def senticnet(text):
"""
Returns a list obtained from SenticNet with the following four features normalized: [pleasantness_value, attention_value, sensiivity_value, aptitude_value]
:param text: input text pre-processed by Spacy
:return: a list with the SenticNet features averaged for all the words in text
"""
list_features = [0] * 4
sn = SenticNet()
count_words = 0
for token in text:
try:
concept_info = sn.concept(token)
list_features[0] += float(concept_info['sentics']['pleasantness'])
list_features[1] += float(concept_info['sentics']['attention'])
list_features[2] += float(concept_info['sentics']['sensitivity'])
list_features[3] += float(concept_info['sentics']['aptitude'])
count_words += 1
except KeyError:
pass
if count_words != 0:
list_features = [feature / count_words for feature in list_features]
return list_features
class Get_IAC():
def __init__(self):
self.col = ['Name', 'Brand', 'Price', 'Title', 'Score', 'Time', 'Text']
self.sn = SenticNet('en')
self.wordnet_lemmatizer = WordNetLemmatizer()
def review_to_sentences(self, review):
# review = review.replace(',','.')
review = review.replace('.', '. ')
raw_sentences = sent_tokenize(review)
return raw_sentences
def InputData(self, input_path):
self.dict_list = []
if '.csv' in input_path:
with open(input_path, 'r', encoding='utf8') as f:
reader = csv.DictReader(f)
for row in reader:
d = {i: row[i] for i in col}
self.dict_list.append(d)
elif '.xlsx' in input_path:
wb = load_workbook(input_path)
sheet = wb.active
count = 0
for row in sheet.rows:
if count == 0:
count += 1
continue
d = {}
name = 0
for cell in row:
d[self.col[name]] = cell.value
name += 1
self.dict_list.append(d)
self.dict_list = [
x for x in self.dict_list if x['Text'] != '' and x['Text'] != None
]
self.sentences = []
for i in range(len(self.dict_list)):
for j in self.review_to_sentences(self.dict_list[i]['Text']):
self.sentences.append(j)
self.sentences = [x for x in self.sentences if len(x) >= 5]
def GetIAC(self):
self.nlp = StanfordCoreNLP(r'stanford-corenlp-full-2018-10-05')
self.IAC = []
for i in tqdm(self.sentences):
dependency = self.nlp.dependency_parse(i)
token = self.nlp.word_tokenize(i)
if [x for x in dependency if 'compound' in x] != []:
for j in [x for x in dependency if 'compound' in x]:
token[j[2] - 1] = token[j[2] - 1] + '-' + token[j[1] - 1]
token[j[1] - 1] = ''
i = ' '.join(token)
parse = self.nlp.parse(i)
dependency = self.nlp.dependency_parse(i)
pos = self.nlp.pos_tag(i)
token = []
for j in pos:
wordnet_pos = self.get_wordnet_pos(j[1])
token.append(
self.wordnet_lemmatizer.lemmatize(j[0].lower(),
pos=wordnet_pos))
# subject noun relation
if [x for x in dependency if 'nsubj' in x] != []:
for j in self.Subject_Noun_Rule(parse, dependency, token, pos):
self.IAC.append(j)
else: # Non subject noun relation
for j in self.Non_Subject_Noun_Rule(parse, dependency, token,
pos):
self.IAC.append(j)
self.nlp.close()
self.IAC = list(set(self.IAC))
def get_wordnet_pos(self, treebank_tag):
if treebank_tag.startswith('J'):
return wn.ADJ
elif treebank_tag.startswith('V'):
return wn.VERB
elif treebank_tag.startswith('N'):
return wn.NOUN
elif treebank_tag.startswith('R'):
return wn.ADV
else:
return wn.NOUN
# Additional Rule: 對等連接詞
def Conj(self, index, dependency, token):
IAC = []
index = list(set(index))
if [x for x in dependency if 'conj' in x] != []:
conj = [x for x in dependency if 'conj' in x]
for j in conj:
if j[1] in index or j[2] in index:
if j[1] not in index:
IAC.append(token[j[1] - 1])
index.append(j[1])
if j[2] not in index:
IAC.append(token[j[2] - 1])
index.append(j[2])
return IAC
