def compression_dist(x, y, l_x=None, l_y=None):
if x == y:
return 0
x_b = x.encode('utf-8')
y_b = y.encode('utf-8')
if l_x is None:
l_x = len(lzma.compress(x_b))
l_y = len(lzma.compress(y_b))
l_xy = len(lzma.compress(x_b + y_b))
l_yx = len(lzma.compress(y_b + x_b))
dist = try_divide(min(l_xy, l_yx) - min(l_x, l_y), max(l_x, l_y))
return dist
def lzma_ratio(a, b):
'''Similarity after compressed using lzma'''
if a == b:
return 1
a, b = a.encode('utf-8'), b.encode('utf-8')
a_len = len(lzma.compress(a))
b_len = len(lzma.compress(b))
ab_len = len(lzma.compress(a + b))
ba_len = len(lzma.compress(b + a))
ratio = 1 - try_divide(
min(ab_len, ba_len) - min(a_len, b_len), max(a_len, b_len))
return ratio
def cosine_distance(a, b):
return np.nan_to_num(
try_divide(np.dot(a, b),
np.linalg.norm(a) * np.linalg.norm(b)))
def dice_ratio(a, b):
a, b = set(a), set(b)
return try_divide(2 * len(a & b), len(a) + len(b))
def jaccard_ratio(a, b):
a, b = set(a), set(b)
c = a & b
return try_divide(len(c), len(a) + len(b) - len(c))
def longest_match_ratio(str1, str2):
sq = SequenceMatcher(lambda x: x == " ", str1, str2)
match = sq.find_longest_match(0, len(str1), 0, len(str2))
return try_divide(match.size, min(len(str1), len(str2)))