Algorithm-VSM
view release on metacpan or search on metacpan
examples/calculate_precision_and_recall_for_LSA.pl view on Meta::CPAN
my $lsa = Algorithm::VSM->new(
break_camelcased_and_underscored => 1, # default: 0
case_sensitive => 0, # default: 0
corpus_directory => $corpus_dir,
file_types => ['.txt', '.java'],
lsa_svd_threshold => 0.05, # Used for rejecting singular
# values that are smaller than
# this threshold fraction of
# the largest singular value.
min_word_length => 4,
query_file => $query_file,
relevancy_file => $relevancy_file, # Relevancy judgments
# are deposited in
# this file.
relevancy_threshold => 5, # Used when estimating relevancies
# with the method
# estimate_doc_relevancies(). A
# doc must have at least this
# number of query words to be
# considered relevant.
examples/calculate_precision_and_recall_for_VSM.pl view on Meta::CPAN
# must be as shown in test_queries.txt
my $relevancy_file = "relevancy.txt"; # The generated relevancies will
# be stored in this file.
my $vsm = Algorithm::VSM->new(
break_camelcased_and_underscored => 1, #default: 1
case_sensitive => 0, # default: 0
corpus_directory => $corpus_dir,
file_types => ['.txt', '.java'],
min_word_length => 4,
query_file => $query_file,
relevancy_file => $relevancy_file, # Relevancy judgments
# are deposited in
# this file.
relevancy_threshold => 5, # Used when estimating relevancies
# with the method
# estimate_doc_relevancies(). A
# doc must have at least this
# number of query words to be
# considered relevant.
examples/calculate_precision_and_recall_from_file_based_relevancies_for_LSA.pl view on Meta::CPAN
my $lsa = Algorithm::VSM->new(
break_camelcased_and_underscored => 1, # default: 1
case_sensitive => 0, # default: 0
corpus_directory => $corpus_dir,
file_types => ['.txt', '.java'],
lsa_svd_threshold => 0.01, # Used for rejecting singular
# values that are smaller than
# this threshold fraction of
# the largest singular value.
min_word_length => 4,
query_file => $query_file,
relevancy_file => $relevancy_file,
stop_words_file => $stop_words_file,
want_stemming => 1, # default: 0
);
$lsa->get_corpus_vocabulary_and_word_counts();
$lsa->generate_document_vectors();
examples/calculate_precision_and_recall_from_file_based_relevancies_for_VSM.pl view on Meta::CPAN
# must be as shown in test_queries.txt
my $relevancy_file = "relevancy.txt"; # The humans-supplied relevancies
# will be read from this file.
my $vsm = Algorithm::VSM->new(
break_camelcased_and_underscored => 1, # default: 1
case_sensitive => 0, # default: 0
corpus_directory => $corpus_dir,
file_types => ['.txt', '.java'],
min_word_length => 4,
query_file => $query_file,
relevancy_file => $relevancy_file,
stop_words_file => $stop_words_file,
want_stemming => 1, # default: 0
);
$vsm->get_corpus_vocabulary_and_word_counts();
$vsm->generate_document_vectors();
examples/calculate_similarity_matrix_for_all_docs.pl view on Meta::CPAN
use Text::CSV;
my $corpus_dir = "minicorpus";
my $stop_words_file = "stop_words.txt";
my $vsm = Algorithm::VSM->new(
break_camelcased_and_underscored => 1, # default: 1
case_sensitive => 0, # default: 0
corpus_directory => $corpus_dir,
file_types => ['.txt', '.java'],
min_word_length => 4,
stop_words_file => $stop_words_file,
want_stemming => 1, # default: 0
);
$vsm->get_corpus_vocabulary_and_word_counts();
$vsm->generate_document_vectors();
# If you would like to directly measure the similarity between two
# specific documents, uncomment the following two statements.
examples/calculate_similarity_matrix_for_all_normalized_docs.pl view on Meta::CPAN
use Text::CSV;
my $corpus_dir = "minicorpus";
my $stop_words_file = "stop_words.txt";
my $vsm = Algorithm::VSM->new(
break_camelcased_and_underscored => 1, # default: 1
case_sensitive => 0, # default: 0
corpus_directory => $corpus_dir,
file_types => ['.txt', '.java'],
min_word_length => 4,
stop_words_file => $stop_words_file,
want_stemming => 1, # default: 0
);
$vsm->get_corpus_vocabulary_and_word_counts();
$vsm->generate_document_vectors();
