def calc_common_word_ngram(text_sentence, question):
common = 0
# Noktalama isaretlerinden temizlendi
text_sentence = remove_punctuation(text_sentence)
question = remove_punctuation(question)
# Kucuk harf ve kelime kelime parcalama islemi
text_sentence = tr_lower(text_sentence).strip()
question = tr_lower(question).strip()
n = NGram(N=N_GRAM)
list_text_sentence = list(n.split(text_sentence))
list_question = list(n.split(question))
# print(list_text_sentence)
# print()
# print(list_question)
# input('')
for question_word in list_question:
if question_word in list_text_sentence:
# print(question_word)
common += 1
return common
class NGramMixSegment(Segment):
def __init__(self, N=(1, 2), pad_len=0):
self.model1 = NGram(N=N[0], pad_len=pad_len)
self.model2 = NGram(N=N[1], pad_len=pad_len)
def cut(self, sentence):
""" 分词.
@params:
sentence - 待分词文本.
@return:
On success - 单词列表.
On failure - 错误信息.
"""
words = list(self.model1.split(sentence))
words.extend(list(self.model2.split(sentence)))
return words
class NGramSegment(Segment):
def __init__(self, N=2, pad_len=0):
self.model = NGram(N=N, pad_len=pad_len)
def cut(self, sentence):
""" 分词.
@params:
sentence - 待分词文本.
@return:
On success - 单词列表.
On failure - 错误信息.
"""
return list(self.model.split(sentence))
print 'jaro winkler', sim_arry6
sim_arry7 = [
jellyfish.match_rating_comparison(unicode(string[0]), unicode(s))
for s in string
]
print 'match rating comparison', sim_arry7
# tokens = word_tokenize([string])
# print(string_token)
# print tfidf_matrix
# print(y.toarray()
ngram_array = [word_grams(s.split(' ')) for s in string]
# print ngram_array
n = NGram()
# print list(n.split(string[0]))
ngram_array = [list(n.split(s)) for s in string]
# print ngram_array
sim_arry8 = [NGram.compare(string[0].lower(), s.lower(), N=4) for s in string]
print 'ngram', sim_arry8
def jaccard_distance(a, b):
# print a, b
inter_len = float(len(list(a.intersection(b))))
union_len = float(len(list(a.union(b))))
return inter_len / union_len
# print list(ngram_array[0].intersection(ngram_array[1]))
sim_arry9 = [
jaccard_distance(NGram(ngram_array[0]), NGram(s)) for s in ngram_array
def ngram_str(s, N=3):
s = s.replace(" ", "_")
ngram = NGram(N=N)
return " ".join(ngram.split(s))
class NgramIndex():
"""
Class used for encoding words in ngram representation
"""
def __init__(self,n,loaded = False):
"""
Constructor
Parameters
----------
n : int
ngram size
"""
self.ngram_gen = NGram(N=n)
self.size = n
self.ngram_index = {"":0}
self.index_ngram = {0:""}
self.cpt = 0
self.max_len = 0
self.loaded = loaded
def split_and_add(self,word):
"""
Split word in multiple ngram and add each one of them to the index
Parameters
----------
word : str
a word
"""
ngrams = word.lower().replace(" ","$")
ngrams = list(self.ngram_gen.split(ngrams))
[self.add(ngram) for ngram in ngrams]
self.max_len = max(self.max_len,len(ngrams))
def add(self,ngram):
"""
Add a ngram to the index
Parameters
----------
ngram : str
ngram
"""
if not ngram in self.ngram_index:
self.cpt+=1
self.ngram_index[ngram]=self.cpt
self.index_ngram[self.cpt]=ngram
def encode(self,word):
"""
Return a ngram representation of a word
Parameters
----------
word : str
a word
Returns
-------
list of int
listfrom shapely.geometry import Point,box
of ngram index
"""
ngrams = word.lower().replace(" ","$")
ngrams = list(self.ngram_gen.split(ngrams))
return [self.ngram_index[ng] for ng in ngrams if ng in self.ngram_index]
def complete(self,ngram_encoding,MAX_LEN,filling_item=0):
"""
Complete a ngram encoded version of word with void ngram. It's necessary for neural network.
Parameters
----------
ngram_encoding : list of int
first encoding of a word
MAX_LEN : int
desired length of the encoding
filling_item : int, optional
ngram index you wish to use, by default 0
Returns
-------
list of int
list of ngram index
"""
if self.loaded and len(ngram_encoding) >=MAX_LEN:
return ngram_encoding[:MAX_LEN]
assert len(ngram_encoding) <= MAX_LEN
diff = MAX_LEN - len(ngram_encoding)
ngram_encoding.extend([filling_item]*diff)
return ngram_encoding
def save(self,fn):
"""
Save the NgramIndex
Parameters
----------
fn : str
output filename
"""
data = {
"ngram_size": self.size,
"ngram_index": self.ngram_index,
"cpt_state": self.cpt,
"max_len_state": self.max_len
}
json.dump(data,open(fn,'w'))
@staticmethod
def load(fn):
"""
Load a NgramIndex state from a file.
Parameters
----------
fn : str
input filename
Returns
-------
NgramIndex
ngram index
Raises
------
KeyError
raised if a required field does not appear in the input file
"""
try:
data = json.load(open(fn))
except json.JSONDecodeError:
print("Data file must be a JSON")
for key in ["ngram_size","ngram_index","cpt_state","max_len_state"]:
if not key in data:
raise KeyError("{0} field cannot be found in given file".format(key))
new_obj = NgramIndex(data["ngram_size"],loaded=True)
new_obj.ngram_index = data["ngram_index"]
new_obj.index_ngram = {v:k for k,v in new_obj.ngram_index.items()}
new_obj.cpt = data["cpt_state"]
new_obj.max_len = data["max_len_state"]
return new_obj
