def GetScore(src_name, input_name, min_score):
src_name = src_name.translate(str.maketrans('', '', string.punctuation))
input_name = input_name.translate(
str.maketrans('', '', string.punctuation))
jarowinkler = JaroWinkler()
result = []
total_score_scr_part = 0
for input_name_part in input_name.split():
column = []
for src_name_part in src_name.split():
winkler_part = jarowinkler.similarity(
input_name_part, src_name_part)
difference = ParsedDifference(input_name_part, src_name_part)
avg = (winkler_part + difference) / 2
column.append(avg)
result.append(max(column))
full_inputted_jaro = jarowinkler.similarity(input_name, src_name)
score = Average(result)
if (full_inputted_jaro > score):
score = full_inputted_jaro
return score * 100
def fuzzy_line_equality_detection(self, lines):
new_lines = []
jarowinkler = JaroWinkler()
#Compare all lines against each other
for k in range(len(lines.split("\n"))):
max_sim = 0
for l in range(len(lines.split("\n"))):
if k == l: continue
jaro_sim = jarowinkler.similarity(
lines.split("\n")[k].lower(),
lines.split("\n")[l].lower())
#Get maximum similarity
if jaro_sim > max_sim:
max_sim = jaro_sim
#If maximum similarity >= similarity threshold: make all tokens technical(T)
if max_sim >= self.similarity_threshold and lines.split(
"\n")[k].replace(" ", ""):
new_lines.append(" ".join(
[w + "_T" for w in lines.split("\n")[k].split(" ")]))
else:
new_lines.append(" ".join(
[w + "_N" for w in lines.split("\n")[k].split(" ")]))
return "\n".join(new_lines)
for i in range(len(data)):
temp_article.append(data[i][0])
print(len(data))
my_string = "human moblity prediction spatiotemporal next place future location point-of-interest hotspot forecasting modelling mobility behaviors traffic trajectory mobile phone"
p = []
filter_thresh_45 = []
for i in range(len(temp_article)):
jarowinkler = JaroWinkler()
sim = jarowinkler.similarity(my_string, temp_article[i])
if sim > 0.45:
filter_thresh_45.append(data[i])
normalized_levenshtein = NormalizedLevenshtein()
filter_normalized_levenshtein = []
for i in range(len(filter_thresh_45)):
sim = normalized_levenshtein.distance(my_string, filter_thresh_45[i][0])