def analyse_sentiment(text):
pol = polarity(text)
if pol < -0.1:
sentiment = "negative"
elif pol > 0.1:
sentiment = "positive"
else:
sentiment = "neutral"
return sentiment
def pattern_assessor(x, *args):
from pattern.web import plaintext
from pattern.en import polarity, subjectivity
key = args[0]
pt = plaintext(x)
sss = {}
sss.update({'polarity': polarity(pt), 'subjectivity': subjectivity(pt)})
#return sss[key]
return sss
def sentiment_new(text, terms):
'''
INPUT string, string
OUTPUT float
'''
# Parse sentences
def Sentences(paragraph):
sentenceEnders = re.compile('[.!?]')
sentenceList = sentenceEnders.split(paragraph)
return sentenceList
# Identify sentences with key terms
def to_filter(text, terms):
if any(word in text for word in terms):
return text
else:
return np.nan
target = []
# Retrieve sentences that include key terms
for i in Sentences(text):
if to_filter(i, terms) == None:
pass
else:
target.append(i)
s_max = 0
comment_score = 0
# Take the most extreme score at the sentence level and use that for the comment
for i in target:
if abs(sentiment(i)) > abs(s_max):
comment_score = polarity(i)
s_max = polarity(i)
return comment_score
def sentiment_new(text, terms):
"""
INPUT string, string
OUTPUT float
"""
# Parse sentences
def Sentences(paragraph):
sentenceEnders = re.compile("[.!?]")
sentenceList = sentenceEnders.split(paragraph)
return sentenceList
# Identify sentences with key terms
def to_filter(text, terms):
if any(word in text for word in terms):
return text
else:
return np.nan
target = []
# Retrieve sentences that include key terms
for i in Sentences(text):
if to_filter(i, terms) == None:
pass
else:
target.append(i)
s_max = 0
comment_score = 0
# Take the most extreme score at the sentence level and use that for the comment
for i in target:
if abs(sentiment(i)) > abs(s_max):
comment_score = polarity(i)
s_max = polarity(i)
return comment_score
def test_polarity(self):
# Assert that en.polarity() yields en.sentiment()[0].
s = "A great day!"
self.assertTrue(en.polarity(s) == en.sentiment(s)[0])
print("pattern.en.polarity()")
def test_polarity(self):
# Assert that en.polarity() yields en.sentiment()[0].
s = "A great day!"
self.assertTrue(en.polarity(s) == en.sentiment(s)[0])
print "pattern.en.polarity()"
def sentiment(text):
'''
INPUT string
OUTPUT float
'''
return polarity(text)
print conjugate('purred', '3sg')
print PAST in tenses('purred') # 'p' in tenses() also works.
print (PAST, 1, PL) in tenses('purred')
print 'Quantification'
print quantify(['goose', 'goose', 'duck', 'chicken', 'chicken', 'chicken'])
print quantify('carrot', amount=90)
print quantify({'carrot': 100, 'parrot': 20})
print 'ngrams'
print ngrams("I am eating a pizza.", n=2)
#parse
s = parse('I eat pizza with a fork.')
pprint(s)
#tag
for word, t in tag('The cat felt happy.'):
print word +' is ' +t
s = "The movie attempts to be surreal by incorporating various time paradoxes, but it's presented in such a ridiculous way it's seriously boring."
print sentiment(s)
print polarity(s)
print subjectivity(s)
#The modality() function returns a value between -1.0 and +1.0, expressing the degree of certainty
s2 = "Some amino acids tend to be acidic while others may be basic." # weaseling
se = Sentence(parse(s, chunks=False, lemmata=True))
print modality(se)
ACCESS_TOKEN_KEY = '----'
ACCESS_TOKEN_SECRET = '---'
api = TwitterAPI(CONSUMER_KEY, CONSUMER_SECRET, ACCESS_TOKEN_KEY,
ACCESS_TOKEN_SECRET)
r = api.request('statuses/filter', {
'track': TRACK_TERM,
'locations': TRACK_LOC
})
### MongoDB Calling
client = MongoClient("mongodb://127.0.0.1:3001/meteor")
db = client['meteor']
for item in r.get_iterator():
if 'text' in item:
a = item['text']
p = polarity(a)
s = subjectivity(a)
if (p != 0.0):
post = {
"track": "newyork",
"tweet": a,
"tweetdate": datetime.datetime.utcnow(),
"polarity": p,
"subjectivity": s
}
db.tweets_newyork.insert_one(post).inserted_id
print("NewYork")
#print(a)
def sentiment(text):
"""
INPUT string
OUTPUT float
"""
return polarity(text)
from pattern.web import Twitter, plaintext
2 from pattern.db import Datasheet
3 from pattern.en import polarity
4
5 class GatherTweets:
6
# a file called companies.txt contains a list of companies to search Twitter for
7 file = open("companies.txt")
8 csv = Datasheet()
9
# traverse companies.txt and retrieve tweets and assign polarity to them
10 for line in file:
11 for tweet in Twitter().search(line.rstrip('\n').rstrip('0xD')):
12 tweet_desc = plaintext(tweet.description)
13 tweet_pol = polarity(tweet.description)
14 csv.append([tweet.date, tweet_desc, tweet_pol])
15
# save the tweet date, tweet, and the polairty of the tweet in gathered_tweets.csv
16 csv.save('gathered_tweets.csv')
from pattern.en import sentiment, polarity
print polarity('DMC Latam 2013 was awesome!')
