BBP-click-whistles_3models.R

########################################################################
#    STATISTICS
#    Author : Loic LEHNHOFF
#    Adapted from Yannick OUTREMAN 
#    Agrocampus Ouest - 2020
#######################################################################
library(pscl)
library(MASS)
library(lmtest)
library(multcomp)
library(emmeans)
library(dplyr)        # "%>%" function
library(forcats)      # "fct_relevel" function
library(stringr)      # "gsub" function 
library(rcompanion)   # "fullPTable" function
library(multcompView) # "multcompLetters" function
library(ggplot2)
library(pgirmess)
library(postHoc)
#library(tidyquant)    # geom_ma() if rolling average needed


################# DATASET IMPORTS #####################################
folder <- './../'
whistles.dta <-read.table(file=paste0(folder, 
              'Whistles/Evaluation/whistles_durations.csv'),
              sep = ',', header=TRUE)
whistles.dta <- whistles.dta[order(whistles.dta$audio_names),]
bbp.dta <-read.table(file=paste0(folder, 
              'BBPs/Results/16-06-22_14h00_number_of_BBP.csv'),
              sep = ',', header=TRUE)
bbp.dta <- bbp.dta[order(bbp.dta$audio_names),]
clicks.dta <-read.table(file=paste0(folder,
              'Clicks/Results/projection_updated_number_of_clicks_02052022.csv'), #number_of_clicks_02052022.csv
              sep = ',', header=TRUE)
clicks.dta <- clicks.dta[order(clicks.dta$audio_names),]

# Merge files into 1 dataset
acoustic.dta <- clicks.dta
acoustic.dta$number_of_bbp <- bbp.dta$number_of_BBP
acoustic.dta$total_whistles_duration <- whistles.dta$total_whistles_duration
rm(whistles.dta, bbp.dta, clicks.dta)

# add group IDs
id2020 <- read.table(file=paste0(folder, 'CSV_data/Audio_Data_2020.csv'),
                     sep = ',', header=TRUE)[1:396,]
id2021 <- read.table(file=paste0(folder, 'CSV_data/Audio_Data_2021.csv'),
                     sep = ',', header=TRUE)[1:96,]
id2021$ID <- id2021$ID+max(id2020$ID)
id2021$Seq <- id2021$Seq+max(id2020$Seq)
id.dta <- rbind(id2020, id2021)
id.dta$Fichier.Audio <-str_sub(id.dta$Fichier.Audio, -27, -5)
acoustic.dta$ID <- rep(-1, 490)
for (name in acoustic.dta$audio_names){
  acoustic.dta$ID[match(name, acoustic.dta$audio_names)] <- id.dta$ID[match(name, id.dta$Fichier.Audio)]
}
acoustic.dta$ID <- as.factor(acoustic.dta$ID)
rm(id2020, id2021, id.dta)


# suppress "T" acoustic data (other groups not tested on our variables)
acoustic.dta <- acoustic.dta[acoustic.dta$acoustic!="T",]
# shuffle dataframe
acoustic.dta <- acoustic.dta[sample(1:nrow(acoustic.dta)), ]
acoustic.dta$acoustic <- factor(acoustic.dta$acoustic)

#################### DATA INSPECTION  #################################
# Data description
names(acoustic.dta)
# self explenatory except acoustic : correspond to the activation sequence.