Added support for SparseDoubleVector

Author: tdebatty

pom.xml

@@ -22,6 +22,7 @@
             <url>http://www.opensource.org/licenses/mit-license.php</url>
         </license>
     </licenses>
+    
     <developers>
         <developer>
             <name>Thibault Debatty</name>
@@ -30,6 +31,7 @@
             <organizationUrl>http://debatty.info</organizationUrl>
         </developer>
     </developers>
+    
     <scm>
         <connection>scm:git:git@github.com:tdebatty/java-LSH.git</connection>
         <developerConnection>scm:git:git@github.com:tdebatty/java-LSH.git</developerConnection>
@@ -136,7 +138,7 @@
         <dependency>
             <groupId>${project.groupId}</groupId>
             <artifactId>java-string-similarity</artifactId>
-            <version>0.11</version>
+            <version>0.12</version>
         </dependency>
     </dependencies>
 </project>

src/main/java/info/debatty/java/lsh/LSHSuperBit.java

@@ -24,6 +24,7 @@
 
 package info.debatty.java.lsh;
 
+import info.debatty.java.utils.SparseDoubleVector;
 import info.debatty.java.utils.SparseIntegerVector;
 import java.io.Serializable;
 
@@ -50,7 +51,7 @@ public class LSHSuperBit extends LSH implements Serializable {
      * @param b buckets (per stage)
      * @param n dimensionality
      */
-    public LSHSuperBit(int s, int b, int n) {
+    public LSHSuperBit(int s, int b, int n) throws Exception {
         super(s, b, n);
 
         // SuberBit code length
@@ -62,6 +63,10 @@ public LSHSuperBit(int s, int b, int n) {
             }
         }
 
+        if (superbit == 0) {
+            throw new Exception("Superbit is 0 with parameters: s=" + s + " b=" + b + " n=" + n);
+        }
+        
         this.sb = new SuperBit(n, superbit, K/superbit);
     }
 
@@ -82,6 +87,10 @@ public int[] hash(SparseIntegerVector vector){
         return hashSignature(sb.signature(vector));
     }
 
+    public int[] hash(SparseDoubleVector vector) {
+        return hashSignature(sb.signature(vector));
+    }
+    
     /**
      * Hash (bin) a vector in s stages into b buckets
      * @param vector

src/main/java/info/debatty/java/lsh/SuperBit.java

@@ -24,6 +24,7 @@
 
 package info.debatty.java.lsh;
 
+import info.debatty.java.utils.SparseDoubleVector;
 import info.debatty.java.utils.SparseIntegerVector;
 import java.io.Serializable;
 import java.util.Random;
@@ -157,6 +158,14 @@ public boolean[] signature(SparseIntegerVector vector) {
         return sig;
     }
 
+    public boolean[] signature(SparseDoubleVector vector) {
+        boolean[] sig = new boolean[this.hyperplanes.length];
+        for (int i = 0; i < this.hyperplanes.length; i++) {
+            sig[i] = (vector.dotProduct(this.hyperplanes[i]) >= 0);
+        }
+        return sig;
+    }
+    
     /**
      * Compute the signature of this vector
      * @param vector

src/main/java/info/debatty/java/lsh/examples/LSHSuperBitExample.java

@@ -26,6 +26,8 @@
 
 import info.debatty.java.lsh.LSHSuperBit;
 import java.util.Random;
+import java.util.logging.Level;
+import java.util.logging.Logger;
 
 /**
  *
@@ -37,36 +39,40 @@ public class LSHSuperBitExample {
      * @param args the command line arguments
      */
     public static void main(String[] args) {
-        int count = 100;
 
-        // R^n
-        int n = 3;
-        
-        int stages = 2;
-        int buckets = 4;
-        
-        // Produce some vectors in R^n
-        Random r = new Random();
-        double[][] vectors = new double[count][];
-        for (int i = 0; i < count; i++) {
-            vectors[i] = new double[n];
+            int count = 100;
+            
+            // R^n
+            int n = 3;
+            
+            int stages = 2;
+            int buckets = 4;
 
-            for (int j = 0; j < n; j++) {
-                vectors[i][j] = r.nextGaussian();
+            // Produce some vectors in R^n
+            Random r = new Random();
+            double[][] vectors = new double[count][];
+            for (int i = 0; i < count; i++) {
+                vectors[i] = new double[n];
+                
+                for (int j = 0; j < n; j++) {
+                    vectors[i][j] = r.nextGaussian();
+                }
             }
-        }
-        
-        LSHSuperBit lsh = new LSHSuperBit(stages, buckets, n);
-        
-        // Compute a SuperBit signature, and a LSH hash
-        for (int i = 0; i < count; i++) {
-            double[] vector = vectors[i];
-            int[] hash = lsh.hash(vector);
-            for (double v : vector) {
-                System.out.printf("%6.2f\t", v);
+        try {
+            LSHSuperBit lsh = new LSHSuperBit(stages, buckets, n);
+            
+            // Compute a SuperBit signature, and a LSH hash
+            for (int i = 0; i < count; i++) {
+                double[] vector = vectors[i];
+                int[] hash = lsh.hash(vector);
+                for (double v : vector) {
+                    System.out.printf("%6.2f\t", v);
+                }
+                System.out.print(hash[0]);
+                System.out.print("\n");
             }
-            System.out.print(hash[0]);
-            System.out.print("\n");
+        } catch (Exception ex) {
+            Logger.getLogger(LSHSuperBitExample.class.getName()).log(Level.SEVERE, null, ex);
         }
     }
 }