From e621502ba37e95d9002c1582e5a08b42e97d4742 Mon Sep 17 00:00:00 2001
From: yabetancourt <yadierbetanc@gmail.com>
Date: Mon, 8 Dec 2025 16:28:15 +0100
Subject: [PATCH] BAEL-9501 Cosine similarity implementation

---
 algorithms-modules/algorithms-numeric/pom.xml | 12 +++
 .../CosineSimilarityUnitTest.java             | 80 +++++++++++++++++++
 2 files changed, 92 insertions(+)
 create mode 100644 algorithms-modules/algorithms-numeric/src/test/java/com/baeldung/algorithms/cosinesimilarity/CosineSimilarityUnitTest.java

diff --git a/algorithms-modules/algorithms-numeric/pom.xml b/algorithms-modules/algorithms-numeric/pom.xml
index 444a3ccd19e7..968ce788a1b6 100644
--- a/algorithms-modules/algorithms-numeric/pom.xml
+++ b/algorithms-modules/algorithms-numeric/pom.xml
@@ -24,10 +24,22 @@
             <artifactId>jmh-generator-annprocess</artifactId>
             <version>${jmh.version}</version>
         </dependency>
+        <dependency>
+            <groupId>org.nd4j</groupId>
+            <artifactId>nd4j-api</artifactId>
+            <version>${nd4j.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.nd4j</groupId>
+            <artifactId>nd4j-native</artifactId>
+            <version>${nd4j.version}</version>
+            <scope>runtime</scope>
+        </dependency>
     </dependencies>
 
     <properties>
         <jmh.version>1.35</jmh.version>
+        <nd4j.version>1.0.0-M2.1</nd4j.version>
     </properties>
 
 </project>
\ No newline at end of file
diff --git a/algorithms-modules/algorithms-numeric/src/test/java/com/baeldung/algorithms/cosinesimilarity/CosineSimilarityUnitTest.java b/algorithms-modules/algorithms-numeric/src/test/java/com/baeldung/algorithms/cosinesimilarity/CosineSimilarityUnitTest.java
new file mode 100644
index 000000000000..ec7fe65a50bb
--- /dev/null
+++ b/algorithms-modules/algorithms-numeric/src/test/java/com/baeldung/algorithms/cosinesimilarity/CosineSimilarityUnitTest.java
@@ -0,0 +1,80 @@
+package com.baeldung.algorithms.cosinesimilarity;
+
+import org.junit.jupiter.api.Test;
+import org.nd4j.linalg.api.ndarray.INDArray;
+import org.nd4j.linalg.api.ops.impl.reduce3.CosineSimilarity;
+import org.nd4j.linalg.factory.Nd4j;
+
+import java.util.Arrays;
+import java.util.stream.IntStream;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+public class CosineSimilarityUnitTest {
+
+    static final double[] VECTOR_A = {3, 4};
+    static final double[] VECTOR_B = {5, 12};
+    static final double EXPECTED_SIMILARITY = 0.9692307692307692;
+
+    static double calculateCosineSimilarity(double[] vectorA, double[] vectorB) {
+        if (vectorA == null || vectorB == null || vectorA.length != vectorB.length || vectorA.length == 0) {
+            throw new IllegalArgumentException("Vectors must be non-null, non-empty, and of the same length.");
+        }
+        double dotProduct = 0.0;
+        double magnitudeA = 0.0;
+        double magnitudeB = 0.0;
+        for (int i = 0; i < vectorA.length; i++) {
+            dotProduct += vectorA[i] * vectorB[i];
+            magnitudeA += vectorA[i] * vectorA[i];
+            magnitudeB += vectorB[i] * vectorB[i];
+        }
+        double finalMagnitudeA = Math.sqrt(magnitudeA);
+        double finalMagnitudeB = Math.sqrt(magnitudeB);
+        if (finalMagnitudeA == 0.0 || finalMagnitudeB == 0.0) {
+            return 0.0;
+        }
+        return dotProduct / (finalMagnitudeA * finalMagnitudeB);
+    }
+
+    public static double calculateCosineSimilarityWithStreams(double[] vectorA, double[] vectorB) {
+        if (vectorA == null || vectorB == null || vectorA.length != vectorB.length || vectorA.length == 0) {
+            throw new IllegalArgumentException("Vectors must be non-null, non-empty, and of the same length.");
+        }
+
+        double dotProduct = IntStream.range(0, vectorA.length).mapToDouble(i -> vectorA[i] * vectorB[i]).sum();
+        double magnitudeA = Arrays.stream(vectorA).map(v -> v * v).sum();
+        double magnitudeB = IntStream.range(0, vectorA.length).mapToDouble(i -> vectorB[i] * vectorB[i]).sum();
+        double finalMagnitudeA = Math.sqrt(magnitudeA);
+        double finalMagnitudeB = Math.sqrt(magnitudeB);
+        if (finalMagnitudeA == 0.0 || finalMagnitudeB == 0.0) {
+            return 0.0;
+        }
+
+        return dotProduct / (finalMagnitudeA * finalMagnitudeB);
+    }
+
+    @Test
+    void givenTwoHighlySimilarVectors_whenCalculatedNatively_thenReturnsHighSimilarityScore() {
+        double actualSimilarity = calculateCosineSimilarity(VECTOR_A, VECTOR_B);
+        assertEquals(EXPECTED_SIMILARITY, actualSimilarity, 1e-15);
+    }
+
+    @Test
+    void givenTwoHighlySimilarVectors_whenCalculatedNativelyWithStreams_thenReturnsHighSimilarityScore() {
+        double actualSimilarity = calculateCosineSimilarityWithStreams(VECTOR_A, VECTOR_B);
+        assertEquals(EXPECTED_SIMILARITY, actualSimilarity, 1e-15);
+    }
+
+    @Test
+    void givenTwoHighlySimilarVectors_whenCalculatedNativelyWithCommonsMath_thenReturnsHighSimilarityScore() {
+
+        INDArray vec1 = Nd4j.create(VECTOR_A);
+        INDArray vec2 = Nd4j.create(VECTOR_B);
+
+        CosineSimilarity cosSim = new CosineSimilarity(vec1, vec2);
+        double actualSimilarity = Nd4j.getExecutioner().exec(cosSim).getDouble(0);
+
+        assertEquals(EXPECTED_SIMILARITY, actualSimilarity, 1e-15);
+    }
+
+}
\ No newline at end of file