSspecies, MStotalspp,
MSrefapp,
file = here::here("results", "msnumbers.RData"))
library(metafor); library(binom); library(data.table)
metanalize <- function(d)
{
m <- rma.glmm(measure = "PLO", xi = Germinated, ni = Number_seeds, data = d)
p <- predict(m, transf = transf.ilogit, digits = 3)
data.frame(mean = p$pred, lower = p$ci.lb, upper = p$ci.ub)
}
TBMFDB %>%
mutate(group = paste(TPLName, Scarification, Stratification_type,
Light, Alternating, Temperature, sep = "_")) %>%
data.table(.) -> df
listd <- split(df, by = "group", drop = TRUE)
ms <- lapply(listd, function(d) tryCatch(metanalize(d), error = function(e) e))
rma.works <- names(ms)[lapply(ms, length) >= 3]
df.rma <- df[group %in% rma.works]
df.rma %>%
group_by(group) %>%
do(metanalize(.)) %>%
group_by -> rma.species
df[! group %in% rma.works] %>%
group_by(group) %>%
summarise(Germinated = sum(Germinated), Number_seeds = sum(Number_seeds)) %>%
data.frame -> GermDF
cbind(group = GermDF[, 1],
binom.confint(GermDF$Germinated, GermDF$Number_seeds, method = "wilson")[, 4:6]) %>%
as_tibble()-> germdf
rbind(germdf, rma.species)  %>%
separate(group, into = c("Species", "Scarification", "Stratification_type",
"Light", "Alternating", "Temperature"), sep = "_",
convert = TRUE) %>%
mutate(Light = ifelse(is.na(Light), "Light unknown", Light),
Species = as.factor(Species),
Scarification = as.factor(Scarification),
Stratification_type = as.factor(Stratification_type),
Light = as.factor(Light),
Alternating = as.factor(Alternating),
Scarification = recode_factor(Scarification, "N" = "Unscarified", "Y" = "Scarified"),
Stratification_type = recode_factor(Stratification_type, "C+W" = "C+W-stratified",
"Cold" = "Cold-stratified",
"None" = "Non-stratified",
"W+C" = "W+C-stratified",
"Warm" = "Warm-stratified"),
Light = recode_factor(Light, "N" = "Darkness", "Y" = "Light"),
Alternating = recode_factor(Alternating, "N" = "Constant temperature",
"Y" = "Alternating temperature"),
Experiment = paste(Light, Alternating, Stratification_type, Scarification, sep = ",\n"),
Experiment = as.factor(Experiment)) %>%
rename(Stratification = Stratification_type) -> Germination
Germination
library(raster); library(sp)
library(maps); library(mapdata); library(rgdal)
library(plyr)
readOGR(dsn = "../#data/wwfmap/WWF",
layer = "wwf_terr_ecos") -> Ecoregions # Map files are in my home drive
readOGR(dsn = "../#data/maps/WWF",
layer = "wwf_terr_ecos") -> Ecoregions # Map files are in my home drive
rownames(Ecoregions@data) -> Ecoregions@data$id
fortify(Ecoregions, region = "id") -> Ecoregions.points
join(Ecoregions.points, Ecoregions@data, by = "id") %>%
inner_join(read.csv("../#data/maps/Biomes.csv"), by = "BIOME") %>%
filter(BIOME == 4) ->
TBMF
TBMFDB %>%
dplyr::select(TPLName, Country, Latitude, Longitude) %>%
dplyr::rename(Species = TPLName) %>%
unique -> coordinates
coordinates %>%
dplyr::select(Longitude, Latitude) %>%
SpatialPoints(proj4string = CRS(proj4string(Ecoregions))) %over% Ecoregions %>%
cbind(coordinates) -> Places
save(Germination,TBMFDB, Places, TBMF,
file = here::here("results", "appdata.RData"))
# Manuscript figures
TBMFDB %>%
ggplot(aes(x = Longitude, y = Latitude)) +
geom_polygon(data = map_data("world"), aes(x = long, y = lat, group = group),
color = "gainsboro", fill = "gainsboro") +
geom_polygon(data = TBMF, aes(x = long, y = lat,group =  group),
fill = "darkolivegreen4", color = "darkolivegreen4") +
geom_point(color = "gold", size = 1.25, alpha = 0.5) +
ggthemes::theme_map() +
theme(legend.position = "none",
axis.title = element_blank()) +
coord_cartesian(xlim = c(-160, 180), ylim = c(-55, 80)) -> p1
Germination %>%
filter(Species == "Fagus sylvatica") %>%
ggplot(aes(x = as.factor(Temperature), y = mean, ymin = lower, ymax = upper, fill = Experiment)) +
geom_bar(stat = "identity", alpha = 0.6, show.legend = FALSE) +
geom_errorbar(aes(color = Experiment), width = 0.1, size = 1,
position = position_dodge(.9), show.legend = FALSE) +
facet_wrap( ~ Experiment, scales = "free", ncol = 3) +
coord_cartesian(ylim = c(0, 1)) +
ylab(label = "Germination proportion") + xlab(label = "Average germination temperature (ºC)") +
ggthemes::theme_tufte() +
theme(panel.background = element_rect(color = "grey96", fill = "grey96"),