# If you would like to directly measure the similarity between two
# specific documents, uncomment the following two statements.
# Obviously, you will have to change the arguments to suit your needs.
examples/continuously_running_VSM_retrieval_engine.pl view on Meta::CPAN
my $stop_words_file = "stop_words.txt"; # This file will typically include the
# keywords of the programming
# language(s) used in the software.
my $vsm = Algorithm::VSM->new(
break_camelcased_and_underscored => 1, # default: 1
case_sensitive => 0, # default: 0
corpus_directory => $corpus_dir,
file_types => ['.txt', '.java'],
max_number_retrievals => 10,
min_word_length => 4,
stop_words_file => $stop_words_file,
use_idf_filter => 1,
want_stemming => 1, # default: 0
);
$vsm->get_corpus_vocabulary_and_word_counts();
$vsm->generate_document_vectors();
while (1) {
print "\nEnter your query in the next line (or just press `Enter' to exit):\n\n";
my $query_string = <STDIN>;
$query_string =~ s/\r?\n?$//;
$query_string =~ s/(^\s*)|(\s*$)//g;
die "... exiting: $!" if length($query_string) == 0;
my @query = grep $_, split /\s+/, $query_string;
my $retrievals = eval {
$vsm->retrieve_with_vsm( \@query );
};
if ($@) {
print "$@\n";
} else {
$vsm->display_retrievals( $retrievals );
}
}
examples/corpus/AbstractShapeIncremental.java view on Meta::CPAN
class Test {
public static void main( String[] args )
{
Shape[] shapes = new Shape[ 3 ];
shapes[0] = new Circle( 2.0 );
shapes[1] = new Rectangle( 1.0, 3.0 );
shapes[2] = new Rectangle( 4.0, 2.0 );
double total_area = 0;
for (int i=0; i < shapes.length; i++ )
total_area += shapes[i].area();
System.out.println("Total area = " + total_area);
}
}
examples/corpus/AddArray.java view on Meta::CPAN
public static void main( String[] args ) //(B)
{
int[] data = { 0, 1, 2, 3, 4, 5, 9, 8, 7, 6 }; //(C)
System.out.println( "The sum is: " //(D)
+ addArray(data) );
}
public static int addArray( int[] a ) { //(E)
int sum = 0;
for ( int i=0; i < a.length; i++ )
sum += a[i];
return sum;
}
}
examples/corpus/ArrayBasic.java view on Meta::CPAN
int age;
public User( String nam, int yy ) {
name = nam;
age = yy;
}
}
class Test {
public static void main( String[] args ) {
User[] user_list = new User[ 4 ];
for ( int i=0; i<user_list.length; i++ )
System.out.print( user_list[ i ] + " " );
// null null null null
}
}
examples/corpus/ArraysFill.java view on Meta::CPAN
//ArraysFill.java
import java.util.*;
class Test {
public static void main( String[] args ) {
int[] intArr = new int[4];
Arrays.fill( intArr, 99 ); //(A)
for ( int i=0; i<intArr.length; i++ )
System.out.print( intArr[ i ] + " " ); // 99 99 99 99
System.out.println();
double[] dbArr = new double[4];
Arrays.fill( dbArr, 2, 3, 9.9 ); //(B)
for ( int i=0; i<dbArr.length; i++ )
System.out.print( dbArr[ i ] + " " ); // 0.0 0.0 9.9 0.0
System.out.println();
int pos = Arrays.binarySearch( dbArr, 9.9 ); //(C)
System.out.println( pos ); // 2
}
}
examples/corpus/ArraysShuffle.java view on Meta::CPAN
//ArraysShuffle.java
import java.util.*;
class Test {
public static void main( String[] args ) {
Integer[] intArr2 = new Integer[10]; //(A)
for ( int i=0; i<intArr2.length; i++ ) //(B)
intArr2[i] = new Integer(i);
List list = Arrays.asList( intArr2 ); //(C)
Collections.shuffle( list ); //(D)
Integer[] intArr3 = (Integer[]) list.toArray(); //(E)
for ( int i=0; i<intArr2.length; i++ ) //(F)
System.out.print( intArr3[ i ].intValue() + " " );
// 9 8 5 1 3 4 7 2 6 0 (different with each run)
System.out.println();
}
}
examples/corpus/CloneArray.java view on Meta::CPAN
public Object clone() throws CloneNotSupportedException { //(B)
X xob = null;
