Most frequently occuring word    no of times occured
second most frequent word        no of times occured
....                             ....
....                             ....

##</code><code>##

%count = ();
    foreach $element (@words) {
    $count{$element}++;
    }

  while ( ($k,$v) = each %count ) {
    print "$k => $v\n";
  }

##</code><code>##

the         150
it          85 
we          60
are         40 

##</code><code>##

sub lexicon_generate
 {
 
 open CP, 'tcorpus.txt' or die $!;   #Open file.  

 my @words;                
    
 while(<CP>){
 chomp;
               
 push @words,split;                  
 }                                    
  
 close CP;
 
 #print "\n@words\n";

 
$lwords=@words;                      
#print "\n$lwords";


for($i=0;$i<$lwords;$i++)            
 {  
    #print "\nThis is the next token:";
    #print "\n$words[$i]";
 }   
 
                         #Remove punctuation marks.
foreach my $item(@words){
      
     $item=~ tr/*//d;               
     $item=~ tr/(//d;               
     $item=~ tr/)//d;               
     $item=~ tr/""//d;              
     $item=~ tr/''//d;             
     $item=~ tr/?//d;               
     $item=~ tr/,//d;                
     $item=~ tr/. //d;                  
     $item=~ tr/-//d;               
     $item=~ tr/"//d;               
     $item=~ tr/'//d;               
     $item=~ tr/!//d;               
     $item=~ tr/;//d;                
 
     $item= '' unless defined $item;
     
     #print "\nThe token after removing punctuation marks:";
     #print "\n$item\n";
     
   }

  
  #Number of words in @words before removing duplicates.  

  $lnwords=@words;                  
  #print "\n$lnwords";             
 
  foreach my $final_thing(@words){    	#print "$final_thing\n";
  }	
                                                                                            #Remove duplicate strings.
    
 my %seen = ();
 my @uniq = ();
 foreach my $u_thing(@words)
 {
      unless ($seen{$u_thing})
       {
          #if we get here, we have not seen it before
          $seen{$u_thing} = 1;
          push (@uniq,$u_thing);
          
        }
  }      
    
    #print"\nThe unique list:"; 
    #print "\n@uniq";


  #Number of words in @words after removing duplicates.  

  $luniq=@uniq;                                      
  #print "\n$luniq";                            

  
 open LEX,'>tcorpus_unique.txt' or die $!;      
  
 foreach my $u_elt(@uniq){                      
         #print "\n$u_elt";           
         print LEX "\n$u_elt";
                  
   }
  
close LEX;

}

&lexicon_generate();