[incubator-datasketches-java] 01/01: terminology, efficiency, restored test

[al...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

alsay pushed a commit to branch jaccard_similarity_changes
in repository https://gitbox.apache.org/repos/asf/incubator-datasketches-java.git

commit 6be785e9ca1bf42374603ab56570ab88d881d2f2
Author: AlexanderSaydakov <Al...@users.noreply.github.com>
AuthorDate: Mon Sep 21 17:40:40 2020 -0700

    terminology, efficiency, restored test
---
 .../org/apache/datasketches/theta/JaccardSimilarity.java     | 12 ++++++------
 .../org/apache/datasketches/theta/JaccardSimilarityTest.java |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/src/main/java/org/apache/datasketches/theta/JaccardSimilarity.java b/src/main/java/org/apache/datasketches/theta/JaccardSimilarity.java
index 9738c60..8abea88 100644
--- a/src/main/java/org/apache/datasketches/theta/JaccardSimilarity.java
+++ b/src/main/java/org/apache/datasketches/theta/JaccardSimilarity.java
@@ -38,7 +38,7 @@ public final class JaccardSimilarity {
   private static final double[] ONES = {1.0, 1.0, 1.0};
 
   /**
-   * Computes the Jaccard similarity ratio with upper and lower bounds. The Jaccard similarity ratio
+   * Computes the Jaccard similarity index with upper and lower bounds. The Jaccard similarity index
    * <i>J(A,B) = (A ^ B)/(A U B)</i> is used to measure how similar the two sketches are to each
    * other. If J = 1.0, the sketches are considered equal. If J = 0, the two sketches are
    * distinct from each other. A Jaccard of .95 means the overlap between the two
@@ -49,7 +49,7 @@ public final class JaccardSimilarity {
    *
    * @param sketchA given sketch A
    * @param sketchB given sketch B
-   * @return a double array {LowerBound, Estimate, UpperBound} of the Jaccard ratio.
+   * @return a double array {LowerBound, Estimate, UpperBound} of the Jaccard index.
    * The Upper and Lower bounds are for a confidence interval of 95.4% or +/- 2 standard deviations.
    */
   public static double[] jaccard(final Sketch sketchA, final Sketch sketchB) {
@@ -70,7 +70,7 @@ public final class JaccardSimilarity {
         SetOperation.builder().setNominalEntries(newK).buildUnion();
     union.update(sketchA);
     union.update(sketchB);
-    final Sketch unionAB = union.getResult();
+    final Sketch unionAB = union.getResult(false, null);
     final long thetaLongUAB = unionAB.getThetaLong();
     final long thetaLongA = sketchA.getThetaLong();
     final long thetaLongB = sketchB.getThetaLong();
@@ -87,7 +87,7 @@ public final class JaccardSimilarity {
     inter.intersect(sketchA);
     inter.intersect(sketchB);
     inter.intersect(unionAB); //ensures that intersection is a subset of the union
-    final Sketch interABU = inter.getResult(true, null);
+    final Sketch interABU = inter.getResult(false, null);
 
     final double lb = getLowerBoundForBoverA(unionAB, interABU);
     final double est = getEstimateOfBoverA(unionAB, interABU);
@@ -134,7 +134,7 @@ public final class JaccardSimilarity {
 
   /**
    * Tests similarity of a measured Sketch against an expected Sketch.
-   * Computes the lower bound of the Jaccard ratio <i>J<sub>LB</sub></i> of the measured and
+   * Computes the lower bound of the Jaccard index <i>J<sub>LB</sub></i> of the measured and
    * expected sketches.
    * if <i>J<sub>LB</sub> &ge; threshold</i>, then the sketches are considered to be
    * similar with a confidence of 97.7%.
@@ -156,7 +156,7 @@ public final class JaccardSimilarity {
 
   /**
    * Tests dissimilarity of a measured Sketch against an expected Sketch.
-   * Computes the upper bound of the Jaccard ratio <i>J<sub>LB</sub></i> of the measured and
+   * Computes the upper bound of the Jaccard index <i>J<sub>UB</sub></i> of the measured and
    * expected sketches.
    * if <i>J<sub>UB</sub> &le; threshold</i>, then the sketches are considered to be
    * dissimilar with a confidence of 97.7%.
diff --git a/src/test/java/org/apache/datasketches/theta/JaccardSimilarityTest.java b/src/test/java/org/apache/datasketches/theta/JaccardSimilarityTest.java
index a069c7d..fe350c2 100644
--- a/src/test/java/org/apache/datasketches/theta/JaccardSimilarityTest.java
+++ b/src/test/java/org/apache/datasketches/theta/JaccardSimilarityTest.java
@@ -208,7 +208,7 @@ public class JaccardSimilarityTest {
     double[] jResults = JaccardSimilarity.jaccard(measured, expected);
     boolean state = JaccardSimilarity.dissimilarityTest(measured, expected, threshold);
     println(state + "\t" + jaccardString(jResults));
-    //assertTrue(state);
+    assertTrue(state);
   }
 
   private static String jaccardString(double[] jResults) {


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@datasketches.apache.org
For additional commands, e-mail: commits-help@datasketches.apache.org