Algorithm-TicketClusterer
view release on metacpan or search on metacpan
examples/retrieve_similar_tickets.pl view on Meta::CPAN
###
###
### depends on the number of tickets in your Excel spreadsheet. If the
### number of tickets is in the low hundreds, this parameter is likely to
### require a value of 1.5 to 1.8. If the number of tickets is in the
### thousands, the value of this parameter is likely to be between 2 and
### 3. See the writeup on this parameter in the API description in the
### main documentation.
#use lib '../blib/lib', '../blib/arch';
use strict;
use Algorithm::TicketClusterer;
my $fieldname_for_clustering = "Description";
my $unique_id_fieldname = "Request No";
my $raw_tickets_db = "raw_tickets.db";
my $processed_tickets_db = "processed_tickets.db";
my $stemmed_tickets_db = "stemmed_tickets.db";
my $inverted_index_db = "inverted_index.db";
examples/ticket_preprocessor_and_doc_modeler.pl view on Meta::CPAN
### This is the script you must run on a new Excel spreadsheet before you
### can retrieve similar tickets from the tickets stored in the
### spreadsheet.
### This script calls on a user to specify names for the nine databases
### that are created for the tickets. This is to avoid having to process
### all the tickets every time you need to make a retrieval for a new
### ticket.
#use lib '../blib/lib', '../blib/arch';
use strict;
use Algorithm::TicketClusterer;
my $excel_filename = "ExampleExcelFile.xls";
#my $excel_filename = "SampleTest.xlsx";
my $fieldname_for_clustering = "Description";
my $unique_id_fieldname = "Request No";
my $raw_tickets_db = "raw_tickets.db";
my $processed_tickets_db = "processed_tickets.db";
use Test::Simple tests => 3;
use lib '../blib/lib','../blib/arch';
use Algorithm::TicketClusterer;
# Test 1 (Read Excel):
my $tclusterer = Algorithm::TicketClusterer->new(
excel_filename => "t/__SampleTest.xlsx",
which_worksheet => 1,
clustering_fieldname => "Description",
unique_id_fieldname => "Request No",
( run in 0.262 second using v1.01-cache-2.11-cpan-87723dcf8b7 )