from senticnet.senticnet import Senticnet
sn = Senticnet()
print "polarity:", sn.polarity('love')
print "semantics:", " ".join(sn.semantics('love'))
print "\n".join([key + ": " + str(value) for key, value in sn.sentics('love').items()])
def emotion_data(comment):
comment = comment.translate({ord(c): '' for c in string.punctuation})
sn = Senticnet()
polarity_intense = 0
comment_sentics = {
'sensitivity': 0,
'attention': 0,
'pleasantness': 0,
'aptitude': 0
}
comment_mood_tags = []
words = comment.split(" ")
total_word_count = len(words)
final_output = {
'sentics': {
'sensitivity': '0',
'attention': '0',
'pleasantness': '0',
'aptitude': '0',
'polarity': '0'
},
'mood tags': {}
}
for i in words:
try:
#word_emotion(i, sn)
polarity_intense += float(sn.polarity_intense(i))
#print sn.sentics(i)
sentics_values(i, sn, comment_sentics)
add_mood_tags(comment_mood_tags, sn, i)
except KeyError:
#print "This word does not exist", i
if (total_word_count > 1):
total_word_count -= 1
pass
comment_sentics_average(total_word_count, comment_sentics)
final_output['sentics']['polarity'] = polarity_intense / total_word_count
final_output['mood tags'] = comment_mood_tags
for output in final_output['sentics']:
if output in comment_sentics:
final_output['sentics'][output] = comment_sentics[output]
json_output = json.dumps(final_output)
print(json_output)
return json_output
def get_avg_polarity(message):
threshold = 0.3
sn = Senticnet()
count = 0
summ = 0
for word_options in get_words_bag(message):
polarity = 0
for word in word_options:
try:
concept = sn.concept(word)
polarity = concept['polarity']
break
except urllib2.HTTPError:
pass #Do next
if abs(polarity) > threshold:
summ += polarity
count += 1
return summ / count if count > 0 else 0
def get_avg_polarity(message):
threshold = 0.3
sn = Senticnet()
count = 0
summ = 0
for word_options in get_words_bag(message):
polarity = 0
for word in word_options:
try:
concept = sn.concept(word)
polarity = concept['polarity']
break
except urllib2.HTTPError:
pass #Do next
if abs(polarity) > threshold:
summ += polarity
count += 1
return summ / count if count > 0 else 0
def getInfo(self, concept):
try:
sn = Senticnet()
concept_info = sn.concept(concept)
polarity_value = sn.polarity_value(concept)
polarity_intense = sn.polarity_intense(concept)
moodtags = sn.moodtags(concept)
semantics = sn.semantics(concept)
sentics = sn.sentics(concept)
"""print(concept)
print("concept_info: {}".format(concept_info))
print("polarity_value: {}".format(polarity_value))
print("polarity_intense: {}".format(polarity_intense))
print("moodtags: {}".format(moodtags))
print("semantics: {}".format(semantics))
print("sentics: {}".format(sentics))
print("\n\n")"""
return "{} - {}".format(polarity_value, polarity_intense)
except:
return "NOT POSSIBLE"
from senticnet.senticnet import Senticnet
sn = Senticnet()
print "polarity value:", sn.polarity_value("love")
print "polarity intense:", sn.polarity_intense("love")
print "moodtags:", ", ".join(sn.moodtags("love"))
print "semantics:", ", ".join(sn.semantics("love"))
print "\n".join(
[key + ": " + str(value) for key, value in sn.sentics("love").items()])
__author__ = 'cloudera'
from senticnet.senticnet import Senticnet
from textblob import TextBlob
sentence = "One of the very first Apple 1 computers, worth about 500,000, goes on sale later this month at Christie's auction house, the latest vintage tech sale."