def Subject_Noun_Rule(self, parse, dependency, token, pos):
be = ['is', 'was', 'am', 'are', 'were']
adv_mod = [x for x in dependency if 'advmod' in x]
adj_mod = [x for x in dependency if 'amod' in x]
active_token = token[[x for x in dependency if 'nsubj' in x][0][2] -
1] # 主詞
result = []
index = []
if adv_mod != [] or adj_mod != []:
A, B = self.Rule1(adv_mod, adj_mod, active_token, token)
result += A
index += B
# does not have auxiliary verb
if any(k in token
for k in be) == False and [x for x in pos if 'MD' in x] == []:
A, B = self.Rule2(token, pos, dependency, active_token, adv_mod,
adj_mod)
result += A
index += B
if [x for x in dependency if 'dobj' in x] != []:
A, B = self.Rule3(dependency, token, pos)
result += A
index += B
if [x for x in dependency if 'xcomp' in x] != []:
A, B = self.Rule4(dependency, token, pos)
result += A
index += B
if [x for x in dependency if 'cop' in x] != []:
A, B = self.Rule5(dependency, pos, active_token, token)
result += A
index += B
result += self.Conj(index, dependency, token)
return list(set(result))
# 3.3.3 Rule 1
def Rule1(self, adv_mod, adj_mod, active_token, token):
IAC = []
index = []
if adv_mod != []:
for j in adv_mod:
try:
concept = self.sn.concept(token[j[2] - 1])
IAC.append(token[j[2] - 1])
index.append(j[2])
except:
a = 0
# print(token[j[2]-1] + ' Not in SenticNet')
if adj_mod != []:
for j in adj_mod:
try:
concept = self.sn.concept(token[j[2] - 1])
IAC.append(token[j[2] - 1])
index.append(j[2])
except:
a = 0
# print(token[j[2]-1] + ' Not in SenticNet')
return IAC, index
# 3.3.3 Rule 2-1
def Rule2(self, token, pos, dependency, active_token, adv_mod, adj_mod):
IAC = []
index = []
advcl = [x for x in dependency
if 'advcl' in x] # adverbial clause modifier
if advcl != []:
for j in advcl:
IAC.append(token[j[1] - 1])
index.append(j[1])
IAC.append(active_token)
index.append([x for x in dependency if 'nsubj' in x][0][2])
if adv_mod != []:
for j in adv_mod:
IAC.append(token[j[1] - 1])
index.append(j[1])
IAC.append(active_token)
index.append([x for x in dependency if 'nsubj' in x][0][2])
if adj_mod != []:
for j in adj_mod:
IAC.append(token[j[1] - 1])
index.append(j[1])
IAC.append(active_token)
index.append([x for x in dependency if 'nsubj' in x][0][2])
return IAC, index
# 3.3.3 Rule 2-2 & 2-3
def Rule3(self, dependency, token, pos):
IAC = []
index = []
dobj = [x for x in dependency
if 'dobj' in x] # open clausal complement
for j in dobj:
if pos[j[2] - 1][1] == 'NN':
try:
# Rule 2-3
concept = self.sn.concept(token[j[2] - 1])
IAC.append(token[j[2] - 1])
index.append(j[2])
conj = []
conj.append(j[2])
if [x for x in dependency if 'conj' in x and j[2] in x
] != []:
for i in [
x for x in dependency
if 'conj' in x and j[2] in x
]:
conj.append(i[1])
conj.append(i[2])
conj = list(set(conj))
for i in conj:
t1 = i
connect = [x for x in dependency if t1 in x]
for k in connect:
if k[1] != t1:
if pos[k[1] - 1][1] == 'NN':
IAC.append(token[k[1] - 1])
index.append(k[1])
if k[2] != t1:
if pos[k[2] - 1][1] == 'NN':
IAC.append(token[k[2] - 1])
index.append(k[2])
except:
# Rule 2-2
IAC.append(token[j[2] - 1])
index.append(j[2])
# print(token[j[2]-1] + ' Not in SenticNet')
return IAC, index
# 3.3.3 Rule 2-4
def Rule4(self, dependency, token, pos):
IAC = []
index = []
xcomp = [x for x in dependency
if 'xcomp' in x] # open clausal complement
for j in xcomp:
try:
concept = self.sn.concept(token[j[1] - 1] + '-' +
token[j[2] - 1])
IAC.append(token[j[1] - 1] + '-' + token[j[2] - 1])
except:
a = 0
# print(token[j[1]-1] + '-' + token[j[2]-1] + ' Not in SenticNet')
t1 = j[2]
connect = [x for x in dependency if t1 in x]
