This code creates Supplemental Table II, which is a table of the mean densities (#/m3) of various zooplankton taxa collected at each station.
This code also creates a stacked bar plot to visualize those data, which is not included in the paper.
The RMarkdown file is here: https://rpubs.com/HailaSchultz/field_species-table

load packages

library(reshape2)
library(dplyr)
library(ggplot2)
library(forcats)
library(stringr)

Make tables

subset database to field stations

Read database into R. If current database changes, just change the path

Database <- read.csv("/Users/hailaschultz/Dropbox/Other studies/Aurelia project/Data Analysis/data/current_data/Final_Aurelia_Database_Jan11_2023.csv")

Subset to field stations and sites inside of inlets but out of jellyfish aggregations (OS). These stations serve as a “baseline” zooplankton abundance.

Field_data<-subset(Database,Trial.Type=="Field")
Field_data<-subset(Field_data,Location=="OS")

Combine taxa

Combine species and life history stage

Field_data$Species_lifestage <- paste(Field_data$Genus.species, Field_data$Life.History.Stage, sep="_")

Combine the following taxa: - Acartia and small calanoida are added to medium calanoida - Calanus pacificus Female Adult, Calanus pacificus Male Adult, and Calanus pacificus C5-adult are combined into Calanus pacficus - Ditrichocorycaeus anlgicus large and small are combined

Field_data <- Field_data %>%
                   mutate(Species_lifestage_combined = fct_recode(Species_lifestage, 
                                     "CALANOIDA_Medium" = "ACARTIA_Copepodite", 
                                     "CALANOIDA_Medium" = "ACARTIA_Female, Adult",
                                     "CALANUS PACIFICUS" = "CALANUS PACIFICUS_C5-adult",
                                     "CALANUS PACIFICUS" = "CALANUS PACIFICUS_Female, Adult",
                                     "CALANUS PACIFICUS" = "CALANUS PACIFICUS_Male, Adult",
                                     "DITRICHOCORYCAEUS ANGLICUS" = "DITRICHOCORYCAEUS ANGLICUS_Large",
                                     "DITRICHOCORYCAEUS ANGLICUS" = "DITRICHOCORYCAEUS ANGLICUS_Small"))

Remove centric diatoms

Field_data<- subset(Field_data, Genus.species !="Diatom-Centric")

Sum grouped taxa

Field_data_sum <-aggregate(Density....m3. ~ Sample.Code+Sample.Year+Sample.Date+Site+Station+Broad.Group+Species_lifestage_combined, data = Field_data, sum)

Deal with duplicate station names

# combine station and date for unique stations
Field_data_sum$Station_unique <- paste(Field_data_sum$Station, Field_data_sum$Sample.Date)
unique(Field_data_sum$Station_unique)

##  [1] "BUDD1a 07/28/2021" "BUDD1s 08/27/2020" "BUDD2a 08/27/2020"
##  [4] "BUDD2s 07/28/2021" "BUDD2s 08/27/2020" "BUDD3 08/27/2021" 
##  [7] "BUDD3s 08/27/2020" "BUDD4 08/27/2020"  "BUDD4s 08/27/2020"
## [10] "BUDD5 08/27/2020"  "BUDD6 08/27/2020"  "Eld1b 07/28/2021" 
## [13] "Eld1s 08/28/2020"  "Eld2 08/28/2020"   "Eld2b 07/28/2021" 
## [16] "Eld2s 08/28/2020"  "Eld3b 07/28/2021"  "Eld3s 08/28/2020" 
## [19] "Eld4 08/28/2020"   "Eld4s 08/28/2020"  "QM10 08/24/2021"  
## [22] "QM11 08/24/2021"   "QM3 07/24/2019"    "QM3 08/28/2019"   
## [25] "QM3a 08/29/2020"   "QM3b 07/29/2021"   "QM4 07/24/2019"   
## [28] "QM4 08/28/2019"    "QM4b 07/29/2021"   "QM4c 08/22/2021"  
## [31] "QM7a 08/29/2020"   "QM9 08/23/2021"    "SC12 08/26/2021"  
## [34] "SC17 08/27/2021"   "SC3 09/25/2019"    "SC3a 07/27/2021"  
## [37] "SC4 09/25/2019"    "SC4a 07/27/2021"   "SC4c 08/25/2021"

rename duplicate stations

Field_data_sum$Station_unique <-recode(Field_data_sum$Station_unique, 
                                        'BUDD2s 08/27/2020'='BUDD2s_2020 08/27/2020', 
                                        'QM3 07/24/2019'='QM3s 08/27/2020',
                                        'QM4 07/24/2019'='QM4s 08/27/2020')
#remove date
Field_data_sum$Station_unique<-str_sub(Field_data_sum$Station_unique, end=-11)

Calculate means and standard error per year and inlet

Summarize by experiment, taxon, and life history stage.

Field_data_averaged <- Field_data_sum %>%
  group_by(Site,Sample.Year,Broad.Group,Species_lifestage_combined) %>%
  summarise(
    mean = mean(Density....m3.),
    sd = sd(Density....m3.),
    n = n(),
    se = sd / sqrt(n)
  )

Make mean and standard error tables

Mean table

#reformat table
Field_data_mean<-dcast(Field_data_averaged,Broad.Group+Species_lifestage_combined~Site+Sample.Year, value.var = "mean")

Standard Error table

#reformat table
Field_data_SE<-dcast(Field_data_averaged,Broad.Group+Species_lifestage_combined~Site+Sample.Year, value.var = "se")

Combine mean and standard error tables and format final table

# Round dataframes to 2 decimal points
Field_data_mean[, -c(1,2)]<-round(Field_data_mean[, -c(1,2)],2)
Field_data_SE[, -c(1,2)]<-round(Field_data_SE[, -c(1,2)],2)
# Exclude first column
columns_to_combine <- names(Field_data_mean)[-c(1,2)]

# Combine means and standard errors for selected columns
Field_densities <- data.frame(
  Field_data_mean[, c(1,2)],
  sapply(columns_to_combine, function(col) {
   paste(Field_data_mean[[col]], " ± ", Field_data_SE[[col]])
  })
)

reformat species

Field_densities$Species_lifestage_combined <- gsub("_", " ", Field_densities$Species_lifestage_combined)

Export table to csv

write.csv(Field_densities,"/Users/hailaschultz/Dropbox/Other studies/Aurelia project/Data Analysis/output/Field_densities.csv", row.names = FALSE)

From this point on, the table can be edited in excel to fit the correct format for the table

Stacked Bar Chart

Field_stacked_barplot<-ggplot(Field_data_averaged, aes(x = Sample.Year, y = mean, fill = Species_lifestage_combined)) +
  geom_bar(stat = "identity",position = "fill") +
  labs(x = "Year", y = "Mean Density") +
  theme_minimal()+ facet_grid(cols = vars(Site))
Field_stacked_barplot

save plot as image

setwd("/Users/hailaschultz/Dropbox/Other studies/Aurelia project/Data Analysis/output")
ggsave(plot = Field_stacked_barplot, width = 20, height = 10, dpi = 300, filename = "Field_stacked_barplot.png")

14_field_species-table

2023-08-24