sn = Senticnet()
concept_info = sn.concept('love')
print 'sn.concept(love) = ', concept_info
polarity = sn.polarity('love')
print 'polarity(love) = ', polarity
semantics = sn.semantics('love')
print 'semantics = ', semantics
sentics = sn.sentics('love')
print 'sentics = ', sentics
sentenceBlob = TextBlob(sentence)
print sentenceBlob.parse()
print sentenceBlob.sentiment
sentenceConcept = sn.concept(sentence)
print sentenceConcept
# yule's I measure (the inverse of yule's K measure)
# higher number is higher diversity - richer vocabulary
def yules_para(para):
words = nltk.tokenize.RegexpTokenizer(r'\w+').tokenize(para)
token_counter = Counter(tok.lower() for tok in words)
m1 = sum(token_counter.values())
m2 = sum([freq**2 for freq in token_counter.values()])
i = (m1 * m1) / (m2 - m1)
k = 1 / i * 10000
return (k, i)
# positive and negative emotion score
sn = Senticnet()
def positiveScore(para):
posScore = 0
words = nltk.tokenize.RegexpTokenizer(r'\w+').tokenize(para)
for i in words:
try:
polarity_intense = float(sn.polarity_intense(i))
if (polarity_intense > 0):
posScore = posScore + polarity_intense
except KeyError:
continue
return (posScore / len(words))
from senticnet.senticnet import Senticnet
sn = Senticnet()
print "polarity:", sn.polarity('love')
print "semantics:", " ".join(sn.semantics('love'))
print "\n".join(
[key + ": " + str(value) for key, value in sn.sentics('love').items()])
lista[0]=lista[0].replace(']','')
lista[0]=lista[0].replace('\'','')
#lista[0]=lista[0].replace(',','')
lista[0]=lista[0].split(',')
#re.sub('[', '', data)
print(lista[0][0])
'''
polarity_value_result = list()
polarity_intense_result = list()
concept_info_result = list()
sn = Senticnet()
for concept in concepts:
concept = concept.replace('[', '')
concept = concept.replace('u\'', '')
concept = concept.replace('_', ' ')
concept = concept.replace('...', '')
concept = concept.replace(']', '')
concept = concept.replace('\'', '')
concept = concept.split(',')
print('internal loop')
for item in concept:
print('item:')
print(item)
item = str(item)
def score_calculation(sentence):
sno = SnowballStemmer('english')
lemma = WordNetLemmatizer()
sn = Senticnet()
polarity_intense = 0
comment_sentics = {
'sensitivity': 0,
'attention': 0,
'pleasantness': 0,
'aptitude': 0
}
comment_mood_tags = []
total_word_count = len(sentence)
final_output = {
'sentics': {
'sensitivity': '0',
'attention': '0',
'pleasantness': '0',
'aptitude': '0',
'polarity': '0'
},
'mood tags': {}
}
for i in sentence:
try:
#word_emotion(i,sn)
polarity_intense += float(sn.polarity_intense(i))
sentics_values(i, sn, comment_sentics)
add_mood_tags(comment_mood_tags, sn, i)
except KeyError:
#print "This word does not exist"
try:
current_word = lemma.lemmatize(i)
#word_emotion(current_word,sn)
polarity_intense += float(sn.polarity_intense(current_word))
sentics_values(current_word, sn, comment_sentics)
add_mood_tags(comment_mood_tags, sn, current_word)
except KeyError:
#print("This didnt work again")
try:
# word_emotion(sno.stem(current_word),sn)
current_word = sno.stem(current_word)
polarity_intense += float(
sn.polarity_intense(current_word))
sentics_values(current_word, sn, comment_sentics)
add_mood_tags(comment_mood_tags, sn, current_word)
except KeyError:
if (total_word_count > 1):
total_word_count -= 1
pass
comment_sentics_average(total_word_count, comment_sentics)
final_output['sentics']['polarity'] = polarity_intense / total_word_count
final_output['mood tags'] = comment_mood_tags
for output in final_output['sentics']:
if output in comment_sentics:
final_output['sentics'][output] = comment_sentics[output]
json_output = json.dumps(final_output)
final_excitement = {'score': '0', 'mood tags': {}}
final_excitement_score = comment_sentics['attention'] + comment_sentics[
'pleasantness']
final_excitement['score'] = str(final_excitement_score)
final_excitement['mood tags'] = comment_mood_tags
#print json_output
#print final_excitement
return final_excitement
#!/usr/bin/python
# -*- coding: utf8 -*-
from senticnet.senticnet import Senticnet
from nltk.classify import NaiveBayesClassifier
import pymorphy2
import codecs
def word_feats(words):
return dict([(word, True) for word in words])
sn = Senticnet('ru')
morph = pymorphy2.MorphAnalyzer()
# заполняем масссив тэгами SenticNet
positive_vocab = ['#интерес', '#радость', '#сюрприз', '#восхищение']
negative_vocab = ['#попугать', '#гнев', '#печаль', '#отвращение']
# добавляем слова из WordNet
with codecs.open('dict/positive.txt', encoding='utf-8') as file_object:
for line in file_object:
line = line.rstrip('\n\r')
positive_vocab.append(morph.parse(line)[0].normal_form)
with codecs.open('dict/negative.txt', encoding='utf-8') as file_object:
for line in file_object:
line = line.rstrip('\n\r')
negative_vocab.append(morph.parse(line)[0].normal_form)
# наполнаяем множества позитивных и негативных слов и обучаем классификатор
content = data
# Create a SummaryTool object
st = SummaryTool()
# Build the sentences dictionary
sentences_dic = st.get_sentences_ranks(content)
# Build the summary with the sentences dictionary
sentences = st.get_summary(title, content, sentences_dic)
# print sentences
## instantiate senticnet
sn = Senticnet()
counter = 0
total = 0
words = re.compile('\w+').findall(sentences)
for word in words:
word = word.lower()
try:
print word
polarity = sn.polarity(word)
counter += 1
total += polarity
# print counter, word, polarity
