# This script was written for data analysis reported in the manuscript:
# Freshwater trematodes differ from marine trematodes in patterns connected with 
#   Division of Labor
# By Allison T Neal, Moira Stettner, Renytzabelle Ortega-Cotto, Daniel Dieringer,
#   and Lydia Reed
# Submitted to PeerJ in October 2023
# The script was written by Allison Neal and is provided to allow easy replication
#   and critical evaluation of the analysis performed.  The script author does not
#   claim to be an efficient or expert R coder, so please excuse any inefficiencies 
#   in the code.

# This script provides a list of the largest and smallest rediae for each infection,
#   which was used to identify rediae to be examined for the presence of appendages
#   and developing embryos.

### First, import data (see referenced script file for more information about data)
source('/Users/aneal1/OneDrive - Norwich University/2_Research/1_Trematode Research/Div of Labor/Analysis/Redial Sizes/DOLVTsizesImportCleanUp.R')

# Get a list of samples I want to look at (this is similar to levels(data$snail) but excludes
#   a sample number, H109, that does not have any data)
samples<-c("H101","H102","H104","H107","H110","H127","H148","H156","H158","H70",
           "H96","P107","P112","P113","P115","P116","P117","P119","P120","P121",
           "P122","P125","P126","P128","P130","P131","P135","P136","P137","P139",
           "P140","P141","P150","P152","P153","P154","P155","P157","P160","P162",
           "P163","P164","P165","P166","P170","P177","P178","Ph100","Ph107","Ph109",
           "Ph112","Ph114","Ph115","Ph116","Ph126","Ph159","Ph95","Ph96","V141","V159",
           "V168","V172","V182","V183","V184")

# Creates a matrix to store the sample numbers of the largest and smallest rediae
bigsmall<-matrix(nrow=length(samples)*10, ncol=2) 

# Use a for loop to sort redia by size for each infection and save sample numbers
#   for the largest and smallest of each infection
for(i in 1:length(samples)){
	data[data$snail==samples[i],]->temp # creates a temporary subset of the data for data from a single snail
	temp[complete.cases(temp$lengthR),]->tempR # gets only the samples with reliable length measurements
	tempR[order(tempR$lengthR),]->tempR # sorts temporary data by length
	start<-(i-1)*10+1 # gives the first row number where the smallest and largest values should be stored in bigsmall
	tempR$sample[1:5]->bigsmall[start:(start+4),1] # smallest values
	bigsmall[start:(start+4),2]<-rep('sm',5)
	tempR$sample[(length(tempR$sample)-4):length(tempR$sample)]->bigsmall[(start+5):(start+9),1] #largest values
	bigsmall[(start+5):(start+9),2]<-rep('lg',5)
}

# Print list of samples to look at for comparison of morphology among largest and 
#   smallest rediae
options(max.print = 1400) # makes sure the full data set is printed in RStudio
bigsmall