def median_word(words, word_counts):
median = lev.median(words, word_counts)
while True:
last_median = median
median = lev.median_improve(median, words, word_counts)
if median == last_median:
break
return median
def get_median(words, counts):
median = lev.median(words, counts)
# print median,
while True:
last_median = median
median = lev.median_improve(median, words, counts)
# print "-->", median,
if median == last_median:
break
return median
def median_string(self, strings, string_counts):
# Find a 'median string' which is a string with the minimal
# sum of edit distances to each string in a list of strings.
# see: https://pypi.python.org/pypi/python-Levenshtein/0.11.2
# Note the python package above also permits the use of
# weights for each string (e.g. counts of occurances)
median = Levenshtein.median(strings, string_counts)
while True:
last_median = median
median = Levenshtein.median_improve(median, strings, string_counts)
if median == last_median:
break
return median
