view release on metacpan or  search on metacpan

examples/calculate_similarity_matrix_for_all_normalized_docs.pl  view on Meta::CPAN

#!/usr/bin/perl -w

use lib '../blib/lib', '../blib/arch';

## calculate_similarity_matrix_for_all_normalized_docs.pl


#  This script demonstrates how you can calculate the similarity matrix for
#  all of the documents in your corpus.  The (i,j)th element of the output
#  matrix is the dot-vector based similarity between the i-th document and
#  the j-th document.  The index associated with a documnet is its place in
#  an alphabetically sorted list of all the documents.

t/test.t  view on Meta::CPAN

use Test::Simple tests => 2;

use lib '../blib/lib','../blib/arch';

use Algorithm::VSM;

# Test 1 (Test VSM:)

my $corpus_dir = "examples/minicorpus";

my @query = qw/ string getallchars throw ioexception distinct treemap histogram map /;
my $corpus_vocab_db = "t/___corpus_vocab_db";
my $doc_vectors_db  = "t/___doc_vectors_db";