for k in connect:
if pos[k[2] - 1][1] == 'NN':
IAC.append(token[k[2] - 1])
index.append(k[2])
return IAC, index
# 3.3.3 Rule 3 & 3.3.3 Rule 4 & 3.3.3 Rule 5
def Rule5(self, dependency, pos, active_token, token):
IAC = []
index = []
cop = [x for x in dependency if 'cop' in x] # copula
# Rule 4
if pos[[x for x in dependency if 'nsubj' in x][0][2] - 1][1] == 'NN':
IAC.append(active_token)
index.append([x for x in dependency if 'nsubj' in x][0][2])
# Rule 3 & Rule 5
for j in cop:
# Rule 3
conj = []
# if token[j[1]-1] in all_term:
IAC.append(token[j[1] - 1])
index.append(j[1])
conj.append(j[1])
if [x for x in dependency if 'conj' in x and j[1] in x] != []:
for i in [x for x in dependency if 'conj' in x and j[1] in x]:
conj.append(i[1])
conj.append(i[2])
# Rule 5
conj = list(set(conj))
for i in conj:
t1 = i
connect = [x for x in dependency if t1 in x]
for k in connect:
if k[1] != t1:
if pos[k[1] - 1][1] == 'VB' or pos[k[1] -
1][1] == 'VV':
IAC.append(token[k[1] - 1])
index.append(k[1])
if token[t1 - 1] not in IAC:
IAC.append(token[t1 - 1])
index.append(t1)
if k[2] != t1:
if pos[k[2] - 1][1] == 'VB' or pos[k[2] -
1][1] == 'VV':
IAC.append(token[k[2] - 1])
index.append(k[2])
if token[t1 - 1] not in IAC:
IAC.append(token[t1 - 1])
index.append(t1)
return IAC, index
def Non_Subject_Noun_Rule(self, parse, dependency, token, pos):
result = []
index = []
if [x for x in dependency if 'xcomp' in x] != []:
A, B = self.Rule6(dependency, token)
result += A
index += B
if [x for x in dependency if 'case' in x] != []:
A, B = self.Rule7(dependency, pos, token)
result += A
index += B
if [x for x in dependency if 'dobj' in x] != []:
A, B = self.Rule8(dependency, token)
result += A
index += B
result += self.Conj(index, dependency, token)
return list(set(result))
# 3.3.4 Rule 1
def Rule6(self, dependency, token):
IAC = []
index = []
xcomp = [x for x in dependency
if 'xcomp' in x] # open clausal complement
for j in xcomp:
# if token[j[1]-1] in all_term:
IAC.append(token[j[1] - 1])
index.append(j[1])
return IAC, index
# 3.3.4 Rule 2
def Rule7(self, dependency, pos, token):
IAC = []
index = []
case = [x for x in dependency
if 'case' in x] # a prepositional relation
for j in case:
if pos[j[1] - 1][1] == 'NN':
connect = [
x for x in dependency if j[1] in x and 'mod' in x[0]
]
for i in connect:
IAC.append(token[i[1] - 1])
IAC.append(token[i[2] - 1])
index.append(i[1])
index.append(i[2])
return list(set(IAC)), list(set(index))
# 3.3.4 Rule 3
def Rule8(self, dependency, token):
IAC = []
index = []
dobj = [x for x in dependency
if 'dobj' in x] # a direct object relation
for j in dobj:
IAC.append(token[j[2] - 1])
index.append(j[2])
return IAC, index
def Save(self, output_path):
with open(output_path, 'wb') as f:
pickle.dump(self.IAC, f)
for _, records in groupby(sorted(lst, key=keyprop), keyprop)
]
a = [{'time': '25 APR', 'total': 10, 'high': 10},
{'time': '26 APR', 'total': 5, 'high': 5}]
b = [{'time': '24 APR', 'total': 10, 'high': 10},
{'time': '26 APR', 'total': 15, 'high': 5}]
merger = merge_list_of_records_by('time', add)
hasil_merge = merger(a+b)
print(hasil_merge)
print("sinonim with thesaurus==================================================================")
# from PyDictionary import PyDictionary
#
# dictionary = PyDictionary()
# print(dictionary.synonym("good"))
from thesaurus import Word
w = Word('suicidal')
syn = w.synonyms()
print(syn)
sn = SenticNet()
try:
concept_info_sinonim = sn.concept("suicidal")
print(concept_info_sinonim)
except Exception as e:
print(e)
# -*- coding: utf-8 -*-
"""
Spyder Editor
This is a temporary script file.
