Cosine Similarity Matrix

Problem

Given a matrix X whose rows are vectors, return the Gram-style cosine similarity matrix:

S[i][j] = (X[i] . X[j]) / (||X[i]||_2 * ||X[j]||_2)

If either row is the zero vector, set the corresponding entry to 0.0.

Hint

Compute pairwise cosine similarities; the diagonal is 1 for nonzero rows.

case 1

in: [[[1,0],[0,1]]]

expected: [[1,0],[0,1]]

case 2

in: [[[1,0],[1,0]]]

expected: [[1,1],[1,1]]

case 3

in: [[[1,1],[1,-1]]]

expected: [[1,0],[0,1]]

case 4

in: [[[0,0],[1,1]]]

expected: [[0,0],[0,1]]

Starter codePython

def cosine_similarity_matrix(X):
    # Your code here
    pass

4 test cases · run your code against them in the editor