2つの疎行列（1*N）のユークリッド距離を求める関数

sparse_euclidean_distance.py

# -*- encoding: utf-8 -*-

import scipy.spatial.distance as dis
import scipy.sparse as sp
import numpy as np, scipy.io as io
import math

def sparse_distance(v1, v2):
    """1*Nのベクトル間のユークリッド距離を求める
    args:
        v1, v2 : 1 * N の(疎)行列
    """
    if not sp.issparse(v1) or not sp.issparse(v2):
        if v1.size != v2.size:
            raise ValueError
        return dis.euclidean(v1, v2)
    indexes1 = v1.rows.item()[:]
    indexes2 = v2.rows.item()[:]
    if len(indexes1) != len(indexes2):
        raise ValueError
    indexes = indexes1 + indexes2  # 2つのベクトルの疎でない所のindex
    euc_dis = 0.0
    for index in indexes:
        _dis = v1[0, index] - v2[0, index]
        euc_dis += _dis ** 2
    return math.sqrt(euc_dis)