"""
import nltk
nltk.download()
import os
from senticnet.senticnet import SenticNet
sn = SenticNet()
sn.concept('')
def fun1(d):
try:
from senticnet.senticnet import SenticNet
sn = SenticNet()
sn.semantics(d)
return True
except KeyError as error:
return False
fun1('day')
from nltk.corpus import wordnet
sk = wordnet.synset('ssd')
def get_clues(text):
text = text
print("*--------(%s)-------------*" % (text))
print(type(text))
nlp = StanfordCoreNLP('http://localhost:9001')
stop_words = set(stopwords.words('english'))
'''
Method to remove numbers appended at last
'''
dep_parse = nlp.annotate(text,
properties={
'annotators': 'depparse',
'outputFormat': 'json',
'timeout': 10000,
})
pos = nlp.annotate(text,
properties={
'annotators': 'lemma',
'outputFormat': 'json',
'timeout': 10000,
})
sn = SenticNet()
word_to_dep = [{} for i in range(len(dep_parse['sentences']))]
word_to_par = [{} for i in range(len(dep_parse['sentences']))]
word_to_pos = [{} for i in range(len(dep_parse['sentences']))]
word_to_lemma = [{} for i in range(len(dep_parse['sentences']))]
word_to_child = [{} for i in range(len(dep_parse['sentences']))]
sents = [[] for i in range(len(dep_parse['sentences']))]
index_to_word = {}
'''
Constructing dicts for maintaining the dependencies among words.
'''
'''
Appending each word by occurence number to maintain distinct word count
'''
#print(dep_parse['sentences'])
print("********")
for i, sent in enumerate(dep_parse['sentences']):
for dep in sent['basicDependencies']:
word_to_dep[i][dep['dependentGloss'] +
str(dep['dependent'])] = dep['dep']
word_to_par[i][dep['dependentGloss'] +
str(dep['dependent'])] = dep['governorGloss'] + str(
dep['governor'])
index_to_word[dep['dependentGloss'] +
str(dep['dependent'])] = dep['dependentGloss']
if (dep['governorGloss'] + str(dep['governor'])
not in word_to_child[i]):
word_to_child[i][dep['governorGloss'] +
str(dep['governor'])] = []
if (dep['dependentGloss'] + str(dep['dependent'])
not in word_to_child[i]):
word_to_child[i][dep['dependentGloss'] +
str(dep['dependent'])] = []
word_to_child[i][dep['governorGloss'] +
str(dep['governor'])].append(
dep['dependentGloss'] + str(dep['dependent']))
sents[i].append(dep['dependentGloss'] + str(dep['dependent']))
word_to_dep[i]['ROOT0'] = 'root'
word_to_par[i]['ROOT0'] = 'root'
for i, sent in enumerate(pos['sentences']):
for pos_tagger in sent['tokens']:
word_to_pos[i][pos_tagger['word']] = pos_tagger['pos']
word_to_lemma[i][pos_tagger['word']] = pos_tagger['lemma']
word_to_pos[i]['ROOT'] = 'root'
word_to_lemma[i]['ROOT'] = 'root'
'''
Displaying the deps
'''
##Implemeting rules to extract aspects
for i, sent in enumerate(sents):
if (__name__ == '__main__'):
print(word_to_dep[i], word_to_par[i], word_to_pos[i])
print("Children==>")
print(word_to_child[i])
aspects = []
for i, sent in enumerate(sents):
for word in sent:
'''
Rule 0
'''
if ('subj' in word_to_dep[i][word]):
for child in word_to_child[i][word_to_par[i][word]]:
if ('amod' in word_to_dep[i][child]
or 'advmod' in word_to_dep[i][child]):
aspects.append(word_to_par[i][word])
if (__name__ == '__main__'):
print("Rule 0 triggered.")
'''
Rule 1 (without sub): Very big to hold.
