def __init__(self,
text,
tokenizer=None,
pos_tagger=None,
np_extractor=None,
analyzer=None,
parser=None,
classifier=None,
clean_html=False):
self.tokenizer = tokenizer if tokenizer is not None else NLTKPunktTokenizer(
)
self.pos_tagger = pos_tagger if pos_tagger is not None else PatternTagger(
tokenizer=self.tokenizer)
self.np_extractor = np_extractor if np_extractor is not None \
else PatternParserNPExtractor(tokenizer=self.tokenizer)
self.analyzer = analyzer if analyzer is not None \
else PatternAnalyzer(tokenizer=self.tokenizer)
self.parser = parser if parser is not None \
else PatternParser(tokenizer=self.tokenizer)
self.classifier = classifier if classifier is not None else None
if not isinstance(text, basestring):
raise TypeError('The `text` argument passed to `__init__(text)` '
'must be a string, not {0}'.format(type(text)))
if clean_html:
raise NotImplementedError(
"clean_html has been deprecated. "
"To remove HTML markup, use BeautifulSoup's "
"get_text() function")
self.raw = self.string = text
self.stripped = lowerstrip(self.raw, all=True)
_initialize_models(self, self.tokenizer, self.pos_tagger,
self.np_extractor, self.analyzer, self.parser,
self.classifier)
def word_counts(self):
"""Dictionary of word frequencies in this text."""
counts = defaultdict(int)
stripped_words = [lowerstrip(word) for word in self.words]
for word in stripped_words:
counts[word] += 1
return counts
def word_counts(self):
"""Dictionary of word frequencies in this text."""
counts = defaultdict(int)
stripped_words = [lowerstrip(word) for word in self.words]
for word in stripped_words:
counts[word] += 1
return counts
def sentiment_overview(df):
st.subheader('Overview of comments')
st.write(
'Sort the comments by sentiment based on polarity and then it displays them in the list below.'
)
option = st.selectbox('Select the sentiment',
('Positive', 'Negative', 'Neutral'))
if option == 'All':
if len(df['comments'].tolist()) > 0:
st.table(df['comments'])
else:
st.info('There is no comments on this video.')
else:
if len(df[df['sentiment'] == lowerstrip(option)]
['comments'].tolist()) > 0:
st.table(df[df['sentiment'] == lowerstrip(option)]['comments'])
else:
st.info(
f'There is no {lowerstrip(option)} comments on this video.')
def __init__(self, text, tokenizer=None,
pos_tagger=None, np_extractor=None, analyzer=None,
parser=None, classifier=None, clean_html=False):
if not isinstance(text, basestring):
raise TypeError('The `text` argument passed to `__init__(text)` '
'must be a string, not {0}'.format(type(text)))
if clean_html:
raise NotImplementedError("clean_html has been deprecated. "
"To remove HTML markup, use BeautifulSoup's "
"get_text() function")
self.raw = self.string = text
self.stripped = lowerstrip(self.raw, all=True)
_initialize_models(self, tokenizer, pos_tagger, np_extractor, analyzer,
parser, classifier)
def __init__(self, text, tokenizer=None,
pos_tagger=None, np_extractor=None, analyzer=None,
parser=None, classifier=None, clean_html=False):
if not isinstance(text, basestring):
raise TypeError('The `text` argument passed to `__init__(text)` '
'must be a string, not {0}'.format(type(text)))
if clean_html:
raise NotImplementedError("clean_html has been deprecated. "
"To remove HTML markup, use BeautifulSoup's "
"get_text() function")
self.raw = self.string = text
self.stripped = lowerstrip(self.raw, all=True)
_initialize_models(self, tokenizer, pos_tagger, np_extractor, analyzer,
parser, classifier)
def __init__(self, text, tokenizer=None,
pos_tagger=None,
np_extractor=None,
analyzer=None,
parser=None,
classifier=None, clean_html=False):
self.tokenizer = tokenizer if tokenizer is not None else NLTKPunktTokenizer()
self.pos_tagger = pos_tagger if pos_tagger is not None else PatternTagger(
tokenizer=self.tokenizer)
self.np_extractor = np_extractor if np_extractor is not None \
else PatternParserNPExtractor(tokenizer=self.tokenizer)
self.analyzer = analyzer if analyzer is not None \
else PatternAnalyzer(tokenizer=self.tokenizer)
self.parser = parser if parser is not None \
else PatternParser(tokenizer=self.tokenizer)
self.classifier = classifier if classifier is not None else None
if not isinstance(text, basestring):
raise TypeError('The `text` argument passed to `__init__(text)` '
'must be a string, not {0}'.format(type(text)))
if clean_html:
raise NotImplementedError(
"clean_html has been deprecated. "
"To remove HTML markup, use BeautifulSoup's "
"get_text() function")
self.raw = self.string = text
self.stripped = lowerstrip(self.raw, all=True)
_initialize_models(
self,
self.tokenizer,
self.pos_tagger,
self.np_extractor,
self.analyzer,
self.parser,
self.classifier)
def test_lowerstrip(self):
assert_equal(lowerstrip(self.text),
'this. has. punctuation')
def test_lowerstrip(self):
assert_equal(lowerstrip(self.text), 'this. has. punctuation')
import keys
from operator import itemgetter
from tweetlistener import TweetListener
import preprocessor as p
from textblob.utils import lowerstrip
#authenticate with Twitter and create an api
auth = tweepy.OAuthHandler(keys.consumer_key, keys.consumer_secret)
auth.set_access_token(keys.access_token, keys.access_token_secret)
api = tweepy.API(auth, wait_on_rate_limit=True, wait_on_rate_limit_notify=True)
search = api.search(q='liverpool', count=100)
# initialize the preprocessor
p.set_options(p.OPT.URL, p.OPT.RESERVED, p.OPT.NUMBER, p.OPT.SMILEY,
p.OPT.EMOJI, p.OPT.MENTION, p.OPT.HASHTAG)
clean = []
for tweet in search:
try:
text = tweet.extended_tweet.text
except:
text = tweet.text
clean.append(p.clean(text))
stripped_text = [lowerstrip(t) for t in clean]
for text in stripped_text:
print(text)
