def main():
wordlist = InitializeWords()
tweetFile = '../dataset_raw/semeval2016-task6-trainingdata.txt'
tweetTags = '../processedTweets.txt'
tweetWriter = open(tweetTags, 'w')
tweets = oldWork.readTweets(tweetFile)
tweets = tweets[:len(tweets) - 1]
tweetClasses = tweets[len(tweets) - 1]
for tweet in tweets:
sentence = ''
for word in tweet:
splitWord = word
# print word
if len(word) > 0 and word[0] == '#' and word != '#semst':
splitWord = ParseSentence(splitWord, wordlist)
# print splitWord
sentence += splitWord
sentence += ' '
# sentence = ' '.join(tweet[1:len(tweet)])
sentence = ' '.join(sentence.split())
tweetWriter.write(sentence + '\n')
def main(): wordlist = InitializeWords() tweetFile = '../dataset_raw/semeval2016-task6-trainingdata.txt' tweetTags = '../processedTweets.txt' tweetWriter = open(tweetTags, 'w') tweets = oldWork.readTweets(tweetFile) tweets = tweets[:len(tweets) - 1] tweetClasses = tweets[len(tweets) - 1] for tweet in tweets: sentence = '' for word in tweet: splitWord = word # print word if len(word) > 0 and word[0] == '#' and word != '#semst': splitWord = ParseSentence(splitWord, wordlist) # print splitWord sentence += splitWord sentence += ' ' # sentence = ' '.join(tweet[1:len(tweet)]) sentence = ' '.join(sentence.split()) tweetWriter.write(sentence + '\n')
import os
import sys
import IntermediateProjectWork as oldWork
origTweetFile = '../dataset_raw/semeval2016-task6-trainingdata.txt'
origTweets = oldWork.readTweets(origTweetFile)
origTweetClasses = origTweets[len(origTweets) - 1]
origTweets = origTweets[:len(origTweets) - 1]
origTweetReader = open(origTweetFile)
taggedTweetFile = '../tweetsTagged.txt'
taggedTweetReader = open(taggedTweetFile)
outputFile = '../dataset_raw/semeval2016-task6-edited-trainingdata.txt'
outputWriter = open(outputFile, 'w')
origLine = origTweetReader.readline()
outputWriter.write(origLine)
# print origTweets[0]
for taggedTweet in taggedTweetReader:
print taggedTweet
origLine = origTweetReader.readline()
# print 'yo'
origLineSplit = origLine.split('\t')
# print origLineSplit
outputWriter.write(origLineSplit[0] + '\t' + origLineSplit[1] + '\t')
# print taggedTweet
line = taggedTweet.strip().split('\t')
tweetString = line[0]