print polarity('Bruno is beautiful')
print polarity('I hate brocoli')
# a text is objective or subjective, positive or negative.
# The sentiment analysis lexicon bundled in Pattern focuses on adjectives.
# It contains adjectives that occur frequently in customer reviews,
# hand-tagged with values for polarity and subjectivity.
# The polarity() function measures positive vs. negative, as a number between -1.0 and +1.0.
# The subjectivity() function measures objective vs. subjective, as a number between 0.0 and 1.0.
# The sentiment() function returns an averaged (polarity, subjectivity)-tuple for a given string.
for word in ("amazing", "horrible", "public"):
print word, sentiment(word)
text = "The movie attempts to be surreal by incorporating time travel and various time paradoxes, but it's presented in such a ridiculous way it's seriously boring."
print
print sentiment(text)
print
print polarity(text)
print
print subjectivity(text)
# The input string can be:
# - a string,
# - a Synset (see pattern.en.wordnet),
# - a parsed Sentence, Text, Chunk or Word (see pattern.en),
# - a Document (see pattern.vector).
# The positive() function returns True if the string's polarity >= threshold.
# The threshold can be lowered or raised,
# but overall for strings with multiple words +0.1 yields the best results.
print
print "good:", positive("good", threshold=0.1)
print " bad:", positive("bad")
def get_polarity(self, sentence):
"""
given sentence provide the polarity {1,-1}
"""
return polarity(sentence)
print lemma('running')
print conjugate('purred', '3sg')
print PAST in tenses('purred') # 'p' in tenses() also works.
print(PAST, 1, PL) in tenses('purred')
print 'Quantification'
print quantify(['goose', 'goose', 'duck', 'chicken', 'chicken', 'chicken'])
print quantify('carrot', amount=90)
print quantify({'carrot': 100, 'parrot': 20})
print 'ngrams'
print ngrams("I am eating a pizza.", n=2)
#parse
s = parse('I eat pizza with a fork.')
pprint(s)
#tag
for word, t in tag('The cat felt happy.'):
print word + ' is ' + t
s = "The movie attempts to be surreal by incorporating various time paradoxes, but it's presented in such a ridiculous way it's seriously boring."
print sentiment(s)
print polarity(s)
print subjectivity(s)
#The modality() function returns a value between -1.0 and +1.0, expressing the degree of certainty
s2 = "Some amino acids tend to be acidic while others may be basic." # weaseling
se = Sentence(parse(s, chunks=False, lemmata=True))
print modality(se)
# a text is objective or subjective, positive or negative.
# The sentiment analysis lexicon bundled in Pattern focuses on adjectives.
# It contains adjectives that occur frequently in customer reviews,
# hand-tagged with values for polarity and subjectivity.
# The polarity() function measures positive vs. negative, as a number between -1.0 and +1.0.
# The subjectivity() function measures objective vs. subjective, as a number between 0.0 and 1.0.
# The sentiment() function returns an averaged (polarity, subjectivity)-tuple for a given string.
for word in ("amazing", "horrible", "public"):
print word, sentiment(word)
text = "The movie attempts to be surreal by incorporating time travel and various time paradoxes, but it's presented in such a ridiculous way it's seriously boring."
print
print sentiment(text)
print
print polarity(text)
print
print subjectivity(text)
# The input string can be:
# - a string,
# - a Synset (see pattern.en.wordnet),
# - a parsed Sentence, Text, Chunk or Word (see pattern.en),
# - a Document (see pattern.vector).
# The positive() function returns True if the string's polarity >= threshold.
# The threshold can be lowered or raised,
# but overall for strings with multiple words +0.1 yields the best results.
print
print "good:", positive("good", threshold=0.1)
print " bad:", positive("bad")
