gistfile1.txt

from __future__ import division
import scipy.sparse as sp
from scipy.sparse.linalg import norm

def cosine_distance(vec1, vec2):
    norm1 = norm(vec1)
    norm2 = norm(vec2)
    
    return vec1.multiply(vec2).sum() / (norm1 * norm2)

def jaccard_index(vec1, vec2):
    bool_vec1 = (vec1 > 0).astype(int)
    bool_vec2 = (vec2 > 0).astype(int)
    
    intersect = bool_vec1.multiply(bool_vec2).sum()
    return intersect / (bool_vec1.sum() + bool_vec2.sum() - intersect)

def generalized_jaccard(vec1, vec2):
    return vec1.minimum(vec2).sum() / vec1.maximum(vec2).sum()