def compare_distance(self, other):
'''
'''
jarowinkler = JaroWinkler()
dist_1 = jarowinkler.similarity(str.lower(self.data['name']),
str.lower(other.data['name']))
dist_2 = jarowinkler.similarity(str.lower(self.data['address']),
str.lower(other.data['address']))
if dist_2 > 0.85:
return dist_1
return 0
def check_for_text_match(self,str1,strlist):
jarowinkler = JaroWinkler()
similarities=[]
for str2 in strlist:
similarities.append(jarowinkler.similarity(str1, str2))
index_max = np.argmax(similarities)
if index_max >= .70:
return strlist[index_max]
similarities=[]
for str2 in strlist:
similarities.append(jarowinkler.similarity(str1.lower(), str2.lower()))
index_max = np.argmax(similarities)
if index_max >= .70:
return strlist[index_max]
else:
return None
async def similarity(username: str, password: str):
jw = JaroWinkler()
res = jw.similarity(username, password)
if res <= 0.6:
return True
else:
return False
def jaro_winkler(keyword, domain):
"""Compute Jaro Winkler similarity
Args:
keyword:
domain:
Returns:
jarowinkler.similarity: (float) between 0.0 and 1.0
"""
jarowinkler = JaroWinkler()
return jarowinkler.similarity(keyword, domain)
# normalized_levenshtein.distance(str1a, str1b), # normalized_levenshtein.distance(str2a, str2b), # normalized_levenshtein.distance(str3a, str3b) # ], # 'Damerau': [ # damerau.distance(str1a, str1b), # damerau.distance(str2a, str2b), # damerau.distance(str3a, str3b) # ], # 'OptimalStringAlignment': [ # optimal_string_alignment.distance(str1a, str1b), # optimal_string_alignment.distance(str2a, str2b), # optimal_string_alignment.distance(str3a, str3b) # ], 'JaroWinkler': [jarowinkler.similarity(strA, strB) for strA, strB in stringsAB], # 'LongestCommonSubsequence': [ # lcs.distance(str1a, str1b), # lcs.distance(str2a, str2b), # lcs.distance(str3a, str3b) # ], # 'MetricLCS': [ # metric_lcs .distance(str1a, str1b), # metric_lcs .distance(str2a, str2b), # metric_lcs .distance(str3a, str3b) # ], 'NGram(2)': [twogram.distance(strA, strB) for strA, strB in stringsAB], # 'QGram(2)': [ # qgram.distance(str1a, str1b), # qgram.distance(str2a, str2b), # qgram.distance(str3a, str3b)
else:
network.get_track(artist, title).unlove()
logger.write(' LOVE: Unloved the Song on LastFm\n')
############### String Compare ####
jarowinkler = JaroWinkler()
if last_song[
0] != title: # Check, so that this program doesn't scrobble the song multiple times
last_scrobble = network.get_user(
lastFmCreds['username']).get_recent_tracks(limit=1)
logger.write(' LastFM: Last song was %s by %s\n' %
(last_scrobble[0][0].title, last_scrobble[0][0].artist))
if jarowinkler.similarity(str(last_scrobble[0][0].title.lower(
)), title.lower()) < 0.9: # check that "nobody else" scrobbled the song
unix_timestamp = int(time.mktime(datetime.datetime.now().timetuple()))
if 'album' in locals():
network.scrobble(artist=artist,
title=title,
timestamp=unix_timestamp,
album=album)
network.update_now_playing(artist=artist, title=title, album=album)
else:
network.scrobble(artist=artist,
title=title,
timestamp=unix_timestamp)
network.update_now_playing(artist=artist, title=title)
logger.write(' Scrobbled %s by %s\n' % (title, artist))
with open('last_song.json', 'w') as f:
f = open("akcigerhastaligi.txt", encoding="utf8")
df = f.read()
def basic_clean(text):
wnl = nltk.stem.WordNetLemmatizer()
stopwords = nltk.corpus.stopwords.words('turkish')
words = re.sub(r'[^\w\s]', '', text).split()
return [wnl.lemmatize(word) for word in words if word not in stopwords]
words = basic_clean(df)
unigrams = nltk.ngrams(words, 1)
unigramsFrequency = Counter(unigrams)
valuesOfUnigrams = list(unigramsFrequency.values())
unigramlist = list(unigramsFrequency)
for x in range(0, len(unigramlist)):
if (valuesOfUnigrams[x] > 4):
print(unigramlist[x], "is used", valuesOfUnigrams[x], "times")
jarowinkler = JaroWinkler()
print(jarowinkler.similarity('öksürük', 'öksürk'))
print(jarowinkler.similarity('akciğer', 'akciğr'))
print(jarowinkler.similarity('kanser', 'akciğr'))
print(jarowinkler.similarity('kanser', 'öksürk'))
print(jarowinkler.similarity('akciğer', 'öksürk'))
print('öksürk ' 'öksürük')
print('akciğr ' 'akciğer')
print('kansr ' 'kanser')
def string_distance(a, b):
jarowinkler = JaroWinkler()
return jarowinkler.similarity(a, b) + jaccard(a, b)
cosine = Cosine(2)
sorensenDice = SorensenDice(2)
jaccard = Jaccard(2)
qgram = QGram(2)
jaroWinkler = JaroWinkler()
normalizedLevenshtein = NormalizedLevenshtein()
stringSimilarity = StringDistance()
s0 = '烟台大学人文学院'
s1 = '江西农业大学'
# print(cosine.get_profile(s1))
# print(sorensenDice.get_profile(s1))
print(cosine.similarity(s0, s1))
print(sorensenDice.similarity(s0, s1))
print(jaccard.similarity(s0, s1))
print(jaroWinkler.similarity(s0, s1))
print(normalizedLevenshtein.similarity(s0, s1))
# print(qgram.distance(s0, s1))
similarity_list = [jaroWinkler, cosine, jaccard, normalizedLevenshtein]
er_process_with_similarity(path_o1, path_o2, path_t,
'result_cn_with_similarity', similarity_list)
# er_process(path_o, path_t, 'result_cn', segment)
# seg = seg.iterator()
# tmp_list = []
# for i in seg:
# tmp_list.append(str(i))
#
# print(tmp_list)
#
from strsimpy.ngram import NGram
from strsimpy.qgram import QGram
qgram = QGram(2)
print(qgram.distance('ABCD', 'ABCE'))
twogram = NGram(2)
print(twogram.distance('ABCD', 'ABTUIO'))
s1 = 'Adobe CreativeSuite 5 Master Collection from cheap 4zp'
s2 = 'Adobe CreativeSuite 5 Master Collection from cheap d1x'
fourgram = NGram(4)
print(fourgram.distance(s1, s2))
jarowinkler = JaroWinkler()
print(jarowinkler.similarity('My string', 'My tsring'))
print(jarowinkler.similarity('My string', 'My ntrisg'))
optimal_string_alignment = OptimalStringAlignment()
print(optimal_string_alignment.distance('CA', 'ABC'))
damerau = Damerau()
print(damerau.distance('ABCDEF', 'ABDCEF'))
print(damerau.distance('ABCDEF', 'BACDFE'))
print(damerau.distance('ABCDEF', 'ABCDE'))
print(damerau.distance('ABCDEF', 'BCDEF'))
print(damerau.distance('ABCDEF', 'ABCGDEF'))
print(damerau.distance('ABCDEF', 'POIU'))
normalized_levenshtein = NormalizedLevenshtein()
print(normalized_levenshtein.distance('My string', 'My $string'))