From 47ddba1d914bf5955a244056e794e718dee9ead1 Mon Sep 17 00:00:00 2001
From: Kushagra Makharia <KushagraMakharia@users.noreply.github.com>
Date: Sat, 29 Oct 2022 21:08:40 +0530
Subject: [PATCH] Added cosine similarity (#7001)

* Added cosine similarity

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
---
 machine_learning/similarity_search.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/machine_learning/similarity_search.py b/machine_learning/similarity_search.py
index 2f5fc46c0..72979181f 100644
--- a/machine_learning/similarity_search.py
+++ b/machine_learning/similarity_search.py
@@ -12,6 +12,7 @@ from __future__ import annotations
 import math
 
 import numpy as np
+from numpy.linalg import norm
 
 
 def euclidean(input_a: np.ndarray, input_b: np.ndarray) -> float:
@@ -135,6 +136,22 @@ def similarity_search(
     return answer
 
 
+def cosine_similarity(input_a: np.ndarray, input_b: np.ndarray) -> float:
+    """
+    Calculates cosine similarity between two data.
+    :param input_a: ndarray of first vector.
+    :param input_b: ndarray of second vector.
+    :return: Cosine similarity of input_a and input_b. By using math.sqrt(),
+             result will be float.
+
+    >>> cosine_similarity(np.array([1]), np.array([1]))
+    1.0
+    >>> cosine_similarity(np.array([1, 2]), np.array([6, 32]))
+    0.9615239476408232
+    """
+    return np.dot(input_a, input_b) / (norm(input_a) * norm(input_b))
+
+
 if __name__ == "__main__":
     import doctest