'''
if (word_to_dep[i][word] == 'xcomp' and
('JJ' in word_to_pos[i][index_to_word[word_to_par[i][word]]] or
'RB' in word_to_pos[i][index_to_word[word_to_par[i][word]]])):
if (__name__ == '__main__'):
print("Rule 1 triggered")
aspects.append(word_to_par[i][word])
'''
Rule 2 (without subj): Not to mention the price of the phone
'''
if (word_to_dep[i][word] == 'dobj' and 'VB'
in word_to_pos[i][index_to_word[(word_to_par[i][word])]]
and ('NN' in word_to_pos[i][index_to_word[(word)]]
or 'JJ' in word_to_pos[i][index_to_word[(word)]])):
aspects.append(word)
if (__name__ == '__main__'):
print("Rule 2 triggered")
print(word)
'''
Rule 3 (without subj): Love the sleekness of the player
'''
if ('NN' in word_to_pos[i][index_to_word[(word)]]
and word_to_dep[i][word] == 'nmod'):
aspects.append(word_to_par[i][word])
if (__name__ == '__main__'):
print("Rule 3 triggered")
print(word_to_par[i][word])
'''
Rule 4 (with sub): The battery lasts little
two aspects
'''
if (word_to_dep[i][word] == 'advmod'
or word_to_dep[i][word] == 'amod' or word_to_dep[i][word]
== 'advcl') and ('VB' in word_to_pos[i][index_to_word[(
word_to_par[i][word])]]):
aspects.append(word_to_par[i][word])
for word2 in sent:
if (word2 != word and word_to_dep[i][word2] == 'nsubj'
and word_to_par[i][word2] == word_to_par[i][word]
and
('NN' in word_to_pos[i][index_to_word[word2]]
or 'JJ' in word_to_pos[i][index_to_word[word2]])):
aspects.append(word2)
if (__name__ == '__main__'):
print("Rule 4 triggered")
print(word2)
'''
Rule 5 (with sub): I like the lens of this camera
'''
if ('NN' in word_to_pos[i][index_to_word[(word)]]
and word_to_dep[i][word] == 'dobj'):
if (__name__ == '__main__'):
print("Rule 5 triggered")
print(word)
try:
concept_info = sn.concept((word))
print("present in senticnet")
except KeyError:
print("Yay")
aspects.append(word)
'''
Rule 6 : I like the beauty of the screen.
Check if senticnet condition should be added
'''
if ('NN' in word_to_pos[i][index_to_word[(word)]]
and word_to_dep[i][word] == 'dobj'):
try:
concept_info = sn.concept((word))
aspects.append(word)
print("yay!")
except KeyError:
print("oops, not there in SenticNet")
for word2 in sent:
if (word2 != word and word_to_par[i][word2] == word and
'NN' in word_to_pos[i][index_to_word[(word2)]]):
aspects.append(word2)
if (__name__ == '__main__'):
print("Rule 6 triggered.")
print(word2)
'''
Rule 7 : I would like to comment on the camera of this phone.
'''
if (word_to_dep[i][word] == 'xcomp'):
try:
concept_info = sn.concept((word))
aspects.append(word)
print("yay!")
except KeyError:
print("oops, not there in SenticNet")
for child in word_to_child[i][word]:
if ('NN' in word_to_pos[i][index_to_word[child]]):
aspects.append(child)
if (__name__ == '__main__'):
print("Rule 7 triggered.")
print(word)
print(child)
'''
Rule 8 : The car is expensive.
'''
if (word_to_dep[i][word] == 'nsubj'):
for word2 in sent:
if (word2 != word and word_to_dep[i][word2] == 'cop'
and word_to_par[i][word2] == word_to_par[i][word]):
aspects.append(word_to_par[i][word])
if (__name__ == '__main__'):
print("Rule 8 triggered")
print(word_to_par[i][word])
'''
Rule 9 : The camera is nice.
'''
if (word_to_dep[i][word] == 'nsubj'
and 'NN' in word_to_pos[i][index_to_word[(word)]]):
for word2 in sent:
if (word2 != word and word_to_dep[i][word2] == 'cop'
and word_to_par[i][word2] == word_to_par[i][word]):
aspects.append(word)
if (__name__ == '__main__'):
print("Rule 9 triggered")
print(word)
'''
Rule 10 : The phone is very lightweight to carry.