xob = (X) super.clone();
//now clone the array separately:
xob.arr = (int[]) arr.clone(); //(C)
return xob;
}
public String toString() {
String printstring = "";
for (int i=0; i<arr.length; i++) printstring += " " + arr[i];
return printstring;
}
public static void main( String[] args ) throws Exception {
X xobj = new X();
X xobj_clone = (X) xobj.clone(); //(D)
System.out.println( xobj ); // 0 4 5 2 5
System.out.println( xobj_clone ); // 0 4 5 2 5
examples/corpus/CloneClassTypeArr.java view on Meta::CPAN
}
public String toString() { return x + ""; }
}
class Z implements Cloneable {
public Y[] yarr;
public Z( Y[] arr ) { this.yarr = arr; }
public Object clone() throws CloneNotSupportedException { //(A)
Z zclone = (Z) super.clone();
// zclone.yarr = ( Y[] ) yarr.clone(); // WRONG //(B)
Y[] yarrClone = new Y[ yarr.length ]; //(C)
for (int i=0; i < yarr.length; i++ )
yarrClone[i] = (Y) yarr[i].clone(); //(D)
zclone.yarr = yarrClone; //(E)
return zclone;
}
public String toString() {
String superString = "";
for ( int i = 0; i < yarr.length; i++ ) {
superString += yarr[i] + " ";
}
return superString;
}
}
class Test {
public static void main( String[] args ) throws Exception
{
examples/corpus/CrazyWindow.java view on Meta::CPAN
contentPane.setLayout(new GridLayout(1, 2));
panel1 = new MyTextPanel(); //(C)
panel2 = new MyDrawPanel(); //(D)
contentPane.add( panel1 );
contentPane.add( panel2 );
setContentPane( contentPane );
}
class MyTextPanel extends JPanel {
class MyDocumentListener implements DocumentListener { //(E)
int lengthText;
StringBuffer word = new StringBuffer(""); //(F)
public void insertUpdate( DocumentEvent e ) { //(G)
Document doc = (Document) e.getDocument();
try {
lengthText = doc.getLength();
String currentChar =
doc.getText( lengthText - 1, 1 );
char ch =
currentChar.charAt( currentChar.length() - 1 );
if ( currentChar.equals( " " ) || ch == '\n' ) {
if ( word.toString().equals( "red" ) ) { //(H)
panel2.drawColoredSquare( "red" ); //(I)
}
if ( word.toString().equals( "green" ) ) {
panel2.drawColoredSquare( "green" );
}
if ( word.toString().equals( "blue" ) ) {
panel2.drawColoredSquare( "blue" );
}
examples/corpus/CrazyWindow.java view on Meta::CPAN
}
else //(J)
word = word.append( currentChar );
} catch( BadLocationException bad ) {
bad.printStackTrace();
}
}
public void removeUpdate( DocumentEvent e ) { //(K)
try {
Document doc = (Document) e.getDocument();
lengthText = doc.getLength();
String currentChar =
doc.getText( lengthText - 1, 1 );
char ch =
currentChar.charAt( currentChar.length() - 1 );
if ( currentChar.equals( " " ) || ch == '\n' ) {
word = new StringBuffer(); //(L)
}
else if ( word.length() >= 1 )
word =
word.deleteCharAt( word.length() - 1 ); //(M)
} catch( BadLocationException bad ) {
bad.printStackTrace();
}
}
public void changedUpdate( DocumentEvent e ) {} //(N)
}
public MyTextPanel() {
JTextArea ta = new JTextArea( 100, 60);
ta.getDocument().addDocumentListener(
examples/corpus/EventThreadDemo.java view on Meta::CPAN
areaScrollPane, BorderLayout.CENTER );
frame.pack();
frame.setVisible( true );
keepBusy( 500, "main" ); //(A)
}
static class MyDocumentListener implements DocumentListener {
public void insertUpdate( final DocumentEvent e ) {
String str = null;
Document doc = e.getDocument();
int lengthText = doc.getLength();
try {
str = doc.getText( lengthText - 1, 1 );
} catch( BadLocationException badloc ) {
badloc.printStackTrace();
}
keepBusy( 500, "MyDocumentListener" ); //(B)
System.out.print( str );
}
public void removeUpdate(DocumentEvent e) { }
public void changedUpdate(DocumentEvent e) { }
}
examples/corpus/EventThreadDemo2.java view on Meta::CPAN
