0. load data

for(i in 1:13){
  load(file=paste0("D:/datasets/citations_data/tourism_satisfaction2021/M",i,".rda"))
}

1. create m_matrix: first line

m_matrix<-as.data.frame(t(c(1,"AU","M1")))
colnames(m_matrix)<-c("col_id","col_names","from_data")

2. loop for 13 sections

# mlist includes the names of the data frame

mlist<-as.data.frame(c('M1','M2','M3','M4','M5','M6','M7','M8','M9','M10','M11','M12','M13'))

for(i in 1:13){
  temp<-get(mlist[i,1])

  # temp is the dataframe

  c1<-1:ncol(temp)      # variable's position
  c2<-colnames(temp)    # variable's name
  c3<-rep(mlist[i,1],ncol(temp)) # section's name

  c123<-as.data.frame(cbind(c1,c2,c3))

  colnames(c123)<-c("col_id","col_names","from_data")

  # rbind
  m_matrix<-rbind(m_matrix,c123)

}
# delete the first row
m_matrix<-m_matrix[-1,]

3. frequency analysis

freq_variable<-as.data.frame(table(m_matrix[,2]))

# filter Freq < 13
freq_variable2<-subset(freq_variable,Freq<13)

4. plot of frequency

library(ggplot2)

Plot_variables<-ggplot(freq_variable2, aes(x = Var1, y = Freq)) +
  geom_col(fill = "lightblue", colour = "grey60", binwidth=10) +
  geom_density(colour="red") +
  ylim(0,max(freq_variable2$Freq)*1.1)+
  geom_text(aes(label = Freq), hjust = -0.5)+
  coord_flip()

Warning: Ignoring unknown parameters: binwidth

Plot_variables

Warning: Groups with fewer than two data points have been dropped.
Warning: Groups with fewer than two data points have been dropped.
Warning: Groups with fewer than two data points have been dropped.
Warning: Groups with fewer than two data points have been dropped.
Warning: Groups with fewer than two data points have been dropped.
Warning: Groups with fewer than two data points have been dropped.
Warning: Groups with fewer than two data points have been dropped.
Warning in max(ids, na.rm = TRUE) :
  no non-missing arguments to max; returning -Inf
Warning in max(ids, na.rm = TRUE) :
  no non-missing arguments to max; returning -Inf
Warning in max(ids, na.rm = TRUE) :
  no non-missing arguments to max; returning -Inf
Warning in max(ids, na.rm = TRUE) :
  no non-missing arguments to max; returning -Inf
Warning in max(ids, na.rm = TRUE) :
  no non-missing arguments to max; returning -Inf
Warning in max(ids, na.rm = TRUE) :
  no non-missing arguments to max; returning -Inf
Warning in max(ids, na.rm = TRUE) :
  no non-missing arguments to max; returning -Inf

5. variable_matrix

start_time <- Sys.time()
colid_matrix<-freq_variable
for(i in 1:nrow(m_matrix)){
  # all 596 rows
  for(j in 1:nrow(mlist)){
    # j is for the 13 sections
    for(m in 1:nrow(colid_matrix)){
      # m is for the final matix: variables
      if((colid_matrix[m,1]==m_matrix[i,2]) &(mlist[j,1]==m_matrix[i,3]) ){
        colid_matrix[m,mlist[j,1]]<-m_matrix[i,1]
      }
    }
  }

}
end_time <- Sys.time()
end_time - start_time

Time difference of 27.44249 secs