'''
if (word_to_dep[i][word] == 'cop'):
for word2 in sent:
if (word2 != word
and 'VB' in word_to_pos[i][index_to_word[(word2)]]
and word_to_par[i][word] == word_to_par[i][word2]):
aspects.append(word2)
if (__name__ == '__main__'):
print("Rule 10 triggered.")
print(word2)
'''
Extracting mods of dobjs
'''
if (word_to_dep[i][word] == 'dobj'):
for child in word_to_child[i][word]:
if ('mod' in word_to_dep[i][child] and 'JJ'
in word_to_pos[i][index_to_word[(child)]]):
aspects.append(child)
'''
Rule 11 : Checking for conjuctions
'''
for asp in aspects:
for word in sent:
if (word_to_dep[i][word] == 'conj'
and word_to_par[i][word] == asp):
aspects.append(word)
if (__name__ == '__main__'):
print("Rule conj triggered.")
print(word)
finalIAC = set(aspects)
finalIAC = [index_to_word[f] for f in finalIAC]
finalIAC = [w for w in finalIAC if not w in stop_words]
finalSenti = []
for iac in finalIAC:
try:
concept_info = sn.concept((iac))
finalSenti.append(iac)
except KeyError:
print("No word available for " + iac)
return finalIAC, finalSenti
# Each line of corpus must be equivalent to each document of the corpus
#boc_model=boc.BOCModel(doc_path="input corpus path")
boc_model = boc.BOCModel('text.txt')
#boc_model.context = text
# output can be saved with save_path parameter
boc_matrix, word2concept_list, idx2word_converter = boc_model.fit()
# SenitcNet lexicon lookup
from senticnet.senticnet import SenticNet
sn = SenticNet()
concept_info = sn.concept(text)
polarity_value = sn.polarity_value(text)
polarity_intense = sn.polarity_intense(text)
moodtags = sn.moodtags(text)
semantics = sn.semantics(text)
sentics = sn.sentics(text)
print('==================================')
print('test: ', text)
print('concept_info: ', concept_info)
print('polarity_value: ', polarity_value)
print('polarity_intense: ', polarity_intense)
print('moodtags: ', moodtags)
print('semantics: ', semantics)
print('sentics: ', sentics)
print('==================================')
def get_clues(text):
text = text
print("*--------(%s)-------------*" % (text))
print(type(text))
nlp = StanfordCoreNLP('http://localhost:9001')
stop_words = set(stopwords.words('english'))
'''
Method to remove numbers appended at last
'''
dep_parse = nlp.annotate(text,
properties={
'annotators': 'depparse',
'outputFormat': 'json',
'timeout': 10000,
})
pos = nlp.annotate(text,
properties={
'annotators': 'lemma',
'outputFormat': 'json',
'timeout': 10000,
})
sn = SenticNet()
word_to_dep = [{} for i in range(len(dep_parse['sentences']))]
word_to_par = [{} for i in range(len(dep_parse['sentences']))]
word_to_pos = [{} for i in range(len(dep_parse['sentences']))]
word_to_lemma = [{} for i in range(len(dep_parse['sentences']))]
word_to_child = [{} for i in range(len(dep_parse['sentences']))]
sents = [[] for i in range(len(dep_parse['sentences']))]
index_to_word = {}
aspect_result = [[] for i in range(len(dep_parse['sentences']))]
'''
Constructing dicts for maintaining the dependencies among words.
