clust_2.cgi

Applied Math & Computer Science Lab

Data Analysis, Optimization & Mathematical Modeling, Artificial Intelligence, Neural Net For Everyday Life Applications

AI/Data Mining Links

Online Free Courses

Online Bookstore

Earn Points for $10 Amazon eGift Card

Practical Data Mining Courses Get Certificate of Completion Now for Free

clust_2.cgi

Take 4 questions survey to help us better serve our customers.

Visit online bookstore
View new arrivals on
artificial intelligence, data mining, text mining, applied math

Projects, Source Code,Downloads from this Site
Clickstream Miner - tool for converting weblog to clickstream data, analyzing website usage and mining navigation patterns.
Web Mining with Perl is currently an active area of our interest.
Tic-Tac-Toe Artificial Intelligence (Reinforcement Learning) is applied to Game Programming.
Clustering K-means algorithm is implemented in Perl

Free online courses
Get certificate of completion
Artificial intelligence, data mining, web mining

$filename="logfile.txt";
open (File_Log , "$filename");

while (<File_Log>) {

my ($url,$date,$host,$misc,$ip,$str_search,$search_type,$q_string,$h,$ref,$k,$k1,$k2,$k3)=/^(\S+)\t((\S+| )*)\t(\S+)\t(\S+)\t((\S+| )*)\t\t((\S+| )*)\t((\S+| )*)\t((\S+| )*)\t/;

if(do_not_count_record ($ip,"C:\\WINDOWS\\Desktop\\robots.txt")==1)  
{ 
    next;
}

$new_rec="$ip $date $page\n";

$line="$page\t$date\t$browser\t$str_search\t$search_type\t$q_string\t$h\t$ref\n";

add_record_to_file  ($new_rec, "C:\\WINDOWS\\Desktop\\log.txt");
add_record_to_file  ($line,"C:\\WINDOWS\\Desktop\\full_log.txt");

if (!defined $count_url{$url})
{
   $count_url{$url}=1;
}
else
{
  $count_url{$url}=$count_url{$url}+1;
}
$total_url=$total_url+1;

if (!defined $count_ip{$ip})
{
   
   $count_ip{$ip}=1;
}
else
{
   $count_ip{$ip}=$count_ip{$ip}+1;
}
$total_ip=$total_ip+1;

}

close (File_Log);

$ind=0;
foreach $key ( keys %count_url )
{

$ar_data[$ind][0]= $key;
  $ar_data[$ind][1]= $count_url{$key};
  $ind=$ind+1;
 
}
  
 @ar_data_sorted=sort {$b->[1]<=>$a->[1]} @ar_data;

for ($i=0; $i<$ind; $i++)
 {
   add_record_to_file("$ar_data_sorted[$i][0] $ar_data_sorted[$i][1] \n",  "C:\\WINDOWS\\Desktop\\stat.txt") ;
 }

$ind=0;
foreach $key ( keys %count_ip )
{

$ar_data_ip[$ind][0]= $key;
  $ar_data_ip[$ind][1]= $count_ip{$key};
  $ind=$ind+1;
 
}
  
 @ar_data_ip_sorted=sort {$b->[1]<=>$a->[1]} @ar_data_ip;

for ($i=0; $i<$ind; $i++)
 {
   add_record_to_file("$ar_data_ip_sorted[$i][0] $ar_data_ip_sorted[$i][1] \n",  "C:\\WINDOWS\\Desktop\\stat_ip.txt") ;
 }

sub add_record_to_file
{

my $record=shift;
    my $f_track=shift;

do {open(FH_track, ">$f_track");
        close(FH_track)}
    unless -f  $f_track;
 open (FH_track, ">>$f_track");

print( FH_track $record);
close (FH_track);
}

sub do_not_count_record
{
    my $log_rec=shift;
    my $f_n=shift;

open (FH_LOG,$f_n );
  
    while ($ln = <FH_LOG>)
    {

$ln=substr($ln, 0, length($ln)-1);
      
         if ( $log_rec =~ m/$ln/ )
            { 
              return 1;   }
      
    }
    close (FH_LOG);
    return 0;
}