# Command for counting frequency of word in the training set.
tr "[ ]*" "[\n*]" < new_Blog.txt | sort | uniq -c | sort -nr | sed -e 's/^[ \t]*//'  > new_Blog_freq.txt 


# Command for deleting frequency and '+' sign from the frequency file and make the data as a 2 dimensional array.
tr -d "[0-9] " < test_set.txt | tr "=|+|:" "[\t*]"  > new4.tx




awk > file3 Begin {
	i = 0;
	errors = 0 ;
}
'NR == FNR {
if (f2[$1] = $1) {
while (f2[$i] ~ $i )
	i++ ;
	next ;
errors ++ ; 
}
}




$2 in f2 {
print $0, f2[$2]
}' new4.tx test_set_compare.txt