'''
'''
Appending each word by occurence number to maintain distinct word count
'''
print("********")
for i, sent in enumerate(dep_parse['sentences']):
for dep in sent['basicDependencies']:
word_to_dep[i][dep['dependentGloss'] +
str(dep['dependent'])] = dep['dep']
word_to_par[i][dep['dependentGloss'] +
str(dep['dependent'])] = dep['governorGloss'] + str(
dep['governor'])
index_to_word[dep['dependentGloss'] +
str(dep['dependent'])] = dep['dependentGloss']
if (dep['governorGloss'] + str(dep['governor'])
not in word_to_child[i]):
word_to_child[i][dep['governorGloss'] +
str(dep['governor'])] = []
if (dep['dependentGloss'] + str(dep['dependent'])
not in word_to_child[i]):
word_to_child[i][dep['dependentGloss'] +
str(dep['dependent'])] = []
word_to_child[i][dep['governorGloss'] +
str(dep['governor'])].append(
dep['dependentGloss'] + str(dep['dependent']))
sents[i].append(dep['dependentGloss'] + str(dep['dependent']))
word_to_dep[i]['ROOT0'] = 'root'
word_to_par[i]['ROOT0'] = 'root'
for i, sent in enumerate(pos['sentences']):
for pos_tagger in sent['tokens']:
word_to_pos[i][pos_tagger['word']] = pos_tagger['pos']
word_to_lemma[i][pos_tagger['word']] = pos_tagger['lemma']
word_to_pos[i]['ROOT'] = 'root'
word_to_lemma[i]['ROOT'] = 'root'
'''
Displaying the deps
'''
##Implemeting rules to extract aspects
for i, sent in enumerate(sents):
if (__name__ == '__main__'):
print(word_to_dep[i], word_to_par[i], word_to_pos[i],
word_to_lemma[i])
print("Children==>")
print(word_to_child[i])
for i, sent in enumerate(sents):
token_t = word_to_child[i]['ROOT0'][0]
is_sub = False
token_h = None
for child in word_to_child[i][token_t]:
if 'subj' in word_to_dep[i][child]:
is_sub = True
token_h = child
#If subject noun relationship present
if is_sub:
"""
Rule 0: if any adv or adj modifies the token t.
"""
for child in word_to_child[i][token_t]:
if ('amod' in word_to_dep[i][child]
or 'advmod' in word_to_dep[i][child]):
try:
concept_info = sn.concept(index_to_word[child])
aspect_result[i].append(token_t)
if __name__ == '__main__':
print("Rule 1 triggered.")
print("present in senticnet")
except KeyError:
print("OOps")
"""
Rule 1: The battery lasts little.
"""
for child in word_to_child[i][token_t]:
if (word_to_dep[i][child] == 'advmod' or word_to_dep[i][child]
== 'amod' or word_to_dep[i][child] == 'advcl') and (
'VB' in word_to_pos[i][index_to_word[token_t]]):
aspect_result[i].append(token_t)
aspect_result[i].append(token_h)
if __name__ == '__main__':
print("Rule 1 triggered.")
print(token_t)
print(token_h)
"""
Rule 2: I like the beauty of the screen (and I like the lens of this camera).
"""
for child in word_to_child[i][token_t]:
if (word_to_dep[i][child] == 'dobj'
and 'NN' in word_to_pos[i][index_to_word[child]]):
aspect_result[i].append(child)
if __name__ == '__main__':
print(child)
try:
concept_info = sn.concept(index_to_word[child])
if __name__ == '__main__':
print("Rule 2 triggered")
for grandchild in word_to_child[i][child]:
if ('NN' in word_to_pos[i][
index_to_word[grandchild]]):
aspect_result[i].append(grandchild)
print(grandchild)
except KeyError:
print("OOps")
"""
Rule 3: I would like to comment on the camera of this phone.
"""
for child in word_to_child[i][token_t]:
if (word_to_dep[i][child] == 'xcomp'):
try:
sn.concept(index_to_word[child])
aspect_result[i].append(child)
if __name__ == '__main__':
print(child)
except KeyError:
print("OOps")
for grandchild in word_to_child[i][child]:
if ('NN' in word_to_pos[i][index_to_word[grandchild]]):
aspect_result[i].append(grandchild)
if __name__ == '__main__':
print(grandchild)
print("Rule 3 triggered.")
"""
Rule 4: The car is expensive.
"""
for child in word_to_child[i][token_t]:
if (word_to_dep[i][child] == 'cop'):
try:
sn.concept(word_to_lemma[i][index_to_word[token_t]])
aspect_result[i].append(token_t)
if __name__ == '__main__':
print("Rule 4 triggered")
print(token_t)
except KeyError:
pass
"""
Rule 5: The camera is nice
"""
for child in word_to_child[i][token_t]:
if (word_to_dep[i][child] == 'cop'
and 'NN' in word_to_pos[i][index_to_word[token_h]]):
aspect_result[i].append(token_h)
if __name__ == '__main__':
print("Rule 5 triggered.")
print(token_h)
"""
Rule 6:
"""
for child in word_to_child[i][token_t]:
if (word_to_dep[i][child] == 'cop'):
for child2 in word_to_child[i][token_t]:
if (child != child2 and 'VB'
in word_to_pos[i][index_to_word[child2]]):
try:
sn.concept(index_to_word[token_t])
sn.concept(index_to_word[child2])
aspect_result[i].append(token_t)
aspect_result[i].append(child2)
if __name__ == '__main__':
print("rule 6 trigg")
print(token_t)
print(child2)
except KeyError:
pass
else:
"""
Rule 7:Very big to hold.
