Python parseB Examples

Example #1

    #print ''

    tags = getTags(scoresSort, test, mfs)
    return tags


# ----------------------------------------------------------------- #

if __name__ == '__main__':
    # file names
    trainingFileA = 'trainA.txt'
    trainingFileB = 'trainB.txt'

    # parse training and testing data
    trainA, testA = parseA(trainingFileA, 5)
    trainB, testB = parseB(trainingFileB, 5)

    # decision list
    print '\nDECISION LIST Part 5'
    tagsA = decisionList(trainA, testA)
    tagsB = decisionList(trainB, testB)
    checkTagsA(tagsA, testA)
    checkTagsB(tagsB, testB)

    # parse training and testing data
    trainA, testA = parseA(trainingFileA, 4)
    trainB, testB = parseB(trainingFileB, 4)

    # decision list
    print '\nDECISION LIST Part 4'
    tagsA = decisionList(trainA, testA)

Example #2

File: decisionList.py Project: emschorsch/nlp-final-project

    # print ''

    tags = getTags(scoresSort, test, mfs)
    return tags


# ----------------------------------------------------------------- #

if __name__ == "__main__":
    # file names
    trainingFileA = "trainA.txt"
    trainingFileB = "trainB.txt"

    # parse training and testing data
    trainA, testA = parseA(trainingFileA, 5)
    trainB, testB = parseB(trainingFileB, 5)

    # decision list
    print "\nDECISION LIST Part 5"
    tagsA = decisionList(trainA, testA)
    tagsB = decisionList(trainB, testB)
    checkTagsA(tagsA, testA)
    checkTagsB(tagsB, testB)

    # parse training and testing data
    trainA, testA = parseA(trainingFileA, 4)
    trainB, testB = parseB(trainingFileB, 4)

    # decision list
    print "\nDECISION LIST Part 4"
    tagsA = decisionList(trainA, testA)

Example #3

File: lexiconTagger.py Project: lijielife/nlp-final-project-1

	# determine the number of weighted words in the tweet
        for position in lexicon[word].keys():
          if lexicon[word][position]['polar'] == 'positive':
            pos += 1
          elif lexicon[word][position]['polar'] == 'negative':
            neg += 1

      # tag the tweet
      if pos > neg:
        tagsB[ID][subject] = 'positive'
      elif pos < neg: 
        tagsB[ID][subject] = 'negative'
      else:
        tagsB[ID][subject] = 'objective'
  
  return tagsA, tagsB
# ----------------------------------------------------------------- #

if __name__ == '__main__':
  trainingFileA = 'trainA.txt'
  trainingFileB = 'trainB.txt'
  lexiconFile   = 'sentimentLexicon.txt'
  trainA, testA  = parseA(trainingFileA)
  trainB, testB  = parseB(trainingFileB)
  lexicon = getSentimentWords(lexiconFile)
  tagsA, tagsB = lexiconTag(trainA, trainB, lexicon)
  checkTagsA(tagsA,trainA)
  checkTagsB(tagsB,trainB)

# ----------------------------------------------------------------- #