library(readxl)
library(ggplot2)
library(dplyr)
library(sandwich)
library(lmtest)
library(car)
library(MASS)


bkf=read_excel("C:/Users/donat.karadayi/Desktop/projeler/BKF Çalışması/yıllara göre tablolar/all_years.xlsx")
colnames(bkf)<-c("name","home","province","km","minutes","fairname","participant_count","university_pop","year")

#necessary changes
bring_rate<-rep(0,times=500)
bkf <- cbind(bkf, bring_rate)
bkf[bkf == "-"] <- NA
bkf$km <- as.numeric(bkf$km)
bkf$minutes <- as.numeric(bkf$minutes)
bkf$participant_count <- as.numeric(bkf$participant_count)
bkf$university_pop <- as.numeric(bkf$university_pop)
bkf$year <- as.numeric(bkf$year)

#subsets
bkf19<-subset(bkf,bkf$year=="2019")
bkf20<-subset(bkf,bkf$year=="2020")
bkf22<-subset(bkf,bkf$year=="2022")
bkf24<-subset(bkf,bkf$year=="2024")


# Extract unique university names
university_names <- unique(bkf$name)

# Convert to a data frame
university_names_df <- data.frame(university_name = sort(university_names))
university_names_df

bkf<-na.omit(bkf)

#Bring rate hesabı hepsi için
for(i in 1:356){
  bkf$bring_rate[i]=((bkf$participant_count[i]*100)/bkf$university_pop[i])
  print(bkf$bring_rate[i])
}


bkfhome<-subset(bkf,bkf$home==1)
bkfaway<-subset(bkf,bkf$home==0)
##########################################################################################################################

# Count the occurrences of each university
university_counts <- table(bkfaway$name)

# Get universities that appear only once
universities_once <- names(university_counts[university_counts == 1])

# Print the list of universities that appear only once
universities_once




# Step 3: Subset the data set for universities that appear only once
bkfaway_one_time <- bkfaway[bkfaway$name %in% universities_once, ]

# View the resulting subset
head(bkfaway_one_time)
# Check how many universities appear only once
length(universities_once)
# Check how many rows are in the resulting subset
nrow(bkfaway_one_time)