def jaccard(stra, strb, tokenizer=None):
""" Return the jaccard distance between stra and strb, condering the tokens
set of stra and strb. If no tokenizer is given, it use if
alignement.normalize.tokenize's default one.
J(A, B) = (A \cap B)/(A \cup B)
d(A, B) = 1 - J(A, B)
"""
seta = set(tokenize(stra, tokenizer))
setb = set(tokenize(strb, tokenizer))
return generic_jaccard(seta, setb)
def _handlespaces(stra, strb, distance, tokenizer=None, **kwargs):
""" Compute the matrix of distances between all tokens of stra and strb
(with function ``distance``). Extra args are given to the distance
function
The distance returned is defined as the max of the min of each rows of
each distance matrix, see the example above :
| Victor | Hugo Victor | Jean | Hugo
Victor | 0 | 5 Victor | 0 | 6 | 5
Jean | 6 | 4 Hugo | 5 | 4 | 0
Hugo | 5 | 0
--> 4 --> 0
Return 4
"""
if ' ' not in stra:
stra += ' '
if ' ' not in strb:
strb += ' '
toka = tokenize(stra, tokenizer)
tokb = tokenize(strb, tokenizer)
# If not same number of tokens, complete the smallest list with empty strings
if len(toka) != len(tokb):
mint = toka if len(toka)<len(tokb) else tokb
maxt = toka if len(toka)>len(tokb) else tokb
mint.extend(['' for i in range(len(maxt)-len(mint))])
listmatrix = []
for i in xrange(len(toka)):
listmatrix.append([distance(toka[i], tokb[j], **kwargs) for j in xrange(len(tokb))])
m = matrix(listmatrix)
minlist = [m[i,:].min() for i in xrange(m.shape[0])]
minlist.extend([m[:,i].min() for i in xrange(m.shape[1])])
return max(minlist)
def test_tokenize(self):
self.assertEqual(tokenize(u"J'aime les frites !"),
[u"J'", u'aime', u'les', u'frites', u'!',])
