def findMatch(line):
words = phrases.splitWord(line)
alphabets = phrases.get_english_phrase(words)
nonalphabets = phrases.generate_katakana_phrase(words)
romanized = []
for nonalphabet in nonalphabets:
romanized.append(to_romaji(nonalphabet))
dim = (len(alphabets), len(romanized))
similarity = numpy.zeros(dim)
for i in range(len(alphabets)):
for j in range(len(romanized)):
similarity[i][j] = Levenshtein.distance(
alphabets[i], romanized[j]) / (
float(min(len(alphabets[i]), len(romanized[j]))) + 1)
ans = []
# if dim[1] > 0:
# for i in range(dim[0]):
# #if min(similarity[i,:]) < 0.5:
# j = numpy.argmin(similarity[i,:])
# ans.append((alphabets[i],nonalphabets[j], similarity[i][j], line))
# return ans
for i in range(min(dim[0], dim[1])):
row_index = similarity.argmin() / similarity.shape[1]
col_index = similarity.argmin() % similarity.shape[1]
ans.append((alphabets[row_index], nonalphabets[col_index],
similarity[row_index, col_index], line))
del alphabets[row_index]
del nonalphabets[col_index]
similarity = numpy.delete(similarity, row_index, 0)
similarity = numpy.delete(similarity, col_index, 1)
return ans
def findMatch(line): words = phrases.splitWord(line) alphabets = phrases.get_english_phrase(words) nonalphabets = phrases.generate_katakana_phrase(words) romanized = [] for nonalphabet in nonalphabets: romanized.append(to_romaji(nonalphabet)) dim = (len(alphabets), len(romanized)) similarity = numpy.zeros(dim) for i in range(len(alphabets)): for j in range(len(romanized)): similarity[i][j] = Levenshtein.distance(alphabets[i],romanized[j]) / (float(min(len(alphabets[i]), len(romanized[j])))+1) ans = [] # if dim[1] > 0: # for i in range(dim[0]): # #if min(similarity[i,:]) < 0.5: # j = numpy.argmin(similarity[i,:]) # ans.append((alphabets[i],nonalphabets[j], similarity[i][j], line)) # return ans for i in range(min(dim[0], dim[1])): row_index = similarity.argmin() / similarity.shape[1] col_index = similarity.argmin() % similarity.shape[1] ans.append((alphabets[row_index],nonalphabets[col_index], similarity[row_index,col_index],line)) del alphabets[row_index] del nonalphabets[col_index] similarity = numpy.delete(similarity, row_index, 0) similarity = numpy.delete(similarity, col_index, 1) return ans
def findMatch(line): words = phrases.splitWord(line) alphabets = phrases.get_english_phrase(words) nonalphabets = phrases.generate_katakana_phrase(words) romanized = [] for nonalphabet in nonalphabets: romanized.append(romkan.to_roma(nonalphabet)) dim = (len(alphabets), len(romanized)) similarity = numpy.zeros(dim) for i in range(len(alphabets)): for j in range(len(romanized)): similarity[i][j] = distance.euclidean(vectorize(alphabets[i]),vectorize(romanized[j])) ans = [] if dim[1] > 0: for i in range(dim[0]): if min(similarity[i,:]) < 0.5: j = numpy.argmin(similarity[i,:]) ans.append((alphabets[i],nonalphabets[j], line)) return ans
def findMatch(line):
words = phrases.splitWord(line)
alphabets = phrases.get_english_phrase(words)
nonalphabets = phrases.generate_katakana_phrase(words)
romanized = []
for nonalphabet in nonalphabets:
romanized.append(romkan.to_roma(nonalphabet))
dim = (len(alphabets), len(romanized))
similarity = numpy.zeros(dim)
for i in range(len(alphabets)):
for j in range(len(romanized)):
similarity[i][j] = distance.euclidean(vectorize(alphabets[i]),
vectorize(romanized[j]))
ans = []
if dim[1] > 0:
for i in range(dim[0]):
if min(similarity[i, :]) < 0.5:
j = numpy.argmin(similarity[i, :])
ans.append((alphabets[i], nonalphabets[j], line))
return ans
