Make sklearn.metrics.pairwise.cosine_similarity optionally return sparse output.

cossim.py

#! /usr/bin/env python
# -*- coding: utf-8 -*-
# vim:fenc=utf-8
#
# Copyright © 2015 jaidev <jaidev@newton>
#
# Distributed under terms of the MIT license.

from sklearn.metrics.pairwise import check_pairwise_arrays
from sklearn.preprocessing import normalize
from sklearn.utils.extmath import safe_sparse_dot


def cosine_similarity(X, Y=None, dense_output=True):
    X, Y = check_pairwise_arrays(X, Y)

    X_normalized = normalize(X, copy=True)
    if X is Y:
        Y_normalized = X_normalized
    else:
        Y_normalized = normalize(Y, copy=True)

    K = safe_sparse_dot(X_normalized, Y_normalized.T, dense_output=dense_output)

    return K