legend.position = "none",
strip.text = element_text(size = 11),
axis.text = element_text(size = 12, face = "bold"),
axis.title = element_text(size = 14, face = "bold"),
legend.text = element_text(size = 16, face = "bold")) -> p2
ggsave(p1, file = "results/Fig1.png",
path = NULL, scale = 1, width = 170, height = 70, units = "mm", dpi = 600)
ggsave(p2, file = "results/Fig2.png",
path = NULL, scale = 1, width = 170, height = 120, units = "mm", dpi = 600)
library(tidyverse); library(here); library(sp); library(openxlsx)
# Cleaning of the search string
## TPL Names from common source
read.csv("../#data/tpl/results/TPLNames.csv") -> Names # TPL taxonomy files are in my home drive
read.csv("../#data/tpl/results/Families.csv") -> SeedFamilies # TPL taxonomy files are in my home drive
## Clean species file
rbind(
read.csv("../#data/plots/data/sPlot12/species_Edu.csv") %>% # sPlot vegetation files are in my home drive
select(PlotObservationID, species, Relative.cover) %>%
rename(Cover = Relative.cover, PlotID = PlotObservationID, Taxon = species) %>%
mutate(PlotID = paste("Rest", PlotID, sep = "_")),
read.csv("../#data/plots/data/sPlot12/forest2_1500.csv", sep = "\t") %>% # sPlot vegetation files are in my home drive
select(Relevé.number, Species.name, Cover..) %>%
rename(Cover = Cover.., PlotID = Relevé.number, Taxon = Species.name) %>%
mutate(PlotID = paste("Japan", PlotID, sep = "_"))) %>%
merge(Names, by = "Taxon", all.x = TRUE) %>%
filter(Family %in% SeedFamilies$Family) %>%
select(PlotID, New.ID, Cover) -> dfSpeciesRevised
## Clean plot header file
rbind(
read.csv("../#data/plots/data/sPlot12/TDFNH3_Edu.csv") %>% # sPlot vegetation files are in my home drive
filter(Herbs.identified..y.n. != "N" |
! Plants.recorded %in% c("All trees & dominant shrubs",
"All woody species",
"Dominant woody plants >= 2.5 cm dbh",
"Woody plants >= 2.5 cm dbh")) %>%
select(PlotObservationID, ECO_NAME, Altitude..m., Aspect..Â..,
Slope..Â.., POINT_X, POINT_Y) %>%
rename(PlotID = PlotObservationID,
Ecoregion = ECO_NAME,
Altitude = Altitude..m.,
Aspect = Aspect..Â..,
Slope = Slope..Â..,
Longitude = POINT_X,
Latitude = POINT_Y) %>%
mutate(PlotID = paste("Rest", PlotID, sep = "_")),
read.table("../#data/plots/data/sPlot12/japan2.txt", sep = ";", header = T) %>% # sPlot vegetation files are in my home drive
select(PlotID, REALM:ECO_NAME) %>%
merge(read.csv("../#data/plots/data/sPlot12/forest2_1500.hea", sep = "\t", quote = ""), by = "PlotID") %>% # sPlot vegetation files are in my home drive
filter(BIOME == 4) %>%
select(Relevé.number, ECO_NAME, Altitude..m., Aspect....,
Slope...., DEG_LON, DEG_LAT) %>%
rename(PlotID = Relevé.number,
Ecoregion = ECO_NAME,
Altitude = Altitude..m.,
Aspect = Aspect....,
Slope = Slope....,
Longitude = DEG_LON,
Latitude = DEG_LAT) %>%
mutate(PlotID = paste("Japan", PlotID, sep = "_"),
Longitude = as.numeric(gsub("*,", ".", Longitude)),
Latitude = as.numeric(gsub("*,", ".", Latitude)))) -> dfHeader
## Calculate frequencies, filter out rare species
dfHeader %>%
select(PlotID, Ecoregion) %>%
unique %>%
group_by(Ecoregion) %>%
summarise(T = length(Ecoregion)) -> dfTotals
merge(dfSpeciesRevised, dfHeader, by = "PlotID") %>%
select(PlotID, New.ID, Ecoregion) %>%
unique %>%
group_by(Ecoregion, New.ID) %>%
summarise(N = length(New.ID)) -> dfCounts
merge(dfCounts, dfTotals, by = "Ecoregion") %>%
mutate(F = N/T) %>%
filter(F > 0.05) %>%
pull(New.ID) %>%
unique -> FrequentSpp
Names %>%
filter(New.ID %in% FrequentSpp) %>%
mutate(Species = paste(Genus, Species, sep = " "),
SpeciesNew = paste(New.Genus, New.Species, sep = " ")) %>%
select(New.ID, Species, SpeciesNew) %>%
arrange(Species) -> dfFrequentNames
merge(dfCounts, dfTotals, by = "Ecoregion") %>%
mutate(F = N/T) %>%
filter(! Ecoregion %in% c("Cascade Mountains leeward forests", "Central and Southern Cascades forests",
"Eastern Cascades forests")) %>% # These ecoregions are in the vegetation db, but belong to different biome
filter(F > 0.05) %>%
select(New.ID) %>%
unique %>%
merge(Names) %>%
mutate(Species = paste(Genus, Species, sep = " "),
SpeciesNew = paste(New.Genus, New.Species, sep = " ")) %>%
select(SpeciesNew) %>%
unique %>%
arrange(SpeciesNew) %>%
pull(SpeciesNew) -> TBMFspp