while ( System.currentTimeMillis() < curr + howLong )
;
}
}
////////////////////// class MyDocumentListener /////////////////////
class MyDocumentListener implements DocumentListener {
public void insertUpdate( final DocumentEvent e ) {
String str = null;
Document doc = e.getDocument();
int lengthText = doc.getLength();
try {
str = doc.getText( lengthText - 1, 1 );
} catch( BadLocationException badloc ) {
badloc.printStackTrace();
}
MyTools.printThreadInfo("From iniside the listener:");//(O)
MyTools.keepBusy( 500 );
System.out.print( str );
}
public void removeUpdate(DocumentEvent e) { }
public void changedUpdate(DocumentEvent e) { }
}
examples/corpus/ExtendedInterface.java view on Meta::CPAN
shapes[0] = dc;
shapes[1] = dr1;
shapes[2] = dr2;
drawScalables[0] = dc;
drawScalables[1] = dr1;
drawScalables[2] = dr2;
int total_area = 0;
DrawWindow dw = new DrawWindow();
for (int i = 0; i < shapes.length; i++ ) {
total_area += shapes[i].area();
drawScalables[i].setPosition( i*10.0, i*10.0 );
drawScalables[i].drawScaledShape( 2, dw );
}
System.out.println("Total area = " + total_area); //(E)
}
}
examples/corpus/FileCopy.java view on Meta::CPAN
import java.io.*; //(A)
class FileCopy { //(B)
public static void main( String[] args ) //(C)
{
int ch = 0;
FileInputStream in = null; //(D)
FileOutputStream out = null; //(E)
if ( args.length != 2 ) { //(F)
System.err.println( "usage: java FileCopy source dest" );
System.exit( 0 );
}
try {
in = new FileInputStream( args[0] ); //(G)
out = new FileOutputStream( args[1] ); //(H)
while ( true ) {
ch = in.read(); //(I)
if (ch == -1) break;
examples/corpus/FontFamilies.java view on Meta::CPAN
class FontFamilies extends JPanel {
public void paintComponent( Graphics g ) {
super.paintComponent( g );
g.translate( getInsets().left, getInsets().top );
GraphicsEnvironment ge =
GraphicsEnvironment.getLocalGraphicsEnvironment();
String[] fontList = ge.getAvailableFontFamilyNames();
Font defaultFont = g.getFont();
for (int i = 0; i < fontList.length; i++ ) {
g.setFont( defaultFont );
g.drawString( fontList[ i ], 10, i * 14 );
Font f = new Font( fontList[ i ], Font.PLAIN, 12 );
g.setFont( f );
g.drawString( "Purdue", 200 , i * 14 );
}
}
public static void main( String[] args ) {
JFrame f = new JFrame();
examples/corpus/Interleaved.java view on Meta::CPAN
String str = "";
if ( dogs != null ) {
str += "\nDOGS: ";
for ( int i=0; i<dogs.size(); i++ ) {
str += (Dog) dogs.elementAt(i);
}
str += "\n";
}
if ( autos != null ) {
str += "\nAUTOS: ";
for ( int i=0; i<autos.length - 1; i++ ) {
str += " " + autos[i] + ",";
}
str += " " + autos[autos.length - 1];
str += "\n";
}
if ( friends != null ) {
str += "\nFRIENDS:";
for ( int i=0; i<friends.length; i++ ) {
str += "\n";
str += friends[i].getFirstName();
str += " " + friends[i].getLastName();
}
str += "\n";
}
if ( kitty != null ) {
str += "\nCAT:";
str += kitty;
}
examples/corpus/Manager.java view on Meta::CPAN
String str = "";
if ( dogs != null ) {
str += "\nDOGS: ";
ListIterator iter = dogs.listIterator();
while ( iter.hasNext() )
str += (Dog) iter.next();
str += "\n";
}
if ( autos != null ) {
str += "\nAUTOS: ";
for ( int i=0; i<autos.length - 1; i++ ) {
str += " " + autos[i] + ",";
}
str += " " + autos[autos.length - 1];
str += "\n";
}
if ( friends != null ) {
str += "\nFRIENDS:";
for ( int i=0; i<friends.length; i++ ) {
str += "\n";
str += friends[i].getFirstName();
str += " " + friends[i].getLastName();
}
str += "\n";
}
if ( kitty != null ) {
str += "\nCAT:";
str += kitty;
}
examples/corpus/MultiPolymorphism.java view on Meta::CPAN
shapes[0] = dc;
shapes[1] = dr1;
shapes[2] = dr2;
drawables[0] = dc;
