def __init__(self):
# Tag/Chunk data with ark_tweet_nlp
if enabled_modules['ark_tweet']:
self.ark_tweet = ark_tweet.ArkTweetNLP()
else:
self.ark_tweet = None
# Count all token frequencies
tf_idf._build_dictionary(self.ark_tweet, '/data1/nlp-data/twitter/data/etc/')
# Spelling correction
self.speller = spell.SpellChecker()
def __init__(self):
# Tag/Chunk data with ark_tweet_nlp
if enabled_modules['ark_tweet']:
self.ark_tweet = ark_tweet.ArkTweetNLP()
else:
self.ark_tweet = None
# Count all token frequencies
tf_idf._build_dictionary(self.ark_tweet, enabled_modules['twitter_data'])
# Spelling correction
self.speller = spell.SpellChecker()
def __init__(self):
# Tag/Chunk data with ark_tweet_nlp
if enabled_modules['ark_tweet']:
self.ark_tweet = ark_tweet.ArkTweetNLP()
else:
self.ark_tweet = None
# Lookup tweet metadata
if enabled_modules['twitter_data']:
self.twitter_data = twitter_data.TwitterData()
# Get HTML data from URLs in tweets
if enabled_modules['url']:
self.url = url.Url()
# Count all token frequencies
tf_idf._build_dictionary(self.ark_tweet, '/data1/nlp-data/twitter/data/etc/')
# Spelling correction
self.speller = spell.SpellChecker()
if enabled_modules['ukb_wsd']:
self.ukb = ukb_wsd.ukbWSD()