"""
for word in sent:
if ('RB' in word_to_pos[i][index_to_word[word]]
or 'JJ' in word_to_pos[i][index_to_word[word]]):
for child in word_to_child[i][word]:
if (word_to_dep[i][child] == 'xcomp'
or word_to_dep[i][child] == 'ccomp'):
aspect_result[i].append(word)
if __name__ == '__main__':
print("Rule 7 triggered")
print(word)
"""
Rule 8: Love the sleekness of the player.
"""
for word in sent:
for child in word_to_child[i][word]:
if ('NN' in word_to_pos[i][index_to_word[child]]
and word_to_dep[i][child] == 'nmod'):
for grandchild in word_to_child[i][child]:
if ('IN' in word_to_pos[i][
index_to_word[grandchild]]):
aspect_result[i].append(word)
aspect_result[i].append(child)
if __name__ == '__main__':
print(word)
print(child)
print("Rule 8 triggered.")
"""
Rule 9: Not to mention the price of the phone.
"""
for word in sent:
for child in word_to_child[i][word]:
if (word_to_dep[i][child] == 'dobj'):
aspect_result[i].append(child)
if __name__ == '__main__':
print(child)
print("Rule 9 triggered")
'''
Rule 11 : Checking for conjuctions
'''
for asp in aspect_result[i]:
for word in sent:
if (word_to_dep[i][word] == 'conj'
and word_to_par[i][word] == asp):
aspect_result[i].append(word)
if (__name__ == '__main__'):
print("Rule conj triggered.")
print(word)
finalIAC = [set(aspect_result[i]) for i in range(len(sents))]
finalIAC = [[index_to_word[w] for w in finalIAC[i]]
for i in range(len(sents))]
print(finalIAC)
singleFinalIAC = []
for i in range(len(sents)):
for w in finalIAC[i]:
if w not in stop_words:
singleFinalIAC.append(w)
print(singleFinalIAC)
finalSenti = []
for iac in singleFinalIAC:
try:
concept_info = sn.concept((iac))
finalSenti.append(iac)
except KeyError:
print("No word available for " + iac)
return singleFinalIAC, finalSenti
sisa = 0
# print("Jumlah existing wordlist : {} ".format(len(existWordlistDepression)))
#here it is
for wordExist in existWordlistDepression:
word = wordExist['word']
tokens = word_tokenize(word)
for token, tag in pos_tag(tokens):
lemma = wn_lemmater.lemmatize(token, tag_map[tag[0]])
print("lemma asli : {}".format(lemma))
if lemma not in lemmaOfExistWordlist:
lemmaOfExistWordlist.append(lemma) # 685 lemma unique ditemukan dari DB
try:
syns = wordnet.synsets(lemma)
concept_info = sn.concept(lemma)
concept_info_origin = concept_info
conceptExist.append(concept_info)
#word dimasukkan ke dalam objek
senticwordObj = WordList_sentic()
senticwordObj = WordList_sentic(None,lemma,concept_info) #OBJEK WORD ASLI
if (float(concept_info['polarity_intense']) < 0): #TERBUKTI NEGATIF
# print(concept_info['polarity_intense'])
# conceptExistNegative.append(concept_info)
objsConceptExistNegative.append(senticwordObj)
elif (float(concept_info['polarity_intense']) > 0): #TIDAK - di senticnet
# SINONIM
# cek SINONIM di wordnet jika tidak dinyatakan -
print("lemma positif masuk di - : {}".format(lemma))
from senticnet.senticnet import SenticNet
teste = []
sn = SenticNet('pt')
concept_info = sn.concept('amor')
polarity_value = sn.polarity_value('amor')
polarity_intense = sn.polarity_intense('amor')
moodtags = sn.moodtags('amor')
semantics = sn.semantics('amor')
sentics = sn.sentics('amor')
teste.append(concept_info)
print(teste)