drawables[1] = dr1;
drawables[2] = dr2;
int total_area = 0;
DrawWindow dw = new DrawWindow();
for (int i = 0; i < shapes.length; i++ ) {
total_area += shapes[i].area();
drawables[i].setPosition( i*10.0, i*10.0 ); //(C)
drawables[i].draw( dw ); //(D)
}
System.out.println("Total area = " + total_area); //(E)
}
}
examples/corpus/RenderGraphics.java view on Meta::CPAN
width = getWidth();
height = getHeight();
int stringY = height - 10;
rectWidth = width - 20;
rectHeight = stringY - maxCharHeight - 10;
int x2Points[] =
{10, 10+rectWidth, 10, 10+rectWidth};
int y2Points[] =
{10, 10+rectHeight, 10+rectHeight, 10};
g.drawPolyline(x2Points,
y2Points, x2Points.length); //(F)
g.drawString("drawPolyline", 10, stringY); //(G)
}
});
//rounded rectangle:
contentPane.add( new JPanel() {
public void paintComponent(Graphics g) {
super.paintComponent(g);
width = getWidth();
height = getHeight();
examples/corpus/StringFind.java view on Meta::CPAN
class StringFind {
public static void main( String[] args ) {
StringBuffer strbuf = new StringBuffer(
"one hello is like any other hello" );
String searchString = "hello";
String replacementString = "armadillo";
int pos = 0;
while ( ( pos = (new String(strbuf)).indexOf(
searchString, pos ) ) != -1 ) {
strbuf.replace( pos, pos +
searchString.length(), replacementString );
pos++;
}
System.out.println( strbuf );
}
}
examples/corpus/StringSort.java view on Meta::CPAN
import java.util.*;
class StringSort {
public static void main( String[] args ) {
String[] strArr = { "apples", "bananas", "Apricots", "Berries",
"oranges", "Oranges", "APPLES", "peaches" };
String[] strArr2 = strArr;
System.out.println("Case sensitive sort :" );
Arrays.sort( strArr );
for (int i=0; i<strArr.length; i++)
System.out.println( strArr[i] );
System.out.println("\nCase insensitive sort:" );
Arrays.sort( strArr2, String.CASE_INSENSITIVE_ORDER );
for (int i=0; i<strArr2.length; i++)
System.out.println( strArr2[i] );
}
}
examples/corpus/WindowWithMenu.java view on Meta::CPAN
}
if ( arg.equals( "Save" ) ) {
saveDialog.setDirectory(".");
saveDialog.show();
filename = saveDialog.getFile();
String superString = ta.getText(); //(L)
if (filename != null) {
try {
FileOutputStream fout =
new FileOutputStream( filename );
for (int i=0; i<superString.length(); i++)
fout.write( superString.charAt(i) ); //(M)
fout.close();
} catch( IOException e ) {
System.out.println( "IO error" );
}
}
}
}
public static void main(String[] args){
examples/corpus_with_java_and_cpp/AbstractShapeIncremental.java view on Meta::CPAN
class Test {
public static void main( String[] args )
{
Shape[] shapes = new Shape[ 3 ];
shapes[0] = new Circle( 2.0 );
shapes[1] = new Rectangle( 1.0, 3.0 );
shapes[2] = new Rectangle( 4.0, 2.0 );
double total_area = 0;
for (int i=0; i < shapes.length; i++ )
total_area += shapes[i].area();
System.out.println("Total area = " + total_area);
}
}
examples/corpus_with_java_and_cpp/AddArray.java view on Meta::CPAN
public static void main( String[] args ) //(B)
{
int[] data = { 0, 1, 2, 3, 4, 5, 9, 8, 7, 6 }; //(C)
System.out.println( "The sum is: " //(D)
+ addArray(data) );
}
public static int addArray( int[] a ) { //(E)
int sum = 0;
for ( int i=0; i < a.length; i++ )
sum += a[i];
return sum;
}
}
examples/corpus_with_java_and_cpp/ArrayBasic.java view on Meta::CPAN
int age;
public User( String nam, int yy ) {
name = nam;
age = yy;
}
}
class Test {
public static void main( String[] args ) {
User[] user_list = new User[ 4 ];
for ( int i=0; i<user_list.length; i++ )
System.out.print( user_list[ i ] + " " );
// null null null null
}
}
( run in 0.413 second using v1.01-cache-2.11-cpan-65fba6d93b7 )